Split (3)

train · 15.9k rows

text_prompt stringlengths 168 30.3k	code_prompt stringlengths 67 124k
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Creating an instance of MeasurementControl Step2: The InstrumentMonitor can be used to see the parameters of any instrument connected to the station and updates during the loop initiated by MeasurementControl. Step3: Create instruments used in the experiment Step4: A 1D hard measurement Step5: By setting persist_mode = True we can see a copy of the last measurements Step6: A simple 1D soft measurement Step7: You can play around a bit with the options in the MC Step8: A simple 2D measurement Step9: 2D combinatioin of a hard inner and soft outer loop Step10: A Hard measurement that uses soft averaging Step11: 2D soft averaging Step12: Starting an adaptive measurement	<ASSISTANT_TASK:> Python Code: import pycqed as pq import numpy as np from pycqed.measurement import measurement_control from pycqed.measurement.sweep_functions import None_Sweep import pycqed.measurement.detector_functions as det from qcodes import station station = station.Station() MC = measurement_control.MeasurementControl('MC',live_plot_enabled=True, verbose=True) MC.station = station station.add_component(MC) from pycqed.instrument_drivers.virtual_instruments import instrument_monitor as im IM = im.InstrumentMonitor('IM', station) station.add_component(IM) # Link the instrument monitor to the MC so that it gets updated in the loop MC.instrument_monitor('IM') IM.update() IM.update_interval(.1) IM.update() from pycqed.instrument_drivers.physical_instruments.dummy_instruments import DummyParHolder dummy_instrument = DummyParHolder('dummy_instrument') station.add_component(dummy_instrument) MC.soft_avg(15) MC.persist_mode(True) MC.set_sweep_function(None_Sweep(sweep_control='hard')) MC.set_sweep_points(np.linspace(0, 10, 30)) MC.set_detector_function(det.Dummy_Detector_Hard(noise=0.5, delay=.02)) dat = MC.run('dummy_hard') data_set = dat['dset'] MC.set_sweep_function(None_Sweep(sweep_control='hard')) MC.set_sweep_points(np.linspace(0, 10, 30)) MC.set_detector_function(det.Dummy_Detector_Hard(noise=0.5, delay=.02)) dat2 = MC.run('dummy_hard persistent') data_set2 = dat2['dset'] dummy_instrument.x(145/134545) IM.update() dummy_instrument.delay(.01) MC.soft_avg(15) MC.set_sweep_function(dummy_instrument.x) MC.set_sweep_points(np.linspace(-1,1,30)) dummy_instrument.noise(1) MC.set_detector_function(dummy_instrument.parabola) dat = MC.run('1D test') data_set = dat['dset'] # the second plot will also show the first line MC.set_sweep_function(dummy_instrument.x) MC.set_sweep_points(np.linspace(-1,1,30)) dat2= MC.run('1D test-persist') data_set2 = dat2['dset'] dummy_instrument.delay(.01) MC.soft_avg(15) MC.set_sweep_function(dummy_instrument.x) MC.set_sweep_points(np.linspace(-1,1,30)) MC.set_detector_function(det.Dummy_Detector_Soft()) dat = MC.run('1D test') data_set = dat['dset'] MC.persist_mode(True) # Turns on and off persistent plotting MC.verbose(True) MC.plotting_interval(.2) MC.live_plot_enabled(True) dummy_instrument.delay(.0001) MC.soft_avg(4) sweep_pts = np.linspace(-2, 2, 30) sweep_pts_2D = np.linspace(-2, 2, 5) MC.set_sweep_function(dummy_instrument.x) MC.set_sweep_function_2D(dummy_instrument.y) MC.set_sweep_points(sweep_pts) MC.set_sweep_points_2D(sweep_pts_2D) MC.set_detector_function(dummy_instrument.parabola) dat=MC.run('test', mode='2D') data_set = dat['dset'] MC.soft_avg(1) sweep_pts = np.linspace(0, 10, 30) sweep_pts_2D = np.linspace(0, 10, 30) MC.set_sweep_function(None_Sweep(sweep_control='hard')) MC.set_sweep_function_2D(None_Sweep(sweep_control='soft')) MC.set_sweep_points(sweep_pts) MC.set_sweep_points_2D(sweep_pts_2D) MC.set_detector_function(det.Dummy_Detector_Hard(delay=.05, noise=.1)) dat = MC.run('2D_hard', mode='2D') data_set = dat['dset'] MC.soft_avg(4) MC.set_sweep_function(None_Sweep(sweep_control='hard')) MC.set_sweep_points(np.linspace(0, 10, 30)) MC.set_detector_function(det.Dummy_Detector_Hard(noise=1.5, delay=.02)) dat = MC.run('dummy_hard') data_set = dat['dset'] MC.soft_avg(10) sweep_pts = np.linspace(0, 10, 30) sweep_pts_2D = np.linspace(0, 10, 5) MC.set_sweep_function(None_Sweep(sweep_control='hard')) MC.set_sweep_function_2D(None_Sweep(sweep_control='soft')) MC.set_sweep_points(sweep_pts) MC.set_sweep_points_2D(sweep_pts_2D) MC.set_detector_function(det.Dummy_Detector_Hard(noise=1.5, delay=.001)) dat = MC.run('dummy_hard_2D', mode='2D') data_set = dat['dset'] dummy_instrument.delay(.05) dummy_instrument.noise(2) from pycqed.measurement.optimization import nelder_mead MC.soft_avg(1) dummy_instrument MC.set_sweep_functions([dummy_instrument.x, dummy_instrument.y]) MC.set_adaptive_function_parameters({'adaptive_function':nelder_mead, 'x0':[-5,-5], 'initial_step': [2.5, 2.5]}) dummy_instrument.noise(2) MC.set_detector_function(dummy_instrument.parabola) dat = MC.run('1D test', mode='adaptive') data_set = dat['dset'] <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Document Authors Step2: Document Contributors Step3: Document Publication Step4: Document Table of Contents Step5: 1.2. Model Name Step6: 1.3. Description Step7: 1.4. Land Atmosphere Flux Exchanges Step8: 1.5. Atmospheric Coupling Treatment Step9: 1.6. Land Cover Step10: 1.7. Land Cover Change Step11: 1.8. Tiling Step12: 2. Key Properties --> Conservation Properties Step13: 2.2. Water Step14: 2.3. Carbon Step15: 3. Key Properties --> Timestepping Framework Step16: 3.2. Time Step Step17: 3.3. Timestepping Method Step18: 4. Key Properties --> Software Properties Step19: 4.2. Code Version Step20: 4.3. Code Languages Step21: 5. Grid Step22: 6. Grid --> Horizontal Step23: 6.2. Matches Atmosphere Grid Step24: 7. Grid --> Vertical Step25: 7.2. Total Depth Step26: 8. Soil Step27: 8.2. Heat Water Coupling Step28: 8.3. Number Of Soil layers Step29: 8.4. Prognostic Variables Step30: 9. Soil --> Soil Map Step31: 9.2. Structure Step32: 9.3. Texture Step33: 9.4. Organic Matter Step34: 9.5. Albedo Step35: 9.6. Water Table Step36: 9.7. Continuously Varying Soil Depth Step37: 9.8. Soil Depth Step38: 10. Soil --> Snow Free Albedo Step39: 10.2. Functions Step40: 10.3. Direct Diffuse Step41: 10.4. Number Of Wavelength Bands Step42: 11. Soil --> Hydrology Step43: 11.2. Time Step Step44: 11.3. Tiling Step45: 11.4. Vertical Discretisation Step46: 11.5. Number Of Ground Water Layers Step47: 11.6. Lateral Connectivity Step48: 11.7. Method Step49: 12. Soil --> Hydrology --> Freezing Step50: 12.2. Ice Storage Method Step51: 12.3. Permafrost Step52: 13. Soil --> Hydrology --> Drainage Step53: 13.2. Types Step54: 14. Soil --> Heat Treatment Step55: 14.2. Time Step Step56: 14.3. Tiling Step57: 14.4. Vertical Discretisation Step58: 14.5. Heat Storage Step59: 14.6. Processes Step60: 15. Snow Step61: 15.2. Tiling Step62: 15.3. Number Of Snow Layers Step63: 15.4. Density Step64: 15.5. Water Equivalent Step65: 15.6. Heat Content Step66: 15.7. Temperature Step67: 15.8. Liquid Water Content Step68: 15.9. Snow Cover Fractions Step69: 15.10. Processes Step70: 15.11. Prognostic Variables Step71: 16. Snow --> Snow Albedo Step72: 16.2. Functions Step73: 17. Vegetation Step74: 17.2. Time Step Step75: 17.3. Dynamic Vegetation Step76: 17.4. Tiling Step77: 17.5. Vegetation Representation Step78: 17.6. Vegetation Types Step79: 17.7. Biome Types Step80: 17.8. Vegetation Time Variation Step81: 17.9. Vegetation Map Step82: 17.10. Interception Step83: 17.11. Phenology Step84: 17.12. Phenology Description Step85: 17.13. Leaf Area Index Step86: 17.14. Leaf Area Index Description Step87: 17.15. Biomass Step88: 17.16. Biomass Description Step89: 17.17. Biogeography Step90: 17.18. Biogeography Description Step91: 17.19. Stomatal Resistance Step92: 17.20. Stomatal Resistance Description Step93: 17.21. Prognostic Variables Step94: 18. Energy Balance Step95: 18.2. Tiling Step96: 18.3. Number Of Surface Temperatures Step97: 18.4. Evaporation Step98: 18.5. Processes Step99: 19. Carbon Cycle Step100: 19.2. Tiling Step101: 19.3. Time Step Step102: 19.4. Anthropogenic Carbon Step103: 19.5. Prognostic Variables Step104: 20. Carbon Cycle --> Vegetation Step105: 20.2. Carbon Pools Step106: 20.3. Forest Stand Dynamics Step107: 21. Carbon Cycle --> Vegetation --> Photosynthesis Step108: 22. Carbon Cycle --> Vegetation --> Autotrophic Respiration Step109: 22.2. Growth Respiration Step110: 23. Carbon Cycle --> Vegetation --> Allocation Step111: 23.2. Allocation Bins Step112: 23.3. Allocation Fractions Step113: 24. Carbon Cycle --> Vegetation --> Phenology Step114: 25. Carbon Cycle --> Vegetation --> Mortality Step115: 26. Carbon Cycle --> Litter Step116: 26.2. Carbon Pools Step117: 26.3. Decomposition Step118: 26.4. Method Step119: 27. Carbon Cycle --> Soil Step120: 27.2. Carbon Pools Step121: 27.3. Decomposition Step122: 27.4. Method Step123: 28. Carbon Cycle --> Permafrost Carbon Step124: 28.2. Emitted Greenhouse Gases Step125: 28.3. Decomposition Step126: 28.4. Impact On Soil Properties Step127: 29. Nitrogen Cycle Step128: 29.2. Tiling Step129: 29.3. Time Step Step130: 29.4. Prognostic Variables Step131: 30. River Routing Step132: 30.2. Tiling Step133: 30.3. Time Step Step134: 30.4. Grid Inherited From Land Surface Step135: 30.5. Grid Description Step136: 30.6. Number Of Reservoirs Step137: 30.7. Water Re Evaporation Step138: 30.8. Coupled To Atmosphere Step139: 30.9. Coupled To Land Step140: 30.10. Quantities Exchanged With Atmosphere Step141: 30.11. Basin Flow Direction Map Step142: 30.12. Flooding Step143: 30.13. Prognostic Variables Step144: 31. River Routing --> Oceanic Discharge Step145: 31.2. Quantities Transported Step146: 32. Lakes Step147: 32.2. Coupling With Rivers Step148: 32.3. Time Step Step149: 32.4. Quantities Exchanged With Rivers Step150: 32.5. Vertical Grid Step151: 32.6. Prognostic Variables Step152: 33. Lakes --> Method Step153: 33.2. Albedo Step154: 33.3. Dynamics Step155: 33.4. Dynamic Lake Extent Step156: 33.5. Endorheic Basins Step157: 34. Lakes --> Wetlands	<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'ncc', 'sandbox-1', 'land') # Set as follows: DOC.set_author("name", "email") # TODO - please enter value(s) # Set as follows: DOC.set_contributor("name", "email") # TODO - please enter value(s) # Set publication status: # 0=do not publish, 1=publish. DOC.set_publication_status(0) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.model_overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.model_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.land_atmosphere_flux_exchanges') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "water" # "energy" # "carbon" # "nitrogen" # "phospherous" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.atmospheric_coupling_treatment') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.land_cover') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "bare soil" # "urban" # "lake" # "land ice" # "lake ice" # "vegetated" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.land_cover_change') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.conservation_properties.energy') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.conservation_properties.water') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.conservation_properties.carbon') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.timestepping_framework.timestep_dependent_on_atmosphere') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.timestepping_framework.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.timestepping_framework.timestepping_method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.software_properties.repository') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.software_properties.code_version') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.key_properties.software_properties.code_languages') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.grid.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.grid.horizontal.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.grid.horizontal.matches_atmosphere_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.grid.vertical.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.grid.vertical.total_depth') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_water_coupling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.number_of_soil layers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.structure') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.texture') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.organic_matter') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.albedo') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.water_table') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.continuously_varying_soil_depth') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.soil_map.soil_depth') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.snow_free_albedo.prognostic') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.snow_free_albedo.functions') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "vegetation type" # "soil humidity" # "vegetation state" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.snow_free_albedo.direct_diffuse') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "distinction between direct and diffuse albedo" # "no distinction between direct and diffuse albedo" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.snow_free_albedo.number_of_wavelength_bands') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.vertical_discretisation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.number_of_ground_water_layers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.lateral_connectivity') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "perfect connectivity" # "Darcian flow" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Bucket" # "Force-restore" # "Choisnel" # "Explicit diffusion" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.freezing.number_of_ground_ice_layers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.freezing.ice_storage_method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.freezing.permafrost') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.drainage.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.hydrology.drainage.types') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Gravity drainage" # "Horton mechanism" # "topmodel-based" # "Dunne mechanism" # "Lateral subsurface flow" # "Baseflow from groundwater" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.vertical_discretisation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.heat_storage') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Force-restore" # "Explicit diffusion" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.soil.heat_treatment.processes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "soil moisture freeze-thaw" # "coupling with snow temperature" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.number_of_snow_layers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.density') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "constant" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.water_equivalent') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.heat_content') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.temperature') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.liquid_water_content') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.snow_cover_fractions') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "ground snow fraction" # "vegetation snow fraction" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.processes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "snow interception" # "snow melting" # "snow freezing" # "blowing snow" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.snow_albedo.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "prescribed" # "constant" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.snow.snow_albedo.functions') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "vegetation type" # "snow age" # "snow density" # "snow grain type" # "aerosol deposition" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.dynamic_vegetation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.vegetation_representation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "vegetation types" # "biome types" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.vegetation_types') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "broadleaf tree" # "needleleaf tree" # "C3 grass" # "C4 grass" # "vegetated" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.biome_types') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "evergreen needleleaf forest" # "evergreen broadleaf forest" # "deciduous needleleaf forest" # "deciduous broadleaf forest" # "mixed forest" # "woodland" # "wooded grassland" # "closed shrubland" # "opne shrubland" # "grassland" # "cropland" # "wetlands" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.vegetation_time_variation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "fixed (not varying)" # "prescribed (varying from files)" # "dynamical (varying from simulation)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.vegetation_map') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.interception') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.phenology') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic (vegetation map)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.phenology_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.leaf_area_index') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prescribed" # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.leaf_area_index_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.biomass') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.biomass_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.biogeography') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.biogeography_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.stomatal_resistance') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "light" # "temperature" # "water availability" # "CO2" # "O3" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.stomatal_resistance_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.vegetation.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.energy_balance.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.energy_balance.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.energy_balance.number_of_surface_temperatures') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.energy_balance.evaporation') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "alpha" # "beta" # "combined" # "Monteith potential evaporation" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.energy_balance.processes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "transpiration" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.anthropogenic_carbon') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "grand slam protocol" # "residence time" # "decay time" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.number_of_carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.forest_stand_dynamics') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.photosynthesis.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.autotrophic_respiration.maintainance_respiration') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.autotrophic_respiration.growth_respiration') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.allocation.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.allocation.allocation_bins') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "leaves + stems + roots" # "leaves + stems + roots (leafy + woody)" # "leaves + fine roots + coarse roots + stems" # "whole plant (no distinction)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.allocation.allocation_fractions') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "fixed" # "function of vegetation type" # "function of plant allometry" # "explicitly calculated" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.phenology.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.vegetation.mortality.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.litter.number_of_carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.litter.carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.litter.decomposition') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.litter.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.soil.number_of_carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.soil.carbon_pools') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.soil.decomposition') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.soil.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.permafrost_carbon.is_permafrost_included') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.permafrost_carbon.emitted_greenhouse_gases') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.permafrost_carbon.decomposition') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.carbon_cycle.permafrost_carbon.impact_on_soil_properties') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.nitrogen_cycle.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.nitrogen_cycle.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.nitrogen_cycle.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.nitrogen_cycle.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.tiling') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.grid_inherited_from_land_surface') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.grid_description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.number_of_reservoirs') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.water_re_evaporation') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "flood plains" # "irrigation" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.coupled_to_atmosphere') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.coupled_to_land') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.quantities_exchanged_with_atmosphere') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "heat" # "water" # "tracers" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.basin_flow_direction_map') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "present day" # "adapted for other periods" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.flooding') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.oceanic_discharge.discharge_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "direct (large rivers)" # "diffuse" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.river_routing.oceanic_discharge.quantities_transported') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "heat" # "water" # "tracers" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.coupling_with_rivers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.quantities_exchanged_with_rivers') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "heat" # "water" # "tracers" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.vertical_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.method.ice_treatment') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.method.albedo') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "prognostic" # "diagnostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.method.dynamics') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "No lake dynamics" # "vertical" # "horizontal" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.method.dynamic_lake_extent') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.method.endorheic_basins') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.land.lakes.wetlands.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Now we start making changes to the driver log file and we create a new driver log file. Step2: We sample (normal dist) 40% of example that are not zero angles; flip them and reverse steering angle. Step3: We have to upsample under represented example and we do this by shifting images and their corresponding angles Step4: The histogram looks more balanced from the upsampling, but this caused us to created steering angles outside the bounds of [-1,1] Step5: Now the histogram is mostly evenly distributed and the question now becomes how much data can we trim and still train the model?! Step6: Now we have a decent starting point and we can start the pipeline process!! Step7: Last step is to create the shift image and load image methods. Step8: We can actually load everthing into memory and we don't need to use a generator! Step16: We are now ready to go into creating our model! Step18: Here is the final 52 param model that we are using for this project. Step19: To run the model training below you'll need to download and run the vis tool Step20: Notice the loss doesn't change greatly and because we use an aggressive learning rate we could benefit from early termination.	<ASSISTANT_TASK:> Python Code: zero_steering = drive_log_df[drive_log_df.steering == 0].sample(frac=0.9) drive_log_df = drive_log_df.drop(zero_steering.index) plt.figure(figsize=(10,4)) drive_log_df.steering.hist(bins=100, color='r') plt.xlabel('steering angle bins') plt.ylabel('counts') plt.show() print("Current Dataset Size: ", len(drive_log_df.steering)) def update_left_right_steering_correction(df): records = [] for index, row in df.iterrows(): left = row.left center = row.center right = row.right steering = row.steering records.append({ 'image': left, 'steering': steering + 0.23 }) records.append({ 'image': right, 'steering': steering - 0.23 }) records.append({ 'image': center, 'steering': steering }) return pd.DataFrame(data=records, columns=['image', 'steering']) new_drive_log = update_left_right_steering_correction(drive_log_df) new_drive_log.tail() def flip_images_augmentation(df): new_df = df[df.steering != 0].sample(frac=0.4) df.loc[:,'is_flipped'] = False new_df.loc[:,'is_flipped'] = True left_rows = (new_df.steering < 0) right_rows = (new_df.steering > 0) new_df.loc[left_rows,'steering'] = new_df[left_rows].steering.abs() new_df.loc[right_rows, 'steering'] = new_df[right_rows].steering * -1 return pd.concat([df, new_df]) augmented = flip_images_augmentation(new_drive_log) plt.figure(figsize=(10,4)) augmented.steering.hist(bins=100, color='r') plt.xlabel('steering angle bins') plt.ylabel('counts') plt.show() print("Current Dataset Size: ", len(augmented.steering)) def shift_img_augmentation(df): df.loc[:,'random_shift'] = 0 new_df = df[df.steering != 0].copy() df.loc[:,'is_shift'] = False new_df.loc[:,'is_shift'] = True max_shift = 30 max_ang = 0.17 def row_shift_update(row): random_shift = np.random.randint(-max_shift, max_shift + 1) row.random_shift = random_shift updated_steer = row.steering + (random_shift / max_shift) * max_ang if abs(updated_steer) > 1: updated_steer = -1 if (updated_steer < 0) else 1 row.steering = updated_steer return row new_df = new_df.apply(row_shift_update, axis=1) return pd.concat([df, new_df]) shifted = shift_img_augmentation(augmented) plt.figure(figsize=(10,4)) shifted.steering.hist(bins=100, color='r') plt.xlabel('steering angle bins') plt.ylabel('counts') plt.show() print("Current Dataset Size: ", len(shifted.steering)) shifted.tail(1) plt.show() def process_driver_log(driver_log): update_log = update_left_right_steering_correction(driver_log) update_log = flip_images_augmentation(update_log) update_log = shift_img_augmentation(update_log) #update_log = change_brightness_augmentation(update_log) #reset index since we it's no longer good. update_log = update_log.reset_index(drop=True) #drop outbound steering examples to be between [-1,1] ! outbound_steering = update_log[abs(update_log.steering) > 1] update_log = update_log.drop(outbound_steering.index) return update_log processed_log = process_driver_log(drive_log_df) plt.figure(figsize=(10,4)) processed_log.steering.hist(bins=100, color='r') plt.xlabel('steering angle bins') plt.ylabel('counts') plt.show() print("Current Dataset Size: ", len(processed_log.steering)) hist, counts = np.histogram(processed_log.steering, bins=100) upper_limit = 400 over = [(i, v) for i, v in enumerate(hist) if v > upper_limit ] over_ranges = [(counts[i],counts[i+1]) for i,_ in over] #loop through ranges and create a mask for each bin masks = ["processed_log[(processed_log.steering >= {0}) & (processed_log.steering < {1})]".format(l,r) for l,r in over_ranges] for mask in masks: selected = eval(mask) selected_length = len(selected) frac_to_drop = (selected_length-upper_limit)/selected_length samples_to_drop = selected.sample(frac=frac_to_drop) processed_log = processed_log.drop(samples_to_drop.index) plt.figure(figsize=(10,4)) processed_log.steering.hist(bins=100, color='g') plt.xlabel('steering angle bins') plt.ylabel('counts') plt.show() print("Current Dataset Size: ", len(processed_log.steering)) processed_log.to_csv('preprocessed_driver_log.csv') def crop_top_and_bottom(image): resized = cv2.resize(image[70:140], (64,64), cv2.INTER_AREA) return cv2.cvtColor(resized, cv2.COLOR_RGB2HSV)[:,:,1] plt.figure(figsize=(10,4)) random_image = drive_log_df.iloc[0] image = cv2.imread("./data/{0}".format(random_image.center)) print(image.shape) plt.figure(1) plt.imshow(image) plt.show() cropped_image = crop_top_and_bottom(image) print(cropped_image.shape) plt.figure(2) plt.imshow(cropped_image) plt.show() def shift_img(image, random_shift): rows, cols = image.shape mat = np.float32([[1, 0, random_shift], [0, 1, 0]]) return cv2.warpAffine(image, mat, (cols, rows)) def load_image(row): image = cv2.imread("./data/{0}".format(row.image.strip())) image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) image = crop_top_and_bottom(image) if(row.is_flipped): image = cv2.flip(image,1) if(row.is_shift): image = shift_img(image, row.random_shift) return image def load_all_features_and_labels(df): images = [load_image(row) for _, row in df.iterrows()] return np.array(images).reshape((len(images), 64, 64, 1)), df.steering features, labels = load_all_features_and_labels(processed_log) print(features.shape, labels.shape) def fire_module(x, fire_id, squeeze=16, expand=64): This is a modified version of: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py#L14 Changes made: * Uses ELU activation * Only supports tf s_id = 'fire' + str(fire_id) + '/' c_axis = 3 sq1x1 = "squeeze1x1" exp1x1 = "expand1x1" exp3x3 = "expand3x3" elu = "elu_" x = Convolution2D(squeeze, 1, 1, border_mode='valid', name=s_id + sq1x1)(x) x = Activation('elu', name=s_id + elu + sq1x1)(x) left = Convolution2D(expand, 1, 1, border_mode='valid', name=s_id + exp1x1)(x) left = Activation('elu', name=s_id + elu + exp1x1)(left) right = Convolution2D(expand, 3, 3, border_mode='same', name=s_id + exp3x3)(x) right = Activation('elu', name=s_id + elu + exp3x3)(right) x = merge([left, right], mode='concat', concat_axis=c_axis, name=s_id + 'concat') return x def squeeze_model_10000(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(2, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=2, expand=6) x = fire_module(x, fire_id=3, squeeze=16, expand=64) x = Dropout(0.2, name='drop9')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet10k.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-3), loss='mse') return model def squeeze_model_1005(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(2, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=2, expand=6) x = fire_module(x, fire_id=3, squeeze=6, expand=12) x = Dropout(0.2, name='drop9')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet1005.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-1), loss='mse') return model def squeeze_model_329(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(2, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=2, expand=6) x = fire_module(x, fire_id=3, squeeze=2, expand=6) x = Dropout(0.2, name='drop9')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet329.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-3), loss='mse') return model def squeeze_model_159(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(1, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=2, expand=6) x = Dropout(0.2, name='drop9')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet159.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-1), loss='mse') return model def squeeze_model_63(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(1, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=2, expand=2) x = Dropout(0.2, name='drop9')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet63.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-1), loss='mse') return model def squeeze_model_52(): This model is a modification from the reference: https://github.com/rcmalli/keras-squeezenet/blob/master/squeezenet.py Normalizing will be done in the model directly for GPU speedup input_shape=(64, 64, 1) input_img = Input(shape=input_shape) x = Lambda(lambda x: x/127.5 - 1.,input_shape=input_shape)(input_img) x = Convolution2D(2, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(x) x = Activation('elu', name='elu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=1, expand=2) x = Dropout(0.2, name='drop3')(x) x = GlobalAveragePooling2D()(x) out = Dense(1, name='loss')(x) model = Model(input=input_img, output=[out]) plot(model, to_file='SqueezeNet52.png', show_shapes=True) model.compile(optimizer=Adam(lr=1e-1), loss='mse') return model model = squeeze_model_52() model.summary() class CustomEarlyStop(Callback): Custom Callback that stops the epoch when val_loss reachs 0.3 This callback assumes you are logging val loss def __init__(self, monitor='val_loss'): super(CustomEarlyStop, self).__init__() self.monitor = monitor def on_epoch_end(self, epoch, logs=None): val_loss = logs.get(self.monitor) if val_loss <= 0.039: print("\nEarly Stop on Epoch {0} with Val_loss {1}\n".format(epoch,val_loss)) self.model.stop_training = True #This is a callback that works with https://github.com/fchollet/hualos and gives you simple vis of the training loss remote = RemoteMonitor(headers=None) early_stop = CustomEarlyStop(monitor='val_loss') h = model.fit(x=features,y=labels,verbose=1,batch_size=128,nb_epoch=50,validation_split=0.3, callbacks=[remote, early_stop]) filename = 'model'#"squeezemodel{0}".format(squeezemodel.count_params()) model.save_weights(filename+".h5", True) with open(filename+'.json', 'w') as outfile: json.dump(model.to_json(), outfile) print("Saved model weights and configuration") <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Each row is an observed flower. These rows are called samples and the number of rows is called n_samples. Step2: Let's split the data according to the convention Step3: To summarize, in order to use Scikit-Learn, the data layout should look like this Step4: 1. Choose a class of model Step5: 2. Model instantiation with hyperparameters Step6: Other models have different parameters. Refer to the documentation. Step7: 4. Fit the model to your data (i.e. learning) Step8: This fit() command causes a number of model-dependent internal computations to take place. Step9: Comparing to the data definition, we see that they are very close to the input slope of 2 and intercept of -1. Step10: Again, we have to coerce our data into a [n_samples, n_features] feature matrix Step11: Finally, let's visualize the results by plotting first the raw data, and then this model fit Step12: Training and Test Set	<ASSISTANT_TASK:> Python Code: import seaborn as sns iris = sns.load_dataset('iris') iris.head() %matplotlib inline import seaborn as sns; sns.set() sns.pairplot(iris, hue='species', size=1.5); X_iris, y_iris = iris.drop('species', axis=1), iris['species'] X_iris.shape, y_iris.shape import matplotlib.pyplot as plt import numpy as np rng = np.random.RandomState(42) x = 10 * rng.rand(50) y = 2 * x - 1 + rng.randn(50) plt.scatter(x, y); from sklearn.linear_model import LinearRegression model = LinearRegression(fit_intercept=True) model X = x[:, np.newaxis] X.shape model.fit(X, y) model.coef_ model.intercept_ xfit = np.linspace(-1, 11) Xfit = xfit[:, np.newaxis] yfit = model.predict(Xfit) plt.scatter(x, y) plt.plot(xfit, yfit); from sklearn.model_selection import train_test_split Xtrain, Xtest, ytrain, ytest = train_test_split(X_iris, y_iris, random_state=1) Xtrain.shape, Xtest.shape <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Forward modelling	<ASSISTANT_TASK:> Python Code: p=Function('p') m,s,h = symbols('m s h') m=M(x,y,z) q=Q(x,y,z,t) d=D(x,y,z,t) e=E(x,y,z) # Choose dimension (2 or 3) dim = 3 # Choose order time_order = 2 space_order = 2 # half width for indexes, goes from -half to half width_t = int(time_order/2) width_h = int(space_order/2) solvep = p(x,y,z,t+width_ts) solvepa = p(x,y,z,t-width_ts) # Indexes for finite differences indx = [] indy = [] indz = [] indt = [] for i in range(-width_h,width_h+1): indx.append(x + i * h) indy.append(y + i * h) indz.append(z + i* h) for i in range(-width_t,width_t+1): indt.append(t + i * s) # Finite differences dtt=as_finite_diff(p(x,y,z,t).diff(t,t),indt) dxx=as_finite_diff(p(x,y,z,t).diff(x,x), indx) dyy=as_finite_diff(p(x,y,z,t).diff(y,y), indy) dzz=as_finite_diff(p(x,y,z,t).diff(z,z), indz) dt=as_finite_diff(p(x,y,z,t).diff(t), indt) lap = dxx + dyy + dzz arglamb=[] arglamba=[] for i in range(-width_t,width_t): arglamb.append( p(x,y,z,indt[i+width_t])) arglamba.append( p(x,y,z,indt[i+width_t+1])) for i in range(-width_h,width_h+1): arglamb.append( p(indx[i+width_h],y,z,t)) arglamba.append( p(indx[i+width_h],y,z,t)) for i in range(-width_h,width_h+1): arglamb.append( p(x,indy[i+width_h],z,t)) arglamba.append( p(x,indy[i+width_h],z,t)) for i in range(-width_h,width_h+1): arglamb.append( p(x,y,indz[i+width_h],t)) arglamba.append( p(x,y,indz[i+width_h],t)) arglamb.extend((q , m, s, h, e)) arglamb=tuple(arglamb) arglamba.extend((q , m, s, h, e)) arglamba=tuple(arglamba) arglamb=[ii for n,ii in enumerate(arglamb) if ii not in arglamb[:n]] arglamb # Forward wave equation wave_equation = mdtt- lap - q + edt stencil = solve(wave_equation,solvep)[0] ts=lambdify(arglamb,stencil,"numpy") stencil # Adjoint wave equation wave_equationA = mdtt- lap - d - edt stencilA = solve(wave_equationA,solvepa)[0] tsA=lambdify(arglamba,stencilA,"numpy") stencilA import matplotlib.pyplot as plt from matplotlib import animation hstep=25 #space increment d = minv/(10f0); tstep=2 #time increment dt < .5 hstep /maxv; tmin=0.0 #initial time tmax=300 #simulate until xmin=-500.0 #left bound xmax=500.0 #right bound...assume packet never reaches boundary ymin=-600.0 #left bound ymax=600.0 #right bound...assume packet never reaches boundary zmin=-250.0 #left bound zmax=400.0 #right bound...assume packet never reaches boundary f0=.010 t0=1/.010 nbpml=10 nx = int((xmax-xmin)/hstep) + 1 #number of points on x grid ny = int((ymax-ymin)/hstep) + 1 #number of points on x grid nz = int((zmax-zmin)/hstep) + 1 #number of points on x grid nt = int((tmax-tmin)/tstep) + 2 #number of points on t grid xsrc=0.0 ysrc=0.0 zsrc=25.0 #set source as Ricker wavelet for f0 def source(x,y,z,t): r = (np.pif0(t-t0)) val = (1-2.r2)np.exp(-r*2) if abs(x-xsrc)<hstep/2 and abs(y-ysrc)<hstep/2 and abs(z-zsrc)<hstep/2: return val else: return 0.0 def dampx(x): dampcoeff=1.5np.log(1.0/0.001)/(5.0hstep); if x<nbpml: return dampcoeff((nbpml-x)/nbpml)*2 elif x>nx-nbpml-1: return dampcoeff((x-nx+nbpml)/nbpml)*2 else: return 0.0 def dampy(y): dampcoeff=1.5np.log(1.0/0.001)/(5.0hstep); if y<nbpml: return dampcoeff((nbpml-y)/nbpml)*2 elif y>ny-nbpml-1: return dampcoeff((y-ny+nbpml)/nbpml)*2 else: return 0.0 def dampz(z): dampcoeff=1.5np.log(1.0/0.001)/(5.0hstep); if z<nbpml: return dampcoeff((nbpml-z)/nbpml)*2 elif z>nz-nbpml-1: return dampcoeff((z-ny+nbpml)/nbpml)2 else: return 0.0 # True velocity vel=np.ones((nx,ny,nz)) + 2.0 vel[:,:,int(nz/2):nz]=4.5 mt=vel-2 def Forward(nt,nx,ny,nz,m): u=np.zeros((nt+2,nx,ny,nz)) for ti in range(2,nt+2): for a in range(1,nx-1): for b in range(1,ny-1): for c in range(1,nz-1): src = source(xmin+ahstep,ymin+bhstep,zmin+chstep,tstepti) damp=dampx(a)+dampy(b)+dampz(c) u[ti,a,b,c]=ts(u[ti-2,a,b,c], u[ti-1,a,b,c], u[ti-1,a-1,b,c], u[ti-1,a+1,b,c], u[ti-1,a,b-1,c], u[ti-1,a,b+1,c], u[ti-1,a,b,c-1], u[ti-1,a,b,c+1], src , m[a,b,c], tstep, hstep, damp) return u u = Forward(nt,nx,ny,nz,mt) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Document Authors Step2: Document Contributors Step3: Document Publication Step4: Document Table of Contents Step5: 1.2. Model Name Step6: 1.3. Chemistry Scheme Scope Step7: 1.4. Basic Approximations Step8: 1.5. Prognostic Variables Form Step9: 1.6. Number Of Tracers Step10: 1.7. Family Approach Step11: 1.8. Coupling With Chemical Reactivity Step12: 2. Key Properties --> Software Properties Step13: 2.2. Code Version Step14: 2.3. Code Languages Step15: 3. Key Properties --> Timestep Framework Step16: 3.2. Split Operator Advection Timestep Step17: 3.3. Split Operator Physical Timestep Step18: 3.4. Split Operator Chemistry Timestep Step19: 3.5. Split Operator Alternate Order Step20: 3.6. Integrated Timestep Step21: 3.7. Integrated Scheme Type Step22: 4. Key Properties --> Timestep Framework --> Split Operator Order Step23: 4.2. Convection Step24: 4.3. Precipitation Step25: 4.4. Emissions Step26: 4.5. Deposition Step27: 4.6. Gas Phase Chemistry Step28: 4.7. Tropospheric Heterogeneous Phase Chemistry Step29: 4.8. Stratospheric Heterogeneous Phase Chemistry Step30: 4.9. Photo Chemistry Step31: 4.10. Aerosols Step32: 5. Key Properties --> Tuning Applied Step33: 5.2. Global Mean Metrics Used Step34: 5.3. Regional Metrics Used Step35: 5.4. Trend Metrics Used Step36: 6. Grid Step37: 6.2. Matches Atmosphere Grid Step38: 7. Grid --> Resolution Step39: 7.2. Canonical Horizontal Resolution Step40: 7.3. Number Of Horizontal Gridpoints Step41: 7.4. Number Of Vertical Levels Step42: 7.5. Is Adaptive Grid Step43: 8. Transport Step44: 8.2. Use Atmospheric Transport Step45: 8.3. Transport Details Step46: 9. Emissions Concentrations Step47: 10. Emissions Concentrations --> Surface Emissions Step48: 10.2. Method Step49: 10.3. Prescribed Climatology Emitted Species Step50: 10.4. Prescribed Spatially Uniform Emitted Species Step51: 10.5. Interactive Emitted Species Step52: 10.6. Other Emitted Species Step53: 11. Emissions Concentrations --> Atmospheric Emissions Step54: 11.2. Method Step55: 11.3. Prescribed Climatology Emitted Species Step56: 11.4. Prescribed Spatially Uniform Emitted Species Step57: 11.5. Interactive Emitted Species Step58: 11.6. Other Emitted Species Step59: 12. Emissions Concentrations --> Concentrations Step60: 12.2. Prescribed Upper Boundary Step61: 13. Gas Phase Chemistry Step62: 13.2. Species Step63: 13.3. Number Of Bimolecular Reactions Step64: 13.4. Number Of Termolecular Reactions Step65: 13.5. Number Of Tropospheric Heterogenous Reactions Step66: 13.6. Number Of Stratospheric Heterogenous Reactions Step67: 13.7. Number Of Advected Species Step68: 13.8. Number Of Steady State Species Step69: 13.9. Interactive Dry Deposition Step70: 13.10. Wet Deposition Step71: 13.11. Wet Oxidation Step72: 14. Stratospheric Heterogeneous Chemistry Step73: 14.2. Gas Phase Species Step74: 14.3. Aerosol Species Step75: 14.4. Number Of Steady State Species Step76: 14.5. Sedimentation Step77: 14.6. Coagulation Step78: 15. Tropospheric Heterogeneous Chemistry Step79: 15.2. Gas Phase Species Step80: 15.3. Aerosol Species Step81: 15.4. Number Of Steady State Species Step82: 15.5. Interactive Dry Deposition Step83: 15.6. Coagulation Step84: 16. Photo Chemistry Step85: 16.2. Number Of Reactions Step86: 17. Photo Chemistry --> Photolysis Step87: 17.2. Environmental Conditions	<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'cas', 'sandbox-3', 'atmoschem') # Set as follows: DOC.set_author("name", "email") # TODO - please enter value(s) # Set as follows: DOC.set_contributor("name", "email") # TODO - please enter value(s) # Set publication status: # 0=do not publish, 1=publish. DOC.set_publication_status(0) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.model_overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.model_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.chemistry_scheme_scope') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "troposhere" # "stratosphere" # "mesosphere" # "mesosphere" # "whole atmosphere" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.basic_approximations') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.prognostic_variables_form') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "3D mass/mixing ratio for gas" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.number_of_tracers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.family_approach') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.coupling_with_chemical_reactivity') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.software_properties.repository') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.software_properties.code_version') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.software_properties.code_languages') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Operator splitting" # "Integrated" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_advection_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_physical_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_chemistry_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_alternate_order') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.integrated_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.integrated_scheme_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Explicit" # "Implicit" # "Semi-implicit" # "Semi-analytic" # "Impact solver" # "Back Euler" # "Newton Raphson" # "Rosenbrock" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.turbulence') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.convection') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.precipitation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.emissions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.deposition') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.gas_phase_chemistry') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.tropospheric_heterogeneous_phase_chemistry') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.stratospheric_heterogeneous_phase_chemistry') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.photo_chemistry') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.timestep_framework.split_operator_order.aerosols') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.tuning_applied.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.tuning_applied.global_mean_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.tuning_applied.regional_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.key_properties.tuning_applied.trend_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.matches_atmosphere_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.resolution.name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.resolution.canonical_horizontal_resolution') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.resolution.number_of_horizontal_gridpoints') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.resolution.number_of_vertical_levels') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.grid.resolution.is_adaptive_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.transport.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.transport.use_atmospheric_transport') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.transport.transport_details') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.sources') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Vegetation" # "Soil" # "Sea surface" # "Anthropogenic" # "Biomass burning" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.method') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Climatology" # "Spatially uniform mixing ratio" # "Spatially uniform concentration" # "Interactive" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.prescribed_climatology_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.prescribed_spatially_uniform_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.interactive_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.surface_emissions.other_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.sources') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Aircraft" # "Biomass burning" # "Lightning" # "Volcanos" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.method') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Climatology" # "Spatially uniform mixing ratio" # "Spatially uniform concentration" # "Interactive" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.prescribed_climatology_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.prescribed_spatially_uniform_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.interactive_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.atmospheric_emissions.other_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.concentrations.prescribed_lower_boundary') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.emissions_concentrations.concentrations.prescribed_upper_boundary') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.species') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "HOx" # "NOy" # "Ox" # "Cly" # "HSOx" # "Bry" # "VOCs" # "isoprene" # "H2O" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_bimolecular_reactions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_termolecular_reactions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_tropospheric_heterogenous_reactions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_stratospheric_heterogenous_reactions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_advected_species') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.number_of_steady_state_species') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.interactive_dry_deposition') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.wet_deposition') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.gas_phase_chemistry.wet_oxidation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.gas_phase_species') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Cly" # "Bry" # "NOy" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.aerosol_species') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Sulphate" # "Polar stratospheric ice" # "NAT (Nitric acid trihydrate)" # "NAD (Nitric acid dihydrate)" # "STS (supercooled ternary solution aerosol particule))" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.number_of_steady_state_species') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.sedimentation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.stratospheric_heterogeneous_chemistry.coagulation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.gas_phase_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.aerosol_species') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Sulphate" # "Nitrate" # "Sea salt" # "Dust" # "Ice" # "Organic" # "Black carbon/soot" # "Polar stratospheric ice" # "Secondary organic aerosols" # "Particulate organic matter" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.number_of_steady_state_species') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.interactive_dry_deposition') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.tropospheric_heterogeneous_chemistry.coagulation') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.photo_chemistry.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.photo_chemistry.number_of_reactions') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.photo_chemistry.photolysis.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Offline (clear sky)" # "Offline (with clouds)" # "Online" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.atmoschem.photo_chemistry.photolysis.environmental_conditions') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Input Parameter Step2: Preparation Step3: Create space and time vector Step4: Source signal - Ricker-wavelet Step5: Time stepping Step6: Save seismograms	<ASSISTANT_TASK:> Python Code: %matplotlib inline import numpy as np import matplotlib.pyplot as plt # Discretization c1=20 # Number of grid points per dominant wavelength c2=0.5 # CFL-Number nx=2000 # Number of grid points T=10 # Total propagation time # Source Signal f0= 10 # Center frequency Ricker-wavelet q0= 1 # Maximum amplitude Ricker-Wavelet xscr = 100 # Source position (in grid points) # Receiver xrec1=400 # Position Reciever 1 (in grid points) xrec2=800 # Position Reciever 2 (in grid points) xrec3=1800 # Position Reciever 3 (in grid points) # Velocity and density modell_v = np.hstack((1000np.ones((int(nx/2))),1500np.ones((int(nx/2))))) rho=np.hstack((1np.ones((int(nx/2))),1.5np.ones((int(nx/2))))) # Init wavefields vx=np.zeros(nx) p=np.zeros(nx) # Calculate first Lame-Paramter l=rho * modell_v * modell_v cmin=min(modell_v.flatten()) # Lowest P-wave velocity cmax=max(modell_v.flatten()) # Highest P-wave velocity fmax=2f0 # Maximum frequency dx=cmin/(fmaxc1) # Spatial discretization (in m) dt=dx/(cmax)c2 # Temporal discretization (in s) lampda_min=cmin/fmax # Smallest wavelength # Output model parameter: print("Model size: x:",dxnx,"in m") print("Temporal discretization: ",dt," s") print("Spatial discretization: ",dx," m") print("Number of gridpoints per minimum wavelength: ",lampda_min/dx) x=np.arange(0,dxnx,dx) # Space vector t=np.arange(0,T,dt) # Time vector nt=np.size(t) # Number of time steps # Plotting model fig, (ax1, ax2) = plt.subplots(1, 2) fig.subplots_adjust(wspace=0.4,right=1.6) ax1.plot(x,modell_v) ax1.set_ylabel('VP in m/s') ax1.set_xlabel('Depth in m') ax1.set_title('P-wave velocity') ax2.plot(x,rho) ax2.set_ylabel('Density in g/cm^3') ax2.set_xlabel('Depth in m') ax2.set_title('Density'); tau=np.pif0(t-1.5/f0) q=q0(1.0-2.0tau2.0)np.exp(-tau2) # Plotting source signal plt.figure(3) plt.plot(t,q) plt.title('Source signal Ricker-Wavelet') plt.ylabel('Amplitude') plt.xlabel('Time in s') plt.draw() # Init Seismograms Seismogramm=np.zeros((3,nt)); # Three seismograms # Calculation of some coefficients i_dx=1.0/(dx) i_dx3=1.0/(dx3) c9=dt*3/24.0 print("Starting time stepping...") ## Time stepping for n in range(2,nt): # Inject source wavelet p[xscr]=p[xscr]+q[n] # Update velocity for kx in range(5,nx-4): # Calculating spatial derivative p_x=i_dx9.0/8.0(p[kx+1]-p[kx])-i_dx1.0/24.0(p[kx+2]-p[kx-1]) p_xxx=i_dx3(-3.0)(p[kx+1]-p[kx])+i_dx3(1)(p[kx+2]-p[kx-1]) # Update velocity vx[kx]=vx[kx]-dt/rho[kx]p_x-l[kx]c91/(rho[kx]*2.0)(p_xxx) # Update pressure for kx in range(5,nx-4): # Calculating spatial derivative vx_x= i_dx9.0/8.0(vx[kx]-vx[kx-1])-i_dx1.0/24.0(vx[kx+1]-vx[kx-2]) vx_xxx=i_dx3(-3.0)(vx[kx]-vx[kx-1])+i_dx3(1)(vx[kx+1]-vx[kx-2]) # Update pressure p[kx]=p[kx]-l[kx]dt(vx_x)-l[kx]*2c91/(rho[kx])(vx_xxx) # Save seismograms Seismogramm[0,n]=p[xrec1] Seismogramm[1,n]=p[xrec2] Seismogramm[2,n]=p[xrec3] print("Finished time stepping!") ## Save seismograms np.save("Seismograms/FD_1D_DX4_DT4_LW",Seismogramm) ## Plot seismograms fig, (ax1, ax2, ax3) = plt.subplots(3, 1) fig.subplots_adjust(hspace=0.4,right=1.6, top = 2 ) ax1.plot(t,Seismogramm[0,:]) ax1.set_title('Seismogram 1') ax1.set_ylabel('Amplitude') ax1.set_xlabel('Time in s') ax1.set_xlim(0, T) ax2.plot(t,Seismogramm[1,:]) ax2.set_title('Seismogram 2') ax2.set_ylabel('Amplitude') ax2.set_xlabel('Time in s') ax2.set_xlim(0, T) ax3.plot(t,Seismogramm[2,:]) ax3.set_title('Seismogram 3') ax3.set_ylabel('Amplitude') ax3.set_xlabel('Time in s') ax3.set_xlim(0, T); <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: So far, we have considered parametric methods that reduce inference Step2: The code uses the histogram function from Numpy. Step3: The train_test_split function makes it easy to split and Step4: Programming Tip. Step5: Programming Tip. Step6: Programming Tip. Step7: <!-- dom Step8: This is tantamount to reorganizing the above previous code Step9: The grid search iterates over all the elements in the params Step10: Programming Tip. Step11: We can use this data to construct a simple nearest neighbor Step12: Programming Tip. Step13: <!-- dom Step14: which produces the following corresponding Figure. Step15: The LeaveOneOut object is an iterable that produces a set of Step16: The next block loops over the disjoint sets of training and test Step17: The last line in the code above reports leave-one-out's estimated Step18: The todense part reformats the sparse matrix that is Step19: The sub-blocks show the windows of the the y data that are being Step20: Or, more concisely checking all entries for approximate equality, Step21: which shows that the results from the nearest neighbor Step22: This code makes it possible to internally optimize over the bandwidth Step23: Figure shows the kernel estimator (heavy Step24: Curse of Dimensionality Step25: <!-- # #ifdef SINGLE --> Step26: <!-- dom	<ASSISTANT_TASK:> Python Code: from __future__ import division %pylab inline from pprint import pprint import textwrap import sys, re old_displayhook = sys.displayhook def displ(x): if x is None: return print "\n".join(textwrap.wrap(repr(x).replace(' ',''),width=80)) sys.displayhook=displ def generate_samples(n,ntrials=500): phat = np.zeros((nbins,ntrials)) for k in range(ntrials): d = rv.rvs(n) phat[:,k],_=histogram(d,bins,density=True) return phat from sklearn.cross_validation import train_test_split from sklearn.neighbors.kde import KernelDensity import numpy as np np.random.seed(123456) from scipy.integrate import quad from scipy import stats rv= stats.beta(2,2) n=100 # number of samples to generate d = rv.rvs(n)[:,None] # generate samples as column-vector train,test,_,_=train_test_split(d,d,test_size=0.5) kdes=[KernelDensity(bandwidth=i).fit(train) for i in [.05,0.1,0.2,0.3]] import numpy as np for i in kdes: f = lambda x: np.exp(i.score_samples(x)) f2 = lambda x: f(x)*2 print 'h=%3.2f\t %3.4f'%(i.bandwidth,quad(f2,0,1)[0] -2np.mean(f(test))) %matplotlib inline from __future__ import division from matplotlib.pylab import subplots fig,ax=subplots() xi = np.linspace(0,1,100)[:,None] for i in kdes: f=lambda x: np.exp(i.score_samples(x)) f2 = lambda x: f(x)2 _=ax.plot(xi,f(xi),label='$h$='+str(i.bandwidth)) _=ax.set_xlabel('$x$',fontsize=28) _=ax.set_ylabel('$y$',fontsize=28) _=ax.plot(xi,rv.pdf(xi),'k:',lw=3,label='true') _=ax.legend(loc=0) ax2 = ax.twinx() _=ax2.hist(d,20,alpha=.3,color='gray') _=ax2.axis(ymax=50) _=ax2.set_ylabel('count',fontsize=28) fig.tight_layout() #fig.savefig('fig-statistics/nonparametric_003.png') class KernelDensityWrapper(KernelDensity): def predict(self,x): return np.exp(self.score_samples(x)) def score(self,test): f = lambda x: self.predict(x) f2 = lambda x: f(x)2 return -(quad(f2,0,1)[0]-2np.mean(f(test))) from sklearn.grid_search import GridSearchCV params = {'bandwidth':np.linspace(0.01,0.5,10)} clf = GridSearchCV(KernelDensityWrapper(), param_grid=params,cv=2) clf.fit(d) print clf.best_params_ from pprint import pprint pprint(clf.grid_scores_) import numpy as np from numpy import cos, pi xi = np.linspace(0,1,100)[:,None] xin = np.linspace(0,1,12)[:,None] f0 = 1 # init frequency BW = 5 y = cos(2pi(f0xin+(BW/2.0)xin2)) from sklearn.neighbors import KNeighborsRegressor knr=KNeighborsRegressor(2) knr.fit(xin,y) from matplotlib.pylab import subplots fig,ax=subplots() yi = cos(2pi(f0xi+(BW/2.0)xi2)) _=ax.plot(xi,yi,'k--',lw=2,label=r'$y(x)$') _=ax.plot(xin,y,'ko',lw=2,ms=11,color='gray',alpha=.8,label='$y(x_i)$') _=ax.fill_between(xi.flat,yi.flat,knr.predict(xi).flat,color='gray',alpha=.3) _=ax.plot(xi,knr.predict(xi),'k-',lw=2,label='$\hat{y}(x)$') _=ax.set_aspect(1/4.) _=ax.axis(ymax=1.05,ymin=-1.05) _=ax.set_xlabel(r'$x$',fontsize=24) _=ax.legend(loc=0) fig.set_tight_layout(True) #fig.savefig('fig-statistics/nonparametric_004.png') knr=KNeighborsRegressor(3) knr.fit(xin,y) fig,ax=subplots() _=ax.plot(xi,yi,'k--',lw=2,label=r'$y(x)$') _=ax.plot(xin,y,'ko',lw=2,ms=11,color='gray',alpha=.8,label='$y(x_i)$') _=ax.fill_between(xi.flat,yi.flat,knr.predict(xi).flat,color='gray',alpha=.3) _=ax.plot(xi,knr.predict(xi),'k-',lw=2,label='$\hat{y}(x)$') _=ax.set_aspect(1/4.) _=ax.axis(ymax=1.05,ymin=-1.05) _=ax.set_xlabel(r'$x$',fontsize=24) _=ax.legend(loc=0) fig.set_tight_layout(True) #fig.savefig('fig-statistics/nonparametric_005.png') from sklearn.cross_validation import LeaveOneOut loo=LeaveOneOut(len(xin)) pprint(list(LeaveOneOut(3))) out=[] for train_index, test_index in loo: _=knr.fit(xin[train_index],y[train_index]) out.append((knr.predict(xi[test_index])-y[test_index])2) print 'Leave-one-out Estimated Risk: ',np.mean(out), _= knr.fit(xin,y) # fit on all data S=(knr.kneighbors_graph(xin)).todense()/float(knr.n_neighbors) print S[:5,:5] print np.hstack([knr.predict(xin[:5]),(Sy)[:5]])#columns match print np.allclose(knr.predict(xin),Sy) xin = np.linspace(0,1,20)[:,None] y = cos(2pi(f0xin+(BW/2.0)xin2)).flatten() from kernel_regression import KernelRegression kr = KernelRegression(gamma=np.linspace(6e3,7e3,500)) kr.fit(xin,y) fig,ax=subplots() #fig.set_size_inches((12,4)) _=ax.plot(xi,kr.predict(xi),'k-',label='kernel',lw=3) _=ax.plot(xin,y,'o',lw=3,color='gray',ms=12) _=ax.plot(xi,yi,'--',color='gray',label='chirp') _=ax.plot(xi,knr.predict(xi),'k-',label='nearest') _=ax.axis(ymax=1.1,ymin=-1.1) _=ax.set_aspect(1/4.) _=ax.axis(ymax=1.05,ymin=-1.05) _=ax.set_xlabel(r'$x$',fontsize=24) _=ax.set_ylabel(r'$y$',fontsize=24) _=ax.legend(loc=0) #fig.savefig('fig-statistics/nonparametric_006.png') sys.displayhook= old_displayhook import numpy as np v=np.random.rand(1000,2)-1/2. from matplotlib.patches import Circle from matplotlib.pylab import subplots fig,ax=subplots() fig.set_size_inches((5,5)) _=ax.set_aspect(1) _=ax.scatter(v[:,0],v[:,1],color='gray',alpha=.3) _=ax.add_patch(Circle((0,0),0.5,alpha=.8,lw=3.,fill=False)) #fig.savefig('fig-statistics/curse_of_dimensionality_001.pdf') for d in [2,3,5,10,20,50]: v=np.random.rand(5000,d)-1/2. hist([np.linalg.norm(i) for i in v]) siz = [2,3,5,10,20,50] fig,axs=subplots(3,2,sharex=True) fig.set_size_inches((10,6)) #fig.set_size_inches((10,8)) for ax,k in zip(axs.flatten(),siz): v=np.random.rand(5000,k)-1/2. _=ax.hist([np.linalg.norm(i) for i in v],color='gray',normed=True); _=ax.vlines(0.5,0,ax.axis()[-1]1.1,lw=3) _=ax.set_title('$d=%d$'%k,fontsize=20) _=ax.tick_params(labelsize='small',top=False,right=False) _=ax.spines['top'].set_visible(False) _=ax.spines['right'].set_visible(False) _=ax.spines['left'].set_visible(False) _=ax.yaxis.set_visible(False) _=ax.axis(ymax=3.5) fig.set_tight_layout(True) #fig.savefig('fig-statistics/curse_of_dimensionality_002.pdf') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The first operation is always to initialize the lucene backend. This only needs to be done once for each running Python process Step2: Tests Step3: Stemming Step4: Tokenizer Step5: Analyzer	<ASSISTANT_TASK:> Python Code: import lucene print(lucene.VERSION) # We can check all the Lucene packages included in this distribution of Pylucene for p in sorted(lucene.CLASSPATH.split(':')): print(p) # Init if not lucene.getVMEnv(): lucene.initVM(vmargs=['-Djava.awt.headless=true']) test_strings = ( 'La lluvia en Sevilla es una pura maravilla', 'En un lugar de La Mancha, de cuyo nombre no quiero acordarme', u'Con diez cañones por banda, viento en popa a toda vela' ) # An auxiliary function used in the tokenizer and analyzer examples from org.apache.lucene.analysis.tokenattributes import CharTermAttribute def fetch_terms(obj): '''fetch all terms from a token list object, as strings''' termAtt = obj.getAttribute(CharTermAttribute.class_) try: obj.clearAttributes() obj.reset() while obj.incrementToken(): yield termAtt.toString() finally: obj.end() obj.close() from lucene import JArray_char, JArray from org.tartarus.snowball.ext import SpanishStemmer, EnglishStemmer def stem(stemmer, word): # Add the word stemmer.setCurrent(JArray_char(word), len(word)) # Fire stemming stemmer.stem() # Fetch the output (buffer & size) result = stemmer.getCurrentBuffer() l = stemmer.getCurrentBufferLength() return ''.join(result)[0:l] st = SpanishStemmer() for w in (u'haciendo', u'lunes', u'vino', u'lápiz'): print( w, '->', stem(st, w)) st = EnglishStemmer() for w in (u'making', u'Monday', u'came', u'pencil'): print( w, '->', stem(st, w)) from java.io import StringReader def tokenize( tk, data ): '''Send a string to a tokenizer and get back the token list''' tk.setReader( StringReader(data) ) return list(fetch_terms(tk)) from org.apache.lucene.analysis.standard import StandardTokenizer from org.apache.lucene.analysis.core import LetterTokenizer from org.apache.lucene.analysis.ngram import NGramTokenizer tokenizers = (StandardTokenizer(), LetterTokenizer(), NGramTokenizer(4, 4)) for n, t in enumerate(tokenizers): print( "\n{} -----------".format(n+1), str(t) ) for s in test_strings: print( "\n", tokenize(t,s) ) from java.io import StringReader def analyze(anal, data): '''Send a string to an analizer and get back the analyzed term list''' ts = anal.tokenStream( "dummy", StringReader(data) ) return list(fetch_terms(ts)) from org.apache.lucene.analysis.core import KeywordAnalyzer, SimpleAnalyzer from org.apache.lucene.analysis.standard import StandardAnalyzer from org.apache.lucene.analysis.es import SpanishAnalyzer from org.apache.lucene.analysis.shingle import ShingleAnalyzerWrapper analyzers = ( KeywordAnalyzer(), SimpleAnalyzer(), SpanishAnalyzer(), ShingleAnalyzerWrapper( SimpleAnalyzer(), 2, 3 ), ShingleAnalyzerWrapper( SpanishAnalyzer(), 2, 3 ), ) for n, a in enumerate(analyzers): print( "\n {} ----------- {}".format(n+1, a) ) for s in test_strings: print( "\n", analyze(a,s) ) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: 2. Set atlas, project and output directories from your nersc home directory Step2: 3. Select groups and get QC files Step3: 4. Get template QC atlas from database Step4: 4b. Uncomment the block below to adjust RT window Step5: 5. Create metatlas dataset from QC files and QC atlas Step6: 5b Optional Step7: 6. Summarize RT peak across files and make data frame Step8: 7. Create Compound atlas RTs plot and choose file for prediction Step9: 8. Create RT adjustment model - Linear & Polynomial Regression Step10: 8. Plot actual vs predict RT values and fit a median coeff+intercept line Step11: 9. Choose your model Step12: 10. Save RT model (optional) Step13: 11. Auto RT adjust Template atlases Step14: OPTIONAL BLOCK FOR RT PREDICTION OF CUSTOM ATLAS	<ASSISTANT_TASK:> Python Code: from IPython.core.display import Markdown, display, clear_output, HTML display(HTML("<style>.container { width:100% !important; }</style>")) %matplotlib notebook %matplotlib inline %env HDF5_USE_FILE_LOCKING=FALSE import sys, os #### add a path to your private code if not using production code #### #print ('point path to metatlas repo') sys.path.insert(0,"/global/homes/v/vrsingan/repos/metatlas") #where your private code is ###################################################################### from metatlas.plots import dill2plots as dp from metatlas.io import metatlas_get_data_helper_fun as ma_data from metatlas.plots import chromatograms_mp_plots as cp from metatlas.plots import chromplotplus as cpp from metatlas.datastructures import metatlas_objects as metob import time import numpy as np import multiprocessing as mp import pandas as pd import operator import matplotlib.pyplot as plt pd.set_option('display.max_rows', 5000) pd.set_option('display.max_columns', 500) pd.set_option('display.max_colwidth', 100) def printmd(string): display(Markdown(string)) project_directory='/global/homes/FIRST-INITIAL-OF-USERNAME/USERNAME/PROJECTDIRECTORY/' # <- edit this line, do not copy the path directly from NERSC (ex. the u1, or u2 directories) output_subfolder='HILIC_POS_20190830/' # <- edit this as 'chromatography_polarity_yyyymmdd/' output_dir = os.path.join(project_directory,output_subfolder) output_data_qc = os.path.join(output_dir,'data_QC') if not os.path.exists(project_directory): os.makedirs(project_directory) if not os.path.exists(output_dir): os.makedirs(output_dir) if not os.path.exists(output_data_qc): os.makedirs(output_data_qc) groups = dp.select_groups_for_analysis(name = '%20201106%505892%HILIC%KLv1%', most_recent = True, remove_empty = True, include_list = ['QC'], exclude_list = ['NEG']) #['QC','Blank'] groups = sorted(groups, key=operator.attrgetter('name')) file_df = pd.DataFrame(columns=['file','time','group']) for g in groups: for f in g.items: if hasattr(f, 'acquisition_time'): file_df = file_df.append({'file':f, 'time':f.acquisition_time,'group':g}, ignore_index=True) else: file_df = file_df.append({'file':f, 'time':0,'group':g}, ignore_index=True) file_df = file_df.sort_values(by=['time']) for file_data in file_df.iterrows(): print(file_data[1].file.name) # DO NOT EDIT THIS BLOCK pos_templates = ['HILICz150_ANT20190824_TPL_EMA_Unlab_POS', 'HILICz150_ANT20190824_TPL_QCv3_Unlab_POS', 'HILICz150_ANT20190824_TPL_ISv5_Unlab_POS', 'HILICz150_ANT20190824_TPL_ISv5_13C15N_POS', 'HILICz150_ANT20190824_TPL_IS_LabUnlab2_POS'] neg_templates = ['HILICz150_ANT20190824_TPL_EMA_Unlab_NEG', 'HILICz150_ANT20190824_TPL_QCv3_Unlab_NEG', 'HILICz150_ANT20190824_TPL_ISv5_Unlab_NEG', 'HILICz150_ANT20190824_TPL_ISv5_13C15N_NEG', 'HILICz150_ANT20190824_TPL_IS_LabUnlab2_NEG'] #Atlas File Name QC_template_filename = pos_templates[1] atlases = metob.retrieve('Atlas',name=QC_template_filename, username='vrsingan') names = [] for i,a in enumerate(atlases): print(i,a.name,pd.to_datetime(a.last_modified,unit='s'),len(a.compound_identifications)) # #Alternatively use this block to create QC atlas from spreadsheet # import datetime #dp = reload(dp) # QC_template_filename = " " #<- Give the template filename to be used for storing in Database #myAtlas = dp.make_atlas_from_spreadsheet('/global/project/projectdirs/metatlas/projects/1_TemplateAtlases/TemplateAtlas_HILICz150mm_Annotation20190824_QCv3_Unlabeled_Positive.csv', # QC_template_filename, # filetype='csv', # sheetname='', # polarity = 'positive', # store=True, # mz_tolerance = 20) #atlases = dp.get_metatlas_atlas(name=QC_template_filename,do_print = True,most_recent=True) myAtlas = atlases[-1] atlas_df = ma_data.make_atlas_df(myAtlas) atlas_df['label'] = [cid.name for cid in myAtlas.compound_identifications] print(myAtlas.name) print(myAtlas.username) # rt_allowance = 1.5 # atlas_df['rt_min'] = atlas_df['rt_peak'].apply(lambda rt: rt-rt_allowance) # atlas_df['rt_max'] = atlas_df['rt_peak'].apply(lambda rt: rt+rt_allowance) # for compound in range(len(myAtlas.compound_identifications)): # rt_peak = myAtlas.compound_identifications[compound].rt_references[0].rt_peak # myAtlas.compound_identifications[compound].rt_references[0].rt_min = rt_peak - rt_allowance # myAtlas.compound_identifications[compound].rt_references[0].rt_max = rt_peak + rt_allowance all_files = [] for file_data in file_df.iterrows(): all_files.append((file_data[1].file,file_data[1].group,atlas_df,myAtlas)) pool = mp.Pool(processes=min(4, len(all_files))) t0 = time.time() metatlas_dataset = pool.map(ma_data.get_data_for_atlas_df_and_file, all_files) pool.close() pool.terminate() #If you're code crashes here, make sure to terminate any processes left open. print(time.time() - t0) # dp = reload(dp) # num_data_points_passing = 3 # peak_height_passing = 1e4 # atlas_df_passing = dp.filter_atlas(atlas_df=atlas_df, input_dataset=metatlas_dataset, num_data_points_passing = num_data_points_passing, peak_height_passing = peak_height_passing) # print("# Compounds in Atlas: "+str(len(atlas_df))) # print("# Compounds passing filter: "+str(len(atlas_df_passing))) # atlas_passing = myAtlas.name+'_filteredby-datapnts'+str(num_data_points_passing)+'-pkht'+str(peak_height_passing) # myAtlas_passing = dp.make_atlas_from_spreadsheet(atlas_df_passing, # atlas_passing, # filetype='dataframe', # sheetname='', # polarity = 'positive', # store=True, # mz_tolerance = 20) # atlases = dp.get_metatlas_atlas(name=atlas_passing,do_print = True, most_recent=True) # myAtlas = atlases[-1] # atlas_df = ma_data.make_atlas_df(myAtlas) # atlas_df['label'] = [cid.name for cid in myAtlas.compound_identifications] # print(myAtlas.name) # print(myAtlas.username) # metob.to_dataframe([myAtlas])# # all_files = [] # for file_data in file_df.iterrows(): # all_files.append((file_data[1].file,file_data[1].group,atlas_df,myAtlas)) # pool = mp.Pool(processes=min(4, len(all_files))) # t0 = time.time() # metatlas_dataset = pool.map(ma_data.get_data_for_atlas_df_and_file, all_files) # pool.close() # pool.terminate() # #If you're code crashes here, make sure to terminate any processes left open. # print(time.time() - t0) from importlib import reload dp=reload(dp) rts_df = dp.make_output_dataframe(input_dataset = metatlas_dataset, fieldname='rt_peak', use_labels=True, output_loc = output_data_qc, summarize=True) rts_df.to_csv(os.path.join(output_data_qc,"QC_Measured_RTs.csv")) rts_df import itertools import math from __future__ import division from matplotlib import gridspec import matplotlib.ticker as mticker rts_df['atlas RT peak'] = [compound['identification'].rt_references[0].rt_peak for compound in metatlas_dataset[0]] # number of columns in rts_df that are not values from a specific input file num_not_files = len(rts_df.columns) - len(metatlas_dataset) rts_df_plot = rts_df.sort_values(by='standard deviation', ascending=False, na_position='last') \ .drop(['#NaNs'], axis=1) \ .dropna(axis=0, how='all', subset=rts_df.columns[:-num_not_files]) fontsize = 2 pad = 0.1 cols = 8 rows = int(math.ceil((rts_df.shape[0]+1)/8)) fig = plt.figure() gs = gridspec.GridSpec(rows, cols, figure=fig, wspace=0.2, hspace=0.4) for i, (index, row) in enumerate(rts_df_plot.iterrows()): ax = fig.add_subplot(gs[i]) ax.tick_params(direction='in', length=1, pad=pad, width=0.1, labelsize=fontsize) ax.scatter(range(rts_df_plot.shape[1]-num_not_files),row[:-num_not_files], s=0.2) ticks_loc = np.arange(0,len(rts_df_plot.columns)-num_not_files , 1.0) ax.axhline(y=row['atlas RT peak'], color='r', linestyle='-', linewidth=0.2) ax.set_xlim(-0.5,len(rts_df_plot.columns)-num_not_files+0.5) ax.xaxis.set_major_locator(mticker.FixedLocator(ticks_loc)) range_columns = list(rts_df_plot.columns[:-num_not_files])+['atlas RT peak'] ax.set_ylim(np.nanmin(row.loc[range_columns])-0.12, np.nanmax(row.loc[range_columns])+0.12) [s.set_linewidth(0.1) for s in ax.spines.values()] # truncate name so it fits above a single subplot ax.set_title(row.name[:33], pad=pad, fontsize=fontsize) ax.set_xlabel('Files', labelpad=pad, fontsize=fontsize) ax.set_ylabel('Actual RTs', labelpad=pad, fontsize=fontsize) plt.savefig(os.path.join(output_data_qc, 'Compound_Atlas_RTs.pdf'), bbox_inches="tight") for i,a in enumerate(rts_df.columns): print(i, a) selected_column=9 from sklearn.linear_model import LinearRegression, RANSACRegressor from sklearn.preprocessing import PolynomialFeatures from sklearn.metrics import mean_absolute_error as mae actual_rts, pred_rts, polyfit_rts = [],[],[] current_actual_df = rts_df.loc[:,rts_df.columns[selected_column]] bad_qc_compounds = np.where(~np.isnan(current_actual_df)) current_actual_df = current_actual_df.iloc[bad_qc_compounds] current_pred_df = atlas_df.iloc[bad_qc_compounds][['rt_peak']] actual_rts.append(current_actual_df.values.tolist()) pred_rts.append(current_pred_df.values.tolist()) ransac = RANSACRegressor(random_state=42) rt_model_linear = ransac.fit(current_pred_df, current_actual_df) coef_linear = rt_model_linear.estimator_.coef_[0] intercept_linear = rt_model_linear.estimator_.intercept_ poly_reg = PolynomialFeatures(degree=2) X_poly = poly_reg.fit_transform(current_pred_df) rt_model_poly = LinearRegression().fit(X_poly, current_actual_df) coef_poly = rt_model_poly.coef_ intercept_poly = rt_model_poly.intercept_ for i in range(rts_df.shape[1]-5): current_actual_df = rts_df.loc[:,rts_df.columns[i]] bad_qc_compounds = np.where(~np.isnan(current_actual_df)) current_actual_df = current_actual_df.iloc[bad_qc_compounds] current_pred_df = atlas_df.iloc[bad_qc_compounds][['rt_peak']] actual_rts.append(current_actual_df.values.tolist()) pred_rts.append(current_pred_df.values.tolist()) #User can change to use particular qc file import itertools import math from __future__ import division from matplotlib import gridspec x = list(itertools.chain(pred_rts)) y = list(itertools.chain(actual_rts)) rows = int(math.ceil((rts_df.shape[1]+1)/5)) cols = 5 fig = plt.figure(constrained_layout=False) gs = gridspec.GridSpec(rows, cols, figure=fig) plt.rc('font', size=6) plt.rc('axes', labelsize=6) plt.rc('xtick', labelsize=3) plt.rc('ytick', labelsize=3) for i in range(rts_df.shape[1]-5): x = list(itertools.chain(pred_rts[i])) y = actual_rts[i] ax = fig.add_subplot(gs[i]) ax.scatter(x, y, s=2) ax.plot(np.linspace(0, max(x),100), coef_linearnp.linspace(0,max(x),100)+intercept_linear, linewidth=0.5,color='red') ax.plot(np.linspace(0, max(x),100), (coef_poly[1]np.linspace(0,max(x),100))+(coef_poly[2](np.linspace(0,max(x),100)*2))+intercept_poly, linewidth=0.5,color='green') ax.set_title("File: "+str(i)) ax.set_xlabel('predicted RTs') ax.set_ylabel('actual RTs') fig_legend = "FileIndex FileName" for i in range(rts_df.shape[1]-5): fig_legend = fig_legend+"\n"+str(i)+" "+rts_df.columns[i] fig.tight_layout(pad=0.5) plt.text(0,-0.03rts_df.shape[1], fig_legend, transform=plt.gcf().transFigure) plt.savefig(os.path.join(output_data_qc, 'Actual_vs_Predicted_RTs.pdf'), bbox_inches="tight") qc_df = rts_df[[rts_df.columns[selected_column]]] qc_df = qc_df.copy() print("Linear Parameters :", coef_linear, intercept_linear) print("Polynomial Parameters :", coef_poly,intercept_poly) qc_df.columns = ['RT Measured'] atlas_df.index = qc_df.index qc_df['RT Reference'] = atlas_df['rt_peak'] qc_df['RT Linear Pred'] = qc_df['RT Reference'].apply(lambda rt: coef_linearrt+intercept_linear) qc_df['RT Polynomial Pred'] = qc_df['RT Reference'].apply(lambda rt: (coef_poly[1]rt)+(coef_poly[2](rt2))+intercept_poly) qc_df['RT Diff Linear'] = qc_df['RT Measured'] - qc_df['RT Linear Pred'] qc_df['RT Diff Polynomial'] = qc_df['RT Measured'] - qc_df['RT Polynomial Pred'] qc_df.to_csv(os.path.join(output_data_qc, "RT_Predicted_Model_Comparison.csv")) qc_df # CHOOSE YOUR MODEL HERE (linear / polynomial). #model = 'linear' model = 'polynomial' # Save model with open(os.path.join(output_data_qc,'rt_model.txt'), 'w') as f: if model == 'linear': f.write('coef = {}\nintercept = {}\nqc_actual_rts = {}\nqc_predicted_rts = {}'.format(coef_linear, intercept_linear, ', '.join([g.name for g in groups]), myAtlas.name)) f.write('\n'+repr(rt_model_linear.set_params())) else: f.write('coef = {}\nintercept = {}\nqc_actual_rts = {}\nqc_predicted_rts = {}'.format(coef_poly, intercept_poly, ', '.join([g.name for g in groups]), myAtlas.name)) f.write('\n'+repr(rt_model_poly.set_params())) pos_atlas_indices = [0,1,2,3,4] neg_atlas_indices = [0,1,2,3,4] free_text = '' # this will be appended to the end of the csv filename exported save_to_db = False for ix in pos_atlas_indices: atlases = metob.retrieve('Atlas',name=pos_templates[ix], username='vrsingan') prd_atlas_name = pos_templates[ix].replace('TPL', 'PRD') if free_text != '': prd_atlas_name = prd_atlas_name+"_"+free_text prd_atlas_filename = prd_atlas_name+'.csv' myAtlas = atlases[-1] PRD_atlas_df = ma_data.make_atlas_df(myAtlas) PRD_atlas_df['label'] = [cid.name for cid in myAtlas.compound_identifications] if model == 'linear': PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: coef_linearrt+intercept_linear) else: PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: (coef_poly[1]rt)+(coef_poly[2](rt*2))+intercept_poly) PRD_atlas_df['rt_min'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt-.5) PRD_atlas_df['rt_max'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt+.5) PRD_atlas_df.to_csv(os.path.join(output_data_qc,prd_atlas_filename), index=False) if save_to_db: dp.make_atlas_from_spreadsheet(PRD_atlas_df, prd_atlas_name, filetype='dataframe', sheetname='', polarity = 'positive', store=True, mz_tolerance = 12) print(prd_atlas_name+" Created!") for ix in neg_atlas_indices: atlases = metob.retrieve('Atlas',name=neg_templates[ix], username='vrsingan') prd_atlas_name = neg_templates[ix].replace('TPL', 'PRD') if free_text != '': prd_atlas_name = prd_atlas_name+"_"+free_text prd_atlas_filename = prd_atlas_name+'.csv' myAtlas = atlases[-1] PRD_atlas_df = ma_data.make_atlas_df(myAtlas) PRD_atlas_df['label'] = [cid.name for cid in myAtlas.compound_identifications] if model == 'linear': PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: coef_linearrt+intercept_linear) else: PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: (coef_poly[1]rt)+(coef_poly[2](rt*2))+intercept_poly) PRD_atlas_df['rt_min'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt-.5) PRD_atlas_df['rt_max'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt+.5) PRD_atlas_df.to_csv(os.path.join(output_data_qc,prd_atlas_filename), index=False) if save_to_db: dp.make_atlas_from_spreadsheet(PRD_atlas_df, prd_atlas_name, filetype='dataframe', sheetname='', polarity = 'negative', store=True, mz_tolerance = 12) print(prd_atlas_name+" Created!") ## Optional for custom template predictions # atlas_name = '' #atlas name # save_to_db = False # atlases = metob.retrieve('Atlas',name=atlas_name, username='') # myAtlas = atlases[-1] # PRD_atlas_df = ma_data.make_atlas_df(myAtlas) # PRD_atlas_df['label'] = [cid.name for cid in myAtlas.compound_identifications] # if model == 'linear': # PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: coef_linearrt+intercept_linear) # else: # PRD_atlas_df['rt_peak'] = PRD_atlas_df['rt_peak'].apply(lambda rt: (coef_poly[1]rt)+(coef_poly[2](rt*2))+intercept_poly) # PRD_atlas_df['rt_min'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt-.5) # PRD_atlas_df['rt_max'] = PRD_atlas_df['rt_peak'].apply(lambda rt: rt+.5) # PRD_atlas_df.to_csv(os.path.join(output_data_qc, name=atlas_name.replace('TPL','PRD'), index=False) # if save_to_db: # dp.make_atlas_from_spreadsheet(PRD_atlas_df, # PRD_atlas_name, # filetype='dataframe', # sheetname='', # polarity = 'positive', # NOTE - Please make sure you are choosing the correct polarity # store=True, # mz_tolerance = 12) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: BASICS OF NETWORKX Step2: PLOT GRAPH Step3: PLOT GRAPH WITH SHORTEST PATH Step4: SHORTEST PATHS	<ASSISTANT_TASK:> Python Code: import psycopg2 import pandas as pd import networkx as nx import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline conn = psycopg2.connect(database="postgres", user="postgres", password="***", host="127.0.0.1", port="5432") query = SELECT fromnode, tonode, distance from edges df = pd.read_sql_query(query, conn) df.shape # from dataframe to graph # import as undirected graph g=nx.from_pandas_dataframe(df, 'fromnode', 'tonode', 'distance') # from graph to dataframe as a matrix nx.to_pandas_dataframe(g, weight='distance') # print nodes and edges print 'list nodes: ', g.nodes(), '\n' print 'no. nodes:', len(g) #no. nodes print 'no. edges:', g.number_of_edges(), '\n' print 'list edges: ', g.edges(), '\n' print 'list all edge attributes: ', dict(((a,b,),c['distance']) for a,b,c in g.edges(data=True)) # choose layoutl pos=position for nodes pos = nx.fruchterman_reingold_layout(g) # draw network nx.draw(g, pos, with_labels = True, node_size=800, node_color='pink', edge_color='grey') # label edges edge_labels = dict([((u,v,),d['distance']) for u,v,d in g.edges(data=True)]) nx.draw_networkx_edge_labels(graph, pos, edge_labels=edge_labels) s=2 t=7 print nx.shortest_path(g, source=s,target=t, weight='distance') plt.figure(figsize=(5, 5)) # choose layout pos = nx.fruchterman_reingold_layout(g) # draw network nx.draw(g, pos, with_labels = True, node_size=800, node_color='pink', edge_color='grey') # nx.draw_networkx_edges(g, pos, edge_color='grey',width=0.1, alpha=0.5) # label edges edge_labels = dict([((u,v,),d['distance']) for u,v,d in g.edges(data=True)]) nx.draw_networkx_edge_labels(graph, pos, edge_labels=edge_labels) # plot shortest path path = nx.shortest_path(g, source=s,target=t, weight='distance') path_edges = zip(path,path[1:]) # nx.draw_networkx_nodes(g,pos,nodelist=path,node_color='black', node_size=1000) nx.draw_networkx_edges(g,pos,edgelist=path_edges,edge_color='r',width=15) # shortest path nx.shortest_path(graph, source=1, target=3, weight='distance') # shortest path paths = nx.all_shortest_paths(graph, source=1, target=7, weight='distance') for path in paths: print path # all simple paths without weight path = nx.all_simple_paths(graph, source=1, target=7) for i in path: print i <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Set up an Observer and list of FixedTargets in astroplan. Step2: Determine which standards are observable tonight.	<ASSISTANT_TASK:> Python Code: catalog_name = 'Landolt 1992' observatory_name = 'Apache Point' from astroquery.vizier import Vizier from astropy.coordinates import SkyCoord import astropy.units as u catalog_list = Vizier.find_catalogs(catalog_name) catalogs = Vizier.get_catalogs(catalog_list.keys()) Vizier.ROW_LIMIT = -1 # Otherwise would only show first 50 values catalog_table = catalogs[0] # This is the table with the data RAs = u.Quantity(catalog_table['_RAJ2000'].data, unit=u.deg) Decs = u.Quantity(catalog_table['_DEJ2000'].data, unit=u.deg) names = list(catalog_table['SimbadName'].data) landolt_standards = SkyCoord(ra=RAs, dec=Decs) from astroplan import Observer, FixedTarget obs = Observer.at_site(observatory_name) target_list = [FixedTarget(coord=coord, name=name) for coord, name in zip(landolt_standards, names)] from astroplan import is_observable, observability_table, AltitudeConstraint, AtNightConstraint from astropy.time import Time constraints = [AltitudeConstraint(min=25*u.deg), AtNightConstraint.twilight_astronomical()] # Figure out when "tonight" is present_time = Time.now() if not obs.is_night(present_time): # If it's currently day time at runtime, find time of sunset and sunrise tonight_start = obs.sun_set_time(present_time, which='next') tonight_end = obs.sun_rise_time(present_time, which='next') else: # Otherwise find time to next sunrise tonight_start = present_time tonight_end = obs.sun_rise_time(present_time, which='next') table = observability_table(constraints, obs, target_list, time_range=Time([tonight_start, tonight_end])) print(table) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: First Overview of the Data Step2: Embedding & Prepping the data Step3: Metrics and Evaluation Step4: What's a Recurrent Neural Network (RNN)? Step5: Let's now compile and train our model, using Sparce Categorical Cross-Entropy Loss as our loss function (you can read more about it <a href="https Step6: Evaluation in terms of EM and F1 Scores Step7: Our first Model - when trained on 70,000+ datapoints - obtains an Exact Match Score of 11.0%, and a F1 Score of 23.8% on the Test set. This is not ideal yet... Below are a few ideas on how we could improve from there - by adding complexity while making sure we keep the regularization in check! Step8: Let's explore our Results!	<ASSISTANT_TASK:> Python Code: # Basics for Data Manipulation import matplotlib.pyplot as plt import seaborn as sns import pandas as pd import numpy as np # Tensorflow and Keras tools import tensorflow as tf import tensorflow_hub as hub from tensorflow.keras.models import Sequential, Model from tensorflow.keras.layers import ( Layer, Input, Dense, Concatenate, Masking, Embedding, Dropout, Softmax, Dot, Lambda, SimpleRNN, GRU, LSTM, Bidirectional ) from tensorflow.keras import regularizers from tensorflow.keras.preprocessing.text import Tokenizer from tensorflow.keras.preprocessing.sequence import pad_sequences from tensorflow.keras.preprocessing.text import text_to_word_sequence from tensorflow.keras.callbacks import ModelCheckpoint from tensorflow.keras.utils import plot_model from tensorflow.keras.models import Model from sklearn.model_selection import train_test_split import string #Loading the training data i.e. a dataframe of 15,000 ground-truth question-context-answer triples from the SQuAD Dataset data = pd.read_csv('../assets/qa/squadlite.csv') data.head(3) #Loading the test data i.e. a dataframe of 5,000+ questions/answers to test on model on test = pd.read_csv('../assets/qa/squadtest.csv') test.head(3) # Splitting the questions/paragraphs into words and embedding them... pars = [] ques = [] embed = hub.KerasLayer("https://tfhub.dev/google/nnlm-en-dim128/2") #NNLM for text in data.context: words = np.array(text_to_word_sequence(text)) pars.append(embed(tf.constant(words))) for text in data.question: words = np.array(text_to_word_sequence(text)) ques.append(embed(tf.constant(words))) # Now padding... padded_pars = pad_sequences(pars, padding="post",dtype='float32') padded_ques = pad_sequences(ques, padding="post",dtype='float32') # Key Dimensions batch_size = np.shape(padded_pars)[0] #Batch Size max_paragraph_length = np.shape(padded_pars)[1] #Time Steps max_question_length = np.shape(padded_ques)[1] #Time Steps emb_dim = np.shape(padded_pars)[2] #Embed Dimension print("Shape of the Padded Embedded Paragraphs: ", np.shape(padded_pars)) print("Shape of the Padded Embedded Questions: ", np.shape(padded_ques)) print("i.e. (Batch Size, Sequence Length, Embed Dimension)") # Our y data (i.e the positions of the answer's start and end words) y_start_word = np.array(data.start_word) y_end_word = np.array(data.end_word) print("Shape of the Y Train set for Start Word: ", np.shape(y_start_word)) print("Shape of the Y Train set for End Word: ", np.shape(y_end_word)) # Train & Validation p_train, p_val, q_train, q_val, ys_train, ys_val, ye_train, ye_val = train_test_split( padded_pars, padded_ques, y_start_word, y_end_word, test_size=0.1, random_state=30 ) # Let's create helper functions to measure these metrics # Both exact_match & f1_score take strings as inputs def exact_match(pred, truth): truth = str(truth).replace("-", " ") truth = "".join(l for l in truth if l not in string.punctuation) return np.sum(str(pred).lower() == str(truth).lower()) def f1_score(pred, truth): p = text_to_word_sequence(str(pred)) t = text_to_word_sequence(str(truth)) tp = [i for i in p if i in t] if len(tp) == 0: f1 = 0 else: precision = len(tp)/len(p) recall = len(tp)/len(t) f1 = 2 * (precision * recall) / (precision + recall) return f1 # First Input = Paragraphs / Straightforward GRU Layer paragraphs = Input(shape=(max_paragraph_length, emb_dim), name="pars_in") p = Masking(mask_value=0)(paragraphs) p = GRU( 256, return_sequences=True, name="pars_out", kernel_regularizer=regularizers.l2(0.002), kernel_initializer="glorot_normal", )(p) # Output is = a 128d vector per word in the paragraph (None, max_paragraph_length, 128). # Second Input = Questions / Straightforward GRU questions = Input(shape=(max_question_length, emb_dim), name="ques_in") q = Masking(mask_value=0)(questions) q = GRU( 256, return_sequences=True, name="ques_gru", kernel_regularizer=regularizers.l2(0.002), kernel_initializer="glorot_normal", )(q) # Output is = a 256d vector per word in the paragraph (None, max_question_length, 256). # Weighted Average to obtain the single vector q' weights = Dense(1, activation="softmax", name="weights")(q) q = Dot(axes=1, name="ques_out")([weights, q]) # Output is = a single 256d vector per question (None, 256, 1). # Outputs for Start & End / Quadratic Layers and Softmax qs = Dense( 256, activation="linear", name="s1", use_bias=False, kernel_regularizer=regularizers.l2(0.001), )(q) outs = Dot(axes=(2, 2), name="s2")([p, qs]) qe = Dense( 256, activation="linear", name="e1", use_bias=False, kernel_regularizer=regularizers.l2(0.001), )(q) oute = Dot(axes=(2, 2), name="e2")([p, qe]) # Output is = a probability vector (None, seq_pars, 1) for each # Model model = Model(inputs=[paragraphs, questions], outputs=[outs, oute]) # print(BaseModel.summary()) # Model Chart plot_model(model, to_file="Baseline.png", show_shapes=True) # Compiling our model acc = tf.keras.metrics.SparseCategoricalAccuracy() opt = tf.keras.optimizers.Adamax() sce = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True) model.compile( optimizer=opt, loss=[sce, sce], loss_weights=[1, 1], metrics=[[acc], [acc]] ) # Defining a checkpoint to save our best weights during Training checkpoint = ModelCheckpoint( filepath="basemodel", frequency="epoch", save_weights_only=True, save_best_only=True, verbose=0, ) # Training (using the predefined checkpoint and our validation set) history = model.fit( [p_train, q_train], [ys_train, ye_train], validation_data=([p_val, q_val], [ys_val, ye_val]), epochs=1, batch_size=64, callbacks=[checkpoint], verbose=0, ) # Using our Best Model i.e. load the saved weights model.load_weights('basemodel') # Function to measure overall EM and F1 on the Test Set def create_masked_matrix(pred_start, pred_end): # Creating the masked matrix of possible answers (where start < end < start 15) masked_matrix = tf.matmul(pred_start, tf.transpose(pred_end, [0, 2, 1])) i, j = np.meshgrid( map(np.arange, (masked_matrix.shape[1], masked_matrix.shape[2])), indexing="ij" ) masked_matrix.mask = (i <= j) & (j < i+15) masked_matrix = np.where(masked_matrix.mask, masked_matrix, 0) max_results = np.amax(masked_matrix, axis=(1, 2)) return masked_matrix, max_results def model_eval(pred): pred_start = tf.exp(pred[0]) pred_end = tf.exp(pred[1]) masked_matrix, max_results = create_masked_matrix(pred_start, pred_end) number_of_examples = masked_matrix.shape[0] em = [] f1 = [] # Find the most probable answer for each question in the test set. # We compare with the four human answers, and keep the max F1 and EM scores. for k in range(number_of_examples): result = np.where(masked_matrix[k] == max_results[k]) if result[1][0] < len(text_to_word_sequence(test.context[k])): answer = np.array(text_to_word_sequence(test.context[k]))[result[0][0]:result[1][0]+1] else: answer = ['-'] if result[0][0] != result[1][0] and result[1][0] < len( text_to_word_sequence(test.context[k]) ): answer = " ".join(answer) else: answer = str(answer[0]) em_k = max( exact_match(answer, test.answer1[k]), exact_match(answer, test.answer2[k]), exact_match(answer, test.answer3[k]), exact_match(answer, test.answer4[k]), ) f1_k = max( f1_score(answer, test.answer1[k]), f1_score(answer, test.answer2[k]), f1_score(answer, test.answer3[k]), f1_score(answer, test.answer4[k]), ) em.append(em_k) f1.append(f1_k) print("Exact Match: ", np.round(np.mean(em), 3)) print("F1 Score: ", np.round(np.mean(f1), 3)) return (em, f1) # Let's embed and pad the Test set too... pars_test = [] ques_test = [] embed = hub.KerasLayer("https://tfhub.dev/google/nnlm-en-dim128/2") # NNLM for text in test.context: words = np.array(text_to_word_sequence(text)) pars_test.append(embed(tf.constant(words))) for text in test.question: words = np.array(text_to_word_sequence(text)) ques_test.append(embed(tf.constant(words))) p_test = pad_sequences( pars_test, padding="post", dtype="float32", maxlen=max_paragraph_length ) q_test = pad_sequences( ques_test, padding="post", dtype="float32", maxlen=max_question_length ) # Evaluate the model on the Test set pred_test = model.predict([p_test, q_test]) print("Results on Test Set:") (em_model, f1_model) = model_eval(pred_test) # First Input = Paragraphs paragraphs = Input(shape=(max_paragraph_length, emb_dim), name="par0") p = Masking(mask_value=0)(paragraphs) # Bidirectional Multi-Layer with Dropout p = Bidirectional( GRU(128, return_sequences=True, name="par1", kernel_initializer="glorot_normal"), merge_mode="concat", )(p) p = Dropout(0.15)(p) p = Bidirectional( GRU(64, return_sequences=True, name="par2", kernel_initializer="glorot_normal"), merge_mode="concat", )(p) p = Dropout(0.15)(p) # Output is = a 128d vector per word in the paragraph (None, max_paragraph_length, 128). # Second Input = Questions questions = Input(shape=(max_question_length, emb_dim), name="ques0") q = Masking(mask_value=0)(questions) q = GRU(256, return_sequences=True, name="ques2")(q) q = Dropout(0.15)(q) # Output is = a 256d vector per word in the paragraph (None, max_question_length, 256). # Weighted Average to obtain the single vector q' weights = Dense(1, activation="softmax", name="weights")(q) q = Dot(axes=1, name="ques3")([weights, q]) # Output is = a single 256d vector per question (None, 256, 1). # Outputs for Start & End / Quadratic Layers and Softmax qs = Dense(128, activation = 'linear', name = "s1", use_bias=False, kernel_regularizer=regularizers.l2(0.002))(q) outs = Dot(axes=(2, 2), name = "s2")([p, qs]) qe = Dense(128, activation = 'linear', name = "e1", use_bias=False, kernel_regularizer=regularizers.l2(0.002))(q) oute = Dot(axes=(2, 2), name = "e2")([p, qe]) # Output is = a probability vector (None, seq_pars, 1) for each # Model model = Model(inputs=[paragraphs, questions], outputs=[outs, oute]) def create_masked_matrix_for_one(pred_start, pred_end): # Creating the masked matrix of possible answers (where start < end < start 15) masked_matrix = tf.matmul(pred_start, tf.transpose(pred_end)) i, j = np.meshgrid( map(np.arange, (masked_matrix.shape)), indexing="ij" ) masked_matrix.mask = (i <= j) & (j < i+15) masked_matrix = np.where(masked_matrix.mask, masked_matrix, 0) max_results = np.where(masked_matrix == np.amax(masked_matrix)) return masked_matrix, max_results # Function to get the result on the kth question def get_result(k, model=model, verbose=True): paragraph = tf.expand_dims(p_test[k], 0) question = tf.expand_dims(q_test[k], 0) out = model([paragraph, question]) start = tf.exp(out[0][0]) end = tf.exp(out[1][0]) _, result = create_masked_matrix_for_one(start, end) if result[1][0] < len(text_to_word_sequence(test.context[k])): answer = np.array(text_to_word_sequence(test.context[k]))[result[0][0]:result[1][0]+1] else: answer = ['-'] if result[0][0] != result[1][0] and result[1][0] < len(text_to_word_sequence(test.context[k])): answer = " ".join(answer) else: answer = str(answer[0]) if verbose: print("--------------------------------------------------------") print("Question: ", test.question[k]) print("--------------------------------------------------------") print("Context: ") print(test.context[k]) print("--------------------------------------------------------") print("Model's answer: ", answer) print("Human answers: ") print( test.answer1[k], " -- ", test.answer2[k], " -- ", test.answer3[k], " -- ", test.answer4[k], ) print("--------------------------------------------------------") print( "EM Score: ", max( exact_match(answer, test.answer1[k]), exact_match(answer, test.answer2[k]), exact_match(answer, test.answer3[k]), exact_match(answer, test.answer4[k]), ), ) print( "F1 Score: ", np.round( max( f1_score(answer, test.answer1[k]), f1_score(answer, test.answer2[k]), f1_score(answer, test.answer3[k]), f1_score(answer, test.answer4[k]), ), 3, ), ) #Let's try... get_result(10) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: 1.Searching and Printing a List of 50 'Lil' Musicians Step2: 2 Genres Most Represented in the Search Results Step3: More Spotify - LIL' GRAPHICS Step4: The Second Highest Popular Artist Step5: 4. List of Lil's Popular Than Lil' Kim Step6: 5.Two Favorite Lils and Their Top Tracks Step7: 6. Average Popularity of My Fav Musicians (Above) for Their explicit songs vs. their non-explicit songs Step8: 7a. Number of Biggies and Lils Step9: 7b. Time to Download All Information on Lil and Biggies Step10: 8. Highest Average Popular Lils and Biggies Out of The Top 50	<ASSISTANT_TASK:> Python Code: import requests Lil_response = requests.get('https://api.spotify.com/v1/search?query=Lil&type=artist&limit=50&country=US') Lil_data = Lil_response.json() #Lil_data Lil_data.keys() Lil_data['artists'].keys() Lil_artists = Lil_data['artists']['items'] #With "Lil Wayne" and "Lil Kim" there are a lot of "Lil" musicians. Do a search and print a list of 50 #that are playable in the USA (or the country of your choice), along with their popularity score. count =0 for artist in Lil_artists: count += 1 print(count,".", artist['name'],"has the popularity of", artist['popularity']) # What genres are most represented in the search results? Edit your previous printout to also display a list of their genres #in the format "GENRE_1, GENRE_2, GENRE_3". If there are no genres, print "No genres listed". #Tip: "how to join a list Python" might be a helpful search # if len(artist['genres']) == 0 ) # print ("no genres") # else: # genres = ", ".join(artist['genres']) genre_list = [] genre_loop = Lil_data['artists']['items'] for item in genre_loop: #print(item['genres']) item_gen = item['genres'] for i in item_gen: genre_list.append(i) #print(sorted(genre_list)) #COUNTING the most genre_counter = {} for word in genre_list: if word in genre_counter: genre_counter[word] += 1 else: genre_counter[word] = 1 popular_genre = sorted(genre_counter, key = genre_counter.get, reverse = True) top_genre = popular_genre[:1] print("The genre most represented is", top_genre) #COUNTING the most with count to confirm from collections import Counter count = Counter(genre_list) most_count = count.most_common(1) print("The genre most represented and the count are", most_count) print("-----------------------------------------------------") for artist in Lil_artists: num_genres = 'no genres listed' if len(artist['genres']) > 0: num_genres= str.join(',', (artist['genres'])) print(artist['name'],"has the popularity of", artist['popularity'], ", and has", num_genres, "under genres") Lil_response = requests.get('https://api.spotify.com/v1/search?query=Lil&type=artist&limit=50&country=US') Lil_data = Lil_response.json() #Lil_data #Use a for loop to determine who BESIDES Lil Wayne has the highest popularity rating. #Is it the same artist who has the largest number of followers? name_highest = "" name_follow ="" second_high_pop = 0 highest_pop = 0 high_follow = 0 for artist in Lil_artists: if (highest_pop < artist['popularity']) & (artist['name'] != "Lil Wayne"): #second_high_pop = highest_pop #name_second = artist['name'] highest_pop = artist['popularity'] name_highest = artist['name'] if (high_follow < artist['followers']['total']): high_follow = artist ['followers']['total'] name_follow = artist['name'] #print(artist['followers']['total']) print(name_highest, "has the second highest popularity, which is", highest_pop) print(name_follow, "has the highest number of followers:", high_follow) #print("the second highest popularity is", second_high_pop) Lil_response = requests.get('https://api.spotify.com/v1/search?query=Lil&type=artist&limit=50&country=US') Lil_data = Lil_response.json() #Lil_data Lil_artists = Lil_data['artists']['items'] #Print a list of Lil's that are more popular than Lil' Kim. count = 0 for artist in Lil_artists: if artist['popularity'] > 62: count+=1 print(count, artist['name'],"has the popularity of", artist['popularity']) #else: #print(artist['name'], "is less popular with a score of", artist['popularity']) response = requests.get("https://api.spotify.com/v1/search?query=Lil&type=artist&limit=2&country=US") data = response.json() for artist in Lil_artists: #print(artist['name'],artist['id']) if artist['name'] == "Lil Wayne": wayne = artist['id'] print(artist['name'], "id is",wayne) if artist['name'] == "Lil Yachty": yachty = artist['id'] print(artist['name'], "id is", yachty) #Pick two of your favorite Lils to fight it out, and use their IDs to print out their top tracks. #Tip: You're going to be making two separate requests, be sure you DO NOT save them into the same variable. response = requests.get("https://api.spotify.com/v1/artists/" +wayne+ "/top-tracks?country=US") data = response.json() tracks = data['tracks'] print("Lil Wayne's top tracks are: ") for track in tracks: print("-", track['name']) print("-----------------------------------------------") response = requests.get("https://api.spotify.com/v1/artists/" +yachty+ "/top-tracks?country=US") data = response.json() tracks = data['tracks'] print("Lil Yachty 's top tracks are: ") for track in tracks: print("-", track['name']) response = requests.get("https://api.spotify.com/v1/artists/" +yachty+ "/top-tracks?country=US") data = response.json() tracks = data['tracks'] #print(tracks) #for track in tracks: #print(track.keys()) #Get an average popularity for their explicit songs vs. their non-explicit songs. #How many minutes of explicit songs do they have? Non-explicit? # How explicit is Lils? response = requests.get("https://api.spotify.com/v1/artists/" +yachty+ "/top-tracks?country=US") data = response.json() tracks = data['tracks'] # counter for tracks for explicit and clean track_count = 0 clean_count = 0 #counter to find avg popularity popular_exp = 0 popular_clean = 0 #counter for avg time in minutes are below: timer = 0 data_timer = 0 timer_clean = 0 for track in tracks: print("The track,", track['name'],", with the id",track['id'], "is", track['explicit'],"for explicit content, and has the popularity of", track['popularity']) track_id = track['id'] time_ms = track['duration_ms'] # TA-COMMENT: (-1) If what is true? "if True" will always evaluate to True.... if True: track_count = track_count + 1 popular_exp = popular_exp + track['popularity'] # TA-COMMENT: What is this supposed to capture? # It HAPPENS to be the case that all the tracks are explicit, but if that were not true, would this be correct? response = requests.get("https://api.spotify.com/v1/tracks/" + track_id) data_track = response.json() print("and has the duration of", data_track['duration_ms'], "milli seconds.") timer = timer + time_ms timer_minutes = ((timer / (100060)) % 60) if not track['explicit']: clean_count = clean_count + 1 popular_clean = popular_clean + track['popularity'] response = requests.get("https://api.spotify.com/v1/tracks/" + track_id) data_tracks = response.json() timer_clean = timer_clean + time_ms timer_minutes_clean = ((data_timer / (100060)) % 60) print(", and has the duration of", timer_minutes_clean, "minutes") print("------------------------------------") avg_pop = popular_exp / track_count print("I have found", track_count, "tracks, and has the average popularity of", avg_pop, "and has the average duration of", timer_minutes,"minutes and", clean_count, "are clean") #print("Overall, I discovered", track_count, "tracks") #print("And", clean_count, "were non-explicit") #print("Which means", , " percent were clean for Lil Wayne") # TA-COMMENT: example of what happens if you do just "if True" as in the code above. if True: print("hello") # TA-COMMENT: Same commends apply here. #Get an average popularity for their explicit songs vs. their non-explicit songs. #How many minutes of explicit songs do they have? Non-explicit? # How explicit is Lils? response = requests.get("https://api.spotify.com/v1/artists/" +wayne+ "/top-tracks?country=US") data = response.json() # counter for tracks for explicit and clean track_count = 0 clean_count = 0 #counter to find avg popularity popular_exp = 0 popular_clean = 0 #counter for avg time in minutes are below: timer = 0 #data_timer = 0 timer_clean = 0 for track in tracks: print("The track,", track['name'],", with the id",track['id'], "is", track['explicit'],"for explicit content, and has the popularity of", track['popularity']) track_id = track['id'] time_ms = data_track['duration_ms'] if True: track_count = track_count + 1 popular_exp = popular_exp + track['popularity'] response = requests.get("https://api.spotify.com/v1/tracks/" + track_id) data_track = response.json() print("and has the duration of", data_track['duration_ms'], "milli seconds.") timer = timer + time_ms timer_minutes = ((timer / (100060)) % 60) if not track['explicit']: clean_count = clean_count + 1 popular_clean = popular_clean + track['popularity'] response = requests.get("https://api.spotify.com/v1/tracks/" + track_id) data_tracks = response.json() timer_clean = timer_clean + time_ms timer_minutes_clean = ((data_timer / (100060)) % 60) print(", and has the duration of", timer_minutes_clean, "minutes") print("------------------------------------") avg_pop = popular_exp / track_count print("I have found", track_count, "tracks, and has the average popularity of", avg_pop, "and has the average duration of", timer_minutes,"minutes and", clean_count, "are clean") #print("Overall, I discovered", track_count, "tracks") #print("And", clean_count, "were non-explicit") #print("Which means", , " percent were clean for Lil Wayne") #How many total "Biggie" artists are there? How many total "Lil"s? #If you made 1 request every 5 seconds, how long would it take to download information on all the Lils vs the Biggies? biggie_response = requests.get('https://api.spotify.com/v1/search?query=biggie&type=artist&country=US') biggie_data = biggie_response.json() biggie_artists = biggie_data['artists']['total'] print("Total number of Biggie artists are", biggie_artists) lil_response = requests.get('https://api.spotify.com/v1/search?query=Lil&type=artist&country=US') lil_data = lil_response.json() lil_artists = lil_data['artists']['total'] print("Total number of Lil artists are", lil_artists) #If you made 1 request every 5 seconds, how long would it take to download information on all the Lils vs the Biggies? limit_download = 50 biggie_artists = biggie_data['artists']['total'] Lil_artist = Lil_data['artists']['total'] #1n 5 sec = 50 #in 1 sec = 50 / 5 req = 10 no, for 1 no, 1/10 sec # for 4501 = 4501/10 sec # for 49 49/ 10 sec big_count = biggie_artists/10 lil_count = Lil_artist / 10 print("It would take", big_count, "seconds for Biggies, where as it would take", lil_count,"seconds for Lils" ) # TA-COMMENT: (-1) If one request takes 5 seconds, then 50 requests would take (50 * 5) seconds # (one request for each 'Biggie') # So, 4510 Lil artists would take 4510 * 5 seconds #Out of the top 50 "Lil"s and the top 50 "Biggie"s, who is more popular on average? biggie_response = requests.get('https://api.spotify.com/v1/search?query=biggie&type=artist&limit=50&country=US') biggie_data = biggie_response.json() biggie_artists = biggie_data['artists']['items'] big_count_pop = 0 for artist in biggie_artists: #count_pop = artist['popularity'] big_count_pop = big_count_pop + artist['popularity'] print("Biggie has a total popularity of ", big_count_pop) big_pop = big_count_pop / 49 print("Biggie is on an average", big_pop,"popular") #Lil Lil_response = requests.get('https://api.spotify.com/v1/search?query=Lil&type=artist&limit=50&country=US') Lil_data = Lil_response.json() Lil_artists = Lil_data['artists']['items'] lil_count_pop = 0 for artist in Lil_artists: count_pop_lil = artist['popularity'] lil_count_pop = lil_count_pop + count_pop_lil lil_pop = lil_count_pop / 50 print("Lil is on an average", lil_pop,"popular") <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: When you try to print the variable created, you will not get what you want. It is just an object created to use in later statements. Step2: We won't get any error because we are creating a new file only error we might get is harddisk full error from system. After we are done manipulating the file we have to close the file. with close() function. Step3: Reading Files Step4: I used while loop to show the logic behind the reading, however for loop gives us a more elegant way. Step5: Writing Files Step6: The write method does not add a newline character to the output string . Thus, a newline character will be output only if it is part of the string being written. But in the example above line variable comes with \n at the end. Step7: There are a number of methods specific to strings in addition to the general sequence operations. Step8: str.isalpha() Step9: str.isdigit() Returns True if str contains only digits. Step10: str.islower() and str.isupper() Step11: str.lower() and str.upper() Step12: Searching the Contents of a String Step13: Replacing the Contents of a String Step14: Removing the Contents of a String Step15: Splitting a String	<ASSISTANT_TASK:> Python Code: input_file = open('sample.txt', 'r') # IOError occured because we should put the write true direction. input_file = open('data/sample.txt', 'r') # True direction, with folder inside. print(input_file) input_file.close() output_file = open('data/mynewfile.txt', 'w') # I used data/name because I want to save in data folder output_file.close() input_file = open('data/sample.txt', 'r') empty_str = '' line = input_file.readline() while line != empty_str: print(line) line = input_file.readline() input_file.close() input_file = open('data/sample.txt', 'r') for line in input_file: print(line) empty_str= '' input_file = open('data/sample.txt', 'r') output_file = open('data/newfile.txt', 'w') line = input_file.readline() while line != empty_str: output_file.write(line) line = input_file.readline() output_file.close() space = ' ' num_spaces = 0 line = input_file.readline() for k in range(0, len(line)): if line[k] == space: num_spaces = num_spaces + 1 num_spaces s = 'Hello World!' s.isalpha() # s.isdigit() "1".isdigit() s.islower() s s.isupper() "HELLO WORLD".isupper() s s.upper() s.lower() s # Does not change... You have to assign it to an new variable or overwrite s = s.lower() s s s.find('d') s.find('x') s s.replace("l", "*") s s.strip('!') s s.strip('!').split(" ") s[:-4] <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Periodic, so probably not a good representation of the 18 domain Step2: Look at same stuff at depth 4 light cones Step3: Look at states for increasing light cone size	<ASSISTANT_TASK:> Python Code: first_test = epsilon_field(domain.get_spacetime()) first_test.estimate_states(2,2,1) first_test.filter_data() print first_test.number_of_states() for state in first_test.causal_states(): print state.plc_configs() second_test = epsilon_field(domain.get_spacetime()) second_test.estimate_states(2,2,1,alpha= 0) second_test.filter_data() print second_test.number_of_states() for state in second_test.causal_states(): print state.plc_configs() big_domain = ECA(18, domain_18(2000)) big_domain.evolve(2000) third_test = epsilon_field(big_domain.get_spacetime()) third_test.estimate_states(2,2,1,alpha=0) third_test.filter_data() print third_test.number_of_states() for state in third_test.causal_states(): print state.plc_configs() print 2*5 print np.size(np.unique(third_test.PLCs().all_labels())) print np.size(np.unique(third_test.FLCs().all_labels())) print third_test.causal_states()[0].plc_shape(0) print third_test.causal_states()[1].plc_shape(0), '\n' print third_test.causal_states()[1].plc_shape(1) print third_test.causal_states()[2].plc_shape(0) diagram(domain.get_spacetime(), t_min = 400, t_max = 440, x_min = 400, x_max = 440) print np.size([0,1]10) checkerish = ECA(18, ([0,0,1]+[0,1,0])*200) checkerish.evolve(1200) checkerish.diagram() fourth_test = epsilon_field(checkerish.get_spacetime()) fourth_test.estimate_states(3,3,1) fourth_test.filter_data() print fourth_test.number_of_states() for state in fourth_test.causal_states(): print state.plc_configs() fifth_test = epsilon_field(domain.get_spacetime()) fifth_test.estimate_states(3,3,1, alpha=0) fifth_test.filter_data() print fifth_test.number_of_states() print np.size(np.unique(fifth_test.PLCs().all_labels())) for state in fifth_test.causal_states(): print state.index(), state.plc_configs() for state in fifth_test.causal_states(): print state.index(), state.morph_support_configs(), np.size(state.morph_support_configs()),'\n' sixth_test = epsilon_field(domain.get_spacetime()) sixth_test.estimate_states(4,4,1,alpha = 0) sixth_test.filter_data() print sixth_test.number_of_states() print np.size(np.unique(sixth_test.PLCs().all_labels())) for state in sixth_test.causal_states(): print state.index(), state.plc_configs(), '\n' for state in sixth_test.causal_states(): print state.index(), state.morph_support_configs(), np.size(state.morph_support_configs()), '\n' diagram(domain.get_spacetime(), t_min = 400, t_max = 440, x_min = 400, x_max = 440) state_overlay_diagram(domain.get_spacetime(), second_test.get_causal_field(),\ t_min = 400, t_max = 440, x_min = 400, x_max = 440) state_overlay_diagram(domain.get_spacetime(), fifth_test.get_causal_field(),\ t_min = 400, t_max = 440, x_min = 400, x_max = 440) state_overlay_diagram(domain.get_spacetime(), sixth_test.get_causal_field(),\ t_min = 400, t_max = 440, x_min = 400, x_max = 440) seventh_test = epsilon_field(domain.get_spacetime()) seventh_test.estimate_states(5,5,1,alpha=0) seventh_test.filter_data() print seventh_test.number_of_states() state_overlay_diagram(domain.get_spacetime(), seventh_test.get_causal_field(),\ t_min = 400, t_max = 440, x_min = 400, x_max = 440) domain = ECA(18, domain_18(400)) domain.evolve(400) domain_states = epsilon_field(domain.get_spacetime()) domain_states.estimate_states(5,3,1) domain_states.filter_data() print domain_states.number_of_states() print domain_states.nonunifilar_transitions() state_overlay_diagram(domain.get_spacetime(), domain_states.get_causal_field(), t_min = 50, t_max = 100, \ x_min = 50, x_max = 100) mask_field = np.copy(domain_states.get_causal_field()) mask_field[mask_field == 3] = 1 state_overlay_diagram(domain.get_spacetime(), mask_field, t_min = 50, t_max = 100, \ x_min = 50, x_max = 100) print mask_field[10:30, 120:140] print len(domain_states.all_transitions()) np.random.seed(0) domain_states = epsilon_field(domain.get_spacetime()) domain_states.estimate_states(3,3,1) domain_states.filter_data() print domain_states.nonunifilar_transitions() print len(domain_states.all_transitions()) for transition in domain_states.all_transitions(): print transition <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Create a DataArray Step2: If you supply a pandas Series or DataFrame, metadata is copied directly Step3: Here are the key properties for a DataArray Step4: Indexing Step5: Computation Step6: However, aggregation operations can use dimension names instead of axis numbers Step7: Arithmetic operations broadcast based on dimension name. This means you don’t need to insert dummy dimensions for alignment Step8: Another broadcast example Step9: It also means that in most cases you do not need to worry about the order of dimensions Step10: Operations also align based on index labels Step11: GroupBy Step12: Convert to pandas Step13: Datasets and NetCDF Step14: You can do almost everything you can do with DataArray objects with Dataset objects if you prefer to work with multiple variables at once.	<ASSISTANT_TASK:> Python Code: import numpy as np import pandas as pd import xarray as xr xr.DataArray(np.random.randn(2, 3)) data = xr.DataArray(np.random.randn(2, 3), [('x', ['a', 'b']), ('y', [-2, 0, 2])]) data xr.DataArray(pd.Series(range(3), index=list('abc'), name='foo')) data.values data.dims data.coords len(data.coords) data.coords['x'] data.attrs data[[0, 1]] data.loc['a':'b'] data.loc data.isel(x=slice(2)) data.sel(x=['a', 'b']) data data + 10 np.sin(data) data.T data.sum() data.mean(dim='x') a = xr.DataArray(np.random.randn(3), [data.coords['y']]) b = xr.DataArray(np.random.randn(4), dims='z') a b a + b v1 = xr.DataArray(np.random.rand(3, 2, 4), dims=['t', 'y', 'x']) v2 = xr.DataArray(np.random.rand(2, 4), dims=['y', 'x']) v1 v2 v1 + v2 data - data.T data[:-1] data[:1] data[:-1] - data[:1] labels = xr.DataArray(['E', 'F', 'E'], [data.coords['y']], name='labels') labels data data.groupby(labels).mean('y') data.groupby(labels).apply(lambda x: x - x.min()) data.to_series() data.to_pandas() ds = data.to_dataset(name='foo') ds ds.to_netcdf('example.nc') xr.open_dataset('example.nc') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: DictVectorizer Step2: CountVectorizer Step3: Stop Word Filtering Step4: Stemming and Lemmatization Step5: As we can see both sentences are having same meaning but their feature vectors have no elements in common. Let's use the lexical analysis on the data Step6: The Porter stemmer cannot consider the inflected form's part of speech and returns gather for both documents Step7: Extending bag-of-words with TF-IDF weights Step8: Data Standardization	<ASSISTANT_TASK:> Python Code: from sklearn.feature_extraction import DictVectorizer from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, HashingVectorizer from sklearn.metrics.pairwise import euclidean_distances from sklearn import preprocessing from nltk.stem.wordnet import WordNetLemmatizer from nltk.stem import PorterStemmer from nltk import word_tokenize from nltk import pos_tag import numpy as np onehot_encoder = DictVectorizer() instances = [ {'city': 'New York'}, {'city': 'San Francisco'}, {'city': 'Chapel Hill'} ] print (onehot_encoder.fit_transform(instances).toarray()) corpus = [ 'UNC played Duke in basketball', 'Duke lost the basketball game' ] vectorizer = CountVectorizer() print (vectorizer.fit_transform(corpus).todense()) print (vectorizer.vocabulary_) # adding one more sentence in corpus corpus = [ 'UNC played Duke in basketball', 'Duke lost the basketball game', 'This is Atul Singh' ] vectorizer = CountVectorizer() print (vectorizer.fit_transform(corpus).todense()) print (vectorizer.vocabulary_) # checking the euclidean distance # converting sentence into CountVectorizer counts = vectorizer.fit_transform(corpus).todense() print("1 & 2", euclidean_distances(counts[0], counts[1])) print("2 & 3", euclidean_distances(counts[1], counts[2])) print("1 & 3", euclidean_distances(counts[0], counts[2])) vectorizer = CountVectorizer(stop_words='english') # added one option which remove the grammer words from corpus print (vectorizer.fit_transform(corpus).todense()) print (vectorizer.vocabulary_) print("1 & 2", euclidean_distances(counts[0], counts[1])) print("2 & 3", euclidean_distances(counts[1], counts[2])) print("1 & 3", euclidean_distances(counts[0], counts[2])) corpus = [ 'He ate the sandwiches', 'Every sandwich was eaten by him' ] vectorizer = CountVectorizer(stop_words='english') # added one option which remove the grammer words from corpus print (vectorizer.fit_transform(corpus).todense()) print (vectorizer.vocabulary_) lemmatizer = WordNetLemmatizer() print (lemmatizer.lemmatize('gathering', 'v')) print (lemmatizer.lemmatize('gathering', 'n')) stemmer = PorterStemmer() print (stemmer.stem('gathering')) wordnet_tags = ['n', 'v'] corpus = [ 'He ate the sandwiches', 'Every sandwich was eaten by him' ] stemmer = PorterStemmer() print ('Stemmed:', [[stemmer.stem(token) for token in word_tokenize(document)] for document in corpus]) def lemmatize(token, tag): if tag[0].lower() in ['n', 'v']: return lemmatizer.lemmatize(token, tag[0].lower()) return token lemmatizer = WordNetLemmatizer() tagged_corpus = [pos_tag(word_tokenize(document)) for document in corpus] print ('Lemmatized:', [[lemmatize(token, tag) for token, tag in document] for document in tagged_corpus]) corpus = ['The dog ate a sandwich, the wizard transfigured a sandwich, and I ate a sandwich'] vectorizer = CountVectorizer(stop_words='english') print (vectorizer.fit_transform(corpus).todense()) print(vectorizer.vocabulary_) corpus = ['The dog ate a sandwich and I ate a sandwich', 'The wizard transfigured a sandwich'] vectorizer = TfidfVectorizer(stop_words='english') print (vectorizer.fit_transform(corpus).todense()) print(vectorizer.vocabulary_) corpus = ['The dog ate a sandwich and I ate a sandwich', 'The wizard transfigured a sandwich'] vectorizer = HashingVectorizer(n_features=6) print (vectorizer.fit_transform(corpus).todense()) X = [[1,2,3], [4,5,1], [3,6,2] ] print(preprocessing.scale(X)) x1 = preprocessing.StandardScaler() print(x1) print(x1.fit_transform(X)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Note Step2: Lesson Step3: Project 1 Step4: We'll create three Counter objects, one for words from postive reviews, one for words from negative reviews, and one for all the words. Step5: TODO Step6: Run the following two cells to list the words used in positive reviews and negative reviews, respectively, ordered from most to least commonly used. Step7: As you can see, common words like "the" appear very often in both positive and negative reviews. Instead of finding the most common words in positive or negative reviews, what you really want are the words found in positive reviews more often than in negative reviews, and vice versa. To accomplish this, you'll need to calculate the ratios of word usage between positive and negative reviews. Step8: Examine the ratios you've calculated for a few words Step9: Looking closely at the values you just calculated, we see the following Step10: Examine the new ratios you've calculated for the same words from before Step11: If everything worked, now you should see neutral words with values close to zero. In this case, "the" is near zero but slightly positive, so it was probably used in more positive reviews than negative reviews. But look at "amazing"'s ratio - it's above 1, showing it is clearly a word with positive sentiment. And "terrible" has a similar score, but in the opposite direction, so it's below -1. It's now clear that both of these words are associated with specific, opposing sentiments. Step12: End of Project 1. Step13: Project 2 Step14: Run the following cell to check your vocabulary size. If everything worked correctly, it should print 74074 Step15: Take a look at the following image. It represents the layers of the neural network you'll be building throughout this notebook. layer_0 is the input layer, layer_1 is a hidden layer, and layer_2 is the output layer. Step16: TODO Step17: Run the following cell. It should display (1, 74074) Step18: layer_0 contains one entry for every word in the vocabulary, as shown in the above image. We need to make sure we know the index of each word, so run the following cell to create a lookup table that stores the index of every word. Step20: TODO Step21: Run the following cell to test updating the input layer with the first review. The indices assigned may not be the same as in the solution, but hopefully you'll see some non-zero values in layer_0. Step23: TODO Step24: Run the following two cells. They should print out'POSITIVE' and 1, respectively. Step25: Run the following two cells. They should print out 'NEGATIVE' and 0, respectively. Step29: End of Project 2. Step30: Run the following cell to create a SentimentNetwork that will train on all but the last 1000 reviews (we're saving those for testing). Here we use a learning rate of 0.1. Step31: Run the following cell to test the network's performance against the last 1000 reviews (the ones we held out from our training set). Step32: Run the following cell to actually train the network. During training, it will display the model's accuracy repeatedly as it trains so you can see how well it's doing. Step33: That most likely didn't train very well. Part of the reason may be because the learning rate is too high. Run the following cell to recreate the network with a smaller learning rate, 0.01, and then train the new network. Step34: That probably wasn't much different. Run the following cell to recreate the network one more time with an even smaller learning rate, 0.001, and then train the new network. Step35: With a learning rate of 0.001, the network should finall have started to improve during training. It's still not very good, but it shows that this solution has potential. We will improve it in the next lesson. Step39: Project 4 Step40: Run the following cell to recreate the network and train it. Notice we've gone back to the higher learning rate of 0.1. Step41: That should have trained much better than the earlier attempts. It's still not wonderful, but it should have improved dramatically. Run the following cell to test your model with 1000 predictions. Step42: End of Project 4. Step46: Project 5 Step47: Run the following cell to recreate the network and train it once again. Step48: That should have trained much better than the earlier attempts. Run the following cell to test your model with 1000 predictions. Step49: End of Project 5. Step53: Project 6 Step54: Run the following cell to train your network with a small polarity cutoff. Step55: And run the following cell to test it's performance. It should be Step56: Run the following cell to train your network with a much larger polarity cutoff. Step57: And run the following cell to test it's performance. Step58: End of Project 6.	<ASSISTANT_TASK:> Python Code: def pretty_print_review_and_label(i): print(labels[i] + "\t:\t" + reviews[i][:80] + "...") g = open('reviews.txt','r') # What we know! reviews = list(map(lambda x:x[:-1],g.readlines())) g.close() g = open('labels.txt','r') # What we WANT to know! labels = list(map(lambda x:x[:-1].upper(),g.readlines())) g.close() len(reviews) reviews[0] labels[0] print("labels.txt \t : \t reviews.txt\n") pretty_print_review_and_label(2137) pretty_print_review_and_label(12816) pretty_print_review_and_label(6267) pretty_print_review_and_label(21934) pretty_print_review_and_label(5297) pretty_print_review_and_label(4998) from collections import Counter import numpy as np # Create three Counter objects to store positive, negative and total counts positive_counts = Counter() negative_counts = Counter() total_counts = Counter() # TODO: Loop over all the words in all the reviews and increment the counts in the appropriate counter objects for label, review in zip(labels, reviews): words = review.lower().replace(",", " ").replace(".", " ").split(" ") total_counts.update(words) if label == "POSITIVE" : positive_counts.update(words) else: negative_counts.update(words) # Examine the counts of the most common words in positive reviews positive_counts.most_common() # Examine the counts of the most common words in negative reviews negative_counts.most_common() # Create Counter object to store positive/negative ratios pos_neg_ratios = Counter() # TODO: Calculate the ratios of positive and negative uses of the most common words # Consider words to be "common" if they've been used at least 100 times for word, count in total_counts.most_common(): ratio = positive_counts[word]/(float(negative_counts[word])+1.0) pos_neg_ratios.update({word:ratio}) if count <100: break print("Pos-to-neg ratio for 'the' = {}".format(pos_neg_ratios["the"])) print("Pos-to-neg ratio for 'amazing' = {}".format(pos_neg_ratios["amazing"])) print("Pos-to-neg ratio for 'terrible' = {}".format(pos_neg_ratios["terrible"])) %matplotlib inline %config InlineBackend.figure_format = 'retina' x = np.arange(0,5,0.01) y = [np.log(x) if x >= 1 else -np.log(1/(x + 0.01)) for x in x] import matplotlib.pyplot as plt plt.plot(x,y) plt.grid(True) plt.show() # TODO: Convert ratios to logs for word, ratio in pos_neg_ratios.most_common(): if ratio >=1: pos_neg_ratios[word] = np.log(ratio) else: pos_neg_ratios[word] = -np.log(1/(ratio + 0.01)) print("Pos-to-neg ratio for 'the' = {}".format(pos_neg_ratios["the"])) print("Pos-to-neg ratio for 'amazing' = {}".format(pos_neg_ratios["amazing"])) print("Pos-to-neg ratio for 'terrible' = {}".format(pos_neg_ratios["terrible"])) # words most frequently seen in a review with a "POSITIVE" label pos_neg_ratios.most_common() # words most frequently seen in a review with a "NEGATIVE" label list(reversed(pos_neg_ratios.most_common()))[0:30] # Note: Above is the code Andrew uses in his solution video, # so we've included it here to avoid confusion. # If you explore the documentation for the Counter class, # you will see you could also find the 30 least common # words like this: pos_neg_ratios.most_common()[:-31:-1] from IPython.display import Image review = "This was a horrible, terrible movie." Image(filename='sentiment_network.png') review = "The movie was excellent" Image(filename='sentiment_network_pos.png') # TODO: Create set named "vocab" containing all of the words from all of the reviews vocab = set(total_counts.keys()) vocab_size = len(vocab) print(vocab_size) from IPython.display import Image Image(filename='sentiment_network_2.png') # TODO: Create layer_0 matrix with dimensions 1 by vocab_size, initially filled with zeros layer_0 = np.zeros((1,vocab_size)) layer_0.shape from IPython.display import Image Image(filename='sentiment_network.png') # Create a dictionary of words in the vocabulary mapped to index positions # (to be used in layer_0) word2index = {} for i,word in enumerate(vocab): word2index[word] = i # display the map of words to indices word2index def update_input_layer(review): Modify the global layer_0 to represent the vector form of review. The element at a given index of layer_0 should represent how many times the given word occurs in the review. Args: review(string) - the string of the review Returns: None # use global avoide create new variable that may fill your RAM! global layer_0 # clear out previous state by resetting the layer to be all 0s layer_0 = 0 # TODO: count how many times each word is used in the given review and store the results in layer_0 words = review.lower().replace(",", " ").replace(".", " ").split(" ") for word in words: layer_0[0][word2index[word]] += 1 update_input_layer(reviews[0]) layer_0 def get_target_for_label(label): Convert a label to `0` or `1`. Args: label(string) - Either "POSITIVE" or "NEGATIVE". Returns: `0` or `1`. # TODO: Your code here return 1 if label=="POSITIVE" else 0 labels[1] get_target_for_label(labels[0]) labels[1] get_target_for_label(labels[1]) import time import sys import numpy as np # Encapsulate our neural network in a class class SentimentNetwork: def __init__(self, reviews,labels,hidden_nodes = 10, learning_rate = 0.1): Create a SentimenNetwork with the given settings Args: reviews(list) - List of reviews used for training labels(list) - List of POSITIVE/NEGATIVE labels associated with the given reviews hidden_nodes(int) - Number of nodes to create in the hidden layer learning_rate(float) - Learning rate to use while training # Assign a seed to our random number generator to ensure we get # reproducable results during development np.random.seed(1) # process the reviews and their associated labels so that everything # is ready for training self.pre_process_data(reviews, labels) # Build the network to have the number of hidden nodes and the learning rate that # were passed into this initializer. Make the same number of input nodes as # there are vocabulary words and create a single output node. self.init_network(len(self.review_vocab),hidden_nodes, 1, learning_rate) def pre_process_data(self, reviews, labels): # populate review_vocab with all of the words in the given reviews review_vocab = set() for review in reviews: for word in review.lower().replace(",", " ").replace(".", " ").split(" "): review_vocab.add(word) # Convert the vocabulary set to a list so we can access words via indices self.review_vocab = list(review_vocab) # populate label_vocab with all of the words in the given labels. label_vocab = set() for label in labels: label_vocab.add(label) # Convert the label vocabulary set to a list so we can access labels via indices self.label_vocab = list(label_vocab) # Store the sizes of the review and label vocabularies. self.review_vocab_size = len(self.review_vocab) self.label_vocab_size = len(self.label_vocab) # Create a dictionary of words in the vocabulary mapped to index positions self.word2index = {} for i, word in enumerate(self.review_vocab): self.word2index[word] = i # Create a dictionary of labels mapped to index positions self.label2index = {} for i, label in enumerate(self.label_vocab): self.label2index[label] = i def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate): # Set number of nodes in input, hidden and output layers. self.input_nodes = input_nodes self.hidden_nodes = hidden_nodes self.output_nodes = output_nodes # Store the learning rate self.learning_rate = learning_rate # Initialize weights # These are the weights between the input layer and the hidden layer. self.weights_0_1 = np.zeros((self.input_nodes,self.hidden_nodes)) # These are the weights between the hidden layer and the output layer. self.weights_1_2 = np.random.normal(0.0, self.output_nodes-0.5, (self.hidden_nodes, self.output_nodes)) # The input layer, a two-dimensional matrix with shape 1 x input_nodes self.layer_0 = np.zeros((1,input_nodes)) def update_input_layer(self,review): # clear out previous state, reset the layer to be all 0s self.layer_0 = 0 for word in review.lower().replace(",", " ").replace(".", " ").split(" "): # NOTE: This if-check was not in the version of this method created in Project 2, # and it appears in Andrew's Project 3 solution without explanation. # It simply ensures the word is actually a key in word2index before # accessing it, which is important because accessing an invalid key # with raise an exception in Python. This allows us to ignore unknown # words encountered in new reviews. if(word in self.word2index.keys()): self.layer_0[0][self.word2index[word]] += 1 def get_target_for_label(self,label): if(label == 'POSITIVE'): return 1 else: return 0 def sigmoid(self,x): return 1 / (1 + np.exp(-x)) def sigmoid_output_2_derivative(self,output): return output * (1 - output) def train(self, training_reviews, training_labels): # make sure out we have a matching number of reviews and labels assert(len(training_reviews) == len(training_labels)) # Keep track of correct predictions to display accuracy during training correct_so_far = 0 # Remember when we started for printing time statistics start = time.time() # loop through all the given reviews and run a forward and backward pass, # updating weights for every item for i in range(len(training_reviews)): # Get the next review and its correct label review = training_reviews[i] label = training_labels[i] #### Implement the forward pass here #### ### Forward pass ### # Input Layer self.update_input_layer(review) # Hidden layer layer_1 = self.layer_0.dot(self.weights_0_1) # Output layer layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2)) #### Implement the backward pass here #### ### Backward pass ### # Output error layer_2_error = layer_2 - self.get_target_for_label(label) # Output layer error is the difference between desired target and actual output. layer_2_delta = layer_2_error * self.sigmoid_output_2_derivative(layer_2) # Backpropagated error layer_1_error = layer_2_delta.dot(self.weights_1_2.T) # errors propagated to the hidden layer layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error # Update the weights self.weights_1_2 -= layer_1.T.dot(layer_2_delta) * self.learning_rate # update hidden-to-output weights with gradient descent step self.weights_0_1 -= self.layer_0.T.dot(layer_1_delta) * self.learning_rate # update input-to-hidden weights with gradient descent step # Keep track of correct predictions. if(layer_2 >= 0.5 and label == 'POSITIVE'): correct_so_far += 1 elif(layer_2 < 0.5 and label == 'NEGATIVE'): correct_so_far += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the training process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \ + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%") if(i % 2500 == 0): print("") def test(self, testing_reviews, testing_labels): Attempts to predict the labels for the given testing_reviews, and uses the test_labels to calculate the accuracy of those predictions. # keep track of how many correct predictions we make correct = 0 # we'll time how many predictions per second we make start = time.time() # Loop through each of the given reviews and call run to predict # its label. for i in range(len(testing_reviews)): pred = self.run(testing_reviews[i]) if(pred == testing_labels[i]): correct += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the prediction process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct) + " #Tested:" + str(i+1) \ + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%") def run(self, review): Returns a POSITIVE or NEGATIVE prediction for the given review. # Run a forward pass through the network, like in the "train" function. # Input Layer self.update_input_layer(review.lower()) # Hidden layer layer_1 = self.layer_0.dot(self.weights_0_1) # Output layer layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2)) # Return POSITIVE for values above greater-than-or-equal-to 0.5 in the output layer; # return NEGATIVE for other values if(layer_2[0] >= 0.5): return "POSITIVE" else: return "NEGATIVE" mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1) mlp.test(reviews[-1000:],labels[-1000:]) mlp.train(reviews[:-1000],labels[:-1000]) mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.01) mlp.train(reviews[:-1000],labels[:-1000]) mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.001) mlp.train(reviews[:-1000],labels[:-1000]) from IPython.display import Image Image(filename='sentiment_network.png') def update_input_layer(review): global layer_0 # clear out previous state, reset the layer to be all 0s layer_0 = 0 for word in review.lower().replace(",", " ").replace(".", " ").split(" "): layer_0[0][word2index[word]] += 1 update_input_layer(reviews[0]) layer_0 review_counter = Counter() for word in reviews[0].lower().replace(",", " ").replace(".", " ").split(" "): review_counter[word] += 1 review_counter.most_common() import time import sys import numpy as np # Encapsulate our neural network in a class class SentimentNetwork: def __init__(self, reviews,labels,hidden_nodes = 10, learning_rate = 0.1): Create a SentimenNetwork with the given settings Args: reviews(list) - List of reviews used for training labels(list) - List of POSITIVE/NEGATIVE labels associated with the given reviews hidden_nodes(int) - Number of nodes to create in the hidden layer learning_rate(float) - Learning rate to use while training # Assign a seed to our random number generator to ensure we get # reproducable results during development np.random.seed(1) # process the reviews and their associated labels so that everything # is ready for training self.pre_process_data(reviews, labels) # Build the network to have the number of hidden nodes and the learning rate that # were passed into this initializer. Make the same number of input nodes as # there are vocabulary words and create a single output node. self.init_network(len(self.review_vocab),hidden_nodes, 1, learning_rate) def pre_process_data(self, reviews, labels): # populate review_vocab with all of the words in the given reviews review_vocab = set() for review in reviews: for word in review.lower().replace(",", " ").replace(".", " ").split(" "): review_vocab.add(word) # Convert the vocabulary set to a list so we can access words via indices self.review_vocab = list(review_vocab) # populate label_vocab with all of the words in the given labels. label_vocab = set() for label in labels: label_vocab.add(label) # Convert the label vocabulary set to a list so we can access labels via indices self.label_vocab = list(label_vocab) # Store the sizes of the review and label vocabularies. self.review_vocab_size = len(self.review_vocab) self.label_vocab_size = len(self.label_vocab) # Create a dictionary of words in the vocabulary mapped to index positions self.word2index = {} for i, word in enumerate(self.review_vocab): self.word2index[word] = i # Create a dictionary of labels mapped to index positions self.label2index = {} for i, label in enumerate(self.label_vocab): self.label2index[label] = i def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate): # Set number of nodes in input, hidden and output layers. self.input_nodes = input_nodes self.hidden_nodes = hidden_nodes self.output_nodes = output_nodes # Store the learning rate self.learning_rate = learning_rate # Initialize weights # These are the weights between the input layer and the hidden layer. self.weights_0_1 = np.zeros((self.input_nodes,self.hidden_nodes)) # These are the weights between the hidden layer and the output layer. self.weights_1_2 = np.random.normal(0.0, self.output_nodes-0.5, (self.hidden_nodes, self.output_nodes)) # The input layer, a two-dimensional matrix with shape 1 x input_nodes self.layer_0 = np.zeros((1,input_nodes)) def update_input_layer(self,review): # clear out previous state, reset the layer to be all 0s self.layer_0 = 0 for word in review.lower().replace(",", " ").replace(".", " ").split(" "): # NOTE: This if-check was not in the version of this method created in Project 2, # and it appears in Andrew's Project 3 solution without explanation. # It simply ensures the word is actually a key in word2index before # accessing it, which is important because accessing an invalid key # with raise an exception in Python. This allows us to ignore unknown # words encountered in new reviews. if(word in self.word2index.keys()): self.layer_0[0][self.word2index[word]] = 1 def get_target_for_label(self,label): if(label == 'POSITIVE'): return 1 else: return 0 def sigmoid(self,x): return 1 / (1 + np.exp(-x)) def sigmoid_output_2_derivative(self,output): return output * (1 - output) def train(self, training_reviews, training_labels): # make sure out we have a matching number of reviews and labels assert(len(training_reviews) == len(training_labels)) # Keep track of correct predictions to display accuracy during training correct_so_far = 0 # Remember when we started for printing time statistics start = time.time() # loop through all the given reviews and run a forward and backward pass, # updating weights for every item for i in range(len(training_reviews)): # Get the next review and its correct label review = training_reviews[i] label = training_labels[i] #### Implement the forward pass here #### ### Forward pass ### # Input Layer self.update_input_layer(review) # Hidden layer layer_1 = self.layer_0.dot(self.weights_0_1) # Output layer layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2)) #### Implement the backward pass here #### ### Backward pass ### # Output error layer_2_error = layer_2 - self.get_target_for_label(label) # Output layer error is the difference between desired target and actual output. layer_2_delta = layer_2_error * self.sigmoid_output_2_derivative(layer_2) # Backpropagated error layer_1_error = layer_2_delta.dot(self.weights_1_2.T) # errors propagated to the hidden layer layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error # Update the weights self.weights_1_2 -= layer_1.T.dot(layer_2_delta) * self.learning_rate # update hidden-to-output weights with gradient descent step self.weights_0_1 -= self.layer_0.T.dot(layer_1_delta) * self.learning_rate # update input-to-hidden weights with gradient descent step # Keep track of correct predictions. if(layer_2 >= 0.5 and label == 'POSITIVE'): correct_so_far += 1 elif(layer_2 < 0.5 and label == 'NEGATIVE'): correct_so_far += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the training process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \ + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%") if(i % 2500 == 0): print("") def test(self, testing_reviews, testing_labels): Attempts to predict the labels for the given testing_reviews, and uses the test_labels to calculate the accuracy of those predictions. # keep track of how many correct predictions we make correct = 0 # we'll time how many predictions per second we make start = time.time() # Loop through each of the given reviews and call run to predict # its label. for i in range(len(testing_reviews)): pred = self.run(testing_reviews[i]) if(pred == testing_labels[i]): correct += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the prediction process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct) + " #Tested:" + str(i+1) \ + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%") def run(self, review): Returns a POSITIVE or NEGATIVE prediction for the given review. # Run a forward pass through the network, like in the "train" function. # Input Layer self.update_input_layer(review.lower()) # Hidden layer layer_1 = self.layer_0.dot(self.weights_0_1) # Output layer layer_2 = self.sigmoid(layer_1.dot(self.weights_1_2)) # Return POSITIVE for values above greater-than-or-equal-to 0.5 in the output layer; # return NEGATIVE for other values if(layer_2[0] >= 0.5): return "POSITIVE" else: return "NEGATIVE" mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1) mlp.train(reviews[:-1000],labels[:-1000]) mlp.test(reviews[-1000:],labels[-1000:]) Image(filename='sentiment_network_sparse.png') layer_0 = np.zeros(10) layer_0 layer_0[4] = 1 layer_0[9] = 1 layer_0 weights_0_1 = np.random.randn(10,5) layer_0.dot(weights_0_1) indices = [4,9] layer_1 = np.zeros(5) for index in indices: layer_1 += (1 * weights_0_1[index]) layer_1 Image(filename='sentiment_network_sparse_2.png') layer_1 = np.zeros(5) for index in indices: layer_1 += (weights_0_1[index]) layer_1 import time import sys import numpy as np # Encapsulate our neural network in a class class SentimentNetwork: def __init__(self, reviews,labels,hidden_nodes = 10, learning_rate = 0.1): Create a SentimenNetwork with the given settings Args: reviews(list) - List of reviews used for training labels(list) - List of POSITIVE/NEGATIVE labels associated with the given reviews hidden_nodes(int) - Number of nodes to create in the hidden layer learning_rate(float) - Learning rate to use while training # Assign a seed to our random number generator to ensure we get # reproducable results during development np.random.seed(1) # process the reviews and their associated labels so that everything # is ready for training self.pre_process_data(reviews, labels) # Build the network to have the number of hidden nodes and the learning rate that # were passed into this initializer. Make the same number of input nodes as # there are vocabulary words and create a single output node. self.init_network(len(self.review_vocab),hidden_nodes, 1, learning_rate) def pre_process_data(self, reviews, labels): # populate review_vocab with all of the words in the given reviews review_vocab = set() for review in reviews: for word in review.split(" "): review_vocab.add(word) # Convert the vocabulary set to a list so we can access words via indices self.review_vocab = list(review_vocab) # populate label_vocab with all of the words in the given labels. label_vocab = set() for label in labels: label_vocab.add(label) # Convert the label vocabulary set to a list so we can access labels via indices self.label_vocab = list(label_vocab) # Store the sizes of the review and label vocabularies. self.review_vocab_size = len(self.review_vocab) self.label_vocab_size = len(self.label_vocab) # Create a dictionary of words in the vocabulary mapped to index positions self.word2index = {} for i, word in enumerate(self.review_vocab): self.word2index[word] = i # Create a dictionary of labels mapped to index positions self.label2index = {} for i, label in enumerate(self.label_vocab): self.label2index[label] = i def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate): # Set number of nodes in input, hidden and output layers. self.input_nodes = input_nodes self.hidden_nodes = hidden_nodes self.output_nodes = output_nodes # Store the learning rate self.learning_rate = learning_rate # Initialize weights # These are the weights between the input layer and the hidden layer. self.weights_0_1 = np.zeros((self.input_nodes,self.hidden_nodes)) # These are the weights between the hidden layer and the output layer. self.weights_1_2 = np.random.normal(0.0, self.output_nodes*-0.5, (self.hidden_nodes, self.output_nodes)) ## New for Project 5: Removed self.layer_0; added self.layer_1 # The input layer, a two-dimensional matrix with shape 1 x hidden_nodes self.layer_1 = np.zeros((1,hidden_nodes)) ## New for Project 5: Removed update_input_layer function def get_target_for_label(self,label): if(label == 'POSITIVE'): return 1 else: return 0 def sigmoid(self,x): return 1 / (1 + np.exp(-x)) def sigmoid_output_2_derivative(self,output): return output (1 - output) ## New for Project 5: changed name of first parameter form 'training_reviews' # to 'training_reviews_raw' def train(self, training_reviews_raw, training_labels): ## New for Project 5: pre-process training reviews so we can deal # directly with the indices of non-zero inputs training_reviews = list() for review in training_reviews_raw: indices = set() for word in review.split(" "): if(word in self.word2index.keys()): indices.add(self.word2index[word]) training_reviews.append(list(indices)) # make sure out we have a matching number of reviews and labels assert(len(training_reviews) == len(training_labels)) # Keep track of correct predictions to display accuracy during training correct_so_far = 0 # Remember when we started for printing time statistics start = time.time() # loop through all the given reviews and run a forward and backward pass, # updating weights for every item for i in range(len(training_reviews)): # Get the next review and its correct label review = training_reviews[i] label = training_labels[i] #### Implement the forward pass here #### ### Forward pass ### ## New for Project 5: Removed call to 'update_input_layer' function # because 'layer_0' is no longer used # Hidden layer ## New for Project 5: Add in only the weights for non-zero items self.layer_1 = 0 for index in review: self.layer_1 += self.weights_0_1[index] # Output layer ## New for Project 5: changed to use 'self.layer_1' instead of 'local layer_1' layer_2 = self.sigmoid(self.layer_1.dot(self.weights_1_2)) #### Implement the backward pass here #### ### Backward pass ### # Output error layer_2_error = layer_2 - self.get_target_for_label(label) # Output layer error is the difference between desired target and actual output. layer_2_delta = layer_2_error self.sigmoid_output_2_derivative(layer_2) # Backpropagated error layer_1_error = layer_2_delta.dot(self.weights_1_2.T) # errors propagated to the hidden layer layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error # Update the weights ## New for Project 5: changed to use 'self.layer_1' instead of local 'layer_1' self.weights_1_2 -= self.layer_1.T.dot(layer_2_delta) * self.learning_rate # update hidden-to-output weights with gradient descent step ## New for Project 5: Only update the weights that were used in the forward pass for index in review: self.weights_0_1[index] -= layer_1_delta[0] * self.learning_rate # update input-to-hidden weights with gradient descent step # Keep track of correct predictions. if(layer_2 >= 0.5 and label == 'POSITIVE'): correct_so_far += 1 elif(layer_2 < 0.5 and label == 'NEGATIVE'): correct_so_far += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the training process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \ + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%") if(i % 2500 == 0): print("") def test(self, testing_reviews, testing_labels): Attempts to predict the labels for the given testing_reviews, and uses the test_labels to calculate the accuracy of those predictions. # keep track of how many correct predictions we make correct = 0 # we'll time how many predictions per second we make start = time.time() # Loop through each of the given reviews and call run to predict # its label. for i in range(len(testing_reviews)): pred = self.run(testing_reviews[i]) if(pred == testing_labels[i]): correct += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the prediction process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct) + " #Tested:" + str(i+1) \ + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%") def run(self, review): Returns a POSITIVE or NEGATIVE prediction for the given review. # Run a forward pass through the network, like in the "train" function. ## New for Project 5: Removed call to update_input_layer function # because layer_0 is no longer used # Hidden layer ## New for Project 5: Identify the indices used in the review and then add # just those weights to layer_1 self.layer_1 = 0 unique_indices = set() for word in review.lower().split(" "): if word in self.word2index.keys(): unique_indices.add(self.word2index[word]) for index in unique_indices: self.layer_1 += self.weights_0_1[index] # Output layer ## New for Project 5: changed to use self.layer_1 instead of local layer_1 layer_2 = self.sigmoid(self.layer_1.dot(self.weights_1_2)) # Return POSITIVE for values above greater-than-or-equal-to 0.5 in the output layer; # return NEGATIVE for other values if(layer_2[0] >= 0.5): return "POSITIVE" else: return "NEGATIVE" mlp = SentimentNetwork(reviews[:-1000],labels[:-1000], learning_rate=0.1) mlp.train(reviews[:-1000],labels[:-1000]) mlp.test(reviews[-1000:],labels[-1000:]) Image(filename='sentiment_network_sparse_2.png') # words most frequently seen in a review with a "POSITIVE" label pos_neg_ratios.most_common() # words most frequently seen in a review with a "NEGATIVE" label list(reversed(pos_neg_ratios.most_common()))[0:30] from bokeh.models import ColumnDataSource, LabelSet from bokeh.plotting import figure, show, output_file from bokeh.io import output_notebook output_notebook() hist, edges = np.histogram(list(map(lambda x:x[1],pos_neg_ratios.most_common())), density=True, bins=100, normed=True) p = figure(tools="pan,wheel_zoom,reset,save", toolbar_location="above", title="Word Positive/Negative Affinity Distribution") p.quad(top=hist, bottom=0, left=edges[:-1], right=edges[1:], line_color="#555555") show(p) frequency_frequency = Counter() for word, cnt in total_counts.most_common(): frequency_frequency[cnt] += 1 hist, edges = np.histogram(list(map(lambda x:x[1],frequency_frequency.most_common())), density=True, bins=100, normed=True) p = figure(tools="pan,wheel_zoom,reset,save", toolbar_location="above", title="The frequency distribution of the words in our corpus") p.quad(top=hist, bottom=0, left=edges[:-1], right=edges[1:], line_color="#555555") show(p) import time import sys import numpy as np # Encapsulate our neural network in a class class SentimentNetwork: ## New for Project 6: added min_count and polarity_cutoff parameters def __init__(self, reviews,labels,min_count = 10,polarity_cutoff = 0.1,hidden_nodes = 10, learning_rate = 0.1): Create a SentimenNetwork with the given settings Args: reviews(list) - List of reviews used for training labels(list) - List of POSITIVE/NEGATIVE labels associated with the given reviews min_count(int) - Words should only be added to the vocabulary if they occur more than this many times polarity_cutoff(float) - The absolute value of a word's positive-to-negative ratio must be at least this big to be considered. hidden_nodes(int) - Number of nodes to create in the hidden layer learning_rate(float) - Learning rate to use while training # Assign a seed to our random number generator to ensure we get # reproducable results during development np.random.seed(1) # process the reviews and their associated labels so that everything # is ready for training ## New for Project 6: added min_count and polarity_cutoff arguments to pre_process_data call self.pre_process_data(reviews, labels, polarity_cutoff, min_count) # Build the network to have the number of hidden nodes and the learning rate that # were passed into this initializer. Make the same number of input nodes as # there are vocabulary words and create a single output node. self.init_network(len(self.review_vocab),hidden_nodes, 1, learning_rate) ## New for Project 6: added min_count and polarity_cutoff parameters def pre_process_data(self, reviews, labels, polarity_cutoff, min_count): ## ---------------------------------------- ## New for Project 6: Calculate positive-to-negative ratios for words before # building vocabulary # positive_counts = Counter() negative_counts = Counter() total_counts = Counter() for i in range(len(reviews)): if(labels[i] == 'POSITIVE'): for word in reviews[i].split(" "): positive_counts[word] += 1 total_counts[word] += 1 else: for word in reviews[i].split(" "): negative_counts[word] += 1 total_counts[word] += 1 pos_neg_ratios = Counter() for term,cnt in list(total_counts.most_common()): if(cnt >= 50): pos_neg_ratio = positive_counts[term] / float(negative_counts[term]+1) pos_neg_ratios[term] = pos_neg_ratio for word,ratio in pos_neg_ratios.most_common(): if(ratio > 1): pos_neg_ratios[word] = np.log(ratio) else: pos_neg_ratios[word] = -np.log((1 / (ratio + 0.01))) # ## end New for Project 6 ## ---------------------------------------- # populate review_vocab with all of the words in the given reviews review_vocab = set() for review in reviews: for word in review.split(" "): ## New for Project 6: only add words that occur at least min_count times # and for words with pos/neg ratios, only add words # that meet the polarity_cutoff if(total_counts[word] > min_count): if(word in pos_neg_ratios.keys()): if((pos_neg_ratios[word] >= polarity_cutoff) or (pos_neg_ratios[word] <= -polarity_cutoff)): review_vocab.add(word) else: review_vocab.add(word) # Convert the vocabulary set to a list so we can access words via indices self.review_vocab = list(review_vocab) # populate label_vocab with all of the words in the given labels. label_vocab = set() for label in labels: label_vocab.add(label) # Convert the label vocabulary set to a list so we can access labels via indices self.label_vocab = list(label_vocab) # Store the sizes of the review and label vocabularies. self.review_vocab_size = len(self.review_vocab) self.label_vocab_size = len(self.label_vocab) # Create a dictionary of words in the vocabulary mapped to index positions self.word2index = {} for i, word in enumerate(self.review_vocab): self.word2index[word] = i # Create a dictionary of labels mapped to index positions self.label2index = {} for i, label in enumerate(self.label_vocab): self.label2index[label] = i def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate): # Set number of nodes in input, hidden and output layers. self.input_nodes = input_nodes self.hidden_nodes = hidden_nodes self.output_nodes = output_nodes # Store the learning rate self.learning_rate = learning_rate # Initialize weights # These are the weights between the input layer and the hidden layer. self.weights_0_1 = np.zeros((self.input_nodes,self.hidden_nodes)) # These are the weights between the hidden layer and the output layer. self.weights_1_2 = np.random.normal(0.0, self.output_nodes-0.5, (self.hidden_nodes, self.output_nodes)) ## New for Project 5: Removed self.layer_0; added self.layer_1 # The input layer, a two-dimensional matrix with shape 1 x hidden_nodes self.layer_1 = np.zeros((1,hidden_nodes)) ## New for Project 5: Removed update_input_layer function def get_target_for_label(self,label): if(label == 'POSITIVE'): return 1 else: return 0 def sigmoid(self,x): return 1 / (1 + np.exp(-x)) def sigmoid_output_2_derivative(self,output): return output (1 - output) ## New for Project 5: changed name of first parameter form 'training_reviews' # to 'training_reviews_raw' def train(self, training_reviews_raw, training_labels): ## New for Project 5: pre-process training reviews so we can deal # directly with the indices of non-zero inputs training_reviews = list() for review in training_reviews_raw: indices = set() for word in review.split(" "): if(word in self.word2index.keys()): indices.add(self.word2index[word]) training_reviews.append(list(indices)) # make sure out we have a matching number of reviews and labels assert(len(training_reviews) == len(training_labels)) # Keep track of correct predictions to display accuracy during training correct_so_far = 0 # Remember when we started for printing time statistics start = time.time() # loop through all the given reviews and run a forward and backward pass, # updating weights for every item for i in range(len(training_reviews)): # Get the next review and its correct label review = training_reviews[i] label = training_labels[i] #### Implement the forward pass here #### ### Forward pass ### ## New for Project 5: Removed call to 'update_input_layer' function # because 'layer_0' is no longer used # Hidden layer ## New for Project 5: Add in only the weights for non-zero items self.layer_1 = 0 for index in review: self.layer_1 += self.weights_0_1[index] # Output layer ## New for Project 5: changed to use 'self.layer_1' instead of 'local layer_1' layer_2 = self.sigmoid(self.layer_1.dot(self.weights_1_2)) #### Implement the backward pass here #### ### Backward pass ### # Output error layer_2_error = layer_2 - self.get_target_for_label(label) # Output layer error is the difference between desired target and actual output. layer_2_delta = layer_2_error self.sigmoid_output_2_derivative(layer_2) # Backpropagated error layer_1_error = layer_2_delta.dot(self.weights_1_2.T) # errors propagated to the hidden layer layer_1_delta = layer_1_error # hidden layer gradients - no nonlinearity so it's the same as the error # Update the weights ## New for Project 5: changed to use 'self.layer_1' instead of local 'layer_1' self.weights_1_2 -= self.layer_1.T.dot(layer_2_delta) * self.learning_rate # update hidden-to-output weights with gradient descent step ## New for Project 5: Only update the weights that were used in the forward pass for index in review: self.weights_0_1[index] -= layer_1_delta[0] * self.learning_rate # update input-to-hidden weights with gradient descent step # Keep track of correct predictions. if(layer_2 >= 0.5 and label == 'POSITIVE'): correct_so_far += 1 elif(layer_2 < 0.5 and label == 'NEGATIVE'): correct_so_far += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the training process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \ + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%") if(i % 2500 == 0): print("") def test(self, testing_reviews, testing_labels): Attempts to predict the labels for the given testing_reviews, and uses the test_labels to calculate the accuracy of those predictions. # keep track of how many correct predictions we make correct = 0 # we'll time how many predictions per second we make start = time.time() # Loop through each of the given reviews and call run to predict # its label. for i in range(len(testing_reviews)): pred = self.run(testing_reviews[i]) if(pred == testing_labels[i]): correct += 1 # For debug purposes, print out our prediction accuracy and speed # throughout the prediction process. elapsed_time = float(time.time() - start) reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0 sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \ + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \ + " #Correct:" + str(correct) + " #Tested:" + str(i+1) \ + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%") def run(self, review): Returns a POSITIVE or NEGATIVE prediction for the given review. # Run a forward pass through the network, like in the "train" function. ## New for Project 5: Removed call to update_input_layer function # because layer_0 is no longer used # Hidden layer ## New for Project 5: Identify the indices used in the review and then add # just those weights to layer_1 self.layer_1 *= 0 unique_indices = set() for word in review.lower().split(" "): if word in self.word2index.keys(): unique_indices.add(self.word2index[word]) for index in unique_indices: self.layer_1 += self.weights_0_1[index] # Output layer ## New for Project 5: changed to use self.layer_1 instead of local layer_1 layer_2 = self.sigmoid(self.layer_1.dot(self.weights_1_2)) # Return POSITIVE for values above greater-than-or-equal-to 0.5 in the output layer; # return NEGATIVE for other values if(layer_2[0] >= 0.5): return "POSITIVE" else: return "NEGATIVE" mlp = SentimentNetwork(reviews[:-1000],labels[:-1000],min_count=20,polarity_cutoff=0.05,learning_rate=0.01) mlp.train(reviews[:-1000],labels[:-1000]) mlp.test(reviews[-1000:],labels[-1000:]) mlp = SentimentNetwork(reviews[:-1000],labels[:-1000],min_count=20,polarity_cutoff=0.8,learning_rate=0.01) mlp.train(reviews[:-1000],labels[:-1000]) mlp.test(reviews[-1000:],labels[-1000:]) mlp_full = SentimentNetwork(reviews[:-1000],labels[:-1000],min_count=0,polarity_cutoff=0,learning_rate=0.01) mlp_full.train(reviews[:-1000],labels[:-1000]) Image(filename='sentiment_network_sparse.png') def get_most_similar_words(focus = "horrible"): most_similar = Counter() for word in mlp_full.word2index.keys(): most_similar[word] = np.dot(mlp_full.weights_0_1[mlp_full.word2index[word]],mlp_full.weights_0_1[mlp_full.word2index[focus]]) return most_similar.most_common() get_most_similar_words("excellent") get_most_similar_words("terrible") import matplotlib.colors as colors words_to_visualize = list() for word, ratio in pos_neg_ratios.most_common(500): if(word in mlp_full.word2index.keys()): words_to_visualize.append(word) for word, ratio in list(reversed(pos_neg_ratios.most_common()))[0:500]: if(word in mlp_full.word2index.keys()): words_to_visualize.append(word) pos = 0 neg = 0 colors_list = list() vectors_list = list() for word in words_to_visualize: if word in pos_neg_ratios.keys(): vectors_list.append(mlp_full.weights_0_1[mlp_full.word2index[word]]) if(pos_neg_ratios[word] > 0): pos+=1 colors_list.append("#00ff00") else: neg+=1 colors_list.append("#000000") from sklearn.manifold import TSNE tsne = TSNE(n_components=2, random_state=0) words_top_ted_tsne = tsne.fit_transform(vectors_list) p = figure(tools="pan,wheel_zoom,reset,save", toolbar_location="above", title="vector T-SNE for most polarized words") source = ColumnDataSource(data=dict(x1=words_top_ted_tsne[:,0], x2=words_top_ted_tsne[:,1], names=words_to_visualize)) p.scatter(x="x1", y="x2", size=8, source=source,color=colors_list) word_labels = LabelSet(x="x1", y="x2", text="names", y_offset=6, text_font_size="8pt", text_color="#555555", source=source, text_align='center') p.add_layout(word_labels) show(p) # green indicates positive words, black indicates negative words <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Parsing is hard... Step3: Exercise I Step4: Python Regexp Step5: Achieve more complex splitting using regular expressions. Step6: Benchmarking in iPython - I Step8: Parsing	<ASSISTANT_TASK:> Python Code: import re import nose # %timeit from __future__ import print_function # Before writing the parser, collect samples of # the interesting lines. For now just mail_sent = 'May 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: to=<jon@doe.it>, relay=examplemx2.doe.it[222.33.44.555]:25, delay=0.8, delays=0.17/0.01/0.43/0.19, dsn=2.0.0, status=sent(250 ok: Message 2108406157 accepted)' mail_delivered = 'May 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: removed' print("I'm goint to parse the following line", mail_sent, sep="\n\n") def test_sent(): hour, host, to = parse_line(mail_sent) assert hour == '08:00:00' assert to == 'jon@doe.it' # Play with mail_sent mail_sent.split() # You can number fields with enumerate. # Remember that ipython puts the last returned value in `_` # in our case: _ = mail_sent.split() # which is useful in interactive mode! fields, counting = _, enumerate(_) print(counting, sep="\n") #counting = enumerate(mail_sent.split()) #for it in counting: # print(it) # Now we can pick fields singularly... hour, host, dest = fields[2], fields[3], fields[6] print("Hour: {}, host: {}, dest: {}".format(hour, host, dest)) test_str_1 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: to=<jon@doe.it>, relay=examplemx2.doe.it[222.33.44.555]:25, delay=0.8, delays=0.17/0.01/0.43/0.19, dsn=2.0.0, status=sent(250 ok: Message 2108406157 accepted)' test_str_2 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: removed' def test_sent(): hour, host, destination = parse_line(test_str_1) assert hour == '08:00:00' assert host == 'test-fe1' assert destination == 'to=<jon@doe.it>,' def test_delivered(): hour, host, destination = parse_line(test_str_2) print(destination) assert hour == '08:00:00' assert host == 'test-fe1' assert destination is None def parse_line(line): Complete the parse line function. # Hint: "you can".split() # Hint: "<you can slice>"[1:-1] or use re.split pass test_sent() test_delivered() # Python supports regular expressions via import re # We start showing a grep-reloaded function def grep(expr, fpath): one = re.compile(expr) # ...has two lookup methods... assert ( one.match # which searches from ^ the beginning and one.search ) # that searches $\pyver{anywhere}$ with open(fpath) as fp: return [x for x in fp if one.search(x)] # The function seems to work as expected ;) assert not grep(r'^localhost', '/etc/hosts') # And some more tests ret = grep('127.0.0.1', '/etc/hosts') assert ret, "ret should not be empty" print(ret) # Splitting with re.findall from re import findall # can be misused too; # eg for adding the ":" to a mac = "00""24""e8""b4""33""20" # ...using this re_hex = "[0-9a-fA-F]{2}" mac_address = ':'.join(findall(re_hex, mac)) print("The mac address is ", mac_address) # Actually this does a bit of validation, requiring all chars to be in the 0-F range # Run the following cell many times. # Do you always get the same results? import timeit test_all_regexps = ("..", "[a-fA-F0-9]{2}") for re_s in test_all_regexps: print(timeit.timeit(stmt="':'.join(findall(re_s, mac))", setup="from re import findall;re_s='{}';mac='{}'".format(re_s, mac))) # We can even compare compiled vs inline regexp import re from time import sleep for re_s in test_all_regexps: print(timeit.timeit(stmt="':'.join(re_c.findall(mac))", setup="from re import findall, compile;re_c=compile('{}');mac='{}'".format(re_s, mac))) # ...or simple print(timeit.timeit(stmt="':'.join([mac[i:i+2] for i in range(0,12,2)])", setup="from re import findall;mac='{}'".format(mac))) # # Use this cell for Exercise II # test_str_1 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: to=<jon@doe.it>, relay=examplemx2.doe.it[222.33.44.555]:25, delay=0.8, delays=0.17/0.01/0.43/0.19, dsn=2.0.0, status=sent(250 ok: Message 2108406157 accepted)' test_str_2 = 'Nov 31 08:00:00 test-fe1 postfix/smtp[16669]: 7CD8E730020: removed' def test_sent(): hour, host, destination = parse_line(test_str_1) assert hour == '08:00:00' assert host == 'test-fe1' assert destination == 'jon@doe.it' def test_delivered(): hour, host, destination = parse_line(test_str_2) assert hour == '08:00:00' assert host == 'test-fe1' assert destination is None def parse_line(line): Complete the parse line function. # Hint: "you can".split() # Hint: "<you can slice>"[1:-1] or use re.split pass test_sent() test_delivered() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: First, import the EBTEL results. Step2: Next, reshape the EBTEL results into something readable by the IonPopSolver code and save them to a file. Set some parameters for reading the data structure. Step3: Now, print the files. Step4: We need to modify the XML input file for the IonPopSolver code to make sure it points to the right atomic database (see install instructions in IonPopSolver). We'll also set the cutoff ion fraction to $1\times10^{-6}$ to speed up the calculation. Step5: Now, we'll run the code in parallel with the subprocess module. First, define the worker function that will run in parallel. Step6: Now, we need to assemble our list of inputs.	<ASSISTANT_TASK:> Python Code: import os import pickle import multiprocessing import subprocess import xml.etree.ElementTree as ET import numpy as np with open(__depends__[0],'rb') as f: varying_tau_results = pickle.load(f) tau_indices = [0,-1] prefixes = ['tau20','tau500'] parameter_sets = {'single':('t','T','n'),'electron':('te','Tee','ne'),'ion':('ti','Tie','ni')} inputs = [] for i,pre in zip(tau_indices,prefixes): for key in parameter_sets: inputs.append(os.path.join('../results/','_tmp_%s.%s.ips.txt'%(pre,key))) np.savetxt(os.path.join('../results/','_tmp_%s.%s.ips.txt'%(pre,key)), np.transpose([varying_tau_results[i][parameter_sets[key][0]], varying_tau_results[i][parameter_sets[key][1]], varying_tau_results[i][parameter_sets[key][2]]]), header=str(len(varying_tau_results[i][parameter_sets[key][0]])),comments='',fmt='%f\t%e\t%e') xml_tree = ET.parse(os.path.join(os.environ['EXP_DIR'],'IonPopSolver/test/radiation.example.cfg.xml')) root = xml_tree.getroot() node1 = root.find('atomicDB') node1.text = os.path.join(os.environ['EXP_DIR'],'apolloDB') + '/' node2 = root.find('cutoff_ion_fraction') node2.text = '1e-6' xml_tree.write(os.path.join(os.environ['EXP_DIR'],'IonPopSolver/test/radiation.local.cfg.xml')) def worker((input_file,output_file)): print("Running IonPopSolver for input %s"%(input_file)) executable = os.path.join(os.environ['EXP_DIR'],'IonPopSolver/bin/IonPopSolver.run') static_args = ["-Z","26","-f","9","-t","27","-r", os.path.join(os.environ['EXP_DIR'],'IonPopSolver/test/radiation.local.cfg.xml')] var_args = ["-I",os.path.abspath(input_file),"-O",os.path.abspath(output_file)] subprocess.call([executable]+static_args+var_args) print("Finished IonPopSolver for input %s"%(input_file)) p = multiprocessing.Pool() p.map(worker,zip(sorted(inputs),__dest__)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: El segundo paso consiste en usar como likelihood una distribución binomial y no una Gaussiana. De esta forma el modelo queda expresado como Step2: Ahora graficaremos las 3 especies versus la longitud del sépalo usando la función stripplot de seaborn Step3: Observe en la figura 4.2 que en el eje y se representan una variable continua mientras que en el eje x la variable es categórica. La dispersión (o jitter) de los puntos a lo largo del eje x no tiene ningún significado, y es solo un truco para evitar que todos los puntos colapsen en una sola línea (pueden probar pasando el argumento jitter=False). Por lo tanto lo único que importa al leer el eje x es la pertenencia de los puntos a las clases setosa, versicolor o virginica. Step4: Antes de continuar, tómese un tiempo para estudiar las gráficas anteriores y familiarizarse con el conjunto de datos y cómo se relacionan las variables dependientes y las independientes. Step5: Al igual que con otros modelos lineales, centrar los datos puede ayudar con el muestreo. Ahora que tenemos los datos en el formato adecuado, finalmente podemos construir el modelo con PyMC3. Step6: Como es habitual, también mostramos el summary del posterior. Más adelante, compararemos el valor que obtengamos para el límite de decisión con un valor calculado utilizando otro método. Step7: Ahora vamos a graficar los datos junto con la curva sigmoide ajustada Step8: La figura 4.4 muestra la longitud del sépalo para las especies (setosa = 0, versicolor = 1). Para mitigar la superposición de los datos, hemos agregado ruido (jitter) a las variables-respuesta binarias. Una línea verde en forma de S representa el valor medio de $\theta$. Esta línea se puede interpretar como la probabilidad que una flor sea versicolor dado el valor de la longitud del sépalo. La banda verde semitransparente es el intervalo del 94% de HPD. De esta forma podemos interpretar a la regresión logística como una forma de combinar variables linealmente a fin de obtener una probabilidad para variables binarias. Step9: El límite de decisión Step10: Como hicimos para una única variable predictiva, vamos a graficar los datos y el límite de decisión. Step11: El límite de decisión es una línea recta, como ya hemos visto. No se confunda con el aspecto curvo de la banda del 94% de HPD. La curvatura aparente es el resultado de tener múltiples líneas que giran alrededor de una región central (aproximadamente alrededor de la media de x y la media de y). Step12: Por lo tanto, los valores de los coeficientes proporcionados por summary están en la escala log-odds. Step13: Una forma muy empírica de entender los modelos es cambiar los parámetros y ver qué sucede. En el siguiente bloque de código, calculamos las log-odds en favor de versicolor como $\text {log_odds_versicolor_i} = \alpha + beta_1 x1 + \beta_2 x2$, y luego la probabilidad de versicolor con la función logística. Luego repetimos el cálculo arreglando $x_2$ y aumentando $x_1$ en 1. Step14: Si ejecutas el código, encontrarás que el aumento en las log-odds es de $\approx 4.7$, que es exactamente el valor de $\beta_0$ (verifique el summary para trace_1). Esto está en línea con nuestro hallazgo anterior que muestra que los coeficientes $\beta$ indican el aumento en unidades log-odds por incremento unitario de la variable $x$. El aumento en la probabilidad es $\approx 0.70$. Step15: Para generar la figura 4.7, hemos utilizado una máscara que elimina el triángulo superior y los elementos diagonales del heatmap, ya que estos son poco informativos o redundantes. Observe también que hemos graficado el valor absoluto de la correlación, ya que en este momento no nos importa el signo de la correlación entre las variables, solo su fuerza. Step16: Y ahora ejecutamos una regresión logística múltiple, tal cual hicimos antes. Step17: El límite de decisión se desplaza hacia la clase menos abundante y la incertidumbre es más grande que antes. Este es el comportamiento típico de un modelo logístico para datos no balanceados. ¡Pero espera un minuto! Bien podrías argumentar que te estoy engañando ya que la mayor incertidumbre es en realidad el producto de tener menos datos y no solo menos setosas que versicolores. Este es un punto totalmente válido, pero si realizas el ejercicio 2 podrás verificar que lo que explica esta gráfica son los datos desequilibrados. Step18: ¿Qué hacer si encontramos datos desequilibrados? Bueno, la solución obvia es obtener un conjunto de datos con aproximadamente la misma cantidad por clase. Este es un punto a tener en cuenta al recopilar o generar los datos. Si no tenés control sobre el conjunto de datos, debes tener cuidado al interpretar los resultados para datos no balanceados. Verifique la incertidumbre del modelo y ejecute algunas verificaciones predictivas posteriores para ver si los resultados son útiles para usted. Otra opción sería utilizar priors más informativos y/o ejecutar un modelo alternativo como se explica más adelante en este capítulo. Step19: El código de PyMC3 refleja los pocos cambios entre el modelo logístico y el modelo softmax. Presta atención a los valores de shape para los coeficientes $\alpha $ y $\beta$. En el siguiente código usamos la función softmax de Theano. Hemos utilizado la expresión import theano.tensor as tt, que es la convención utilizada por los desarrolladores de PyMC3 Step20: ¿Qué tan bien funciona nuestro modelo? Averigüemos cuántos casos podemos predecir correctamente. En el siguiente código, solo usamos la media de los parámetros para calcular la probabilidad de que cada punto de datos pertenezca a cada una de las tres clases, luego asignamos la clase usando la función argmax. Y comparamos el resultado con los valores observados Step21: El resultado es que clasificamos correctamente $\approx 98 \%$ de los datos, es decir, clasificamos erroneamente solo tres casos. Ese es realmente un muy buen trabajo. Sin embargo, una verdadera prueba para evaluar el rendimiento de nuestro modelo sería verificarlo con un conjunto de datos no usado para ajustar al modelo. De lo contrario, es posible que estemos sobreestimando la capacidad real del modelo para generalizar a otros datos. Step22: Linear discriminant analysis (LDA) Step23: Ahora vamos a generar una figura que muestra las dos clases (setosa = 0 yversicolor = 1) contra los valores de la longitud del sépalo, y también el límite de decisión como una línea naranja y el intervalo del 94% de HPD como una banda naranja semitransparente. Step24: Como habrá notado, la figura 4.9 es bastante similar a la figura 4.4. Verifique también los valores de la decisión de límite en el siguiente summary Step25: Tanto el modelo LDA como la regresión logística proporcionan resultados similares. El modelo discriminante lineal puede extenderse a más de una característica al modelar las clases como Gaussianas multivariadas. Además, es posible relajar el supuesto de que las clases comparten una varianza común (o covarianza). Esto conduce a un modelo conocido como análisis discriminante cuadrático (QDA). Step26: Es importante notar que $\mu$ puede ser un flotante, pero la distribución modela probabilidad de un número discreto de eventos. En la figura 4.10, los puntos representan los valores de la distribución, mientras que las líneas continuas son una ayuda visual que nos ayuda a comprender fácilmente la forma de la distribución. Recuerde, la distribución de Poisson es una distribución discreta. Step27: Regresión de Poisson y regresión ZIP Step28: Lo dejo como un ejercicio para que explore el conjunto de datos utilizando gráficos y / o una función de Pandas, como describe(). Por ahora vamos a continuar traduciendo el diagrama de Kruschke anterior a PyMC3 Step29: Para entender mejor los resultados de nuestra inferencia, hagamos una gráfica. Step30: Regresión logística robusta Step31: Aquí tenemos algunas versicolors (1s) con una longitud de sépalo inusualmente corta. Podemos arreglar esto con un modelo de mezcla. Vamos a decir que la variable de salida viene con probabilidad $\pi$ por adivinación aleatoria o con probabilidad $1-\pi$ de un modelo de regresión logística. Matemáticamente, tenemos	<ASSISTANT_TASK:> Python Code: z = np.linspace(-6, 6) logística = 1 / (1 + np.exp(-z)) plt.plot(z, logística) plt.xlabel('z') plt.ylabel('logística(z)') plt.title('Figure 4.1'); iris = pd.read_csv('datos/iris.csv') iris.head() sns.stripplot(x="species", y="sepal_length", data=iris, jitter=True) plt.title('Figure 4.2'); sns.pairplot(iris, hue='species') plt.title('Figure 4.3'); df = iris.query("species == ('setosa', 'versicolor')") y_0 = pd.Categorical(df['species']).codes x_n = 'sepal_length' x_0 = df[x_n].values x_c = x_0 - x_0.mean() with pm.Model() as modelo_0: α = pm.Normal('α', mu=0, sd=10) β = pm.Normal('β', mu=0, sd=10) μ = α + pm.math.dot(x_c, β) θ = pm.Deterministic('θ', pm.math.sigmoid(μ)) bd = pm.Deterministic('bd', -α/β) yl = pm.Bernoulli('yl', p=θ, observed=y_0) trace_0 = pm.sample(1000) varnames = ['α', 'β', 'bd'] az.plot_trace(trace_0, varnames); az.summary(trace_0, varnames) theta = trace_0['θ'].mean(axis=0) idx = np.argsort(x_c) plt.figure(figsize=(10, 6)) plt.plot(x_c[idx], theta[idx], color='C2', lw=3); plt.vlines(trace_0['bd'].mean(), 0, 1, color='k') bd_hpd = az.hpd(trace_0['bd']) plt.fill_betweenx([0, 1], bd_hpd[0], bd_hpd[1], color='k', alpha=0.5) plt.scatter(x_c, np.random.normal(y_0, 0.02), marker='.', color=[f'C{x}' for x in y_0]) theta_hpd = az.hpd(trace_0['θ'])[idx] plt.fill_between(x_c[idx], theta_hpd[:,0], theta_hpd[:,1], color='C2', alpha=0.5) plt.xlabel(x_n) plt.ylabel('θ', rotation=0, labelpad=20) # use original scale for xticks locs, _ = plt.xticks() plt.xticks(locs, np.round(locs + x_0.mean(), 1)) plt.title('Figure 4.4'); df = iris.query("species == ('setosa', 'versicolor')") y_1 = pd.Categorical(df['species']).codes x_n = ['sepal_length', 'sepal_width'] #x_n = ['petal_length', 'petal_width'] x_1 = df[x_n].values with pm.Model() as modelo_1: α = pm.Normal('α', mu=0, sd=10) β = pm.Normal('β', mu=0, sd=2, shape=len(x_n)) μ = α + pm.math.dot(x_1, β) θ = pm.Deterministic('θ', pm.math.sigmoid(μ)) bd = pm.Deterministic('bd', -α/β[1] - β[0]/β[1] * x_1[:,0]) yl = pm.Bernoulli('yl', p=θ, observed=y_1) trace_1 = pm.sample(2000) varnames = ['α', 'β'] az.plot_forest(trace_1, var_names=varnames); idx = np.argsort(x_1[:,0]) bd = trace_1['bd'].mean(0)[idx] plt.scatter(x_1[:,0], x_1[:,1], c=[f'C{x}' for x in y_0]) plt.plot(x_1[:,0][idx], bd, color='k'); bd_hpd = az.hpd(trace_1['bd'])[idx] plt.fill_between(x_1[:,0][idx], bd_hpd[:,0], bd_hpd[:,1], color='k', alpha=0.5); plt.xlabel(x_n[0]) plt.ylabel(x_n[1]) plt.title('Figure 4.5'); probability = np.linspace(0.01, 1, 100) odds = probability / (1 - probability) _, ax1 = plt.subplots() ax2 = ax1.twinx() ax1.plot(probability, odds, 'C0') ax2.plot(probability, np.log(odds), 'C1') ax1.set_xlabel('probability') ax1.set_ylabel('odds', color='C0') ax2.set_ylabel('log-odds', color='C1') ax1.grid(False) ax2.grid(False) plt.title('Figure 4.6'); df = az.summary(trace_1, varnames) df x_1 = 4.5 # sepal_length x_2 = 3 # sepal_width log_odds_versicolor_i = (df['mean'] * [1, x_1, x_2]).sum() probability_versicolor_i = logistic(log_odds_versicolor_i) log_odds_versicolor_f = (df['mean'] * [1, x_1 + 1, x_2]).sum() probability_versicolor_f = logistic(log_odds_versicolor_f) (f'{log_odds_versicolor_f - log_odds_versicolor_i:.2f}', f'{probability_versicolor_f - probability_versicolor_i:.2f}') corr = iris[iris['species'] != 'virginica'].corr() mask = np.tri(corr.shape).T sns.heatmap(corr.abs(), mask=mask, annot=True, cmap='viridis') plt.title('Figure 4.7'); df = iris.query("species == ('setosa', 'versicolor')") df = df[45:] y_3 = pd.Categorical(df['species']).codes x_n = ['sepal_length', 'sepal_width'] x_3 = df[x_n].values with pm.Model() as modelo_3: α = pm.Normal('α', mu=0, sd=10) β = pm.Normal('β', mu=0, sd=2, shape=len(x_n)) μ = α + pm.math.dot(x_3, β) θ = pm.math.sigmoid(μ) bd = pm.Deterministic('bd', -α/β[1] - β[0]/β[1] x_3[:,0]) yl = pm.Bernoulli('yl', p=θ, observed=y_3) trace_3 = pm.sample(1000) idx = np.argsort(x_3[:,0]) bd = trace_3['bd'].mean(0)[idx] plt.scatter(x_3[:,0], x_3[:,1], c= [f'C{x}' for x in y_3]) plt.plot(x_3[:,0][idx], bd, color='k'); bd_hpd = pm.hpd(trace_3['bd'])[idx] plt.fill_between(x_3[:,0][idx], bd_hpd[:,0], bd_hpd[:,1], color='k', alpha=0.5); plt.xlabel(x_n[0]) plt.ylabel(x_n[1]); plt.title('Figure 4.8') iris = sns.load_dataset('iris') y_s = pd.Categorical(iris['species']).codes x_n = iris.columns[:-1] x_s = iris[x_n].values x_s = (x_s - x_s.mean(axis=0)) / x_s.std(axis=0) with pm.Model() as modelo_s: α = pm.Normal('α', mu=0, sd=5, shape=3) β = pm.Normal('β', mu=0, sd=5, shape=(4,3)) μ = pm.Deterministic('μ', α + pm.math.dot(x_s, β)) θ = tt.nnet.softmax(μ) yl = pm.Categorical('yl', p=θ, observed=y_s) trace_s = pm.sample(2000) az.plot_forest(trace_s, var_names=['α', 'β']); data_pred = trace_s['μ'].mean(0) y_pred = [np.exp(point)/np.sum(np.exp(point), axis=0) for point in data_pred] f'{np.sum(y_s == np.argmax(y_pred, axis=1)) / len(y_s):.2f}' with pm.Model() as modelo_sf: α = pm.Normal('α', mu=0, sd=2, shape=2) β = pm.Normal('β', mu=0, sd=2, shape=(4,2)) α_f = tt.concatenate([[0] ,α]) β_f = tt.concatenate([np.zeros((4,1)) , β], axis=1) μ = α_f + pm.math.dot(x_s, β_f) θ = tt.nnet.softmax(μ) yl = pm.Categorical('yl', p=θ, observed=y_s) trace_sf = pm.sample(1000) az.plot_forest(trace_sf, var_names=['α', 'β']); with pm.Model() as modelo_lda: μ = pm.Normal('μ', mu=0, sd=10, shape=2) σ = pm.HalfNormal('σ', 10) setosa = pm.Normal('setosa', mu=μ[0], sd=σ, observed=x_0[:50]) versicolor = pm.Normal('versicolor', mu=μ[1], sd=σ, observed=x_0[50:]) bd = pm.Deterministic('bd', (μ[0] + μ[1]) / 2) trace_lda = pm.sample(1000) plt.axvline(trace_lda['bd'].mean(), ymax=1, color='C1') bd_hpd = pm.hpd(trace_lda['bd']) plt.fill_betweenx([0, 1], bd_hpd[0], bd_hpd[1], color='C1', alpha=0.5) plt.plot(x_0, np.random.normal(y_0, 0.02), '.', color='k') plt.ylabel('θ', rotation=0) plt.xlabel('sepal_length') plt.title('Figure 4.9'); az.summary(trace_lda) mu_params = [0.5, 1.5, 3, 8] x = np.arange(0, max(mu_params) * 3) for mu in mu_params: y = stats.poisson(mu).pmf(x) plt.plot(x, y, 'o-', label=f'μ = {mu:3.1f}') plt.legend() plt.xlabel('x') plt.ylabel('f(x)') plt.title('Figure 4.10') plt.savefig('B11197_04_10.png', dpi=300); #np.random.seed(42) n = 100 θ_real = 2.5 ψ = 0.1 # Simulate some data counts = np.array([(np.random.random() > (1-ψ)) * np.random.poisson(θ_real) for i in range(n)]) with pm.Model() as ZIP: ψ = pm.Beta('ψ', 1., 1.) θ = pm.Gamma('θ', 2., 0.1) y = pm.ZeroInflatedPoisson('y', ψ, θ, observed=counts) trace = pm.sample(1000) az.plot_trace(trace) plt.title('Figure 4.11'); az.summary(trace) fish_data = pd.read_csv('datos/fish.csv') with pm.Model() as ZIP_reg: ψ = pm.Beta('ψ', 1, 1) α = pm.Normal('α', 0, 10) β = pm.Normal('β', 0, 10, shape=2) θ = pm.math.exp(α + β[0] * fish_data['child'] + β[1] * fish_data['camper']) yl = pm.ZeroInflatedPoisson('yl', ψ, θ, observed=fish_data['count']) trace_ZIP_reg = pm.sample(1000) az.plot_trace(trace_ZIP_reg); children = [0, 1, 2, 3, 4] fish_count_pred_0 = [] fish_count_pred_1 = [] for n in children: without_camper = trace_ZIP_reg['α'] + trace_ZIP_reg['β'][:,0] * n with_camper = without_camper + trace_ZIP_reg['β'][:,1] fish_count_pred_0.append(np.exp(without_camper)) fish_count_pred_1.append(np.exp(with_camper)) plt.plot(children, fish_count_pred_0, 'C0.', alpha=0.01) plt.plot(children, fish_count_pred_1, 'C1.', alpha=0.01) plt.xticks(children); plt.xlabel('Number of children') plt.ylabel('Fish caught') plt.plot([], 'C0o', label='without camper') plt.plot([], 'C1o', label='with camper') plt.legend(); plt.title('Figure 4.12'); iris = sns.load_dataset("iris") df = iris.query("species == ('setosa', 'versicolor')") y_0 = pd.Categorical(df['species']).codes x_n = 'sepal_length' x_0 = df[x_n].values y_0 = np.concatenate((y_0, np.ones(6, dtype=int))) x_0 = np.concatenate((x_0, [4.2, 4.5, 4.0, 4.3, 4.2, 4.4])) x_c = x_0 - x_0.mean() plt.plot(x_c, y_0, 'o', color='k'); with pm.Model() as modelo_rlg: α = pm.Normal('α', mu=0, sd=10) β = pm.Normal('β', mu=0, sd=10) μ = α + x_c * β θ = pm.Deterministic('θ', pm.math.sigmoid(μ)) bd = pm.Deterministic('bd', -α/β) π = pm.Beta('π', 1, 1) p = π * 0.5 + (1 - π) * θ yl = pm.Bernoulli('yl', p=p, observed=y_0) trace_rlg = pm.sample(1000) az.summary(trace_rlg, varnames) theta = trace_rlg['θ'].mean(axis=0) idx = np.argsort(x_c) plt.plot(x_c[idx], theta[idx], color='C2', lw=3); plt.vlines(trace_rlg['bd'].mean(), 0, 1, color='k') bd_hpd = pm.hpd(trace_rlg['bd']) plt.fill_betweenx([0, 1], bd_hpd[0], bd_hpd[1], color='k', alpha=0.5) plt.scatter(x_c, np.random.normal(y_0, 0.02), marker='.', color=[f'C{x}' for x in y_0]) theta_hpd = pm.hpd(trace_rlg['θ'])[idx] plt.fill_between(x_c[idx], theta_hpd[:,0], theta_hpd[:,1], color='C2', alpha=0.5) plt.xlabel(x_n) plt.ylabel('θ', rotation=0) # use original scale for xticks locs, _ = plt.xticks() plt.xticks(locs, np.round(locs + x_0.mean(), 1)) plt.title('Figure 4.13'); <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Violations of graphical excellence and integrity	<ASSISTANT_TASK:> Python Code: from IPython.display import Image # Add your filename and uncomment the following line: # Image(filename='yourfile.png') Image('netfli.png') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Let's coarse grain an atomic PDB structure to the amino acid level Step2: Create Input and run MC simulation Step3: Analysis	<ASSISTANT_TASK:> Python Code: from __future__ import division, unicode_literals, print_function import matplotlib as mpl import matplotlib.pyplot as plt %matplotlib inline import numpy as np, pandas as pd import os.path, os, sys, json, filecmp, copy plt.rcParams.update({'font.size': 16, 'figure.figsize': [8.0, 6.0]}) try: workdir except NameError: workdir=%pwd else: %cd $workdir print(workdir) %%bash -s "$workdir" %cd $1 if [ ! -d "faunus/" ]; then git clone https://github.com/mlund/faunus.git cd faunus git checkout 86a1f74 else cd faunus fi # if different, copy custom gctit.cpp into faunus if ! cmp ../titrate.cpp src/examples/gctit.cpp then cp ../titrate.cpp src/examples/gctit.cpp fi pwd cmake . -DCMAKE_BUILD_TYPE=Release -DENABLE_APPROXMATH=on &>/dev/null make example_gctit -j4 %cd $workdir import mdtraj as md traj = md.load_pdb('1BPI.pdb') for chain in traj.topology.chains: print('chain: ', chain.index) # filter pdb to only select protein(s) sel = chain.topology.select('protein') top = chain.topology.subset(sel) f = open('chain'+str(chain.index)+'.aam','w') f.write(str(top.n_residues)+'\n') # locate disulfide bonds (not used for anything yet) for b in top.bonds: i = b[0].residue.index j = b[1].residue.index if j>i+1: if (b[0].residue.name == 'CYS'): if (b[1].residue.name == 'CYS'): print('SS-bond between residues', i, j) # loop over residues and calculate residue mass centers, radius, and weight top.create_disulfide_bonds( traj.xyz[0] ) for res in top.residues: if res.is_protein: cm = [0,0,0] # residue mass center mw = 0 # residue weight for a in res.atoms: cm = cm + a.element.mass * traj.xyz[0][a.index] mw = mw + a.element.mass cm = cm/mw10 radius = ( 3./(4np.pi)mw/1.0 )*(1/3.) f.write('{0:4} {1:5} {2:8.3f} {3:8.3f} {4:8.3f} {5:6.3f} {6:6.2f} {7:6.2f}\n'\ .format(res.name,res.index,cm[0],cm[1],cm[2],0,mw,radius)) f.close() pH_range = [7.0] salt_range = [0.03] # mol/l %cd $workdir'/' def mkinput(): js = { "energy": { "eqstate": { "processfile": "titrate.json" }, "nonbonded": { "coulomb": { "epsr": 80 } } }, "system": { "temperature": 298.15, "sphere" : { "radius" : 90 }, "mcloop": { "macro": 10, "micro": micro } }, "moves": { "gctit" : { "molecule": "salt", "prob": 0.5 }, "atomtranslate" : { "salt": { "prob": 0.5 } } }, "moleculelist": { "protein": { "structure":"../chain0.aam", "Ninit":1, "insdir":"0 0 0"}, "salt": {"atoms":"Na Cl", "Ninit":60, "atomic":True } }, "atomlist" : { "Na" : { "q": 1, "r":1.9, "eps":0.005, "mw":22.99, "dp":100, "activity":salt }, "Cl" : { "q":-1, "r":1.7, "eps":0.005, "mw":35.45, "dp":100, "activity":salt }, "ASP" : { "q":-1, "r":3.6, "eps":0.05, "mw":110 }, "HASP" : { "q":0, "r":3.6, "eps":0.05, "mw":110 }, "LASP" : { "q":2, "r":3.6, "eps":0.05, "mw":110 }, "CTR" : { "q":-1, "r":2.0, "eps":0.05, "mw":16 }, "HCTR" : { "q":0, "r":2.0, "eps":0.05, "mw":16 }, "GLU" : { "q":-1, "r":3.8, "eps":0.05, "mw":122 }, "HGLU" : { "q":0, "r":3.8, "eps":0.05, "mw":122 }, "LGLU" : { "q":2, "r":3.8, "eps":0.05, "mw":122 }, "HIS" : { "q":0, "r":3.9, "eps":0.05, "mw":130 }, "HHIS" : { "q":1, "r":3.9, "eps":0.05, "mw":130 }, "NTR" : { "q":0, "r":2.0, "eps":0.05, "mw":14 }, "HNTR" : { "q":1, "r":2.0, "eps":0.05, "mw":14 }, "TYR" : { "q":-1, "r":4.1, "eps":0.05, "mw":154 }, "HTYR" : { "q":0, "r":4.1, "eps":0.05, "mw":154 }, "LYS" : { "q":0, "r":3.7, "eps":0.05, "mw":116 }, "HLYS" : { "q":1, "r":3.7, "eps":0.05, "mw":116 }, "CYb" : { "q":0, "r":3.6, "eps":0.05, "mw":103 }, "CYS" : { "q":-1, "r":3.6, "eps":0.05, "mw":103 }, "HCYS" : { "q":0, "r":3.6, "eps":0.05, "mw":103 }, "ARG" : { "q":0, "r":4.0, "eps":0.05, "mw":144 }, "HARG" : { "q":1, "r":4.0, "eps":0.05, "mw":144 }, "ALA" : { "q":0, "r":3.1, "eps":0.05, "mw":66 }, "ILE" : { "q":0, "r":3.6, "eps":0.05, "mw":102 }, "LEU" : { "q":0, "r":3.6, "eps":0.05, "mw":102 }, "MET" : { "q":0, "r":3.8, "eps":0.05, "mw":122 }, "PHE" : { "q":0, "r":3.9, "eps":0.05, "mw":138 }, "PRO" : { "q":0, "r":3.4, "eps":0.05, "mw":90 }, "TRP" : { "q":0, "r":4.3, "eps":0.05, "mw":176 }, "VAL" : { "q":0, "r":3.4, "eps":0.05, "mw":90 }, "SER" : { "q":0, "r":3.3, "eps":0.05, "mw":82 }, "THR" : { "q":0, "r":3.5, "eps":0.05, "mw":94 }, "ASN" : { "q":0, "r":3.6, "eps":0.05, "mw":108 }, "GLN" : { "q":0, "r":3.8, "eps":0.05, "mw":120 }, "GLY" : { "q":0, "r":2.9, "eps":0.05, "mw":54 } }, "processes" : { "H-Asp" : { "bound":"HASP" , "free":"ASP" , "pKd":4.0 , "pX":pH }, "H-Ctr" : { "bound":"HCTR" , "free":"CTR" , "pKd":2.6 , "pX":pH }, "H-Glu" : { "bound":"HGLU" , "free":"GLU" , "pKd":4.4 , "pX":pH }, "H-His" : { "bound":"HHIS" , "free":"HIS" , "pKd":6.3 , "pX":pH }, "H-Arg" : { "bound":"HARG" , "free":"ARG" , "pKd":12.0 , "pX":pH }, "H-Ntr" : { "bound":"HNTR" , "free":"NTR" , "pKd":7.5 , "pX":pH }, "H-Cys" : { "bound":"HCYS" , "free":"CYS" , "pKd":10.8 , "pX":pH }, "H-Tyr" : { "bound":"HTYR" , "free":"TYR" , "pKd":9.6 , "pX":pH }, "H-Lys" : { "bound":"HLYS" , "free":"LYS" , "pKd":10.4 , "pX":pH } } } with open('titrate.json', 'w+') as f: f.write(json.dumps(js, indent=4)) for pH in pH_range: for salt in salt_range: pfx='pH'+str(pH)+'-I'+str(salt) if not os.path.isdir(pfx): %mkdir -p $pfx %cd $pfx # equilibration run (no translation) !rm -fR state micro=100 mkinput() !../faunus/src/examples/gctit > eq # production run micro=1000 mkinput() %time !../faunus/src/examples/gctit > out %cd .. %cd .. print('done.') %cd $workdir'/' import json for pH in pH_range: for salt in salt_range: pfx='pH'+str(pH)+'-I'+str(salt) if os.path.isdir(pfx): %cd $pfx js = json.load( open('gctit-output.json') ) charge = js['protein']['charge'] index = js['protein']['index'] resname = js['protein']['resname'] plt.plot(index,charge, 'ro') %cd .. for i in range(0,len(index)): label = resname[i]+' '+str(index[i]+1) plt.annotate(label, xy=(index[i], charge[i]), fontsize=8, rotation=70) plt.title('Protonation States of All Residues') plt.legend(loc=0, frameon=False) plt.xlabel(r'residue number') plt.ylabel(r'average charge, $z$') plt.ylim((-1.1, 1.1)) #plt.xticks(i, resname, rotation=70, fontsize='small') plt.savefig('fig.pdf', bbox_inches='tight') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Exercise 1 Step2: Exercise 2 Step3: Exercise 3 Step4: b. Confidence Intervals. Step5: Exercise 4	<ASSISTANT_TASK:> Python Code: # Useful Functions class DiscreteRandomVariable: def __init__(self, a=0, b=1): self.variableType = "" self.low = a self.high = b return def draw(self, numberOfSamples): samples = np.random.randint(self.low, self.high, numberOfSamples) return samples class BinomialRandomVariable(DiscreteRandomVariable): def __init__(self, numberOfTrials = 10, probabilityOfSuccess = 0.5): self.variableType = "Binomial" self.numberOfTrials = numberOfTrials self.probabilityOfSuccess = probabilityOfSuccess return def draw(self, numberOfSamples): samples = np.random.binomial(self.numberOfTrials, self.probabilityOfSuccess, numberOfSamples) return samples def factorial(n):return reduce(lambda x,y:xy,[1]+range(1,n+1)) # Useful Libraries import pandas as pd import numpy as np import matplotlib.pyplot as plt import statsmodels.stats as stats from statsmodels.stats import stattools from __future__ import division # Histograms with 10 tosses. cointoss = DiscreteRandomVariable(1, 3) plt.hist(cointoss.draw(10), align = 'mid') plt.xlabel('Value') plt.ylabel('Occurences') plt.legend(['Coin Tosses']); # Histograms with 1000000 tosses. cointoss = DiscreteRandomVariable(1, 3) plt.hist(cointoss.draw(1000000), align = 'mid') plt.xlabel('Value') plt.ylabel('Occurences') plt.legend(['Coin Tosses']); # Binomial distribution with p=0.25 and n=20 binomialdistribution = BinomialRandomVariable(20, 0.25) bins = np.arange(0,21,1) n, bins, patches = plt.hist(binomialdistribution.draw(1000000), bins=bins) plt.title('Binomial Distribution with p=0.25 and n=20') plt.xlabel('Value') plt.ylabel('Occurrences') plt.legend(['Die Rolls']); # Finding x which occurs most often elem = np.argmax(n) print 'Maximum occurance for x =', elem # Calculating the probability of finding x. n = 20 p = 0.5 x = elem n_factorial = factorial(n) x_factorial = factorial(x) n_x_factorial = factorial(n-x) fact = n_factorial / (n_x_factorial x_factorial) probability = fact * (p*x) ((1-p)*(n-x)) print 'proabability of x = %d' % x, probability # Graphing a normal distribution pdf. mu = 0 sigma = 5 x = np.linspace(-30, 30, 200) y = (1/(sigma np.sqrt(2 * 3.14159))) * np.exp(-(x - mu)(x - mu) / (2 sigma * sigma)) plt.plot(x, y) plt.title('Graph of PDF with mu = 0 and sigma = 5') plt.xlabel('Value') plt.ylabel('Probability'); # finding the 1st, 2nd, and third confidence intervals. first_ci = (-sigma, sigma) second_ci = (-2sigma, 2sigma) third_ci = (-3sigma, 3sigma) print '1-sigma -> mu +/-', sigma print '2-sigma -> mu +/-', second_ci[1] print '3-sigma -> mu +/-', third_ci[1] plt.axvline(first_ci[0], linestyle='dashdot', label='68% of observations', color = 'blue') plt.axvline(first_ci[1], linestyle='dashdot', label='68% of observations', color = 'blue') plt.axvline(second_ci[0], linestyle='dashdot', label='95% of observations', color = 'red') plt.axvline(second_ci[1],linestyle='dashdot', color = 'red') plt.axvline(third_ci[0], linestyle='dashdot', label='99% of observations', color = 'green') plt.axvline(third_ci[1], linestyle='dashdot', color = 'green') plt.plot(x,y) plt.title('Graph of PDF with 3 confidence intervals.') plt.legend(); # Collect prices and returns. prices = get_pricing('SPY', start_date = '2016-01-01', end_date='2016-05-01', fields = 'price') returns = prices.pct_change()[1:] # Calculating the mean and standard deviation. sample_mean = np.mean(returns) sample_std_dev = np.std(returns) x = np.linspace(-(sample_mean + 4 * sample_std_dev), (sample_mean + 4 * sample_std_dev), len(returns)) sample_distribution = ((1/(sample_std_dev * 2 * np.pi)) * np.exp(-(x - sample_mean)(x - sample_mean) / (2 sample_std_dev * sample_std_dev))) # Plotting histograms and confidence intervals. plt.hist(returns, range=(returns.min(), returns.max()), normed = True); plt.plot(x, sample_distribution) plt.axvline(sample_std_dev, linestyle='dashed', color='red', label='1st Confidence Interval') plt.axvline(-sample_std_dev, linestyle='dashed', color='red') plt.axvline(2sample_std_dev, linestyle='dashed', color='k', label='2st Confidence Interval') plt.axvline(-2sample_std_dev, linestyle='dashed', color='k') plt.axvline(3sample_std_dev, linestyle='dashed', color='green', label='3st Confidence Interval') plt.axvline(-3sample_std_dev, linestyle='dashed', color='green') plt.legend(); # Run the JB test for normality. cutoff = 0.01 _, p_value, skewness, kurtosis = stattools.jarque_bera(returns) print "The JB test p-value is: ", p_value print "We reject the hypothesis that the data are normally distributed ", p_value < cutoff print "The skewness of the returns is: ", skewness print "The kurtosis of the returns is: ", kurtosis <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Este es como se leen los mapas de direcciones y dem para el trazado de cuencas y corrientes Step2: Trazado de corrientes Step3: El perfil de una corriente puede ser utilizado como punto de referencia para la búsqueda de puntos de trazado Step4: Trazado de cuenca Step5: La ultima cuenca tiene un conteo de celdas igual a 1, lo cual significa que no se ha trazado nada y que por esta celda no pasa ninguna otra celda, por lo tanto esto no es una cuenca, y no debe ser usado para ningún tipo de cálculos, en la siguiente línea este elemento es eliminado Step6: Balance sobre cuencas Step7: En la Figura se presenta el caudal medio estimado para cada elemento de la cuenca, incluidas celdas en donde no se considera la presencia de red hídrica. Step8: La figura anterior ha sido guardada en el disco mediante el comando ruta = 'Caldas_ETR.png', en este caso ha sido sobre el directorio de trabajo actual, si este se cambia, se cambia el directorio donde se guarda. Step9: Cada entrada en Qmax y Qmin corresponde al periodo de retorno Tr [2.33, 5, 10, 25, 50, 100], estos pueden ser cambiados al interior de la función al cambiar la propiedad Tr en el momento en que esta es invocada. Step10: Guardado en shp Step11: Geomorfologia	<ASSISTANT_TASK:> Python Code: #Paquete Watershed Modelling Framework (WMF) para el trabajo con cuencas. from wmf import wmf # Lectura del DEM DEM = wmf.read_map_raster('/media/nicolas/discoGrande/raster/dem_corr.tif',isDEMorDIR=True, dxp=30.0) DIR = wmf.read_map_raster('/media/nicolas/discoGrande/raster/dirAMVA.tif',isDEMorDIR=True, dxp= 30.0) wmf.cu.nodata=-9999.0; wmf.cu.dxp=30.0 DIR[DIR<=0]=wmf.cu.nodata.astype(int) DIR=wmf.cu.dir_reclass(DIR,wmf.cu.ncols,wmf.cu.nrows) st = wmf.Stream(-75.618,6.00,DEM=DEM,DIR=DIR,name ='Rio Medellin') st.structure st.Plot_Profile() # Mediante el comando de busqueda hemos buscado donde se localizan las coordenadas que cumplen la propiedad de estar a #una distancia de la salida que oscila entre 10000 y 10100 metros. np.where((st.structure[3]>10000) & (st.structure[3]<10100)) # Las coordenadas en la entrada 289 son: print st.structure[0,289] print st.structure[1,289] # La cuenca puede ser trtazada utilizando las coordenadas de forma implicita (como en este ejemplo), o de una # manera explicita como se realizaría en la segunda línea de código. cuenca = wmf.Basin(-75.6364,6.11051,DEM,DIR,name='ejemplo',stream=st) # en esta segunda linea estamos trazando una cuenca con unas coordenadas que no son exactas y no se sabe si estan # sobre la corriente, este problema se corrige al pasarle la corriente al trazador mediante el comando stream, el cual # recibe como entrada el objeto corriente previamente obtenido. cuenca2 = wmf.Basin(-75.6422,6.082,DEM,DIR,name='ejemplo',stream=st) # Cuenca error: en este caso no se para el argumento stream, por lo que la cuenca se traza sobre las coordenadas # que se han dado, lo cual probablemente produzca un error. cuenca3 = wmf.Basin(-75.6364,6.11051,DEM,DIR,name='ejemplo',stream=st) # Se imprime la cantidad de celdas que comprenden a cada una de las cuencas obtenidas, esto para ver que efectivamente # existe una diferencia entre ambas debida a las diferencias de coordenadas. print cuenca.ncells print cuenca2.ncells print cuenca3.ncells del(cuenca3) # Balance en una cuenca asumiendo precipitación anual igual a 2000 mm/año sobre toda la cuenca cuenca.GetQ_Balance(2100) # La variable de balance de largo plazo se calcula para cada celda de la cuenca y queda almacenada en cuenca.CellQmed cuenca.Plot_basin(cuenca.CellQmed) # Plot de la evaporación sobre la cuenca de caldas cuenca.Plot_basin(cuenca.CellETR, extra_lat= 0.001, extra_long= 0.001, lines_spaces= 0.02, ruta = 'Caldas_ETR.png') # Estimacion de maximos, por defecto lo hace por gumbel, lo puede hacer tambien por lognormal Qmax = cuenca.GetQ_Max(cuenca.CellQmed) Qmax2 = cuenca.GetQ_Max(cuenca.CellQmed, Tr= [3, 15]) # Estimacion de minimos, por defecto lo hace por gumbel, lo puede hacer tambien por lognormal Qmin = cuenca.GetQ_Min(cuenca.CellQmed) Qmin[Qmin<0]=0 # Plot del caudal máximo para un periodo de retorno de 2.33 cuenca.Plot_basin(Qmax[0]) # Plot del caudal máximo para un periodo de retorno de 100 cuenca.Plot_basin(Qmax[5]) cuenca.Save_Basin2Map('Cuenca.kml',DriverFormat='kml') cuenca.Save_Net2Map('Red.kml',DriverFormat='kml',qmed=cuenca.CellQmed) # Calcula geomorfología por cauces cuenca.GetGeo_Cell_Basics() # reporte de geomorfologia generico y los almacena en cuenca.GeoParameters y en cuenca.Tc cuenca.GetGeo_Parameters() cuenca.GeoParameters # Tiempos de concentracion cuenca.Tc cuenca.Plot_Tc() cuenca.GetGeo_IsoChrones(1.34) cuenca.Plot_basin(cuenca.CellTravelTime) cuenca.Plot_Travell_Hist() cuenca.GetGeo_Ppal_Hipsometric() cuenca.PlotPpalStream() cuenca.Plot_Hipsometric() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Import pyfabm - the python module that contains the Fortran based FABM Step2: Configuration Step3: Model increment Step4: Time axis and model integration Step5: Plot the results	<ASSISTANT_TASK:> Python Code: import numpy import scipy.integrate import pyfabm #pyfabm.get_version() yaml_file = 'fabm-bb-lorenz63.yaml' model = pyfabm.Model(yaml_file) model.findDependency('bottom_depth').value = 1. model.checkReady(stop=True) def dy(y,t0): model.state[:] = y return model.getRates() t = numpy.arange(0.0, 40.0, 0.01) y = scipy.integrate.odeint(dy,model.state,t) import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D fig = plt.figure() ax = fig.gca(projection='3d') ax.plot(y[:,0], y[:,1], y[:,2]) plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: 1.1 Required Module Step7: 2. Classfication Model Step8: 3. Training Step11: 3.2 Initialize model parameters Step15: 作业1 Step17: 3.3 Repeat over certain numbers of epoch Step20: 3.3.2 & 3.3.3 compute gradient of loss over parameters & update parameters with gradient descent Step23: Define function fit and use train_epoch and test_epoch Step24: 作业 2 Step25: 模型没有训练到过拟合，观察上面训练数据，随着代数增多，测试集的正确率并没有下降。 Step26: 作业 3 Step27: 观察数据可以发现其实10代也没有过拟合。 Step28: 3.4 save model Step29: 作业 4 Step30: 4. Training Advanced Step31: 作业 5 Step32: 4.2 dropout Step33: 4.3 batch_normalization Step34: 4.4 data augmentation Step35: 作业 6 Step36: 5. Visualizatio of training and validation phase Step37: 6.1.1 Gradient Vanishing Step38: 6.1.2 Gradient Explosion Step40: 6.1.2.2 normalization for input data	<ASSISTANT_TASK:> Python Code: %load_ext autoreload %autoreload 2 # Load all necessary modules here, for clearness import torch import numpy as np import torch.nn as nn import torch.nn.functional as F import torch.optim as optim # from torchvision.datasets import MNIST import torchvision from torchvision import transforms from torch.optim import lr_scheduler # from tensorboardX import SummaryWriter from collections import OrderedDict import matplotlib.pyplot as plt # from tqdm import tqdm # Whether to put data in GPU according to GPU is available or not # cuda = torch.cuda.is_available() # In case the default gpu does not have enough space, you can choose which device to use # torch.cuda.set_device(device) # device: id # Since gpu in lab is not enough for your guys, we prefer to cpu computation cuda = torch.device('cpu') class FeedForwardNeuralNetwork(nn.Module): Inputs Linear/Function Output [128, 1, 28, 28] -> Linear(2828, 100) -> [128, 100] # first hidden lyaer -> ReLU -> [128, 100] # relu activation function, may sigmoid -> Linear(100, 100) -> [128, 100] # second hidden lyaer -> ReLU -> [128, 100] # relu activation function, may sigmoid -> Linear(100, 100) -> [128, 100] # third hidden lyaer -> ReLU -> [128, 100] # relu activation function, may sigmoid -> Linear(100, 10) -> [128, 10] # Classification Layer def __init__(self, input_size, hidden_size, output_size, activation_function='RELU'): super(FeedForwardNeuralNetwork, self).__init__() self.use_dropout = False self.use_bn = False self.hidden1 = nn.Linear(input_size, hidden_size) # Linear function 1: 784 --> 100 self.hidden2 = nn.Linear(hidden_size, hidden_size) # Linear function 2: 100 --> 100 self.hidden3 = nn.Linear(hidden_size, hidden_size) # Linear function 3: 100 --> 100 # Linear function 4 (readout): 100 --> 10 self.classification_layer = nn.Linear(hidden_size, output_size) self.dropout = nn.Dropout(p=0.5) # Drop out with prob = 0.5 self.hidden1_bn = nn.BatchNorm1d(hidden_size) # Batch Normalization self.hidden2_bn = nn.BatchNorm1d(hidden_size) self.hidden3_bn = nn.BatchNorm1d(hidden_size) # Non-linearity if activation_function == 'SIGMOID': self.activation_function1 = nn.Sigmoid() self.activation_function2 = nn.Sigmoid() self.activation_function3 = nn.Sigmoid() elif activation_function == 'RELU': self.activation_function1 = nn.ReLU() self.activation_function2 = nn.ReLU() self.activation_function3 = nn.ReLU() def forward(self, x): Defines the computation performed at every call. Should be overridden by all subclasses. Args: x: [batch_size, channel, height, width], input for network Returns: out: [batch_size, n_classes], output from network x = x.view(x.size(0), -1) # flatten x in [128, 784] out = self.hidden1(x) out = self.activation_function1(out) # Non-linearity 1 if self.use_bn == True: out = self.hidden1_bn(out) out = self.hidden2(out) out = self.activation_function2(out) if self.use_bn == True: out = self.hidden2_bn(out) out = self.hidden3(out) if self.use_bn == True: out = self.hidden3_bn(out) out = self.activation_function3(out) if self.use_dropout == True: out = self.dropout(out) out = self.classification_layer(out) return out def set_use_dropout(self, use_dropout): Whether to use dropout. Auxiliary function for our exp, not necessary. Args: use_dropout: True, False self.use_dropout = use_dropout def set_use_bn(self, use_bn): Whether to use batch normalization. Auxiliary function for our exp, not necessary. Args: use_bn: True, False self.use_bn = use_bn def get_grad(self): Return average grad for hidden2, hidden3. Auxiliary function for our exp, not necessary. hidden2_average_grad = np.mean(np.sqrt(np.square(self.hidden2.weight.grad.detach().numpy()))) hidden3_average_grad = np.mean(np.sqrt(np.square(self.hidden3.weight.grad.detach().numpy()))) return hidden2_average_grad, hidden3_average_grad ### Hyper parameters batch_size = 128 # batch size is 128 n_epochs = 5 # train for 5 epochs learning_rate = 0.01 # learning rate is 0.01 input_size = 2828 # input image has size 28x28 hidden_size = 100 # hidden neurons is 100 for each layer output_size = 10 # classes of prediction l2_norm = 0 # not to use l2 penalty dropout = False # not to use get_grad = False # not to obtain grad # create a model object model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) def show_weight_bias(model): Show some weights and bias distribution every layers in model. !!YOU CAN READ THIS CODE LATER!! # Create a figure and a set of subplots fig, axs = plt.subplots(2,3, sharey=False, tight_layout=True) # weight and bias for every hidden layer h1_w = model.hidden1.weight.detach().numpy().flatten() h1_b = model.hidden1.bias.detach().numpy().flatten() h2_w = model.hidden2.weight.detach().numpy().flatten() h2_b = model.hidden2.bias.detach().numpy().flatten() h3_w = model.hidden3.weight.detach().numpy().flatten() h3_b = model.hidden3.bias.detach().numpy().flatten() axs[0,0].hist(h1_w) axs[0,1].hist(h2_w) axs[0,2].hist(h3_w) axs[1,0].hist(h1_b) axs[1,1].hist(h2_b) axs[1,2].hist(h3_b) # set title for every sub plots axs[0,0].set_title('hidden1_weight') axs[0,1].set_title('hidden2_weight') axs[0,2].set_title('hidden3_weight') axs[1,0].set_title('hidden1_bias') axs[1,1].set_title('hidden2_bias') axs[1,2].set_title('hidden3_bias') # Show default initialization for every hidden layer by pytorch # it's uniform distribution show_weight_bias(model) # If you want to use other intialization method, you can use code below # and define your initialization below def weight_bias_reset(model): Custom initialization, you can use your favorable initialization method. for m in model.modules(): if isinstance(m, nn.Linear): # initialize linear layer with mean and std mean, std = 0, 0.1 # Initialization method torch.nn.init.normal_(m.weight, mean, std) torch.nn.init.normal_(m.bias, mean, std) # Another way to initialize # m.weight.data.normal_(mean, std) # m.bias.data.normal_(mean, std) weight_bias_reset(model) # reset parameters for each hidden layer show_weight_bias(model) # show weight and bias distribution, normal distribution now. def weight_bias_reset_constant(model): Constant initalization for m in model.modules(): if isinstance(m, nn.Linear): val = 0.1 torch.nn.init.constant_(m.weight, val) torch.nn.init.constant_(m.bias, val) weight_bias_reset_constant(model) show_weight_bias(model) def weight_bias_reset_xavier_uniform(model): xaveir_uniform, gain=1 for m in model.modules(): if isinstance(m, nn.Linear): gain = 1 torch.nn.init.xavier_uniform_(m.weight, gain) # torch.nn.init.xavier_uniform_(m.bias, gain) weight_bias_reset_xavier_uniform(model) show_weight_bias(model) def weight_bias_reset_kaiming_uniform(model): kaiming_uniform, a=0, mode='fan_in', non_linearity='relu' for m in model.modules(): if isinstance(m, nn.Linear): a = 0 torch.nn.init.kaiming_uniform_(m.weight, a=a, mode='fan_in', nonlinearity='relu') # torch.nn.init.kaiming_uniform_(m.bias, a=a, mode='fan_in', nonlinearity='relu') weight_bias_reset_kaiming_uniform(model) show_weight_bias(model) # define method of preprocessing data for evaluating train_transform = transforms.Compose([ transforms.ToTensor(), # Convert a PIL Image or numpy.ndarray to tensor. # Normalize a tensor image with mean 0.1307 and standard deviation 0.3081 transforms.Normalize((0.1307,), (0.3081,)) ]) test_transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ]) # use MNIST provided by torchvision # torchvision.datasets provide MNIST dataset for classification train_dataset = torchvision.datasets.MNIST(root='./data', train=True, transform=train_transform, download=True) test_dataset = torchvision.datasets.MNIST(root='./data', train=False, transform=test_transform, download=False) # pay attention to this, train_dataset doesn't load any data # It just defined some method and store some message to preprocess data train_dataset # Data loader. # Combines a dataset and a sampler, # and provides single- or multi-process iterators over the dataset. train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=False) test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False) # functions to show an image def imshow(img): show some imgs in datasets !!YOU CAN READ THIS CODE LATER!! npimg = img.numpy() # convert tensor to numpy plt.imshow(np.transpose(npimg, (1, 2, 0))) # [channel, height, width] -> [height, width, channel] plt.show() # get some random training images by batch dataiter = iter(train_loader) images, labels = dataiter.next() # get a batch of images # show images imshow(torchvision.utils.make_grid(images)) def train(train_loader, model, loss_fn, optimizer, get_grad=False): train model using loss_fn and optimizer. When thid function is called, model trains for one epoch. Args: train_loader: train data model: prediction model loss_fn: loss function to judge the distance between target and outputs optimizer: optimize the loss function get_grad: True, False Returns: total_loss: loss average_grad2: average grad for hidden 2 in this epoch average_grad3: average grad for hidden 3 in this epoch # set the module in training model, affecting module e.g., Dropout, BatchNorm, etc. model.train() total_loss = 0 grad_2 = 0.0 # store sum(grad) for hidden 3 layer grad_3 = 0.0 # store sum(grad) for hidden 3 layer for batch_idx, (data, target) in enumerate(train_loader): optimizer.zero_grad() # clear gradients of all optimized torch.Tensors' outputs = model(data) # make predictions loss = loss_fn(outputs, target) # compute loss total_loss += loss.item() # accumulate every batch loss in a epoch loss.backward() # compute gradient of loss over parameters if get_grad == True: g2, g3 = model.get_grad() # get grad for hiddern 2 and 3 layer in this batch grad_2 += g2 # accumulate grad for hidden 2 grad_3 += g3 # accumulate grad for hidden 2 optimizer.step() # update parameters with gradient descent average_loss = total_loss / batch_idx # average loss in this epoch average_grad2 = grad_2 / batch_idx # average grad for hidden 2 in this epoch average_grad3 = grad_3 / batch_idx # average grad for hidden 3 in this epoch return average_loss, average_grad2, average_grad3 def evaluate(loader, model, loss_fn): test model's prediction performance on loader. When thid function is called, model is evaluated. Args: loader: data for evaluation model: prediction model loss_fn: loss function to judge the distance between target and outputs Returns: total_loss accuracy # context-manager that disabled gradient computation with torch.no_grad(): # set the module in evaluation mode model.eval() correct = 0.0 # account correct amount of data total_loss = 0 # account loss for batch_idx, (data, target) in enumerate(loader): outputs = model(data) # make predictions # return the maximum value of each row of the input tensor in the # given dimension dim, the second return vale is the index location # of each maxium value found(argmax) _, predicted = torch.max(outputs, 1) # Detach: Returns a new Tensor, detached from the current graph. #The result will never require gradient. correct += (predicted == target).sum().detach().numpy() loss = loss_fn(outputs, target) # compute loss total_loss += loss.item() # accumulate every batch loss in a epoch accuracy = correct100.0 / len(loader.dataset) # accuracy in a epoch return total_loss, accuracy def fit(train_loader, val_loader, model, loss_fn, optimizer, n_epochs, get_grad=False): train and val model here, we use train_epoch to train model and val_epoch to val model prediction performance Args: train_loader: train data val_loader: validation data model: prediction model loss_fn: loss function to judge the distance between target and outputs optimizer: optimize the loss function n_epochs: training epochs get_grad: Whether to get grad of hidden2 layer and hidden3 layer Returns: train_accs: accuracy of train n_epochs, a list train_losses: loss of n_epochs, a list grad_2 = [] # save grad for hidden 2 every epoch grad_3 = [] # save grad for hidden 3 every epoch train_accs = [] # save train accuracy every epoch train_losses = [] # save train loss every epoch for epoch in range(n_epochs): # train for n_epochs # train model on training datasets, optimize loss function and update model parameters train_loss, average_grad2, average_grad3 = train(train_loader, model, loss_fn, optimizer, get_grad) # evaluate model performance on train dataset _, train_accuracy = evaluate(train_loader, model, loss_fn) message = 'Epoch: {}/{}. Train set: Average loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, \ n_epochs, train_loss, train_accuracy) print(message) # save loss, accuracy, grad train_accs.append(train_accuracy) train_losses.append(train_loss) grad_2.append(average_grad2) grad_3.append(average_grad3) # evaluate model performance on val dataset val_loss, val_accuracy = evaluate(val_loader, model, loss_fn) message = 'Epoch: {}/{}. Validation set: Average loss: {:.4f}, Accuracy: {:.4f}'.format(epoch+1, \ n_epochs, val_loss, val_accuracy) print(message) # Whether to get grad for showing if get_grad == True: fig, ax = plt.subplots() # add a set of subplots to this figure ax.plot(grad_2, label='Gradient for Hidden 2 Layer') # plot grad 2 ax.plot(grad_3, label='Gradient for Hidden 3 Layer') # plot grad 3 plt.ylim(top=0.004) # place a legend on axes legend = ax.legend(loc='best', shadow=True, fontsize='x-large') return train_accs, train_losses def show_curve(ys, title): plot curlve for Loss and Accuacy !!YOU CAN READ THIS LATER, if you are interested Args: ys: loss or acc list title: Loss or Accuracy x = np.array(range(len(ys))) y = np.array(ys) plt.plot(x, y, c='b') plt.axis() plt.title('{} Curve:'.format(title)) plt.xlabel('Epoch') plt.ylabel('{} Value'.format(title)) plt.show() ### Hyper parameters batch_size = 128 # batch size is 128 n_epochs = 5 # train for 5 epochs learning_rate = 0.01 # learning rate is 0.01 input_size = 2828 # input image has size 28x28 hidden_size = 100 # hidden neurons is 100 for each layer output_size = 10 # classes of prediction l2_norm = 0 # not to use l2 penalty dropout = False # not to use get_grad = False # not to obtain grad # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) show_curve(train_accs, 'accuracy') show_curve(train_losses, 'loss') ### Hyper parameters batch_size = 128 # batch size is 128 n_epochs = 5 # train for 5 epochs learning_rate = 0.01 # learning rate is 0.01 input_size = 2828 # input image has size 28x28 hidden_size = 100 # hidden neurons is 100 for each layer output_size = 10 # classes of prediction l2_norm = 0 # not to use l2 penalty dropout = False # not to use get_grad = False # not to obtain grad # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) # 3.1 Train n_epochs = 10 train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # 3.1 show_curve show_curve(train_accs, 'accuracy') show_curve(train_losses, 'loss') # 3.2 Train batch_size = 128 # batch size is 128 n_epochs = 5 # train for 5 epochs learning_rate = 0.7 input_size = 2828 # input image has size 28x28 hidden_size = 100 # hidden neurons is 100 for each layer output_size = 10 # classes of prediction l2_norm = 0 # not to use l2 penalty dropout = False # not to use get_grad = False # not to obtain grad # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # 3.2 show_curve show_curve(train_accs, 'accuracy') show_curve(train_losses, 'loss') # show parameters in model # Print model's state_dict print("Model's state_dict:") for param_tensor in model.state_dict(): print(param_tensor, "\t", model.state_dict()[param_tensor].size()) # Print optimizer's state_dict print("\nOptimizer's state_dict:") for var_name in optimizer.state_dict(): print(var_name, "\t", optimizer.state_dict()[var_name]) # save model save_path = './model.pt' torch.save(model.state_dict(), save_path) # load parameters from files saved_parametes = torch.load(save_path) print(saved_parametes) # initailze model by saved parameters new_model = FeedForwardNeuralNetwork(input_size, hidden_size, output_size) new_model.load_state_dict(saved_parametes) # test your model prediction performance new_test_loss, new_test_accuracy = evaluate(test_loader, new_model, loss_fn) message = 'Average loss: {:.4f}, Accuracy: {:.4f}'.format(new_test_loss, new_test_accuracy) print(message) ### Hyper parameters batch_size = 128 n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0.01 # use l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # Hyper parameters batch_size = 128 n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 1 # use l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) ### Hyper parameters batch_size = 128 n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # without using l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) # Set dropout to True and probability = 0.5 model.set_use_dropout(True) train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) ### Hyper parameters batch_size = 128 n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # without using l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) model.set_use_bn(True) model.use_bn train_accs, train_losses = fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # only add random horizontal flip train_transform_1 = transforms.Compose([ transforms.RandomHorizontalFlip(), transforms.ToTensor(), # Convert a PIL Image or numpy.ndarray to tensor. # Normalize a tensor image with mean and standard deviation transforms.Normalize((0.1307,), (0.3081,)) ]) # only add random crop train_transform_2 = transforms.Compose([ transforms.RandomCrop(size=[28,28], padding=4), transforms.ToTensor(), # Convert a PIL Image or numpy.ndarray to tensor. # Normalize a tensor image with mean and standard deviation transforms.Normalize((0.1307,), (0.3081,)) ]) # add random horizontal flip and random crop train_transform_3 = transforms.Compose([ transforms.RandomHorizontalFlip(), transforms.RandomCrop(size=[28,28], padding=4), transforms.ToTensor(), # Convert a PIL Image or numpy.ndarray to tensor. # Normalize a tensor image with mean and standard deviation transforms.Normalize((0.1307,), (0.3081,)) ]) # reload train_loader using trans train_dataset_1 = torchvision.datasets.MNIST(root='./data', train=True, transform=train_transform_1, download=False) train_loader_1 = torch.utils.data.DataLoader(dataset=train_dataset_1, batch_size=batch_size, shuffle=True) print(train_dataset_1) ### Hyper parameters batch_size = 128 n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # without using l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader_1, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # train_transform_2 batch_size = 128 train_dataset_2 = torchvision.datasets.MNIST(root='./data', train=True, transform=train_transform_2, download=False) train_loader_2 = torch.utils.data.DataLoader(dataset=train_dataset_2, batch_size=batch_size, shuffle=True) n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # without using l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader_2, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) # train_transform_3 batch_size = 128 train_dataset_3 = torchvision.datasets.MNIST(root='./data', train=True, transform=train_transform_3, download=False) train_loader_3 = torch.utils.data.DataLoader(dataset=train_dataset_3, batch_size=batch_size, shuffle=True) n_epochs = 5 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # without using l2 penalty get_grad = False # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) train_accs, train_losses = fit(train_loader_3, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) ### Hyper parameters batch_size = 128 n_epochs = 15 learning_rate = 0.01 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # use l2 penalty get_grad = True # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad) ### Hyper parameters batch_size = 128 n_epochs = 15 learning_rate = 1e-10 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # use l2 penalty get_grad = True # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad=get_grad) ### Hyper parameters batch_size = 128 n_epochs = 15 learning_rate = 10 input_size = 2828 hidden_size = 100 output_size = 10 l2_norm = 0 # not to use l2 penalty get_grad = True # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad=True) ### Hyper parameters batch_size = 128 n_epochs = 15 learning_rate = 1 input_size = 28*28 hidden_size = 100 output_size = 10 l2_norm = 0 # not to use l2 penalty get_grad = True # declare a model model = FeedForwardNeuralNetwork(input_size=input_size, hidden_size=hidden_size, output_size=output_size) # Cross entropy loss_fn = torch.nn.CrossEntropyLoss() # l2_norm can be done in SGD optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, weight_decay=l2_norm) # reset parameters as 10 def wrong_weight_bias_reset(model): Using normalization with mean=0, std=1 to initialize model's parameter for m in model.modules(): if isinstance(m, nn.Linear): # initialize linear layer with mean and std mean, std = 0, 1 # Initialization method torch.nn.init.normal_(m.weight, mean, std) torch.nn.init.normal_(m.bias, mean, std) wrong_weight_bias_reset(model) show_weight_bias(model) fit(train_loader, test_loader, model, loss_fn, optimizer, n_epochs, get_grad=True) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The module re provides support for <a href='https Step2: The function $\texttt{tokenize}(s)$ takes a string $s$ representing an arithmetic expression and splits this string into a list of tokens. Step3: Given an operator $o$, the expression $\texttt{precedence}(o)$ returns the precedence of the operator Step4: The expression isLeftAssociative}(o) is True iff the operator $o$ Step5: The function evalBefore(o1, o2) receives to strings representing arithmetical operators. It returns True if the operator $o_1$ should be evaluated before the operator $o_2$ in an arithmetical expression of the form $a \;\texttt{o}_1\; b \;\texttt{o}_2\; c$. In order to determine whether $o_1$ should be evaluated before $o_2$ it uses the precedence and the associativity of the operators. Step6: The class Calculator supports three member variables Step7: The method __str__ is used to convert an object of class Calculator to a string. Step8: The function $\texttt{evaluate}(\texttt{self})$ evaluates the expression that is given by the tokens on the mTokenStack. Step9: The method $\texttt{popAndEvaluate}(\texttt{self})$ removes the two topmost numbers $\texttt{rhs}$ and $\texttt{lhs}$ from the argument stack and	<ASSISTANT_TASK:> Python Code: def toInt(s): try: return int(s) except ValueError: return s toInt('123') toInt('*') import re def tokenize(s): regExp = r'[0-9]+\|\\\|[()+\-%/]' L = [ toInt(t) for t in re.findall(regExp, s) ] return list(reversed(L)) re.findall(r'[0-9]+\|\\\|[()+%/-]', '11 22 * 33*45') tokenize('12 23 * 34*45') def precedence(o): Precedence = { '+': 1, '-': 1, '': 2, '/': 2, '%': 2, '*' : 3 } return Precedence[o] def isLeftAssociative(o): if o in { '+', '-', '', '/', '%' }: return True if o in { '*' }: return False assert False, f'unknown operator {o}' def evalBefore(stackOp, nextOp): if precedence(stackOp) > precedence(nextOp): return True if stackOp == nextOp: return isLeftAssociative(stackOp) if precedence(stackOp) == precedence(nextOp) and stackOp != nextOp: return True if precedence(stackOp) < precedence(nextOp): return False assert False, f'incomplete case distinction in evalBefore({stackOp}, {nextOp})' %%capture %run Stack.ipynb class Calculator: def __init__(self, s): self.mTokens = createStack(tokenize(s)) self.mOperators = Stack() self.mArguments = Stack() def toString(self): return '\n'.join(['_'50, 'Tokens: ', str(self.mTokens), 'Arguments: ', str(self.mArguments), 'Operators: ', str(self.mOperators), '_'50]) Calculator.__str__ = toString del toString Calculator.__repr__ = Calculator.__str__ def evaluate(self): while not self.mTokens.isEmpty(): print(self) # only for debugging nextOp = self.mTokens.top(); self.mTokens.pop() if isinstance(nextOp, int): self.mArguments.push(nextOp) continue if self.mOperators.isEmpty(): self.mOperators.push(nextOp) continue if nextOp == "(": self.mOperators.push(nextOp) continue stackOp = self.mOperators.top() if stackOp == "(" and nextOp == ")": self.mOperators.pop() continue if nextOp == ")": self.popAndEvaluate() self.mTokens.push(nextOp) continue if stackOp == '(': self.mOperators.push(nextOp) continue if evalBefore(stackOp, nextOp): self.popAndEvaluate() self.mTokens.push(nextOp) else: self.mOperators.push(nextOp) while not self.mOperators.isEmpty(): print(self) # only for debugging self.popAndEvaluate() print(self) return self.mArguments.top() Calculator.evaluate = evaluate del evaluate def popAndEvaluate(self): rhs = self.mArguments.top(); self.mArguments.pop() lhs = self.mArguments.top(); self.mArguments.pop() op = self.mOperators.top(); self.mOperators.pop() result = None if op == '+': result = lhs + rhs if op == '-': result = lhs - rhs if op == '': result = lhs * rhs if op == '/': result = lhs // rhs if op == '%': result = lhs % rhs if op == '': result = lhs rhs assert result != None, f'ERROR: * Unknown Operator * "{op}"' self.mArguments.push(result) Calculator.popAndEvaluate = popAndEvaluate del popAndEvaluate C = Calculator('1)(3(2+1)-4)**2') C.evaluate() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The Step2: Notice that the reader function returned a list of evoked instances. This is Step3: If you're gone through the tutorials of raw and epochs datasets, you're Step4: The evoked data structure also contains some new attributes easily Step5: The data is also easily accessible. Since the evoked data arrays are usually Step6: The data is arranged in an array of shape (n_channels, n_times). Notice Step7: If you want to import evoked data from some other system and you have it in a	<ASSISTANT_TASK:> Python Code: import os.path as op import mne data_path = mne.datasets.sample.data_path() fname = op.join(data_path, 'MEG', 'sample', 'sample_audvis-ave.fif') evokeds = mne.read_evokeds(fname, baseline=(None, 0), proj=True) print(evokeds) evoked = mne.read_evokeds(fname, condition='Left Auditory') evoked.apply_baseline((None, 0)).apply_proj() print(evoked) print(evoked.info) print(evoked.times) print(evoked.nave) # Number of averaged epochs. print(evoked.first) # First time sample. print(evoked.last) # Last time sample. print(evoked.comment) # Comment on dataset. Usually the condition. print(evoked.kind) # Type of data, either average or standard_error. data = evoked.data print(data.shape) print('Data from channel {0}:'.format(evoked.ch_names[10])) print(data[10]) evoked = mne.EvokedArray(data, evoked.info, tmin=evoked.times[0]) evoked.plot() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Load the data, in this case a sample data. Step2: Make a single DataFrame containing all the users Step3: Drop useless column(test_users don't have it) Step4: Age Step5: Set limits to age Step6: Fill NaNs with -1 to make it more noticiable Step7: The age, is really fine grained. We are going to make bins and fit each user in the proper age group Step8: NaNs Step9: Date Step10: Convert to DatetimeIndex Step11: Split dates into day, week, month, year Step12: Get the difference(time lag) between the date in which the account was created and when it was first active Step13: Drop duplicated columns Step14: Session Information Step15: Frequency Count Step16: Elapsed Seconds Stats Step17: Encode categorical features Step18: Persistence	<ASSISTANT_TASK:> Python Code: import numpy as np import pandas as pd train_users = pd.read_csv('../data/train_users_sample.csv') test_users = pd.read_csv('../data/test_users_sample.csv') sessions = pd.read_csv('../data/sessions_sample.csv') users = pd.concat([train_users, test_users], axis=0, ignore_index=True) users.drop('date_first_booking', axis=1, inplace=True) user_with_year_age_mask = users['age'] > 1000 users.loc[user_with_year_age_mask, 'age'] = 2015 - users.loc[user_with_year_age_mask, 'age'] users.loc[(users['age'] > 100) \| (users['age'] < 18), 'age'] = -1 users['age'].fillna(-1, inplace=True) bins = [-1, 20, 25, 30, 40, 50, 60, 75, 100] users['age_group'] = np.digitize(users['age'], bins, right=True) users['nans'] = np.sum([ (users['age'] == -1), (users['gender'] == '-unknown-'), (users['language'] == '-unknown-'), (users['first_affiliate_tracked'] == 'untracked'), (users['first_browser'] == '-unknown-') ], axis=0) users['date_account_created'] = pd.to_datetime(users['date_account_created'], errors='ignore') users['date_first_active'] = pd.to_datetime(users['timestamp_first_active'], format='%Y%m%d%H%M%S') date_account_created = pd.DatetimeIndex(users['date_account_created']) date_first_active = pd.DatetimeIndex(users['date_first_active']) users['day_account_created'] = date_account_created.day users['weekday_account_created'] = date_account_created.weekday users['week_account_created'] = date_account_created.week users['month_account_created'] = date_account_created.month users['year_account_created'] = date_account_created.year users['day_first_active'] = date_first_active.day users['weekday_first_active'] = date_first_active.weekday users['week_first_active'] = date_first_active.week users['month_first_active'] = date_first_active.month users['year_first_active'] = date_first_active.year users['time_lag'] = (date_account_created.values - date_first_active.values).astype(int) drop_list = [ 'date_account_created', 'date_first_active', 'timestamp_first_active' ] users.drop(drop_list, axis=1, inplace=True) sessions.rename(columns = {'user_id': 'id'}, inplace=True) action_count = sessions.groupby(['id', 'action'])['secs_elapsed'].agg(len).unstack() action_type_count = sessions.groupby(['id', 'action_type'])['secs_elapsed'].agg(len).unstack() action_detail_count = sessions.groupby(['id', 'action_detail'])['secs_elapsed'].agg(len).unstack() device_type_sum = sessions.groupby(['id', 'device_type'])['secs_elapsed'].agg(sum).unstack() sessions_data = pd.concat([action_count, action_type_count, action_detail_count, device_type_sum],axis=1) sessions_data.columns = sessions_data.columns.map(lambda x: str(x) + '_count') # Most used device sessions_data['most_used_device'] = sessions.groupby('id')['device_type'].max() users = users.join(sessions_data, on='id') secs_elapsed = sessions.groupby('id')['secs_elapsed'] secs_elapsed = secs_elapsed.agg( { 'secs_elapsed_sum': np.sum, 'secs_elapsed_mean': np.mean, 'secs_elapsed_min': np.min, 'secs_elapsed_max': np.max, 'secs_elapsed_median': np.median, 'secs_elapsed_std': np.std, 'secs_elapsed_var': np.var, 'day_pauses': lambda x: (x > 86400).sum(), 'long_pauses': lambda x: (x > 300000).sum(), 'short_pauses': lambda x: (x < 3600).sum(), 'session_length' : np.count_nonzero } ) users = users.join(secs_elapsed, on='id') categorical_features = [ 'gender', 'signup_method', 'signup_flow', 'language', 'affiliate_channel', 'affiliate_provider', 'first_affiliate_tracked', 'signup_app', 'first_device_type', 'first_browser', 'most_used_device' ] users = pd.get_dummies(users, columns=categorical_features) users.set_index('id', inplace=True) users.loc[train_users['id']].to_csv('../cache/train_users.csv') users.loc[test_users['id']].drop('country_destination', axis=1).to_csv('../cache/test_users.csv') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Prepare the data Step2: Build the model Step3: Prepare the text sampling function Step4: Train the model	<ASSISTANT_TASK:> Python Code: from tensorflow import keras from tensorflow.keras import layers import numpy as np import random import io path = keras.utils.get_file( "nietzsche.txt", origin="https://s3.amazonaws.com/text-datasets/nietzsche.txt" ) with io.open(path, encoding="utf-8") as f: text = f.read().lower() text = text.replace("\n", " ") # We remove newlines chars for nicer display print("Corpus length:", len(text)) chars = sorted(list(set(text))) print("Total chars:", len(chars)) char_indices = dict((c, i) for i, c in enumerate(chars)) indices_char = dict((i, c) for i, c in enumerate(chars)) # cut the text in semi-redundant sequences of maxlen characters maxlen = 40 step = 3 sentences = [] next_chars = [] for i in range(0, len(text) - maxlen, step): sentences.append(text[i : i + maxlen]) next_chars.append(text[i + maxlen]) print("Number of sequences:", len(sentences)) x = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool) y = np.zeros((len(sentences), len(chars)), dtype=np.bool) for i, sentence in enumerate(sentences): for t, char in enumerate(sentence): x[i, t, char_indices[char]] = 1 y[i, char_indices[next_chars[i]]] = 1 model = keras.Sequential( [ keras.Input(shape=(maxlen, len(chars))), layers.LSTM(128), layers.Dense(len(chars), activation="softmax"), ] ) optimizer = keras.optimizers.RMSprop(learning_rate=0.01) model.compile(loss="categorical_crossentropy", optimizer=optimizer) def sample(preds, temperature=1.0): # helper function to sample an index from a probability array preds = np.asarray(preds).astype("float64") preds = np.log(preds) / temperature exp_preds = np.exp(preds) preds = exp_preds / np.sum(exp_preds) probas = np.random.multinomial(1, preds, 1) return np.argmax(probas) epochs = 40 batch_size = 128 for epoch in range(epochs): model.fit(x, y, batch_size=batch_size, epochs=1) print() print("Generating text after epoch: %d" % epoch) start_index = random.randint(0, len(text) - maxlen - 1) for diversity in [0.2, 0.5, 1.0, 1.2]: print("...Diversity:", diversity) generated = "" sentence = text[start_index : start_index + maxlen] print('...Generating with seed: "' + sentence + '"') for i in range(400): x_pred = np.zeros((1, maxlen, len(chars))) for t, char in enumerate(sentence): x_pred[0, t, char_indices[char]] = 1.0 preds = model.predict(x_pred, verbose=0)[0] next_index = sample(preds, diversity) next_char = indices_char[next_index] sentence = sentence[1:] + next_char generated += next_char print("...Generated: ", generated) print() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Load data and have initial look Step2: Look at class distribution Step3: Data in the table is organized the following way Step4: Split the data in training and test set Step5: Train the model Step6: Predict y (class) on test set and probabilities that sample belongs to each of two classes. Step7: Calculate confusion matrix	<ASSISTANT_TASK:> Python Code: import pandas as pd import numpy as np from sklearn.metrics import roc_curve, roc_auc_score, auc, recall_score, accuracy_score, confusion_matrix from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier df = pd.read_csv('../data/pima-indians-diabetes-data.csv', index_col=[0]) df.head() df.describe() len(df[df['class'] == 1]), len(df[df['class'] == 0]) X = df.drop('class', axis=1).values y = df['class'].values X_train, X_test, y_train, y_test = train_test_split(X, y) clf = RandomForestClassifier(n_estimators=100) clf.fit(X_train, y_train) y_pred = clf.predict(X_test) y_pred_proba = clf.predict_proba(X_test) print("AUC: %.3f" % roc_auc_score(y_test, y_pred_proba.T[1])) confusion_matrix(y_test, y_pred, labels=[1,0]) recall_score(y_test, y_pred, pos_label=1) # Low-moderate sensitivity recall_score(y_test, y_pred, pos_label=0) # High specificity <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Load capacity curves Step2: Load ground motion records Step3: Load damage state thresholds Step4: Obtain the damage probability matrix Step5: Fit lognormal CDF fragility curves Step6: Plot fragility functions Step7: Save fragility functions Step8: Obtain vulnerability function Step9: Plot vulnerability function Step10: Save vulnerability function	<ASSISTANT_TASK:> Python Code: import capacitySpectrumMethod from rmtk.vulnerability.common import utils %matplotlib inline capacity_curves_file = "../../../../../../rmtk_data/capacity_curves_Sa-Sd.csv" capacity_curves = utils.read_capacity_curves(capacity_curves_file) utils.plot_capacity_curves(capacity_curves) gmrs_folder = "../../../../../../rmtk_data/GMRs" minT, maxT = 0.1, 2.0 gmrs = utils.read_gmrs(gmrs_folder) #utils.plot_response_spectra(gmrs, minT, maxT) damage_model_file = "../../../../../../rmtk_data/damage_model_Sd.csv" damage_model = utils.read_damage_model(damage_model_file) damping_model = "Iwan_1980" damping_ratio = 0.05 PDM, Sds = capacitySpectrumMethod.calculate_fragility(capacity_curves, gmrs, damage_model, damping_model, damping_ratio) IMT = "Sa" period = 0.3 regression_method = "least squares" fragility_model = utils.calculate_mean_fragility(gmrs, PDM, period, damping_ratio, IMT, damage_model, regression_method) minIML, maxIML = 0.01, 2.00 utils.plot_fragility_model(fragility_model, minIML, maxIML) # utils.plot_fragility_stats(fragility_statistics,minIML,maxIML) taxonomy = "RC" minIML, maxIML = 0.01, 2.00 output_type = "csv" output_path = "../../../../../../rmtk_data/output/" utils.save_mean_fragility(taxonomy, fragility_model, minIML, maxIML, output_type, output_path) cons_model_file = "../../../../../../rmtk_data/cons_model.csv" imls = [0.05, 0.10, 0.15, 0.20, 0.25, 0.30, 0.35, 0.40, 0.45, 0.50, 0.60, 0.70, 0.80, 0.90, 1.00, 1.20, 1.40, 1.60, 1.80, 2.00, 2.20, 2.40, 2.60, 2.80, 3.00, 3.20, 3.40, 3.60, 3.80, 4.00] distribution_type = "lognormal" cons_model = utils.read_consequence_model(cons_model_file) vulnerability_model = utils.convert_fragility_vulnerability(fragility_model, cons_model, imls, distribution_type) utils.plot_vulnerability_model(vulnerability_model) taxonomy = "RC" output_type = "csv" output_path = "../../../../../../rmtk_data/output/" utils.save_vulnerability(taxonomy, vulnerability_model, output_type, output_path) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Define a function that returns a slice as a Plotly Surface Step2: Let us plot the slices z=0 and y=-0.5 in the volume defined by Step3: In order to be able to compare the two slices, we choose a unique interval of values to be mapped to the colorscale Step4: Oblique slice in volumetric data	<ASSISTANT_TASK:> Python Code: import numpy as np import plotly.graph_objects as go from IPython def get_the_slice(x,y,z, surfacecolor): return go.Surface(x=x, y=y, z=z, surfacecolor=surfacecolor, coloraxis='coloraxis') def get_lims_colors(surfacecolor):# color limits for a slice return np.min(surfacecolor), np.max(surfacecolor) scalar_f = lambda x,y,z: xnp.exp(-x2-y2-z2) x = np.linspace(-2,2, 50) y = np.linspace(-2,2, 50) x, y = np.meshgrid(x,y) z = np.zeros(x.shape) surfcolor_z = scalar_f(x,y,z) sminz, smaxz = get_lims_colors(surfcolor_z) slice_z = get_the_slice(x, y, z, surfcolor_z) x = np.linspace(-2,2, 50) z = np.linspace(-2,2, 50) x, z = np.meshgrid(x,y) y = -0.5 np.ones(x.shape) surfcolor_y = scalar_f(x,y,z) sminy, smaxy = get_lims_colors(surfcolor_y) vmin = min([sminz, sminy]) vmax = max([smaxz, smaxy]) slice_y = get_the_slice(x, y, z, surfcolor_y) def colorax(vmin, vmax): return dict(cmin=vmin, cmax=vmax) fig1 = go.Figure(data=[slice_z, slice_y]) fig1.update_layout( title_text='Slices in volumetric data', title_x=0.5, width=700, height=700, scene_zaxis_range=[-2,2], coloraxis=dict(colorscale='BrBG', colorbar_thickness=25, colorbar_len=0.75, *colorax(vmin, vmax))) #fig1.show() from IPython.display import IFrame IFrame('https://chart-studio.plotly.com/~empet/13862', width=700, height=700) alpha = np.pi/4 x = np.linspace(-2, 2, 50) y = np.linspace(-2, 2, 50) x, y = np.meshgrid(x,y) z = -x np.tan(alpha) surfcolor_obl = scalar_f(x,y,z) smino, smaxo = get_lims_colors(surfcolor_obl) vmin = min([sminz, smino]) vmax = max([smaxz, smaxo]) slice_obl = get_the_slice(x,y,z, surfcolor_obl) fig2 = go.Figure(data=[slice_z, slice_obl], layout=fig1.layout) fig2.update_layout( coloraxis=colorax(vmin, vmax)) #fig2.show() IFrame('https://chart-studio.plotly.com/~empet/13864', width=700, height=700) from IPython.core.display import HTML def css_styling(): styles = open("./custom.css", "r").read() return HTML(styles) css_styling() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Document Authors Step2: Document Contributors Step3: Document Publication Step4: Document Table of Contents Step5: 1.2. Model Name Step6: 1.3. Ice Albedo Step7: 1.4. Atmospheric Coupling Variables Step8: 1.5. Oceanic Coupling Variables Step9: 1.6. Prognostic Variables Step10: 2. Key Properties --> Software Properties Step11: 2.2. Code Version Step12: 2.3. Code Languages Step13: 3. Grid Step14: 3.2. Adaptive Grid Step15: 3.3. Base Resolution Step16: 3.4. Resolution Limit Step17: 3.5. Projection Step18: 4. Glaciers Step19: 4.2. Description Step20: 4.3. Dynamic Areal Extent Step21: 5. Ice Step22: 5.2. Grounding Line Method Step23: 5.3. Ice Sheet Step24: 5.4. Ice Shelf Step25: 6. Ice --> Mass Balance Step26: 7. Ice --> Mass Balance --> Basal Step27: 7.2. Ocean Step28: 8. Ice --> Mass Balance --> Frontal Step29: 8.2. Melting Step30: 9. Ice --> Dynamics Step31: 9.2. Approximation Step32: 9.3. Adaptive Timestep Step33: 9.4. Timestep	<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'inm', 'sandbox-3', 'landice') # Set as follows: DOC.set_author("name", "email") # TODO - please enter value(s) # Set as follows: DOC.set_contributor("name", "email") # TODO - please enter value(s) # Set publication status: # 0=do not publish, 1=publish. DOC.set_publication_status(0) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.model_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.ice_albedo') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "prescribed" # "function of ice age" # "function of ice density" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.atmospheric_coupling_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.oceanic_coupling_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.prognostic_variables') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "ice velocity" # "ice thickness" # "ice temperature" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.software_properties.repository') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.software_properties.code_version') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.key_properties.software_properties.code_languages') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.grid.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.grid.adaptive_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.grid.base_resolution') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.grid.resolution_limit') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.grid.projection') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.glaciers.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.glaciers.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.glaciers.dynamic_areal_extent') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.grounding_line_method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "grounding line prescribed" # "flux prescribed (Schoof)" # "fixed grid size" # "moving grid" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.ice_sheet') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.ice_shelf') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.mass_balance.surface_mass_balance') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.mass_balance.basal.bedrock') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.mass_balance.basal.ocean') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.mass_balance.frontal.calving') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.mass_balance.frontal.melting') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.dynamics.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.dynamics.approximation') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "SIA" # "SAA" # "full stokes" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.dynamics.adaptive_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.landice.ice.dynamics.timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Load pickled coordinates for the first Hungriger Wolf camera Step2: Set the paramters for the image clustering Step3: Load image and preprocess it Step4: Predict the labels with the trained model and convert it into a mask store Step5: Denoise the cloud mask and label the clouds Step6: Load the second image and cutted Step7: Move the cloud around to find the best matching point Step8: Example for SpatialCloud	<ASSISTANT_TASK:> Python Code: %matplotlib inline import os import matplotlib import numpy as np import matplotlib.pyplot as plt import logging import pyclamster import pickle import scipy import scipy.misc from skimage.feature import match_template logger = logging.getLogger() logger.setLevel(logging.DEBUG) logging.debug("test") filename = "../examples/calibration/wolf-3-calibration.pk" calibration = pickle.load(open(filename, 'rb')) cal_coords = calibration.create_coordinates() cal_coords.z = 2000 plt.subplot(221) plt.title("elevation on the image [deg]") plt.imshow(cal_coords.elevation360/(2np.pi)) plt.colorbar() plt.subplot(222) plt.title("azimuth on the image [deg]") plt.imshow(cal_coords.azimuth360/(2np.pi)) plt.colorbar() plt.subplot(223) plt.title("[z=2000 plane]\nreal-world x on the image [m]") plt.imshow(cal_coords.x) plt.colorbar() plt.subplot(224) plt.title("[z=2000 plane]\nreal-world y on the image [m]") plt.imshow(cal_coords.y) plt.colorbar() plt.tight_layout() base_folder = "../" image_directory = os.path.join(base_folder, "examples", "images", "wolf") trained_models = os.path.join(base_folder, "trained_models") good_angle = 45 center = int(1920/2) good_angle_dpi = int(np.round(1920 / 180 * good_angle)) denoising_ratio = 10 #all_images = glob.glob(os.path.join(image_directory, "Image_20160531_114000_UTCp1_.jpg")) #print(all_images) all_images = [ os.path.join(image_directory, "Image_20160531_114100_UTCp1_3.jpg"), os.path.join(image_directory, "Image_20160531_114100_UTCp1_4.jpg")] kmeans = pickle.load(open(os.path.join(trained_models, "kmeans.pk"), "rb")) image = pyclamster.Image(all_images[0]) image.coordinates = cal_coords cutted_image = image.cut([960, 960, 1460, 1460]) plt.title("The raw cutted image") plt.imshow(cutted_image) plt.axis('off') image.data = pyclamster.clustering.preprocess.LCN(size=(25,25,3), scale=False).fit_transform(image.data) image = image.cut([960, 960, 1460, 1460]) w, h, _ = original_shape = image.data.shape raw_image = pyclamster.clustering.functions.rbDetection(image.data).reshape((wh, -1)) label = kmeans.predict(raw_image) label.reshape((w, h), replace=True) plt.title("The masked clouds") plt.imshow(label.labels, cmap='gray') plt.axis('off') masks = label.getMaskStore() masks.denoise([0], 1000) cloud_labels, _ = masks.labelMask([0,]) plt.title("The labeled clouds") plt.imshow(cloud_labels.labels, cmap='gray') plt.axis('off') cloud_store = cloud_labels.getMaskStore() clouds = [cloud_store.getCloud(cutted_image, [k,]) for k in cloud_store.masks.keys()] cloud1 = cloud_store.cutMask(cutted_image, [1,]) print(cloud1.data.shape) image = pyclamster.Image(all_images[1]) image = image.cut([850, 850, 1460, 1460]) plt.title("The raw cutted image") plt.imshow(image) plt.axis('off') result = match_template(image.data, cloud1.data, pad_input=True, mode='reflect', constant_values=0) plt.title("The matching result") plt.imshow(result, cmap='gray') plt.colorbar() plt.axis('off') #print(np.unravel_index(np.argmax(result), result.shape)) image = pyclamster.Image(all_images[1]) image.coordinates = cal_coords # Fake the second coordiante image.crop([931, 981, 1430, 1480]) cloud2 = pyclamster.matching.Cloud(image) sCloud = pyclamster.matching.SpatialCloud(pyclamster.matching.Cloud(cloud1), cloud2) position = sCloud._calc_position() print(position[2]) plt.title("A faked height map") plt.imshow(position[2], cmap='gray') plt.colorbar() plt.axis('off') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Data conversion Step2: Standard In, Standard Out and Standard Error	<ASSISTANT_TASK:> Python Code: fd = open('README.md', 'r') print(fd.readline(), end='') # \n is included in input string for s in fd: # file object(descriptor) is iterable, and can be used in for loop print(s.strip()) # strip() removes extra space and \n # print(s.split()) # convert string to List s = '100' print(int(s)+1) s = '1 2 3' for i in map(int, s.split()): print(i) s = '1 2 3 4' x = list(map(int, s.split())) print(x) y = list() for i in s.split(): # ['1', '2', '3', '4'] y.append(int(i)) print(y) # need to import sys module to use standard I/O file descriptor import sys print('input somthing: ') # jupyter does not handle stdin ? # sys.stdin is used as a file-descriptor s = sys.stdin.readline() print(s.split()) # convert input to List <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Part 2 Step2: Error in approximation at q = 2 Step3: q = 4 Step4: Error in approximation at q = 4 Step5: q = 8 Step6: Error in approximation at q = 8 Step7: q= 16 Step8: Error in approximation at q = 16 Step9: B.2 Studying a function for different parameter values Step10: How large n needs to be in order for the difference between the max of the function $f(x) = sin\dfrac{1}{x+eps}$ in [0,1] using n nodes and n+10 nodes to be less than 0.1 Step11: n = 200 * eps (for an epsilon of 0.2). Increasing n further does not change the plot so that it is visible on the screen. Step12: B.6 Using the trapezoid method to approximate integrals Step13: The plot is symmetric over the y-axis. Therefore the integral of the function from -$\infty$ to $\infty$ will be the same as twice the integral of the function from 0 to $\infty$ Step14: $$\int_{-L}^{L} {e}^{-x^2} dx = 2\int_{0}^{L} {e}^{-x^2} dx$$ Step15: The error decreases as n increases and as L increases Step16: $$g'(x)-10{e}^{10x}sin({e}^{10x})$$ Step17: $$h'(x)=(ln x)x^x+xx^{x-1}$$	<ASSISTANT_TASK:> Python Code: p1.f(-.45) p1.S_k(-1, 1, -.45, 10) p1.f(-.45) p1.S_k(-1, 1, -.45, 2) p1.error(-1, 1, -.45, 2) p1.S_k(-1, 1, -.45, 4) p1.error(-1, 1, -.45, 4) p1.S_k(-1, 1, -.45, 8) p1.error(-1, 1, -.45, 8) p1.S_k(-1, 1, -.45, 16) p1.error(-1, 1, -.45, 16) p2.sin_graph(0.2, 10) p2.multigraph(0.2, 10) p2.choose_n(0.2) p2.choose_n(0.1) p2.choose_n(0.05) p2.multigraph(0.2, 40) p3.graph() p3.T(100, 10) p3.trap(100, 10) * 2 p3.table() p3.error() p4.graph(p4.diff(p4.f, 1/1000, 1, 100)) p4.multigraph(p4.diff(p4.f, 1/1000, 1, 100), p4.fprime) p4.graph(p4.diff(p4.g, 1/1000, 1, 100)) p4.multigraph(p4.diff(p4.g, 1/1000, 1, 100), p4.gprime) p4.graph(p4.diff(p4.h, 1/1000, 1, 100)) p4.multigraph(p4.diff(p4.h, 1/1000, 1, 100), p4.hprime) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Create Table Step2: View Table Step3: Create New Empty Table Step4: Copy Contents Of First Table Into Empty Table Step5: View Previously Empty Table	<ASSISTANT_TASK:> Python Code: # Ignore %load_ext sql %sql sqlite:// %config SqlMagic.feedback = False %%sql -- Create a table of criminals_1 CREATE TABLE criminals_1 (pid, name, age, sex, city, minor); INSERT INTO criminals_1 VALUES (412, 'James Smith', 15, 'M', 'Santa Rosa', 1); INSERT INTO criminals_1 VALUES (234, 'Bill James', 22, 'M', 'Santa Rosa', 0); INSERT INTO criminals_1 VALUES (632, 'Stacy Miller', 23, 'F', 'Santa Rosa', 0); INSERT INTO criminals_1 VALUES (621, 'Betty Bob', NULL, 'F', 'Petaluma', 1); INSERT INTO criminals_1 VALUES (162, 'Jaden Ado', 49, 'M', NULL, 0); INSERT INTO criminals_1 VALUES (901, 'Gordon Ado', 32, 'F', 'Santa Rosa', 0); INSERT INTO criminals_1 VALUES (512, 'Bill Byson', 21, 'M', 'Santa Rosa', 0); INSERT INTO criminals_1 VALUES (411, 'Bob Iton', NULL, 'M', 'San Francisco', 0); %%sql -- Select all SELECT * -- From the table 'criminals_1' FROM criminals_1 %%sql -- Create a table called criminals_2 CREATE TABLE criminals_2 (pid, name, age, sex, city, minor); %%sql -- Insert into the empty table INSERT INTO criminals_2 -- Everything SELECT * -- From the first table FROM criminals_1; %%sql -- Select everything SELECT * -- From the previously empty table FROM criminals_2 <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Photo-count detection Step2: Solve using stochastic master equation Step3: Homodyne detection Step4: Theory Step5: $$ Step6: Solve problem again, this time with a specified noise (from previous run) Step7: Using QuTiP built-in homodyne detection functions for $D_1$ and $D_2$ Step8: Solve problem again, this time with a specified noise (from previous run) Step9: Heterodyne detection Step10: $$D_{2}^{(1)}[c, \|\psi(t)\rangle] = \sqrt{1/2} (c - \langle c + c^\dagger \rangle / 2) \psi$$ Step11: Using QuTiP built-in heterodyne detection functions for $D_1$ and $D_2$ Step12: Solve problem again, this time with a specified noise (from previous run) Step13: Software version	<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt from qutip import * import numpy as np N = 10 w0 = 0.5 * 2 * np.pi times = np.linspace(0, 15, 150) dt = times[1] - times[0] gamma = 0.25 A = 2.5 ntraj = 50 nsubsteps = 100 a = destroy(N) x = a + a.dag() H = w0 * a.dag() * a psi0 = fock(N, 5) sc_ops = [np.sqrt(gamma) * a] e_ops = [a.dag() * a, a + a.dag(), (-1j)(a - a.dag())] result_ref = mesolve(H, psi0, times, sc_ops, e_ops) plot_expectation_values(result_ref); result = photocurrent_sesolve(H, psi0, times, sc_ops, e_ops, ntraj=ntraj5, nsubsteps=nsubsteps, store_measurement=True, normalize=0) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.step(times, dt * m.real) ntraj = 50 nsubsteps = 200 H = w0 * a.dag() * a + A * (a + a.dag()) result_ref = mesolve(H, psi0, times, sc_ops, e_ops) op = sc_ops[0] opp = (op + op.dag()).data opn = (op.dag()op).data op = op.data Hd = H.data -1j def d1_psi_func(t, psi): e_x = cy.cy_expect_psi(opp, psi, 0) return cy.spmv(Hd, psi) + 0.5 * (e_x * cy.spmv(op, psi) - cy.spmv(opn, psi) - 0.25 * e_x ** 2 * psi) def d2_psi_func(t, psi): out = np.zeros((1,len(psi)), dtype=complex) e_x = cy.cy_expect_psi(opp, psi, 0) out[0,:] = cy.spmv(op,psi) out -= 0.5 * e_x * psi return out result = general_stochastic(psi0, times, d1=d1_psi_func, d2=d2_psi_func, e_ops=e_ops, ntraj=ntraj, m_ops=[a + a.dag()], dW_factors=[1/np.sqrt(gamma)], nsubsteps=nsubsteps, store_measurement=True) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0].real, 'b', alpha=0.1) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real, 'r', lw=2) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.ylim(-15, 15); result = general_stochastic(psi0, times, d1=d1_psi_func, d2=d2_psi_func, e_ops=e_ops, ntraj=ntraj, noise=result.noise, m_ops=[a + a.dag()], dW_factors=[1/np.sqrt(gamma)], nsubsteps=nsubsteps, store_measurement=True) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0].real, 'b', alpha=0.1) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real, 'r', lw=2) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.ylim(-15, 15); result = ssesolve(H, psi0, times, sc_ops, e_ops, ntraj=ntraj, nsubsteps=nsubsteps, method='homodyne', store_measurement=True, dW_factors=[1]) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0].real, 'b', alpha=0.1) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real/np.sqrt(gamma), 'r', lw=2) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.ylim(-15, 15); plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real/np.sqrt(gamma), 'r', lw=2) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.plot(times, result.expect[1], 'b', lw=2) result = ssesolve(H, psi0, times, sc_ops, e_ops, ntraj=ntraj, nsubsteps=nsubsteps, method='homodyne', store_measurement=True, noise=result.noise) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0].real, 'b', alpha=0.1) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real/np.sqrt(gamma), 'r', lw=2) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.ylim(-15, 15); op = sc_ops[0] opd = (op.dag()).data opp = (op + op.dag()).data opm = (op + op.dag()).data opn = (op.dag()op).data op = op.data Hd = H.data -1j def d1_psi_func(t, psi): e_xd = cy.cy_expect_psi(opd, psi, 0) e_x = cy.cy_expect_psi(op, psi, 0) return cy.spmv(Hd, psi) - 0.5 * (cy.spmv(opn, psi) - e_xd * cy.spmv(op, psi) + 0.5 * e_x * e_xd * psi) sqrt2 = np.sqrt(0.5) def d2_psi_func(t, psi): out = np.zeros((2,len(psi)), dtype=complex) e_p = cy.cy_expect_psi(opp, psi, 0) e_m = cy.cy_expect_psi(opm, psi, 0) out[0,:] = (cy.spmv(op,psi) - e_p * 0.5 * psi)sqrt2 out[1,:] = (cy.spmv(op,psi) - e_m 0.5 * psi)sqrt2-1j return out result = general_stochastic(psi0, times, d1=d1_psi_func, d2=d2_psi_func, e_ops=e_ops, ntraj=ntraj, len_d2=2, m_ops=[(a + a.dag()), (-1j)*(a - a.dag())], dW_factors=[2/np.sqrt(gamma), 2/np.sqrt(gamma)], nsubsteps=nsubsteps, store_measurement=True) plot_expectation_values([result, result_ref]); #fig, ax = subplots() for m in result.measurement: plt.plot(times, m[:, 0].real, 'r', alpha=0.025) plt.plot(times, m[:, 1].real, 'b', alpha=0.025) plt.plot(times, result_ref.expect[1], 'k', lw=2); plt.plot(times, result_ref.expect[2], 'k', lw=2); plt.ylim(-10, 10) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0].real, 'r', lw=2); plt.plot(times, np.array(result.measurement).mean(axis=0)[:,1].real, 'b', lw=2); result = ssesolve(H, psi0, times, sc_ops, e_ops, ntraj=ntraj, nsubsteps=nsubsteps, method='heterodyne', store_measurement=True) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0, 0].real, 'r', alpha=0.025) plt.plot(times, m[:, 0, 1].real, 'b', alpha=0.025) plt.plot(times, result_ref.expect[1], 'k', lw=2) plt.plot(times, result_ref.expect[2], 'k', lw=2) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0,0].real/np.sqrt(gamma), 'r', lw=2) plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0,1].real/np.sqrt(gamma), 'b', lw=2) result = ssesolve(H, psi0, times, sc_ops, e_ops, ntraj=ntraj, nsubsteps=nsubsteps, method='heterodyne', store_measurement=True, noise=result.noise) plot_expectation_values([result, result_ref]); for m in result.measurement: plt.plot(times, m[:, 0, 0].real, 'r', alpha=0.025) plt.plot(times, m[:, 0, 1].real, 'b', alpha=0.025) plt.plot(times, result_ref.expect[1], 'k', lw=2); plt.plot(times, result_ref.expect[2], 'k', lw=2); plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0,0].real/np.sqrt(gamma), 'r', lw=2); plt.plot(times, np.array(result.measurement).mean(axis=0)[:,0,1].real/np.sqrt(gamma), 'b', lw=2); from qutip.ipynbtools import version_table version_table() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: CIFAR-10 Data Loading and Preprocessing Step2: SVM Classifier Step3: The grad returned from the function above is right now all zero. Derive and implement the gradient for the SVM cost function and implement it inline inside the function svm_loss_naive. You will find it helpful to interleave your new code inside the existing function. Step4: Inline Question 1 Step5: Stochastic Gradient Descent	<ASSISTANT_TASK:> Python Code: # Run some setup code for this notebook. import random import numpy as np from cs231n.data_utils import load_CIFAR10 import matplotlib.pyplot as plt # This is a bit of magic to make matplotlib figures appear inline in the # notebook rather than in a new window. %matplotlib inline plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots plt.rcParams['image.interpolation'] = 'nearest' plt.rcParams['image.cmap'] = 'gray' # Some more magic so that the notebook will reload external python modules; # see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython %load_ext autoreload %autoreload 2 # Load the raw CIFAR-10 data. cifar10_dir = 'cs231n/datasets/cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) # As a sanity check, we print out the size of the training and test data. print 'Training data shape: ', X_train.shape print 'Training labels shape: ', y_train.shape print 'Test data shape: ', X_test.shape print 'Test labels shape: ', y_test.shape # Visualize some examples from the dataset. # We show a few examples of training images from each class. classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'] num_classes = len(classes) samples_per_class = 7 for y, cls in enumerate(classes): idxs = np.flatnonzero(y_train == y) idxs = np.random.choice(idxs, samples_per_class, replace=False) for i, idx in enumerate(idxs): plt_idx = i * num_classes + y + 1 plt.subplot(samples_per_class, num_classes, plt_idx) plt.imshow(X_train[idx].astype('uint8')) plt.axis('off') if i == 0: plt.title(cls) plt.show() # Split the data into train, val, and test sets. In addition we will # create a small development set as a subset of the training data; # we can use this for development so our code runs faster. num_training = 49000 num_validation = 1000 num_test = 1000 num_dev = 500 # Our validation set will be num_validation points from the original # training set. mask = range(num_training, num_training + num_validation) X_val = X_train[mask] y_val = y_train[mask] # Our training set will be the first num_train points from the original # training set. mask = range(num_training) X_train = X_train[mask] y_train = y_train[mask] # We will also make a development set, which is a small subset of # the training set. mask = np.random.choice(num_training, num_dev, replace=False) X_dev = X_train[mask] y_dev = y_train[mask] # We use the first num_test points of the original test set as our # test set. mask = range(num_test) X_test = X_test[mask] y_test = y_test[mask] print 'Train data shape: ', X_train.shape print 'Train labels shape: ', y_train.shape print 'Validation data shape: ', X_val.shape print 'Validation labels shape: ', y_val.shape print 'Test data shape: ', X_test.shape print 'Test labels shape: ', y_test.shape # Preprocessing: reshape the image data into rows X_train = np.reshape(X_train, (X_train.shape[0], -1)) X_val = np.reshape(X_val, (X_val.shape[0], -1)) X_test = np.reshape(X_test, (X_test.shape[0], -1)) X_dev = np.reshape(X_dev, (X_dev.shape[0], -1)) # As a sanity check, print out the shapes of the data print 'Training data shape: ', X_train.shape print 'Validation data shape: ', X_val.shape print 'Test data shape: ', X_test.shape print 'dev data shape: ', X_dev.shape # Preprocessing: subtract the mean image # first: compute the image mean based on the training data mean_image = np.mean(X_train, axis=0) print mean_image[:10] # print a few of the elements plt.figure(figsize=(4,4)) plt.imshow(mean_image.reshape((32,32,3)).astype('uint8')) # visualize the mean image plt.show() # second: subtract the mean image from train and test data X_train -= mean_image X_val -= mean_image X_test -= mean_image X_dev -= mean_image # third: append the bias dimension of ones (i.e. bias trick) so that our SVM # only has to worry about optimizing a single weight matrix W. X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))]) X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))]) X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))]) X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))]) print X_train.shape, X_val.shape, X_test.shape, X_dev.shape # Evaluate the naive implementation of the loss we provided for you: from cs231n.classifiers.linear_svm import svm_loss_naive import time # generate a random SVM weight matrix of small numbers W = np.random.randn(3073, 10) * 0.0001 loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.00001) print 'loss: %f' % (loss, ) # Once you've implemented the gradient, recompute it with the code below # and gradient check it with the function we provided for you # Compute the loss and its gradient at W. loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.0) # Numerically compute the gradient along several randomly chosen dimensions, and # compare them with your analytically computed gradient. The numbers should match # almost exactly along all dimensions. from cs231n.gradient_check import grad_check_sparse f = lambda w: svm_loss_naive(w, X_dev, y_dev, 0.0)[0] grad_numerical = grad_check_sparse(f, W, grad) # do the gradient check once again with regularization turned on # you didn't forget the regularization gradient did you? loss, grad = svm_loss_naive(W, X_dev, y_dev, 1e2) f = lambda w: svm_loss_naive(w, X_dev, y_dev, 1e2)[0] grad_numerical = grad_check_sparse(f, W, grad) # Next implement the function svm_loss_vectorized; for now only compute the loss; # we will implement the gradient in a moment. tic = time.time() loss_naive, grad_naive = svm_loss_naive(W, X_dev, y_dev, 0.00001) toc = time.time() print 'Naive loss: %e computed in %fs' % (loss_naive, toc - tic) from cs231n.classifiers.linear_svm import svm_loss_vectorized tic = time.time() loss_vectorized, _ = svm_loss_vectorized(W, X_dev, y_dev, 0.00001) toc = time.time() print 'Vectorized loss: %e computed in %fs' % (loss_vectorized, toc - tic) # The losses should match but your vectorized implementation should be much faster. print 'difference: %f' % (loss_naive - loss_vectorized) # Complete the implementation of svm_loss_vectorized, and compute the gradient # of the loss function in a vectorized way. # The naive implementation and the vectorized implementation should match, but # the vectorized version should still be much faster. tic = time.time() _, grad_naive = svm_loss_naive(W, X_dev, y_dev, 0.00001) toc = time.time() print 'Naive loss and gradient: computed in %fs' % (toc - tic) tic = time.time() _, grad_vectorized = svm_loss_vectorized(W, X_dev, y_dev, 0.00001) toc = time.time() print 'Vectorized loss and gradient: computed in %fs' % (toc - tic) # The loss is a single number, so it is easy to compare the values computed # by the two implementations. The gradient on the other hand is a matrix, so # we use the Frobenius norm to compare them. difference = np.linalg.norm(grad_naive - grad_vectorized, ord='fro') print 'difference: %f' % difference # In the file linear_classifier.py, implement SGD in the function # LinearClassifier.train() and then run it with the code below. from cs231n.classifiers import LinearSVM svm = LinearSVM() tic = time.time() loss_hist = svm.train(X_train, y_train, learning_rate=1e-7, reg=5e4, num_iters=1500, verbose=True) toc = time.time() print 'That took %fs' % (toc - tic) # A useful debugging strategy is to plot the loss as a function of # iteration number: plt.plot(loss_hist) plt.xlabel('Iteration number') plt.ylabel('Loss value') plt.show() # Write the LinearSVM.predict function and evaluate the performance on both the # training and validation set y_train_pred = svm.predict(X_train) print 'training accuracy: %f' % (np.mean(y_train == y_train_pred), ) y_val_pred = svm.predict(X_val) print 'validation accuracy: %f' % (np.mean(y_val == y_val_pred), ) # Use the validation set to tune hyperparameters (regularization strength and # learning rate). You should experiment with different ranges for the learning # rates and regularization strengths; if you are careful you should be able to # get a classification accuracy of about 0.4 on the validation set. learning_rates = [1e-7, 5e-5] regularization_strengths = [5e4, 1e5] # results is dictionary mapping tuples of the form # (learning_rate, regularization_strength) to tuples of the form # (training_accuracy, validation_accuracy). The accuracy is simply the fraction # of data points that are correctly classified. results = {} best_val = -1 # The highest validation accuracy that we have seen so far. best_svm = None # The LinearSVM object that achieved the highest validation rate. ################################################################################ # TODO: # # Write code that chooses the best hyperparameters by tuning on the validation # # set. For each combination of hyperparameters, train a linear SVM on the # # training set, compute its accuracy on the training and validation sets, and # # store these numbers in the results dictionary. In addition, store the best # # validation accuracy in best_val and the LinearSVM object that achieves this # # accuracy in best_svm. # # # # Hint: You should use a small value for num_iters as you develop your # # validation code so that the SVMs don't take much time to train; once you are # # confident that your validation code works, you should rerun the validation # # code with a larger value for num_iters. # ################################################################################ pass ################################################################################ # END OF YOUR CODE # ################################################################################ # Print out results. for lr, reg in sorted(results): train_accuracy, val_accuracy = results[(lr, reg)] print 'lr %e reg %e train accuracy: %f val accuracy: %f' % ( lr, reg, train_accuracy, val_accuracy) print 'best validation accuracy achieved during cross-validation: %f' % best_val # Visualize the cross-validation results import math x_scatter = [math.log10(x[0]) for x in results] y_scatter = [math.log10(x[1]) for x in results] # plot training accuracy marker_size = 100 colors = [results[x][0] for x in results] plt.subplot(2, 1, 1) plt.scatter(x_scatter, y_scatter, marker_size, c=colors) plt.colorbar() plt.xlabel('log learning rate') plt.ylabel('log regularization strength') plt.title('CIFAR-10 training accuracy') # plot validation accuracy colors = [results[x][1] for x in results] # default size of markers is 20 plt.subplot(2, 1, 2) plt.scatter(x_scatter, y_scatter, marker_size, c=colors) plt.colorbar() plt.xlabel('log learning rate') plt.ylabel('log regularization strength') plt.title('CIFAR-10 validation accuracy') plt.show() # Evaluate the best svm on test set y_test_pred = best_svm.predict(X_test) test_accuracy = np.mean(y_test == y_test_pred) print 'linear SVM on raw pixels final test set accuracy: %f' % test_accuracy # Visualize the learned weights for each class. # Depending on your choice of learning rate and regularization strength, these may # or may not be nice to look at. w = best_svm.W[:-1,:] # strip out the bias w = w.reshape(32, 32, 3, 10) w_min, w_max = np.min(w), np.max(w) classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'] for i in xrange(10): plt.subplot(2, 5, i + 1) # Rescale the weights to be between 0 and 255 wimg = 255.0 * (w[:, :, :, i].squeeze() - w_min) / (w_max - w_min) plt.imshow(wimg.astype('uint8')) plt.axis('off') plt.title(classes[i]) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Fetch the dataset Step2: Prepare dataset Step3: Parse the baseline files for "eyes open" Step4: Parse the baseline files for "eyes closed" Step5: Dump arrays	<ASSISTANT_TASK:> Python Code: import numpy as np import pyedflib # please check the "requirements.txt" file import tqdm import pathlib import os curr_dir = pathlib.Path("./") edf_dir = (curr_dir / "raw_data/").resolve() if not edf_dir.exists(): try: edf_dir.mkdir() except Exeption as err: print(err) else: print(f"\"{edf_dir}\" already exists.") # Skip fetching the data if the notebook run on Binder. host = os.environ.get("BINDER_LAUNCH_HOST", None) if host is None or host != "https://mybinder.org/": !wget -P "$edf_dir" -c https://physionet.org/static/published-projects/eegmmidb/eeg-motor-movementimagery-dataset-1.0.0.zip !unzip "$edf_dir"/eeg-motor-movementimagery-dataset-1.0.0.zip -d "$edf_dir/eeg-motor-movementimagery-dataset/" dataset_root = f"{edf_dir}/eeg-motor-movementimagery-dataset/files" n_subjects = 106 n_rois = 64 n_samples = 9600 eyes_open = np.zeros((n_subjects, n_rois, n_samples)) eyes_closed = np.zeros((n_subjects, n_rois, n_samples)) for sub_id in tqdm.tqdm(range(n_subjects)): subj_prefix = f"S{sub_id + 1:03}" subj_dir = f"{dataset_root}/{subj_prefix}" baseline_eyes_open = f"{subj_dir}/{subj_prefix}R01" edf = pyedflib.EdfReader(baseline_eyes_open + ".edf") annot = edf.read_annotation() n_signals = edf.signals_in_file signal_labels = edf.getSignalLabels() for chan in np.arange(n_signals): eyes_open[sub_id, chan, :] = edf.readSignal(chan)[0:9600] for sub_id in tqdm.tqdm(range(n_subjects)): subj_prefix = f"S{sub_id + 1:03}" subj_dir = f"{dataset_root}/{subj_prefix}" baseline_eyes_open = f"{subj_dir}/{subj_prefix}R02" edf = pyedflib.EdfReader(baseline_eyes_open + ".edf") annot = edf.read_annotation() n_signals = edf.signals_in_file signal_labels = edf.getSignalLabels() for chan in np.arange(n_signals): eyes_closed[sub_id, chan, :] = edf.readSignal(chan)[0:9600] store_dir = (curr_dir / "data/").resolve() if not store_dir.exists(): try: store_dir.mkdir() except Exeption as err: print(err) else: print(f"\"{store_dir}\" already exists.") np.save(f'{store_dir}/eeg_eyes_opened.npy', eyes_open) np.save(f'{store_dir}/eeg_eyes_closed.npy', eyes_closed) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Getting the data Step2: These SVHN files are .mat files typically used with Matlab. However, we can load them in with scipy.io.loadmat which we imported above. Step3: Here I'm showing a small sample of the images. Each of these is 32x32 with 3 color channels (RGB). These are the real images we'll pass to the discriminator and what the generator will eventually fake. Step4: Here we need to do a bit of preprocessing and getting the images into a form where we can pass batches to the network. First off, we need to rescale the images to a range of -1 to 1, since the output of our generator is also in that range. We also have a set of test and validation images which could be used if we're trying to identify the numbers in the images. Step5: Network Inputs Step6: Generator Step7: Discriminator Step9: Model Loss Step11: Optimizers Step12: Building the model Step13: Here is a function for displaying generated images. Step14: And another function we can use to train our network. Notice when we call generator to create the samples to display, we set training to False. That's so the batch normalization layers will use the population statistics rather than the batch statistics. Also notice that we set the net.input_real placeholder when we run the generator's optimizer. The generator doesn't actually use it, but we'd get an errror without it because of the tf.control_dependencies block we created in model_opt. Step15: Hyperparameters	<ASSISTANT_TASK:> Python Code: %matplotlib inline import pickle as pkl import matplotlib.pyplot as plt import numpy as np from scipy.io import loadmat import tensorflow as tf !mkdir data from urllib.request import urlretrieve from os.path import isfile, isdir from tqdm import tqdm data_dir = 'data/' if not isdir(data_dir): raise Exception("Data directory doesn't exist!") class DLProgress(tqdm): last_block = 0 def hook(self, block_num=1, block_size=1, total_size=None): self.total = total_size self.update((block_num - self.last_block) * block_size) self.last_block = block_num if not isfile(data_dir + "train_32x32.mat"): with DLProgress(unit='B', unit_scale=True, miniters=1, desc='SVHN Training Set') as pbar: urlretrieve( 'http://ufldl.stanford.edu/housenumbers/train_32x32.mat', data_dir + 'train_32x32.mat', pbar.hook) if not isfile(data_dir + "test_32x32.mat"): with DLProgress(unit='B', unit_scale=True, miniters=1, desc='SVHN Training Set') as pbar: urlretrieve( 'http://ufldl.stanford.edu/housenumbers/test_32x32.mat', data_dir + 'test_32x32.mat', pbar.hook) trainset = loadmat(data_dir + 'train_32x32.mat') testset = loadmat(data_dir + 'test_32x32.mat') idx = np.random.randint(0, trainset['X'].shape[3], size=36) fig, axes = plt.subplots(6, 6, sharex=True, sharey=True, figsize=(5,5),) for ii, ax in zip(idx, axes.flatten()): ax.imshow(trainset['X'][:,:,:,ii], aspect='equal') ax.xaxis.set_visible(False) ax.yaxis.set_visible(False) plt.subplots_adjust(wspace=0, hspace=0) def scale(x, feature_range=(-1, 1)): # scale to (0, 1) x = ((x - x.min())/(255 - x.min())) # scale to feature_range min, max = feature_range x = x * (max - min) + min return x class Dataset: def __init__(self, train, test, val_frac=0.5, shuffle=False, scale_func=None): split_idx = int(len(test['y'])(1 - val_frac)) self.test_x, self.valid_x = test['X'][:,:,:,:split_idx], test['X'][:,:,:,split_idx:] self.test_y, self.valid_y = test['y'][:split_idx], test['y'][split_idx:] self.train_x, self.train_y = train['X'], train['y'] self.train_x = np.rollaxis(self.train_x, 3) self.valid_x = np.rollaxis(self.valid_x, 3) self.test_x = np.rollaxis(self.test_x, 3) if scale_func is None: self.scaler = scale else: self.scaler = scale_func self.shuffle = shuffle def batches(self, batch_size): if self.shuffle: idx = np.arange(len(dataset.train_x)) np.random.shuffle(idx) self.train_x = self.train_x[idx] self.train_y = self.train_y[idx] n_batches = len(self.train_y)//batch_size for ii in range(0, len(self.train_y), batch_size): x = self.train_x[ii:ii+batch_size] y = self.train_y[ii:ii+batch_size] yield self.scaler(x), y def model_inputs(real_dim, z_dim): inputs_real = tf.placeholder(tf.float32, (None, real_dim), name='input_real') inputs_z = tf.placeholder(tf.float32, (None, z_dim), name='input_z') return inputs_real, inputs_z def generator(z, output_dim, reuse=False, alpha=0.2, training=True): with tf.variable_scope('generator', reuse=reuse): # First fully connected layer x1 = tf.layers.dense(z, 44512) # Reshape it to start the convolutional stack x1 = tf.reshape(x1, (-1, 4, 4, 512)) x1 = tf.layers.batch_normalization(x1, training=training) x1 = tf.maximum(alpha * x1, x1) # 4x4x512 now x2 = tf.layers.conv2d_transpose(x1, 256, 5, strides=2, padding='same') x2 = tf.layers.batch_normalization(x2, training=training) x2 = tf.maximum(alpha * x2, x2) # 8x8x256 now x3 = tf.layers.conv2d_transpose(x2, 128, 5, strides=2, padding='same') x3 = tf.layers.batch_normalization(x3, training=training) x3 = tf.maximum(alpha * x3, x3) # 16x16x128 now # Output layer logits = tf.layers.conv2d_transpose(x3, output_dim, 5, strides=2, padding='same') # 32x32x3 now out = tf.tanh(logits) return out def discriminator(x, reuse=False, alpha=0.2): with tf.variable_scope('discriminator', reuse=reuse): # Input layer is 32x32x3 x1 = tf.layers.conv2d(x, 64, 5, strides=2, padding='same') relu1 = tf.maximum(alpha * x1, x1) # 16x16x64 x2 = tf.layers.conv2d(relu1, 128, 5, strides=2, padding='same') bn2 = tf.layers.batch_normalization(x2, training=True) relu2 = tf.maximum(alpha * bn2, bn2) # 8x8x128 x3 = tf.layers.conv2d(relu2, 256, 5, strides=2, padding='same') bn3 = tf.layers.batch_normalization(x3, training=True) relu3 = tf.maximum(alpha * bn3, bn3) # 4x4x256 # Flatten it flat = tf.reshape(relu3, (-1, 44256)) logits = tf.layers.dense(flat, 1) out = tf.sigmoid(logits) return out, logits def model_loss(input_real, input_z, output_dim, alpha=0.2): Get the loss for the discriminator and generator :param input_real: Images from the real dataset :param input_z: Z input :param out_channel_dim: The number of channels in the output image :return: A tuple of (discriminator loss, generator loss) g_model = generator(input_z, output_dim, alpha=alpha) d_model_real, d_logits_real = discriminator(input_real, alpha=alpha) d_model_fake, d_logits_fake = discriminator(g_model, reuse=True, alpha=alpha) d_loss_real = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.ones_like(d_model_real))) d_loss_fake = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.zeros_like(d_model_fake))) g_loss = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake))) d_loss = d_loss_real + d_loss_fake return d_loss, g_loss def model_opt(d_loss, g_loss, learning_rate, beta1): Get optimization operations :param d_loss: Discriminator loss Tensor :param g_loss: Generator loss Tensor :param learning_rate: Learning Rate Placeholder :param beta1: The exponential decay rate for the 1st moment in the optimizer :return: A tuple of (discriminator training operation, generator training operation) # Get weights and bias to update t_vars = tf.trainable_variables() d_vars = [var for var in t_vars if var.name.startswith('discriminator')] g_vars = [var for var in t_vars if var.name.startswith('generator')] # Optimize with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)): d_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(d_loss, var_list=d_vars) g_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(g_loss, var_list=g_vars) return d_train_opt, g_train_opt class GAN: def __init__(self, real_size, z_size, learning_rate, alpha=0.2, beta1=0.5): tf.reset_default_graph() self.input_real, self.input_z = model_inputs(real_size, z_size) self.d_loss, self.g_loss = model_loss(self.input_real, self.input_z, real_size[2], alpha=0.2) self.d_opt, self.g_opt = model_opt(self.d_loss, self.g_loss, learning_rate, beta1) def view_samples(epoch, samples, nrows, ncols, figsize=(5,5)): fig, axes = plt.subplots(figsize=figsize, nrows=nrows, ncols=ncols, sharey=True, sharex=True) for ax, img in zip(axes.flatten(), samples[epoch]): ax.axis('off') img = ((img - img.min())*255 / (img.max() - img.min())).astype(np.uint8) ax.set_adjustable('box-forced') im = ax.imshow(img, aspect='equal') plt.subplots_adjust(wspace=0, hspace=0) return fig, axes def train(net, dataset, epochs, batch_size, print_every=10, show_every=100, figsize=(5,5)): saver = tf.train.Saver() sample_z = np.random.uniform(-1, 1, size=(72, z_size)) samples, losses = [], [] steps = 0 with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for e in range(epochs): for x, y in dataset.batches(batch_size): steps += 1 # Sample random noise for G batch_z = np.random.uniform(-1, 1, size=(batch_size, z_size)) # Run optimizers _ = sess.run(net.d_opt, feed_dict={net.input_real: x, net.input_z: batch_z}) _ = sess.run(net.g_opt, feed_dict={net.input_z: batch_z, net.input_real: x}) if steps % print_every == 0: # At the end of each epoch, get the losses and print them out train_loss_d = net.d_loss.eval({net.input_z: batch_z, net.input_real: x}) train_loss_g = net.g_loss.eval({net.input_z: batch_z}) print("Epoch {}/{}...".format(e+1, epochs), "Discriminator Loss: {:.4f}...".format(train_loss_d), "Generator Loss: {:.4f}".format(train_loss_g)) # Save losses to view after training losses.append((train_loss_d, train_loss_g)) if steps % show_every == 0: gen_samples = sess.run( generator(net.input_z, 3, reuse=True, training=False), feed_dict={net.input_z: sample_z}) samples.append(gen_samples) _ = view_samples(-1, samples, 6, 12, figsize=figsize) plt.show() saver.save(sess, './checkpoints/generator.ckpt') with open('samples.pkl', 'wb') as f: pkl.dump(samples, f) return losses, samples real_size = (32,32,3) z_size = 100 learning_rate = 0.0002 batch_size = 128 epochs = 25 alpha = 0.2 beta1 = 0.5 # Create the network net = GAN(real_size, z_size, learning_rate, alpha=alpha, beta1=beta1) dataset = Dataset(trainset, testset) losses, samples = train(net, dataset, epochs, batch_size, figsize=(10,5)) fig, ax = plt.subplots() losses = np.array(losses) plt.plot(losses.T[0], label='Discriminator', alpha=0.5) plt.plot(losses.T[1], label='Generator', alpha=0.5) plt.title("Training Losses") plt.legend() fig, ax = plt.subplots() losses = np.array(losses) plt.plot(losses.T[0], label='Discriminator', alpha=0.5) plt.plot(losses.T[1], label='Generator', alpha=0.5) plt.title("Training Losses") plt.legend() _ = view_samples(-1, samples, 6, 12, figsize=(10,5)) _ = view_samples(-1, samples, 6, 12, figsize=(10,5)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Note that the example_num argument is passed in but not used in the monty_hall function. Although it's unneeded for the function, it is easier to use interact to call functions when they have arguments to manipulate Step2: By interacting with the function above, we are able to informally verify that the function never allows the host to open a door with a car behind it. Even though the function is random we are able to use interaction to examine its long-term behavior! Step3: Again, a bit of interaction lets us quickly examine the behavior of winner. We can see that switch appears more often than stay. Step4: To make an interactive chart, pass a response function in place of one or both of bar's arguments. Step5: Visualizing the Winners Step6: Note that by default the plot will adjust its y-axis to match the limits of the data. We can manually set the y-axis limits to better visualize this plot being built up. We will also add labels to our plot Step7: We can get even fancy and use the Play widget from ipywidgets to animate the plot. Step8: Now we have an interactive, animated bar plot showing the distribution of wins over time for both Monty Hall strategies. This is a convincing argument that switching is better than staying. In fact, the bar plot above suggests that switching is about twice as likely to win as staying! Step9: We can then define a function to play sets of games and generate a list of win proportions for each set Step10: Interacting with generate_proportions shows the relationship between its arguments sample_size and repetitions more quickly than reading the function itself! Step11: As with last time, it's illustrative to specify the limits of the axes Step12: We can see that the distribution of wins is centered at roughly 0.66 but the distribution almost spans the entire x-axis. Will increasing the sample size make our distribution more narrow? Will increasing repetitions do the trick? Or both? We can find out through simulation and interaction. Step13: So increasing the sample size makes the distribution narrower. We can now see more clearly that the distribution is centered at 0.66.	<ASSISTANT_TASK:> Python Code: from ipywidgets import interact import numpy as np import random PRIZES = ['Car', 'Goat 1', 'Goat 2'] def monty_hall(example_num=0): ''' Simulates one round of the Monty Hall Problem. Outputs a tuple of (result if stay, result if switch, result behind opened door) where each results is one of PRIZES. ''' pick = random.choice(PRIZES) opened = random.choice( [p for p in PRIZES if p != pick and p != 'Car'] ) remainder = next(p for p in PRIZES if p != pick and p != opened) return (pick, remainder, opened) interact(monty_hall, example_num=(0, 100)); def winner(example_num=0): ''' Plays a game of Monty Hall. If staying with the original door wins a car, return 'stay'. Otherwise, the remaining door contains the car so 'switch' would have won. ''' picked, _, _ = monty_hall() return 'stay' if picked == 'Car' else 'switch' interact(winner, example_num=(0, 100)); import nbinteract as nbi nbi.bar(['a', 'b'], [4, 6]) # This function generates the x-values def categories(n): return list('abcdefg')[:n] # This function generates the y-values (heights of bars) # The y response function always takes in the x-values as its # first argument def offset_y(xs, offset): num_categories = len(xs) return np.arange(num_categories) + offset # Each argument of the response functions is passed in as a keyword # argument to `nbi.bar` in the same format as `interact` nbi.bar(categories, offset_y, n=(1, 7), offset=(0, 10)) categories = ['stay', 'switch'] winners = [winner() for _ in range(1000)] # Note that the the first argument to the y response function # will be the x-values which we don't need def won(_, num_games): ''' Outputs a 2-tuple of the number of times each strategy won after num_games games. ''' return (winners[:num_games].count('stay'), winners[:num_games].count('switch')) nbi.bar(categories, won, num_games=(1, 1000)) options = { 'title': 'Number of times each strategy wins', 'xlabel': 'Strategy', 'ylabel': 'Number of wins', 'ylim': (0, 700), } nbi.bar(categories, won, options=options, num_games=(1, 1000)) from ipywidgets import Play nbi.bar(categories, won, options=options, num_games=Play(min=0, max=1000, step=10, value=0, interval=17)) def prop_wins(sample_size): '''Returns proportion of times switching wins after sample_size games.''' return sum(winner() == 'switch' for _ in range(sample_size)) / sample_size interact(prop_wins, sample_size=(10, 100)); def generate_proportions(sample_size, repetitions): ''' Returns an array of length reptitions. Each element in the list is the proportion of times switching won in sample_size games. ''' return np.array([prop_wins(sample_size) for _ in range(repetitions)]) interact(generate_proportions, sample_size=(10, 100), repetitions=(10, 100)); # Play the game 10 times, recording the proportion of times switching wins. # Repeat 100 times to record 100 proportions proportions = generate_proportions(sample_size=10, repetitions=100) def props_up_to(num_sets): return proportions[:num_sets] nbi.hist(props_up_to, num_sets=Play(min=0, max=100, value=0, interval=50)) options = { 'title': 'Distribution of win proportion over 100 sets of 10 games when switching', 'xlabel': 'Proportions', 'ylabel': 'Percent per area', 'xlim': (0.3, 1), 'ylim': (0, 3), 'bins': 7, } nbi.hist(props_up_to, options=options, num_sets=Play(min=0, max=100, value=0, interval=50)) varying_sample_size = [generate_proportions(sample_size, repetitions=100) for sample_size in range(10, 101)] def props_for_sample_size(sample_size): return varying_sample_size[sample_size - 10] changed_options = { 'title': 'Distribution of win proportions as sample size increases', 'ylim': (0, 6), 'bins': 20, } nbi.hist(props_for_sample_size, options={options, changed_options}, sample_size=Play(min=10, max=100, value=10, interval=50)) varying_reps = [generate_proportions(sample_size=10, repetitions=reps) for reps in range(10, 101)] def props_for_reps(reps): return varying_reps[reps - 10] changed_options = { 'title': 'Distribution of win proportions as repetitions increase', 'ylim': (0, 5), } nbi.hist(props_for_reps, options={options, changed_options}, reps=Play(min=10, max=100, value=10, interval=50)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step3: Let's first implement sequential updates for GLMs. Step5: Let's make a function which can sample from a multivariate normal distribution. Step9: Let's makes some classes to represent different kinds of knobs - we'll just implement fixed and categorical (including binary) knobs here, but of course you can implement other ones. Step11: And now, to sample and optimize these knobs... Step13: Now we have all the pieces that we need to do contextual bandit. Let's run a binomial contextual bandit with a bunch of binary knobs, each of which can have a modest effect on the reward - in the range of 10%. We'll run 10 trials per batch, and run this for a number of batches.	<ASSISTANT_TASK:> Python Code: %matplotlib inline from __future__ import division import numpy as np import matplotlib.pyplot as plt import scipy.signal def logistic(x): Returns the logistic of the numeric argument to the function. return 1 / (1 + np.exp(-x)) def estimate_glm_params(X, y, prior_mean, prior_precision, model = 'binomial', niters = 1): Estimate model parameters for a GLM. Find MAP estimate of a GLM with a normal prior on the model parameters. Args: X: an NxM matrix - the design matrix y: a N length vector - the measured outcome prior_mean: an M length vector - the prior mean prior_precision: an MxM matrix - the prior precision model: a string - accepts normal, binomial, poisson. Uses canonical links. Gaussian assumes observation noise has variance 1. niters: the number of Newton iterations to do. Returns: (w_MAP, precision_MAP): the MAP parameter and its precision ( == the Hessian at the MAP) w = prior_mean for i in range(niters): eta = X.dot(w) if model == 'normal': mu = eta H = X.T.dot(X) + prior_precision elif model == 'binomial': mu = logistic(eta) H = X.T.dot(((1 - mu) mu).reshape((-1,1)) X) + prior_precision elif model == 'poisson': mu = np.exp(eta) H = X.T.dot(mu.reshape((-1,1)) * X) + prior_precision else: raise ValueError('Model should be one of normal, binomial, poisson') g = X.T.dot(mu - y) Hg, _, _, _ = np.linalg.lstsq(H, g) w = w - Hg return w, H # Check that one-shot estimation works. ndata_points = 10000 ndims = 10 X = np.random.randn(ndata_points, ndims) prior_precision = 100np.eye(10) w = np.random.randn((ndims)).1 threshold = .95 for family in ['normal', 'binomial', 'poisson']: w_mean = np.zeros((ndims)) if family == 'normal': mu = X.dot(w) y = mu + np.random.randn(mu.size) elif family == 'binomial': mu = logistic(X.dot(w)) y = np.random.binomial(1, mu) elif family == 'poisson': mu = np.exp(X.dot(w)) y = np.random.poisson(mu) w_est, H_est = estimate_glm_params(X, y, w_mean, prior_precision, family, niters= 10) assert np.corrcoef(w_est, w)[0, 1] > threshold w_est0 = w_est.copy() # Check that sequential estimation works nbatches = 100 w_est = w_mean.copy() prior_precision_est = prior_precision.copy() for n in range(nbatches): rg = slice( int(n / nbatches), int((n+1)ndata_points / nbatches)) w_est, prior_precision_est = estimate_glm_params(X[rg,:], y[rg], w_est, prior_precision_est, family) assert np.corrcoef(w_est0, w)[0, 1] > threshold assert np.corrcoef(w_est0, w_est)[0, 1] > threshold print "Sequential estimation in GLMs is working." def sample_normal_mean_precision(mean, precision, N_samples = 1): Samples from a normal distribution with a mean and precision. Uses eigenvalue decomposition to sample from the right distribution. Reference: https://en.wikipedia.org/wiki/Multivariate_normal_distribution#Drawing_values_from_the_distribution Args: mean: an M-length vector, the mean of the normal. precision: an MxM matrix, the precision of the normal. N_samples: the number of samples. Returns: An MxN sample matrix. S, U = np.linalg.eig(precision) noise_vector = np.random.randn(precision.shape[1], N_samples) projection_matrix = (U (S (-1/2)).reshape((1, -1))) sample = mean.reshape((-1, 1)) + projection_matrix.dot(noise_vector) return sample X = np.random.randn(100, 10) S, U = np.linalg.eig(X.T.dot(X)) S = S 3 cov = U.dot(S.reshape((-1, 1)) * U.T) precision = np.linalg.inv(cov) samples = sample_normal_mean_precision(np.zeros(precision.shape[0]), precision, 1000) cov_est = samples.dot(samples.T) / samples.shape[1] assert abs((cov_est - cov) / cov.max()).max() < .1 class FixedKnob(object): def __init__(self): Defines a fixed knob self.dim = 1 def optimal_design(self, knob_values): Returns the optimal design contingent on the knob values. return np.ones_like(knob_values) class CategoricalKnob(object): def __init__(self, nclasses = 2): Defines a categorical knob. With nclasses = 2, this becomes a binary knob. self.dim = nclasses - 1 def optimal_design(self, knob_values): if self.dim == 1: return (1 * (knob_values > 0)).reshape((-1, 1)) else: max_vals = 1 * (knob_values == knob_values.max(axis = 1).reshape((-1, 1))) # De-dup in case of ties max_vals = max_vals * (np.cumsum(max_vals, axis = 1) == 1) return 1 * (knob_values > 0) * max_vals # Check that de-duping works knob = CategoricalKnob(3) optimal_design = knob.optimal_design(np.array([.5, .5]).reshape((1, -1))) assert np.allclose(optimal_design, np.array([1, 0])) # Check that it selects the default category when all the parameters # are negative. optimal_design = knob.optimal_design(np.array([-.5, -.5]).reshape((1, -1))) assert np.allclose(optimal_design, np.array([0, 0])) def thompson_sampling(knobs, prior_mean, prior_precision, N_samples): Do Thompson sampling for the posterior distribution of the parameters of the knobs. Args: knobs: a list of knobs prior_mean: a M-length vector of means prior_precision: an MxM matrix of means N_samples: the number of samples to take Returns: (sampled_params, optimal_design) the sampled parameters (M x N_samples) and the optimal design (N_samples X N) corresponding to each draw from the sampled params. sampled_params = sample_normal_mean_precision(prior_mean, prior_precision, N_samples) X = [] start_block = 0 # Sample from each knob in sequence. for knob in knobs: rg = slice(start_block, start_block + knob.dim) X.append(knob.optimal_design(sampled_params[rg,:].T)) start_block += knob.dim return sampled_params, np.hstack(X) knobs = [FixedKnob(), CategoricalKnob(2)] # All these knobs are good, so we expect a matrix of ones. w, X = sample_optimize_knobs(knobs, np.ones(2), np.eye((2))100, 10) assert X.shape[0] == 10 assert X.shape[1] == 2 assert np.allclose(X, np.ones((10, 2))) knobs = [CategoricalKnob(3)] # Check that we get roughly the same number of 1's in each column w, X = thompson_sampling(knobs, np.ones(2), np.eye((2))100, 1000) assert X.mean(0)[0] > .45 and X.mean(0)[1] < .55 def simulate_binomial_bandit(true_parameters, knobs, prior_mean, prior_precision, batch_size, N_batches): Run the binomial contextual bandit with Thompson sampling policy. rewards = np.zeros((N_batches,batch_size)) for i in range(N_batches): # Get a design matrix for this batch _, X = thompson_sampling(knobs, prior_mean, prior_precision, batch_size) # Simulate rewards reward_rate = logistic(X.dot(true_parameters)) batch_rewards = np.random.binomial(1, reward_rate) # Update the matrix. prior_mean, prior_precision = estimate_glm_params(X, batch_rewards, prior_mean, prior_precision) # Store the outcome. rewards[i, :] = batch_rewards return rewards, prior_mean def logit(p): return np.log(p / (1 - p)) baseline_rate = .5 beta = logit(baseline_rate) beta_sd = .2 N_knobs = 10 knob_sd = .5 batch_size = 10 N_batches = 50 prior_mean = np.hstack((beta, np.zeros(N_knobs))) prior_precision = np.diag(np.hstack((1 / beta_sd2, np.ones(N_knobs) / knob_sd2))) # Pick the parameters from the prior distribution. true_parameters = sample_normal_mean_precision(prior_mean, prior_precision).squeeze() knobs = [FixedKnob()] for i in range(N_knobs): knobs.append(CategoricalKnob()) rewards, _ = simulate_binomial_bandit(true_parameters, knobs, prior_mean, prior_precision, batch_size, N_batches) reward_sequence = rewards.ravel() plt.figure(figsize=(13, 5)) # And also plot a smoother version sigma = 3 rg = np.arange(-int(3sigma), int(3sigma) + 1) thefilt = np.exp(-(rg2) / 2 / sigma2) thefilt = thefilt / thefilt.sum() smoothed_sequence = scipy.signal.convolve(reward_sequence, thefilt, 'same') smoothed_sequence /= scipy.signal.convolve(np.ones_like(reward_sequence), thefilt, 'same') plt.plot(smoothed_sequence) plt.axis('tight') plt.box('off') # And show the optimal average reward _, opt_design = sample_optimize_knobs(knobs, true_parameters, prior_precision10000, 1) opt_reward = logistic(opt_design.dot(true_parameters)) plt.plot([0, N_batchesbatch_size], [opt_reward, opt_reward], 'r-') plt.text(0, opt_reward, 'Best attainable average reward') plt.xlabel('Trial #') plt.title('Smoothed reward') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: If we have a specific point in space and time we wish to test, it can be Step2: Absent specific hypotheses, we can also conduct an exploratory Step3: The results of these mass univariate analyses can be visualised by plotting	<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib.pyplot as plt from scipy.stats import ttest_ind import mne from mne.channels import find_ch_adjacency, make_1020_channel_selections from mne.stats import spatio_temporal_cluster_test np.random.seed(0) # Load the data path = mne.datasets.kiloword.data_path() + '/kword_metadata-epo.fif' epochs = mne.read_epochs(path) # These data are quite smooth, so to speed up processing we'll (unsafely!) just # decimate them epochs.decimate(4, verbose='error') name = "NumberOfLetters" # Split up the data by the median length in letters via the attached metadata median_value = str(epochs.metadata[name].median()) long_words = epochs[name + " > " + median_value] short_words = epochs[name + " < " + median_value] time_windows = ((.2, .25), (.35, .45)) elecs = ["Fz", "Cz", "Pz"] index = ['condition', 'epoch', 'time'] # display the EEG data in Pandas format (first 5 rows) print(epochs.to_data_frame(index=index)[elecs].head()) report = "{elec}, time: {tmin}-{tmax} s; t({df})={t_val:.3f}, p={p:.3f}" print("\nTargeted statistical test results:") for (tmin, tmax) in time_windows: long_df = long_words.copy().crop(tmin, tmax).to_data_frame(index=index) short_df = short_words.copy().crop(tmin, tmax).to_data_frame(index=index) for elec in elecs: # extract data A = long_df[elec].groupby("condition").mean() B = short_df[elec].groupby("condition").mean() # conduct t test t, p = ttest_ind(A, B) # display results format_dict = dict(elec=elec, tmin=tmin, tmax=tmax, df=len(epochs.events) - 2, t_val=t, p=p) print(report.format(format_dict)) # Calculate adjacency matrix between sensors from their locations adjacency, _ = find_ch_adjacency(epochs.info, "eeg") # Extract data: transpose because the cluster test requires channels to be last # In this case, inference is done over items. In the same manner, we could # also conduct the test over, e.g., subjects. X = [long_words.get_data().transpose(0, 2, 1), short_words.get_data().transpose(0, 2, 1)] tfce = dict(start=.4, step=.4) # ideally start and step would be smaller # Calculate statistical thresholds t_obs, clusters, cluster_pv, h0 = spatio_temporal_cluster_test( X, tfce, adjacency=adjacency, n_permutations=100) # a more standard number would be 1000+ significant_points = cluster_pv.reshape(t_obs.shape).T < .05 print(str(significant_points.sum()) + " points selected by TFCE ...") # We need an evoked object to plot the image to be masked evoked = mne.combine_evoked([long_words.average(), short_words.average()], weights=[1, -1]) # calculate difference wave time_unit = dict(time_unit="s") evoked.plot_joint(title="Long vs. short words", ts_args=time_unit, topomap_args=time_unit) # show difference wave # Create ROIs by checking channel labels selections = make_1020_channel_selections(evoked.info, midline="12z") # Visualize the results fig, axes = plt.subplots(nrows=3, figsize=(8, 8)) axes = {sel: ax for sel, ax in zip(selections, axes.ravel())} evoked.plot_image(axes=axes, group_by=selections, colorbar=False, show=False, mask=significant_points, show_names="all", titles=None, time_unit) plt.colorbar(axes["Left"].images[-1], ax=list(axes.values()), shrink=.3, label="µV") plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Install the latest GA version of google-cloud-storage library as well. Step2: Restart the kernel Step3: Before you begin Step4: Region Step5: Timestamp Step6: Authenticate your Google Cloud account Step7: Create a Cloud Storage bucket Step8: Only if your bucket doesn't already exist Step9: Finally, validate access to your Cloud Storage bucket by examining its contents Step10: Set up variables Step11: Vertex constants Step12: Hardware Accelerators Step13: Container (Docker) image Step14: Machine Type Step15: Tutorial Step16: Train a model Step17: Prepare your disk specification Step18: Define the worker pool specification Step19: Assemble a job specification Step20: Examine the training package Step21: Task.py contents Step22: Store training script on your Cloud Storage bucket Step23: Train the model Step24: Now get the unique identifier for the custom job you created. Step25: Get information on a custom job Step26: Deployment Step27: Load the saved model Step28: Evaluate the model Step29: Perform the model evaluation Step30: Upload the model for serving Step31: Upload the model Step32: Get Model resource information Step33: Deploy the Model resource Step34: Now get the unique identifier for the Endpoint resource you created. Step35: Compute instance scaling Step36: Deploy Model resource to the Endpoint resource Step37: Make a online prediction request Step38: Send the prediction request Step39: Undeploy the Model resource Step40: Cleaning up	<ASSISTANT_TASK:> Python Code: import os import sys # Google Cloud Notebook if os.path.exists("/opt/deeplearning/metadata/env_version"): USER_FLAG = "--user" else: USER_FLAG = "" ! pip3 install -U google-cloud-aiplatform $USER_FLAG ! pip3 install -U google-cloud-storage $USER_FLAG if not os.getenv("IS_TESTING"): # Automatically restart kernel after installs import IPython app = IPython.Application.instance() app.kernel.do_shutdown(True) PROJECT_ID = "[your-project-id]" # @param {type:"string"} if PROJECT_ID == "" or PROJECT_ID is None or PROJECT_ID == "[your-project-id]": # Get your GCP project id from gcloud shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null PROJECT_ID = shell_output[0] print("Project ID:", PROJECT_ID) ! gcloud config set project $PROJECT_ID REGION = "us-central1" # @param {type: "string"} from datetime import datetime TIMESTAMP = datetime.now().strftime("%Y%m%d%H%M%S") # If you are running this notebook in Colab, run this cell and follow the # instructions to authenticate your GCP account. This provides access to your # Cloud Storage bucket and lets you submit training jobs and prediction # requests. # If on Google Cloud Notebook, then don't execute this code if not os.path.exists("/opt/deeplearning/metadata/env_version"): if "google.colab" in sys.modules: from google.colab import auth as google_auth google_auth.authenticate_user() # If you are running this notebook locally, replace the string below with the # path to your service account key and run this cell to authenticate your GCP # account. elif not os.getenv("IS_TESTING"): %env GOOGLE_APPLICATION_CREDENTIALS '' BUCKET_NAME = "gs://[your-bucket-name]" # @param {type:"string"} if BUCKET_NAME == "" or BUCKET_NAME is None or BUCKET_NAME == "gs://[your-bucket-name]": BUCKET_NAME = "gs://" + PROJECT_ID + "aip-" + TIMESTAMP ! gsutil mb -l $REGION $BUCKET_NAME ! gsutil ls -al $BUCKET_NAME import time from google.cloud.aiplatform import gapic as aip from google.protobuf import json_format from google.protobuf.json_format import MessageToJson, ParseDict from google.protobuf.struct_pb2 import Struct, Value # API service endpoint API_ENDPOINT = "{}-aiplatform.googleapis.com".format(REGION) # Vertex location root path for your dataset, model and endpoint resources PARENT = "projects/" + PROJECT_ID + "/locations/" + REGION if os.getenv("IS_TESTING_TRAIN_GPU"): TRAIN_GPU, TRAIN_NGPU = ( aip.AcceleratorType.NVIDIA_TESLA_K80, int(os.getenv("IS_TESTING_TRAIN_GPU")), ) else: TRAIN_GPU, TRAIN_NGPU = (None, None) if os.getenv("IS_TESTING_DEPOLY_GPU"): DEPLOY_GPU, DEPLOY_NGPU = ( aip.AcceleratorType.NVIDIA_TESLA_K80, int(os.getenv("IS_TESTING_DEPOLY_GPU")), ) else: DEPLOY_GPU, DEPLOY_NGPU = (None, None) if os.getenv("IS_TESTING_TF"): TF = os.getenv("IS_TESTING_TF") else: TF = "2-1" if TF[0] == "2": if TRAIN_GPU: TRAIN_VERSION = "tf-gpu.{}".format(TF) else: TRAIN_VERSION = "tf-cpu.{}".format(TF) if DEPLOY_GPU: DEPLOY_VERSION = "tf2-gpu.{}".format(TF) else: DEPLOY_VERSION = "tf2-cpu.{}".format(TF) else: if TRAIN_GPU: TRAIN_VERSION = "tf-gpu.{}".format(TF) else: TRAIN_VERSION = "tf-cpu.{}".format(TF) if DEPLOY_GPU: DEPLOY_VERSION = "tf-gpu.{}".format(TF) else: DEPLOY_VERSION = "tf-cpu.{}".format(TF) TRAIN_IMAGE = "gcr.io/cloud-aiplatform/training/{}:latest".format(TRAIN_VERSION) DEPLOY_IMAGE = "gcr.io/cloud-aiplatform/prediction/{}:latest".format(DEPLOY_VERSION) print("Training:", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU) print("Deployment:", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU) if os.getenv("IS_TESTING_TRAIN_MACHINE"): MACHINE_TYPE = os.getenv("IS_TESTING_TRAIN_MACHINE") else: MACHINE_TYPE = "n1-standard" VCPU = "4" TRAIN_COMPUTE = MACHINE_TYPE + "-" + VCPU print("Train machine type", TRAIN_COMPUTE) if os.getenv("IS_TESTING_DEPLOY_MACHINE"): MACHINE_TYPE = os.getenv("IS_TESTING_DEPLOY_MACHINE") else: MACHINE_TYPE = "n1-standard" VCPU = "4" DEPLOY_COMPUTE = MACHINE_TYPE + "-" + VCPU print("Deploy machine type", DEPLOY_COMPUTE) # client options same for all services client_options = {"api_endpoint": API_ENDPOINT} def create_job_client(): client = aip.JobServiceClient(client_options=client_options) return client def create_model_client(): client = aip.ModelServiceClient(client_options=client_options) return client def create_endpoint_client(): client = aip.EndpointServiceClient(client_options=client_options) return client def create_prediction_client(): client = aip.PredictionServiceClient(client_options=client_options) return client clients = {} clients["job"] = create_job_client() clients["model"] = create_model_client() clients["endpoint"] = create_endpoint_client() clients["prediction"] = create_prediction_client() for client in clients.items(): print(client) if TRAIN_GPU: machine_spec = { "machine_type": TRAIN_COMPUTE, "accelerator_type": TRAIN_GPU, "accelerator_count": TRAIN_NGPU, } else: machine_spec = {"machine_type": TRAIN_COMPUTE, "accelerator_count": 0} DISK_TYPE = "pd-ssd" # [ pd-ssd, pd-standard] DISK_SIZE = 200 # GB disk_spec = {"boot_disk_type": DISK_TYPE, "boot_disk_size_gb": DISK_SIZE} JOB_NAME = "custom_job_" + TIMESTAMP MODEL_DIR = "{}/{}".format(BUCKET_NAME, JOB_NAME) if not TRAIN_NGPU or TRAIN_NGPU < 2: TRAIN_STRATEGY = "single" else: TRAIN_STRATEGY = "mirror" EPOCHS = 20 STEPS = 100 DIRECT = True if DIRECT: CMDARGS = [ "--model-dir=" + MODEL_DIR, "--epochs=" + str(EPOCHS), "--steps=" + str(STEPS), "--distribute=" + TRAIN_STRATEGY, ] else: CMDARGS = [ "--epochs=" + str(EPOCHS), "--steps=" + str(STEPS), "--distribute=" + TRAIN_STRATEGY, ] worker_pool_spec = [ { "replica_count": 1, "machine_spec": machine_spec, "disk_spec": disk_spec, "python_package_spec": { "executor_image_uri": TRAIN_IMAGE, "package_uris": [BUCKET_NAME + "/trainer_imdb.tar.gz"], "python_module": "trainer.task", "args": CMDARGS, }, } ] if DIRECT: job_spec = {"worker_pool_specs": worker_pool_spec} else: job_spec = { "worker_pool_specs": worker_pool_spec, "base_output_directory": {"output_uri_prefix": MODEL_DIR}, } custom_job = {"display_name": JOB_NAME, "job_spec": job_spec} # Make folder for Python training script ! rm -rf custom ! mkdir custom # Add package information ! touch custom/README.md setup_cfg = "[egg_info]\n\ntag_build =\n\ntag_date = 0" ! echo "$setup_cfg" > custom/setup.cfg setup_py = "import setuptools\n\nsetuptools.setup(\n\n install_requires=[\n\n 'tensorflow_datasets==1.3.0',\n\n ],\n\n packages=setuptools.find_packages())" ! echo "$setup_py" > custom/setup.py pkg_info = "Metadata-Version: 1.0\n\nName: IMDB Movie Reviews text binary classification\n\nVersion: 0.0.0\n\nSummary: Demostration training script\n\nHome-page: www.google.com\n\nAuthor: Google\n\nAuthor-email: aferlitsch@google.com\n\nLicense: Public\n\nDescription: Demo\n\nPlatform: Vertex" ! echo "$pkg_info" > custom/PKG-INFO # Make the training subfolder ! mkdir custom/trainer ! touch custom/trainer/__init__.py %%writefile custom/trainer/task.py # Single, Mirror and Multi-Machine Distributed Training for IMDB import tensorflow_datasets as tfds import tensorflow as tf from tensorflow.python.client import device_lib import argparse import os import sys tfds.disable_progress_bar() parser = argparse.ArgumentParser() parser.add_argument('--model-dir', dest='model_dir', default=os.getenv('AIP_MODEL_DIR'), type=str, help='Model dir.') parser.add_argument('--lr', dest='lr', default=1e-4, type=float, help='Learning rate.') parser.add_argument('--epochs', dest='epochs', default=20, type=int, help='Number of epochs.') parser.add_argument('--steps', dest='steps', default=100, type=int, help='Number of steps per epoch.') parser.add_argument('--distribute', dest='distribute', type=str, default='single', help='distributed training strategy') args = parser.parse_args() print('Python Version = {}'.format(sys.version)) print('TensorFlow Version = {}'.format(tf.__version__)) print('TF_CONFIG = {}'.format(os.environ.get('TF_CONFIG', 'Not found'))) print(device_lib.list_local_devices()) # Single Machine, single compute device if args.distribute == 'single': if tf.test.is_gpu_available(): strategy = tf.distribute.OneDeviceStrategy(device="/gpu:0") else: strategy = tf.distribute.OneDeviceStrategy(device="/cpu:0") # Single Machine, multiple compute device elif args.distribute == 'mirror': strategy = tf.distribute.MirroredStrategy() # Multiple Machine, multiple compute device elif args.distribute == 'multi': strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy() # Multi-worker configuration print('num_replicas_in_sync = {}'.format(strategy.num_replicas_in_sync)) # Preparing dataset BUFFER_SIZE = 10000 BATCH_SIZE = 64 def make_datasets(): dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True, as_supervised=True) train_dataset, test_dataset = dataset['train'], dataset['test'] encoder = info.features['text'].encoder padded_shapes = ([None],()) return train_dataset.shuffle(BUFFER_SIZE).padded_batch(BATCH_SIZE, padded_shapes), encoder train_dataset, encoder = make_datasets() # Build the Keras model def build_and_compile_rnn_model(encoder): model = tf.keras.Sequential([ tf.keras.layers.Embedding(encoder.vocab_size, 64), tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)), tf.keras.layers.Dense(64, activation='relu'), tf.keras.layers.Dense(1, activation='sigmoid') ]) model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), optimizer=tf.keras.optimizers.Adam(args.lr), metrics=['accuracy']) return model with strategy.scope(): # Creation of dataset, and model building/compiling need to be within # `strategy.scope()`. model = build_and_compile_rnn_model(encoder) # Train the model model.fit(train_dataset, epochs=args.epochs, steps_per_epoch=args.steps) model.save(args.model_dir) ! rm -f custom.tar custom.tar.gz ! tar cvf custom.tar custom ! gzip custom.tar ! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_imdb.tar.gz def create_custom_job(custom_job): response = clients["job"].create_custom_job(parent=PARENT, custom_job=custom_job) print("name:", response.name) print("display_name:", response.display_name) print("state:", response.state) print("create_time:", response.create_time) print("update_time:", response.update_time) return response response = create_custom_job(custom_job) # The full unique ID for the custom job job_id = response.name # The short numeric ID for the custom job job_short_id = job_id.split("/")[-1] print(job_id) def get_custom_job(name, silent=False): response = clients["job"].get_custom_job(name=name) if silent: return response print("name:", response.name) print("display_name:", response.display_name) print("state:", response.state) print("create_time:", response.create_time) print("update_time:", response.update_time) return response response = get_custom_job(job_id) while True: response = get_custom_job(job_id, True) if response.state != aip.JobState.JOB_STATE_SUCCEEDED: print("Training job has not completed:", response.state) model_path_to_deploy = None if response.state == aip.JobState.JOB_STATE_FAILED: break else: if not DIRECT: MODEL_DIR = MODEL_DIR + "/model" model_path_to_deploy = MODEL_DIR print("Training Time:", response.update_time - response.create_time) break time.sleep(60) print("model_to_deploy:", model_path_to_deploy) import tensorflow as tf model = tf.keras.models.load_model(MODEL_DIR) import tensorflow_datasets as tfds dataset, info = tfds.load("imdb_reviews/subwords8k", with_info=True, as_supervised=True) test_dataset = dataset["test"] encoder = info.features["text"].encoder BATCH_SIZE = 64 padded_shapes = ([None], ()) test_dataset = test_dataset.padded_batch(BATCH_SIZE, padded_shapes) model.evaluate(test_dataset) loaded = tf.saved_model.load(model_path_to_deploy) serving_input = list( loaded.signatures["serving_default"].structured_input_signature[1].keys() )[0] print("Serving function input:", serving_input) IMAGE_URI = DEPLOY_IMAGE def upload_model(display_name, image_uri, model_uri): model = { "display_name": display_name, "metadata_schema_uri": "", "artifact_uri": model_uri, "container_spec": { "image_uri": image_uri, "command": [], "args": [], "env": [{"name": "env_name", "value": "env_value"}], "ports": [{"container_port": 8080}], "predict_route": "", "health_route": "", }, } response = clients["model"].upload_model(parent=PARENT, model=model) print("Long running operation:", response.operation.name) upload_model_response = response.result(timeout=180) print("upload_model_response") print(" model:", upload_model_response.model) return upload_model_response.model model_to_deploy_id = upload_model("imdb-" + TIMESTAMP, IMAGE_URI, model_path_to_deploy) def get_model(name): response = clients["model"].get_model(name=name) print(response) get_model(model_to_deploy_id) ENDPOINT_NAME = "imdb_endpoint-" + TIMESTAMP def create_endpoint(display_name): endpoint = {"display_name": display_name} response = clients["endpoint"].create_endpoint(parent=PARENT, endpoint=endpoint) print("Long running operation:", response.operation.name) result = response.result(timeout=300) print("result") print(" name:", result.name) print(" display_name:", result.display_name) print(" description:", result.description) print(" labels:", result.labels) print(" create_time:", result.create_time) print(" update_time:", result.update_time) return result result = create_endpoint(ENDPOINT_NAME) # The full unique ID for the endpoint endpoint_id = result.name # The short numeric ID for the endpoint endpoint_short_id = endpoint_id.split("/")[-1] print(endpoint_id) MIN_NODES = 1 MAX_NODES = 1 DEPLOYED_NAME = "imdb_deployed-" + TIMESTAMP def deploy_model( model, deployed_model_display_name, endpoint, traffic_split={"0": 100} ): if DEPLOY_GPU: machine_spec = { "machine_type": DEPLOY_COMPUTE, "accelerator_type": DEPLOY_GPU, "accelerator_count": DEPLOY_NGPU, } else: machine_spec = { "machine_type": DEPLOY_COMPUTE, "accelerator_count": 0, } deployed_model = { "model": model, "display_name": deployed_model_display_name, "dedicated_resources": { "min_replica_count": MIN_NODES, "max_replica_count": MAX_NODES, "machine_spec": machine_spec, }, "disable_container_logging": False, } response = clients["endpoint"].deploy_model( endpoint=endpoint, deployed_model=deployed_model, traffic_split=traffic_split ) print("Long running operation:", response.operation.name) result = response.result() print("result") deployed_model = result.deployed_model print(" deployed_model") print(" id:", deployed_model.id) print(" model:", deployed_model.model) print(" display_name:", deployed_model.display_name) print(" create_time:", deployed_model.create_time) return deployed_model.id deployed_model_id = deploy_model(model_to_deploy_id, DEPLOYED_NAME, endpoint_id) import tensorflow_datasets as tfds dataset, info = tfds.load("imdb_reviews/subwords8k", with_info=True, as_supervised=True) test_dataset = dataset["test"] test_dataset.take(1) for data in test_dataset: print(data) break test_item = data[0].numpy() def predict_data(data, endpoint, parameters_dict): parameters = json_format.ParseDict(parameters_dict, Value()) # The format of each instance should conform to the deployed model's prediction input schema. instances_list = [{serving_input: data.tolist()}] instances = [json_format.ParseDict(s, Value()) for s in instances_list] response = clients["prediction"].predict( endpoint=endpoint, instances=instances, parameters=parameters ) print("response") print(" deployed_model_id:", response.deployed_model_id) predictions = response.predictions print("predictions") for prediction in predictions: print(" prediction:", prediction) predict_data(test_item, endpoint_id, None) def undeploy_model(deployed_model_id, endpoint): response = clients["endpoint"].undeploy_model( endpoint=endpoint, deployed_model_id=deployed_model_id, traffic_split={} ) print(response) undeploy_model(deployed_model_id, endpoint_id) delete_dataset = True delete_pipeline = True delete_model = True delete_endpoint = True delete_batchjob = True delete_customjob = True delete_hptjob = True delete_bucket = True # Delete the dataset using the Vertex fully qualified identifier for the dataset try: if delete_dataset and "dataset_id" in globals(): clients["dataset"].delete_dataset(name=dataset_id) except Exception as e: print(e) # Delete the training pipeline using the Vertex fully qualified identifier for the pipeline try: if delete_pipeline and "pipeline_id" in globals(): clients["pipeline"].delete_training_pipeline(name=pipeline_id) except Exception as e: print(e) # Delete the model using the Vertex fully qualified identifier for the model try: if delete_model and "model_to_deploy_id" in globals(): clients["model"].delete_model(name=model_to_deploy_id) except Exception as e: print(e) # Delete the endpoint using the Vertex fully qualified identifier for the endpoint try: if delete_endpoint and "endpoint_id" in globals(): clients["endpoint"].delete_endpoint(name=endpoint_id) except Exception as e: print(e) # Delete the batch job using the Vertex fully qualified identifier for the batch job try: if delete_batchjob and "batch_job_id" in globals(): clients["job"].delete_batch_prediction_job(name=batch_job_id) except Exception as e: print(e) # Delete the custom job using the Vertex fully qualified identifier for the custom job try: if delete_customjob and "job_id" in globals(): clients["job"].delete_custom_job(name=job_id) except Exception as e: print(e) # Delete the hyperparameter tuning job using the Vertex fully qualified identifier for the hyperparameter tuning job try: if delete_hptjob and "hpt_job_id" in globals(): clients["job"].delete_hyperparameter_tuning_job(name=hpt_job_id) except Exception as e: print(e) if delete_bucket and "BUCKET_NAME" in globals(): ! gsutil rm -r $BUCKET_NAME <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Implementation Step2: Preparing the Data Step3: For highly-skewed feature distributions such as 'capital-gain' and 'capital-loss', it is common practice to apply a <a href="https Step4: Normalizing Numerical Features Step5: Implementation Step6: Shuffle and Split Data Step7: Evaluating Model Performance Step8: Supverised Learning Models Step9: Implementation Step10: Improving Results Step11: Question 5 - Final Model Evaluation Step12: Question 7 - Extracting Feature Importance	<ASSISTANT_TASK:> Python Code: # Import libraries necessary for this project import numpy as np import pandas as pd from time import time from IPython.display import display # Allows the use of display() for DataFrames # Import supplementary visualization code visuals.py import visuals as vs # Pretty display for notebooks %matplotlib inline # Load the Census dataset data = pd.read_csv("census.csv") # Success - Display the first record display(data.head(n=1)) # TODO: Total number of records n_records = len(data) # TODO: Number of records where individual's income is more than $50,000 n_greater_50k = 0 for entry in data.income: if entry == '>50K': n_greater_50k = n_greater_50k+1 # TODO: Number of records where individual's income is at most $50,000 n_at_most_50k = 0 for entry in data.income: if entry == '<=50K': n_at_most_50k = n_at_most_50k + 1 # TODO: Percentage of individuals whose income is more than $50,000 greater_percent = (float(n_greater_50k)/n_records)100 # Print the results print "Total number of records: {}".format(n_records) print "Individuals making more than $50,000: {}".format(n_greater_50k) print "Individuals making at most $50,000: {}".format(n_at_most_50k) print "Percentage of individuals making more than $50,000: {:.2f}%".format(greater_percent) # Split the data into features and target label income_raw = data['income'] features_raw = data.drop('income', axis = 1) # Visualize skewed continuous features of original data vs.distribution(data) # Log-transform the skewed features skewed = ['capital-gain', 'capital-loss'] features_raw[skewed] = data[skewed].apply(lambda x: np.log(x + 1)) # Visualize the new log distributions vs.distribution(features_raw, transformed = True) # Import sklearn.preprocessing.StandardScaler from sklearn.preprocessing import MinMaxScaler # Initialize a scaler, then apply it to the features scaler = MinMaxScaler() numerical = ['age', 'education-num', 'capital-gain', 'capital-loss', 'hours-per-week'] features_raw[numerical] = scaler.fit_transform(data[numerical]) # Show an example of a record with scaling applied display(features_raw.head(n = 1)) from sklearn.preprocessing import LabelEncoder import pandas as pd # TODO: One-hot encode the 'features_raw' data using pandas.get_dummies() features = pd.get_dummies(features_raw) le = LabelEncoder() le.fit(income_raw) # TODO: Encode the 'income_raw' data to numerical values income = le.transform(income_raw) # Print the number of features after one-hot encoding encoded = list(features.columns) print "{} total features after one-hot encoding.".format(len(encoded)) # Uncomment the following line to see the encoded feature names print encoded # Import train_test_split from sklearn.cross_validation import train_test_split # Split the 'features' and 'income' data into training and testing sets X_train, X_test, y_train, y_test = train_test_split(features, income, test_size = 0.2, random_state = 0) # Show the results of the split print "Training set has {} samples.".format(X_train.shape[0]) print "Testing set has {} samples.".format(X_test.shape[0]) # TODO: Calculate accuracy accuracy = 0.2478 # TODO: Calculate F-score using the formula above for beta = 0.5 fscore = (1+0.52)(0.24781)/(((0.52)0.2478)+1) # Print the results print "Naive Predictor: [Accuracy score: {:.4f}, F-score: {:.4f}]".format(accuracy, fscore) # TODO: Import two metrics from sklearn - fbeta_score and accuracy_score from sklearn.metrics import fbeta_score, accuracy_score def train_predict(learner, sample_size, X_train, y_train, X_test, y_test): ''' inputs: - learner: the learning algorithm to be trained and predicted on - sample_size: the size of samples (number) to be drawn from training set - X_train: features training set - y_train: income training set - X_test: features testing set - y_test: income testing set ''' results = {} # TODO: Fit the learner to the training data using slicing with 'sample_size' start = time() # Get start time learner.fit(X_train[:sample_size], y_train[:sample_size]) end = time() # Get end time # TODO: Calculate the training time results['train_time'] = end-start # TODO: Get the predictions on the test set, # then get predictions on the first 300 training samples start = time() # Get start time predictions_test = learner.predict(X_test) predictions_train = learner.predict(X_train[:300]) end = time() # Get end time # TODO: Calculate the total prediction time results['pred_time'] = end-start # TODO: Compute accuracy on the first 300 training samples results['acc_train'] = accuracy_score(y_train[:300],predictions_train) # TODO: Compute accuracy on test set results['acc_test'] = accuracy_score(y_test,predictions_test) # TODO: Compute F-score on the the first 300 training samples results['f_train'] = fbeta_score(y_train[:300],predictions_train, beta = 0.5) # TODO: Compute F-score on the test set results['f_test'] = fbeta_score(y_test,predictions_test,beta =0.5) # Success print "{} trained on {} samples.".format(learner.__class__.__name__, sample_size) # Return the results return results # TODO: Import the three supervised learning models from sklearn from sklearn.naive_bayes import GaussianNB from sklearn.tree import DecisionTreeClassifier from sklearn.svm import SVC # TODO: Initialize the three models clf_A = GaussianNB() clf_B = DecisionTreeClassifier(random_state = 1234) clf_C = SVC(random_state = 1234) # TODO: Calculate the number of samples for 1%, 10%, and 100% of the training data samples_1 = len(X_train)/100 samples_10 = len(X_train)/10 samples_100 = len(X_train)/1 # Collect results on the learners results = {} for clf in [clf_A, clf_B, clf_C]: clf_name = clf.__class__.__name__ results[clf_name] = {} for i, samples in enumerate([samples_1, samples_10, samples_100]): results[clf_name][i] = \ train_predict(clf, samples, X_train, y_train, X_test, y_test) # Run metrics visualization for the three supervised learning models chosen vs.evaluate(results, accuracy, fscore) # TODO: Import 'GridSearchCV', 'make_scorer', and any other necessary libraries from sklearn.model_selection import GridSearchCV from sklearn.metrics import make_scorer # TODO: Initialize the classifier clf = DecisionTreeClassifier(random_state = 1234) # TODO: Create the parameters list you wish to tune parameters = {'max_depth' : range(1,10)} # TODO: Make an fbeta_score scoring object scorer = make_scorer(fbeta_score, beta = 0.5) # TODO: Perform grid search on the classifier using 'scorer' as the scoring method grid_obj = GridSearchCV(clf, parameters,scoring = scorer) # TODO: Fit the grid search object to the training data and find the optimal parameters grid_fit = grid_obj.fit(X_train,y_train) # Get the estimator best_clf = grid_fit.best_estimator_ # Make predictions using the unoptimized and model predictions = (clf.fit(X_train, y_train)).predict(X_test) best_predictions = best_clf.predict(X_test) # Report the before-and-afterscores print "Unoptimized model\n------" print "Accuracy score on testing data: {:.4f}".format(accuracy_score(y_test, predictions)) print "F-score on testing data: {:.4f}".format(fbeta_score(y_test, predictions, beta = 0.5)) print "\nOptimized Model\n------" print "Final accuracy score on the testing data: {:.4f}".format(accuracy_score(y_test, best_predictions)) print "Final F-score on the testing data: {:.4f}".format(fbeta_score(y_test, best_predictions, beta = 0.5)) # TODO: Import a supervised learning model that has 'feature_importances_' # TODO: Train the supervised model on the training set model = DecisionTreeClassifier(random_state = 1234) model.fit(X_train , y_train) # TODO: Extract the feature importances importances = model.feature_importances_ # Plot vs.feature_plot(importances, X_train, y_train) # Import functionality for cloning a model from sklearn.base import clone # Reduce the feature space X_train_reduced = X_train[X_train.columns.values[(np.argsort(importances)[::-1])[:5]]] X_test_reduced = X_test[X_test.columns.values[(np.argsort(importances)[::-1])[:5]]] # Train on the "best" model found from grid search earlier clf = (clone(best_clf)).fit(X_train_reduced, y_train) # Make new predictions reduced_predictions = clf.predict(X_test_reduced) # Report scores from the final model using both versions of data print "Final Model trained on full data\n------" print "Accuracy on testing data: {:.4f}".format(accuracy_score(y_test, best_predictions)) print "F-score on testing data: {:.4f}".format(fbeta_score(y_test, best_predictions, beta = 0.5)) print "\nFinal Model trained on reduced data\n------" print "Accuracy on testing data: {:.4f}".format(accuracy_score(y_test, reduced_predictions)) print "F-score on testing data: {:.4f}".format(fbeta_score(y_test, reduced_predictions, beta = 0.5)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Premade Estimators Step2: The data set Step3: Next, download and parse the Iris data set using Keras and Pandas. Note that you keep distinct datasets for training and testing. Step4: You can inspect your data to see that you have four float feature columns and one int32 label. Step5: For each of the datasets, split out the labels, which the model will be trained to predict. Step6: Overview of programming with Estimators Step8: Your input function may generate the features dictionary and label list any Step9: Define the feature columns Step10: Feature columns can be far more sophisticated than those shown here. You can read more about Feature Columns in this guide. Step11: Train, Evaluate, and Predict Step12: Note that you wrap up your input_fn call in a Step14: Unlike the call to the train method, you did not pass the steps Step15: The predict method returns a Python iterable, yielding a dictionary of	<ASSISTANT_TASK:> Python Code: #@title Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # https://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import tensorflow as tf import pandas as pd CSV_COLUMN_NAMES = ['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth', 'Species'] SPECIES = ['Setosa', 'Versicolor', 'Virginica'] train_path = tf.keras.utils.get_file( "iris_training.csv", "https://storage.googleapis.com/download.tensorflow.org/data/iris_training.csv") test_path = tf.keras.utils.get_file( "iris_test.csv", "https://storage.googleapis.com/download.tensorflow.org/data/iris_test.csv") train = pd.read_csv(train_path, names=CSV_COLUMN_NAMES, header=0) test = pd.read_csv(test_path, names=CSV_COLUMN_NAMES, header=0) train.head() train_y = train.pop('Species') test_y = test.pop('Species') # The label column has now been removed from the features. train.head() def input_evaluation_set(): features = {'SepalLength': np.array([6.4, 5.0]), 'SepalWidth': np.array([2.8, 2.3]), 'PetalLength': np.array([5.6, 3.3]), 'PetalWidth': np.array([2.2, 1.0])} labels = np.array([2, 1]) return features, labels def input_fn(features, labels, training=True, batch_size=256): An input function for training or evaluating # Convert the inputs to a Dataset. dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels)) # Shuffle and repeat if you are in training mode. if training: dataset = dataset.shuffle(1000).repeat() return dataset.batch(batch_size) # Feature columns describe how to use the input. my_feature_columns = [] for key in train.keys(): my_feature_columns.append(tf.feature_column.numeric_column(key=key)) # Build a DNN with 2 hidden layers with 30 and 10 hidden nodes each. classifier = tf.estimator.DNNClassifier( feature_columns=my_feature_columns, # Two hidden layers of 30 and 10 nodes respectively. hidden_units=[30, 10], # The model must choose between 3 classes. n_classes=3) # Train the Model. classifier.train( input_fn=lambda: input_fn(train, train_y, training=True), steps=5000) eval_result = classifier.evaluate( input_fn=lambda: input_fn(test, test_y, training=False)) print('\nTest set accuracy: {accuracy:0.3f}\n'.format(*eval_result)) # Generate predictions from the model expected = ['Setosa', 'Versicolor', 'Virginica'] predict_x = { 'SepalLength': [5.1, 5.9, 6.9], 'SepalWidth': [3.3, 3.0, 3.1], 'PetalLength': [1.7, 4.2, 5.4], 'PetalWidth': [0.5, 1.5, 2.1], } def input_fn(features, batch_size=256): An input function for prediction. # Convert the inputs to a Dataset without labels. return tf.data.Dataset.from_tensor_slices(dict(features)).batch(batch_size) predictions = classifier.predict( input_fn=lambda: input_fn(predict_x)) for pred_dict, expec in zip(predictions, expected): class_id = pred_dict['class_ids'][0] probability = pred_dict['probabilities'][class_id] print('Prediction is "{}" ({:.1f}%), expected "{}"'.format( SPECIES[class_id], 100 probability, expec)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Set parameters Step2: Read epochs for the channel of interest Step3: Find the FieldTrip neighbor definition to setup sensor adjacency Step4: Compute permutation statistic Step5: Note. The same functions work with source estimate. The only differences	<ASSISTANT_TASK:> Python Code: # Authors: Denis Engemann <denis.engemann@gmail.com> # Jona Sassenhagen <jona.sassenhagen@gmail.com> # # License: BSD (3-clause) import numpy as np import matplotlib.pyplot as plt from mpl_toolkits.axes_grid1 import make_axes_locatable import mne from mne.stats import spatio_temporal_cluster_test from mne.datasets import sample from mne.channels import find_ch_adjacency from mne.viz import plot_compare_evokeds print(__doc__) data_path = sample.data_path() raw_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw.fif' event_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif' event_id = {'Aud/L': 1, 'Aud/R': 2, 'Vis/L': 3, 'Vis/R': 4} tmin = -0.2 tmax = 0.5 # Setup for reading the raw data raw = mne.io.read_raw_fif(raw_fname, preload=True) raw.filter(1, 30, fir_design='firwin') events = mne.read_events(event_fname) picks = mne.pick_types(raw.info, meg='mag', eog=True) reject = dict(mag=4e-12, eog=150e-6) epochs = mne.Epochs(raw, events, event_id, tmin, tmax, picks=picks, baseline=None, reject=reject, preload=True) epochs.drop_channels(['EOG 061']) epochs.equalize_event_counts(event_id) X = [epochs[k].get_data() for k in event_id] # as 3D matrix X = [np.transpose(x, (0, 2, 1)) for x in X] # transpose for clustering adjacency, ch_names = find_ch_adjacency(epochs.info, ch_type='mag') print(type(adjacency)) # it's a sparse matrix! plt.imshow(adjacency.toarray(), cmap='gray', origin='lower', interpolation='nearest') plt.xlabel('{} Magnetometers'.format(len(ch_names))) plt.ylabel('{} Magnetometers'.format(len(ch_names))) plt.title('Between-sensor adjacency') # set cluster threshold threshold = 50.0 # very high, but the test is quite sensitive on this data # set family-wise p-value p_accept = 0.01 cluster_stats = spatio_temporal_cluster_test(X, n_permutations=1000, threshold=threshold, tail=1, n_jobs=1, buffer_size=None, adjacency=adjacency) T_obs, clusters, p_values, _ = cluster_stats good_cluster_inds = np.where(p_values < p_accept)[0] # configure variables for visualization colors = {"Aud": "crimson", "Vis": 'steelblue'} linestyles = {"L": '-', "R": '--'} # organize data for plotting evokeds = {cond: epochs[cond].average() for cond in event_id} # loop over clusters for i_clu, clu_idx in enumerate(good_cluster_inds): # unpack cluster information, get unique indices time_inds, space_inds = np.squeeze(clusters[clu_idx]) ch_inds = np.unique(space_inds) time_inds = np.unique(time_inds) # get topography for F stat f_map = T_obs[time_inds, ...].mean(axis=0) # get signals at the sensors contributing to the cluster sig_times = epochs.times[time_inds] # create spatial mask mask = np.zeros((f_map.shape[0], 1), dtype=bool) mask[ch_inds, :] = True # initialize figure fig, ax_topo = plt.subplots(1, 1, figsize=(10, 3)) # plot average test statistic and mark significant sensors f_evoked = mne.EvokedArray(f_map[:, np.newaxis], epochs.info, tmin=0) f_evoked.plot_topomap(times=0, mask=mask, axes=ax_topo, cmap='Reds', vmin=np.min, vmax=np.max, show=False, colorbar=False, mask_params=dict(markersize=10)) image = ax_topo.images[0] # create additional axes (for ERF and colorbar) divider = make_axes_locatable(ax_topo) # add axes for colorbar ax_colorbar = divider.append_axes('right', size='5%', pad=0.05) plt.colorbar(image, cax=ax_colorbar) ax_topo.set_xlabel( 'Averaged F-map ({:0.3f} - {:0.3f} s)'.format(*sig_times[[0, -1]])) # add new axis for time courses and plot time courses ax_signals = divider.append_axes('right', size='300%', pad=1.2) title = 'Cluster #{0}, {1} sensor'.format(i_clu + 1, len(ch_inds)) if len(ch_inds) > 1: title += "s (mean)" plot_compare_evokeds(evokeds, title=title, picks=ch_inds, axes=ax_signals, colors=colors, linestyles=linestyles, show=False, split_legend=True, truncate_yaxis='auto') # plot temporal cluster extent ymin, ymax = ax_signals.get_ylim() ax_signals.fill_betweenx((ymin, ymax), sig_times[0], sig_times[-1], color='orange', alpha=0.3) # clean up viz mne.viz.tight_layout(fig=fig) fig.subplots_adjust(bottom=.05) plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Set parameters Step2: Read epochs for all channels, removing a bad one Step3: Transform to source space Step4: Transform to common cortical space Step5: It's a good idea to spatially smooth the data, and for visualization Step6: Now we need to prepare the group matrix for the ANOVA statistic. To make the Step7: Prepare function for arbitrary contrast Step8: Finally we will pick the interaction effect by passing 'A Step9: A stat_fun must deal with a variable number of input arguments. Step10: Compute clustering statistic Step11: Visualize the clusters Step12: Finally, let's investigate interaction effect by reconstructing the time	<ASSISTANT_TASK:> Python Code: # Authors: Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr> # Eric Larson <larson.eric.d@gmail.com> # Denis Engemannn <denis.engemann@gmail.com> # # License: BSD (3-clause) import os.path as op import numpy as np from numpy.random import randn import matplotlib.pyplot as plt import mne from mne import (io, spatial_tris_connectivity, compute_morph_matrix, grade_to_tris) from mne.stats import (spatio_temporal_cluster_test, f_threshold_mway_rm, f_mway_rm, summarize_clusters_stc) from mne.minimum_norm import apply_inverse, read_inverse_operator from mne.datasets import sample print(__doc__) data_path = sample.data_path() raw_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw.fif' event_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif' subjects_dir = data_path + '/subjects' tmin = -0.2 tmax = 0.3 # Use a lower tmax to reduce multiple comparisons # Setup for reading the raw data raw = io.read_raw_fif(raw_fname) events = mne.read_events(event_fname) raw.info['bads'] += ['MEG 2443'] picks = mne.pick_types(raw.info, meg=True, eog=True, exclude='bads') # we'll load all four conditions that make up the 'two ways' of our ANOVA event_id = dict(l_aud=1, r_aud=2, l_vis=3, r_vis=4) reject = dict(grad=1000e-13, mag=4000e-15, eog=150e-6) epochs = mne.Epochs(raw, events, event_id, tmin, tmax, picks=picks, baseline=(None, 0), reject=reject, preload=True) # Equalize trial counts to eliminate bias (which would otherwise be # introduced by the abs() performed below) epochs.equalize_event_counts(event_id) fname_inv = data_path + '/MEG/sample/sample_audvis-meg-oct-6-meg-inv.fif' snr = 3.0 lambda2 = 1.0 / snr ** 2 method = "dSPM" # use dSPM method (could also be MNE or sLORETA) inverse_operator = read_inverse_operator(fname_inv) # we'll only use one hemisphere to speed up this example # instead of a second vertex array we'll pass an empty array sample_vertices = [inverse_operator['src'][0]['vertno'], np.array([], int)] # Let's average and compute inverse, then resample to speed things up conditions = [] for cond in ['l_aud', 'r_aud', 'l_vis', 'r_vis']: # order is important evoked = epochs[cond].average() evoked.resample(50, npad='auto') condition = apply_inverse(evoked, inverse_operator, lambda2, method) # Let's only deal with t > 0, cropping to reduce multiple comparisons condition.crop(0, None) conditions.append(condition) tmin = conditions[0].tmin tstep = conditions[0].tstep n_vertices_sample, n_times = conditions[0].lh_data.shape n_subjects = 7 print('Simulating data for %d subjects.' % n_subjects) # Let's make sure our results replicate, so set the seed. np.random.seed(0) X = randn(n_vertices_sample, n_times, n_subjects, 4) * 10 for ii, condition in enumerate(conditions): X[:, :, :, ii] += condition.lh_data[:, :, np.newaxis] fsave_vertices = [np.arange(10242), np.array([], int)] # right hemi is empty morph_mat = compute_morph_matrix('sample', 'fsaverage', sample_vertices, fsave_vertices, 20, subjects_dir) n_vertices_fsave = morph_mat.shape[0] # We have to change the shape for the dot() to work properly X = X.reshape(n_vertices_sample, n_times * n_subjects * 4) print('Morphing data.') X = morph_mat.dot(X) # morph_mat is a sparse matrix X = X.reshape(n_vertices_fsave, n_times, n_subjects, 4) X = np.transpose(X, [2, 1, 0, 3]) # X = [np.squeeze(x) for x in np.split(X, 4, axis=-1)] factor_levels = [2, 2] effects = 'A:B' # Tell the ANOVA not to compute p-values which we don't need for clustering return_pvals = False # a few more convenient bindings n_times = X[0].shape[1] n_conditions = 4 def stat_fun(args): return f_mway_rm(np.swapaxes(args, 1, 0), factor_levels=factor_levels, effects=effects, return_pvals=return_pvals)[0] # get f-values only. source_space = grade_to_tris(5) # as we only have one hemisphere we need only need half the connectivity lh_source_space = source_space[source_space[:, 0] < 10242] print('Computing connectivity.') connectivity = spatial_tris_connectivity(lh_source_space) # Now let's actually do the clustering. Please relax, on a small # notebook and one single thread only this will take a couple of minutes ... pthresh = 0.0005 f_thresh = f_threshold_mway_rm(n_subjects, factor_levels, effects, pthresh) # To speed things up a bit we will ... n_permutations = 128 # ... run fewer permutations (reduces sensitivity) print('Clustering.') T_obs, clusters, cluster_p_values, H0 = clu = \ spatio_temporal_cluster_test(X, connectivity=connectivity, n_jobs=1, threshold=f_thresh, stat_fun=stat_fun, n_permutations=n_permutations, buffer_size=None) # Now select the clusters that are sig. at p < 0.05 (note that this value # is multiple-comparisons corrected). good_cluster_inds = np.where(cluster_p_values < 0.05)[0] print('Visualizing clusters.') # Now let's build a convenient representation of each cluster, where each # cluster becomes a "time point" in the SourceEstimate stc_all_cluster_vis = summarize_clusters_stc(clu, tstep=tstep, vertices=fsave_vertices, subject='fsaverage') # Let's actually plot the first "time point" in the SourceEstimate, which # shows all the clusters, weighted by duration subjects_dir = op.join(data_path, 'subjects') # The brighter the color, the stronger the interaction between # stimulus modality and stimulus location brain = stc_all_cluster_vis.plot(subjects_dir=subjects_dir, colormap='mne', views='lateral', time_label='Duration significant (ms)') brain.save_image('cluster-lh.png') brain.show_view('medial') inds_t, inds_v = [(clusters[cluster_ind]) for ii, cluster_ind in enumerate(good_cluster_inds)][0] # first cluster times = np.arange(X[0].shape[1]) tstep * 1e3 plt.figure() colors = ['y', 'b', 'g', 'purple'] event_ids = ['l_aud', 'r_aud', 'l_vis', 'r_vis'] for ii, (condition, color, eve_id) in enumerate(zip(X, colors, event_ids)): # extract time course at cluster vertices condition = condition[:, :, inds_v] # normally we would normalize values across subjects but # here we use data from the same subject so we're good to just # create average time series across subjects and vertices. mean_tc = condition.mean(axis=2).mean(axis=0) std_tc = condition.std(axis=2).std(axis=0) plt.plot(times, mean_tc.T, color=color, label=eve_id) plt.fill_between(times, mean_tc + std_tc, mean_tc - std_tc, color='gray', alpha=0.5, label='') ymin, ymax = mean_tc.min() - 5, mean_tc.max() + 5 plt.xlabel('Time (ms)') plt.ylabel('Activation (F-values)') plt.xlim(times[[0, -1]]) plt.ylim(ymin, ymax) plt.fill_betweenx((ymin, ymax), times[inds_t[0]], times[inds_t[-1]], color='orange', alpha=0.3) plt.legend() plt.title('Interaction between stimulus-modality and location.') plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The strategy, unlike our first attempt, requires a real train/test split in the dataset because we're going to fit an actual model (although a true LOO cross validation is still of course possible). But we need a train_test_split function which is able ot deal with lists of NetworkX objects. Step2: First Classifier Step3: Finding Optimal Hyperparameters	<ASSISTANT_TASK:> Python Code: import numpy as np import networkx as nx import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import cPickle as pickle from copy import deepcopy from sklearn.utils import shuffle import sklearn_mmadsen.graphs as skmg %matplotlib inline plt.style.use("fivethirtyeight") sns.set() all_graphs = pickle.load(open("train-sc-4-5-cont-graphs.pkl",'r')) all_labels = pickle.load(open("train-sc-4-5-cont-labels.pkl",'r')) train_graphs, train_labels, test_graphs, test_labels = skmg.graph_train_test_split(all_graphs, all_labels, test_fraction=0.10) print "train size: %s" % len(train_graphs) print "test size: %s" % len(test_graphs) from sklearn.ensemble import GradientBoostingClassifier from sklearn.metrics import accuracy_score, classification_report, confusion_matrix train_matrix = skmg.graphs_to_eigenvalue_matrix(train_graphs, num_eigenvalues=10) test_matrix = skmg.graphs_to_eigenvalue_matrix(test_graphs, num_eigenvalues=10) clf = GradientBoostingClassifier(n_estimators = 250) clf.fit(train_matrix, train_labels) pred_label = clf.predict(test_matrix) cm = confusion_matrix(test_labels, pred_label) cmdf = pd.DataFrame(cm) cmdf.columns = map(lambda x: 'predicted {}'.format(x), cmdf.columns) cmdf.index = map(lambda x: 'actual {}'.format(x), cmdf.index) print cmdf print classification_report(test_labels, pred_label) print "Accuracy on test: %0.3f" % accuracy_score(test_labels, pred_label) from sklearn.pipeline import Pipeline from sklearn.grid_search import GridSearchCV pipeline = Pipeline([ ('clf', GradientBoostingClassifier()) ]) params = { 'clf__learning_rate': [5.0,2.0,1.0, 0.75, 0.5, 0.25, 0.1, 0.05, 0.01], 'clf__n_estimators': [10,25,50,100,250,500] } grid_search = GridSearchCV(pipeline, params, n_jobs = -1, verbose = 1) grid_search.fit(train_matrix, train_labels) print("Best score: %0.3f" % grid_search.best_score_) print("Best parameters:") best_params = grid_search.best_estimator_.get_params() for param in sorted(params.keys()): print("param: %s: %r" % (param, best_params[param])) pred_label = grid_search.predict(test_matrix) cm = confusion_matrix(test_labels, pred_label) cmdf = pd.DataFrame(cm) cmdf.columns = map(lambda x: 'predicted {}'.format(x), cmdf.columns) cmdf.index = map(lambda x: 'actual {}'.format(x), cmdf.index) print cmdf print classification_report(test_labels, pred_label) print "Accuracy on test: %0.3f" % accuracy_score(test_labels, pred_label) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Class1 Step2: Morphology of the neurons Step3: Feature of interneuron Step4: Feature of Pyramidal Step5: Sholl Diagram Step6: histogram of diameters Step7: Histogram of Slope of each segments Step8: Histogram of distance from soma Step9: Local Angle Step10: Global Angle Step11: Angle at the branching point Step12: Rall Ratio Step13: Slope Step14: distance from parent Step15: Ratio of neuronal distance over Euclidian distance from root Step16: Connectivity matrix	<ASSISTANT_TASK:> Python Code: import numpy as np import McNeuron import matplotlib.pyplot as plt %matplotlib inline #loc1 = "/Volumes/Arch/Projects/Computational Anatomy/neuron_nmo/poorthuis/CNG version/060110-LII-III.CNG.swc" loc1 = "../Generative-Models-of-Neuron-Morphology/Data/Pyramidal/poorthuis/CNG version/060110-LV.CNG.swc" loc2 = "../Generative-Models-of-Neuron-Morphology/Data/Interneuron/allen cell types/CNG version/Pvalb-IRES-Cre-Ai14-475465561.CNG.swc" pyramidal = McNeuron.Neuron(file_format = 'swc', input_file=loc1) inter = McNeuron.Neuron(file_format = 'swc', input_file=loc2) a = pyramidal.subsample(20.) McNeuron.visualize.plot_2D(a,show_radius=True) print len(a.nodes_list) a.show_features(15,17,30) btmorph3.visualize.plot_2D(inter,show_radius=False) len(inter.nodes_list) ax1 = McNeuron.visualize.plot_2D(pyramidal, show_radius=False) ax2 = McNeuron.visualize.plot_2D(inter, show_radius=False) inter.show_features(15,17,30) pyramidal.show_features(15,17,50) f,(ax1, ax2) = plt.subplots(1, 2) ax1.plot(pyramidal.sholl_r,pyramidal.sholl_n,'g') ax2.plot(inter.sholl_r,inter.sholl_n,'m') inter.features f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.diameter1 b = pyramidal.distance_from_root c = ax1.hist(a[b>20],bins = 30,color = 'g') ax1.set_xlabel('diameter (um3)') ax1.set_ylabel('density') #ax1.set_title('Histogram of the size of compartments of neuron') a = inter.diameter b = inter.distance_from_root c = ax2.hist(a[b>20],bins = 15,color = 'm') ax2.set_xlabel('diameter (um3)') #ax2.set_ylabel('density') #ax2.set_title('Histogram of the size of compartments of neuron') a = inter.diameter b = inter.distance_from_root c = plt.hist(a[b>20],bins = 15,color = 'm') plt.xlabel('diameter (um3)') f, (ax1, ax2) = plt.subplots(1, 2) e = pyramidal.slope x = ax1.hist(e[e!=0],bins=40,color = 'g') ax1.set_xlabel('Value of Slope') ax1.set_ylabel('density') e = inter.slope x = ax2.hist(e[e!=0],bins=40,color = 'm') ax2.set_xlabel('Value of Slope') #ax2.set_ylabel('density') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.distance_from_root b = ax1.hist(a[~np.isnan(a)],bins = 50,color = 'g') ax1.set_xlabel('distance (um)') ax1.set_ylabel('density') #plt.title('Histogram of distance from soma for different compartments of neuron') a = inter.distance_from_root b = ax2.hist(a[~np.isnan(a)],bins = 50,color = 'm') ax2.set_xlabel('distance (um)') #ax2.set_ylabel('density') #plt.title('Histogram of distance from soma for different compartments of neuron') a = inter.distance_from_root b = plt.hist(a[~np.isnan(a)],bins = 50,color = 'm') plt.xlabel('distance (um)') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.local_angle b = ax1.hist(a[~np.isnan(a)],bins = 50,color = 'g') ax1.set_xlabel('angle (radian)') ax1.set_ylabel('density') #plt.title('Histogram of local angles') a = inter.local_angle b = ax2.hist(a[~np.isnan(a)],bins = 50,color = 'm') ax2.set_xlabel('angle (radian)') #ax2.set_ylabel('density') a = inter.local_angle b = plt.hist(a[~np.isnan(a)],bins = 50,color = 'm') plt.xlabel('angle (radian)') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.angle_global b = ax1.hist(a[~np.isnan(a)],bins = 50,color = 'g') ax1.set_xlabel('angle (radian)') ax1.set_ylabel('density') #plt.title('Histogram of global angles') a = inter.angle_global b = ax2.hist(a[~np.isnan(a)],bins = 50,color = 'm') ax2.set_xlabel('angle (radian)') a = inter.angle_global b = plt.hist(a[~np.isnan(a)],bins = 50,color = 'm') plt.xlabel('angle (radian)') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.angle_branch[0,:] b = ax1.hist(a[~np.isnan(a)],bins = 20,color = 'g') a = inter.angle_branch[0,:] b = ax2.hist(a[~np.isnan(a)],bins = 20,color = 'm') a = inter.angle_branch[0,:] b = plt.hist(a[~np.isnan(a)],bins = 10,color = 'm') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.rall_ratio b = ax1.hist(a[~np.isnan(a)],bins = 20,color = 'g') a = inter.rall_ratio b = ax2.hist(a[~np.isnan(a)],bins = 20,color = 'm') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.slope b = ax1.hist(a[~np.isnan(a)],bins = 40,color = 'g') a = inter.slope b = ax2.hist(a[~np.isnan(a)],bins = 40,color = 'm') a = inter.slope b = plt.hist(a[~np.isnan(a)],bins = 40,color = 'm') f, (ax1, ax2) = plt.subplots(1, 2) a = pyramidal.length_to_parent b = ax1.hist(a[~np.isnan(a)],bins = 40,color = 'g') a = inter.length_to_parent b = ax2.hist(a[~np.isnan(a)],bins = 40,color = 'm') a = inter.length_to_parent b = a[~np.isnan(a)] c = plt.hist(b[np.absolute(b)<4],bins = 70,color = 'm') np.absolute(b)<3 f, (ax1, ax2) = plt.subplots(1, 2) ax1.hist(inter.overall_connectivity_matrix.sum(axis = 1)/inter.distance_from_root,bins = 40,color = 'g') ax2.hist(pyramidal.overall_connectivity_matrix.sum(axis = 1)/pyramidal.distance_from_root,bins = 40,color = 'g') plt.hist(inter.features['ratio_euclidian_neuronal'],bins = 40,color = 'g') import matplotlib.pyplot as plt %matplotlib inline plt.imshow(inter.connection) plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Importez les modules Step2: Planche 160 Step3: On conjecture que $I_n$ est décroissante. C'est évident puisque si on note $f_n(t)$ son intégrande, on observe que $f_{n+1}(t) \leq f_n(t)$ pour tout $t$, et donc par monotonie de l'intégrale, $I_{n+1} \leq I_n$. Step4: Ce qu'on observe permet de conjecturer que $\alpha=1$ est l'unique entier tel que $n^{\alpha} I_n$ converge vers une limite non nulle. Step5: On en déduit qu'il en est de même pour $J_n$, on a $n^{\alpha} J_n \to l$ la même limite que $n^{\alpha} I_n$. Step6: Puis rapidement, on montre que $\forall x \geq 0, \ln(1 + x) \geq \frac{x}{1+x}$. Ca peut se prouver de plein de façons différentes, mais par exemple on écrit $f(x) = (x+1) \log(x+1) - x$ qui est de classe $\mathcal{C}^1$, et on la dérive. $f'(x) = \log(x+1) + 1 - 1 > 0$ donc $f$ est croissante, et $f(0) = 0$ donc $f(x) \geq f(0) = 0$ pour tout $x \geq 0$. Step7: Planche 162 Step8: Pas besoin de lire le maximum sur un graphique Step9: On affiche la fonction, comme demandé, avec un titre Step10: Pour calculer l'intégrale, on utilise scipy.integrate.quad Step11: On vérifie avant de se lancer dans l'affichage Step12: $S_n(x)$ semble diverger pour $x\to2^-$ quand $n\to\infty$. Step13: Ici, un ne peut pas être utilisé comme une fonction "numpy" qui travaille sur un tableau, on stocke donc les valeurs "plus manuellement" Step14: La suite $u_n$ semble être croissante (on peut le prouver), toujours plus petite que $1$ (se prouve facilement aussi, $I_{n+1} < I_n$), et semble converger. Step15: Pour conclure, on peut prouver que la suite est monotone et bornée, donc elle converge. Step16: Avant de s'en servir pour simuler plein de trajectoirs, on peut vérifier Step17: En 100 coups, on commence à ne plus voir de tendance Step18: Pour l'histogramme, on triche un peu en utilisant numpy.bincount. Mais on peut le faire à la main très simplement ! Step19: On va afficher des histogrammes Step20: On s'approche d'une distribution uniforme ! Step21: On a besoin d'éliminer les erreurs d'arrondis, mais on voit que $1$ est valeur propre, associée au vecteur $[1,\dots,1,\dots,1]$ avec un $1$ seulement à la 8ème composante. Step22: $P$ n'est pas diagonalisable, à prouver au tableau si l'examinateur le demande. Step23: Soit $g(x) = 2 - \exp(x)$, telle que $g(x) f(x) = 1$. En dérivant $n > 0$ fois cette identité et en utilisant la formule de Leibniz, on trouve Step24: On observe que $a(n)$ est comprise entre $\frac{1}{2(\log(2))^n}$ et $\frac{1}{\log(2)^n}$, donc le rayon de convergence de $S(x) = \sum a(n) x^n$ est $\log(2)$. Step25: On peut vérifie que notre fonction marche Step26: <span style="color Step27: Planche 170 Step28: On peut vérifier le prognostic quant à la somme de la série $\sum u_n$ Step29: Avec seulement $50$ termes, on a moins de $1.5\%$ d'erreur relative, c'est déjà pas mal ! Step30: Pour $e = (e_n){n\in\mathbb{N}}$ une suite de nombres égaux à $0$ ou $1$ (i.e., $\forall n, e_n \in {0,1}$, $S_n(e) = \sum{i=0}^n e_i u_i$ est bornée entre $0$ et $\sum{i=0}^n u_i$. Et $u_n \sim \frac{1}{n(n+1)}$ qui est le terme général d'une série convergente (par critère de Cauchy, par exemple, avec $\alpha=2$). Donc la série $\sum u_n$ converge et donc par encadrement, $S_n(e)$ converge pour $n\to\infty$, i.e., $S(e)$ converge. Ces justifications donnent aussi que $$0 \leq S(e) \leq \sum_{n\geq0} u_n = \lim_{n\to\infty} \arctan(n) - \arctan(0) = \frac{\pi}{2}.$$ Step31: Pour inverser la fonction, et trouver la suite $e$ telle que $S(e) = x$ pour un $x$ donné, il faut réfléchir un peu plus. Step33: Ca suffit pour la partie Python. Step34: D'abord, on écrit une fonction pour simuler l'événement aléatoire Step35: Par exemple, pour seulement $2$ lancés, on a $1 - p_n = p^2$ car $\overline{E_n}$ est l'événement d'obtenir $2$ piles qui est de probabilité $p^2$. Step36: Avec $4$ lancés, on a $p_n$ bien plus petit. Step37: On vérifie que $p_n(n, p)$ est décroissante en $p$, à $n$ fixé Step38: On vérifie que $p_n(n, p)$ est décroissante en $n$, à $p$ fixé Step39: Notons que la suite semble converger ? Ou alors elle décroit de moins en moins rapidement. Step40: L'intégrale $g(t) = \int_0^x \frac{\ln(1 - t)}{t} \mathrm{d}t$ est bien défine sur $D = [-1, 1]$ puisque son intégrande existe, est continue et bien intégrable sur tout interval de la forme $]a, 0[$ ou $]0, b[$ pour $-1 < a < 0$ ou $0 < b < 1$. Le seul point qui peut déranger l'intégrabilité est en $0$, mais $\ln(1-t) \sim t$ quand $t\to0$ donc l'intégrande est $\sim 1$ en $0^-$ et $0^+$ et donc est bien intégrable. De plus, comme "intégrale de la borne supérieure" d'une fonction continue, $g$ est dérivable sur l'intérieur de son domaine, i.e., sur $]-1, 1[$. Step41: On visualise les deux fonctions $f$ et $g$ sur le domaine $D$	<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib as mpl mpl.rcParams['figure.figsize'] = (10, 7) import matplotlib.pyplot as plt from scipy import integrate import numpy.random as rd import seaborn as sns sns.set(context="notebook", style="whitegrid", palette="hls", font="sans-serif", font_scale=1.1) import numpy as np import matplotlib.pyplot as plt from scipy import integrate import numpy.random as rd def I(n): def f(t): return 1 / ((1+t)*n np.sqrt(1-t)) i, err = integrate.quad(f, 0, 1) return i def J(n): def f(t): return 1 / ((1+t)*n np.sqrt(1-t)) i, err = integrate.quad(f, 0, 0.5) return i valeurs_n = np.arange(1, 50) valeurs_In = np.array([I(n) for n in valeurs_n]) plt.figure() plt.plot(valeurs_n, valeurs_In, 'ro') plt.title("Valeurs de $I_n$") plt.show() plt.figure() plt.plot(np.log(valeurs_n), np.log(valeurs_In), 'go') plt.title(r"Valeurs de $\ln(I_n)$ en fonction de $\ln(n)$") plt.show() valeurs_n = np.arange(1, 500) valeurs_In = np.array([I(n) for n in valeurs_n]) valeurs_Jn = np.array([J(n) for n in valeurs_n]) alpha = 0.9 plt.figure() plt.plot(valeurs_n, valeurs_n*alpha valeurs_In, 'r+', label=r'$n^{\alpha} I_n$') plt.plot(valeurs_n, valeurs_n*alpha valeurs_Jn, 'b+', label=r'$n^{\alpha} J_n$') plt.legend() plt.title(r"Valeurs de $n^{\alpha} I_n$ et $n^{\alpha} J_n$") plt.show() plt.figure() plt.plot(valeurs_n, valeurs_n*alpha (valeurs_In - valeurs_Jn), 'g+', label=r'$n^{\alpha} (I_n - J_n)$') plt.legend() plt.title(r"Valeurs de $n^{\alpha} (I_n - J_n)$") plt.show() X = np.linspace(0, 100, 1000) plt.plot(X, np.log(1 + X), 'ro-', label=r'$\log(1+x)$', markevery=50) plt.plot(X, X / (1 + X), 'b+-', label=r'$\frac{x}{1+x}$', markevery=50) plt.legend() plt.title("Comparaison entre deux fonctions") plt.show() def f(x): return x * (1 - x) * (1 + np.cos(5 * np.pi * x)) Xs = np.linspace(0, 1, 2000) Ys = f(Xs) M = max_de_f = max(Ys) print("Sur [0, 1], avec 2000 points, le maximum de f(x) est M =", M) i_maximisant_f = np.argmax(Ys) x_maximisant_f = Xs[i_maximisant_f] print("Sur ces 2000 points, le maximum est atteint en x =", x_maximisant_f) plt.figure() plt.plot(Xs, Ys) plt.vlines(x_maximisant_f, min(Ys), max(Ys), color="b", linestyles="dotted") plt.hlines(max(Ys), min(Xs), max(Xs), color="b", linestyles="dotted") plt.title("Fonction $f(x)$ sur $[0,1]$") plt.show() def In(x, n): def fn(x): return f(x) ** n return integrate.quad(fn, 0, 1)[0] def Sn(x): return np.sum([In(Xs, n) * x*n for n in range(0, n+1)], axis=0) for n in range(10): print("In(x,", n, ") =", In(Xs, n)) a = 1/M + 0.1 X2s = np.linspace(-a, a, 2000) plt.figure() for n in [10, 20, 30, 40, 50]: plt.plot(X2s, Sn(X2s), "-+", label="n =" + str(n), markevery=20) plt.legend() plt.show() def un(n): return In(Xs, n + 1) / In(Xs, n) for n in range(10): print("un =", un(n), "pour n =", n) def affiche_termes_un(N): valeurs_un = [0] N for n in range(N): valeurs_un[n] = un(n) plt.figure() plt.plot(valeurs_un, 'o-') plt.title("Suite $u_n$") plt.grid(True) plt.show() affiche_termes_un(30) affiche_termes_un(100) case_max = 12 univers = list(range(case_max)) def prochaine_case(case): return (case + rd.randint(1, 6+1)) % case_max def Yn(duree, depart=0): case = depart for coup in range(duree): case = prochaine_case(case) return case [Yn(1) for _ in range(10)] [Yn(100) for _ in range(10)] observations = [Yn(100) for _ in range(10)] print(observations) np.bincount(observations, minlength=case_max) def histogramme(duree, repetitions=5000): cases = [Yn(duree) for _ in range(repetitions)] frequences = np.bincount(cases, minlength=case_max) # aussi a la main si besoin frequences = [0] * case_max for case in cases: frequences[case] += 1 return frequences / np.sum(frequences) histogramme(50) def voir_histogramme(valeurs_n): for n in valeurs_n: plt.figure() plt.bar(np.arange(case_max), histogramme(n)) plt.title("Histogramme de cases visitées en " + str(n) + " coups") plt.show() voir_histogramme([1, 2, 3, 50, 100, 200]) case_max = 12 P = np.zeros((case_max, case_max)) for k in range(case_max): for i in range(k - 6, k): P[k, i] = 1/6 P import numpy.linalg as LA spectre, vecteur_propres = LA.eig(P) np.round(spectre,10) np.round(vecteur_propres[0]) def f(x): return 1 / (2 - np.exp(x)) from math import factorial def a_0an(nMax): valeurs_a = np.zeros(nMax+1) valeurs_a[0] = 1.0 for n in range(1, nMax+1): valeurs_a[n] = sum(valeurs_a[n-k] / factorial(k) for k in range(1, n+1)) return valeurs_a nMax = 10 valeurs_n = np.arange(0, nMax + 1) valeurs_a = a_0an(nMax) for n in valeurs_n: print("Pour n =", n, "on a a(n) =", valeurs_a[n]) plt.figure() plt.plot(valeurs_n, valeurs_a, 'ro-', label=r'$a(n)$', markersize=12) plt.plot(valeurs_n, 1 / np.log(2)*valeurs_n, 'g+-', label=r'$1/\log(2)^n$') plt.plot(valeurs_n, 1 / (2 np.log(2)*valeurs_n), 'bd-', label=r'$1/(2\log(2)^n)$') plt.title("$a(n)$ et deux autres suites") plt.legend() plt.show() def Sn(x, n): valeurs_a = a_0an(n) return sum(valeurs_a[k] x*k for k in range(0, n + 1)) x = 0.5 for n in range(0, 6 + 1): print("Pour n =", n, "S_n(x) =", Sn(x, n)) valeurs_x = np.linspace(0, 0.5, 1000) valeurs_f = f(valeurs_x) plt.figure() for n in range(0, 6 + 1): valeurs_Sn = [] for x in valeurs_x: valeurs_Sn.append(Sn(x, n)) plt.plot(valeurs_x, valeurs_Sn, 'o:', label='$S_' + str(n) + '(x)$', markevery=50) plt.plot(valeurs_x, valeurs_f, '+-', label='$f(x)$', markevery=50) plt.title("$f(x)$ et $S_n(x)$ pour $n = 0$ à $n = 6$") plt.legend() plt.show() def u(n): return np.arctan(n+1) - np.arctan(n) valeurs_n = np.arange(50) valeurs_u = u(valeurs_n) plt.figure() plt.plot(valeurs_n, valeurs_u, "o-") plt.xlabel("Entier $n$") plt.ylabel("Valeur $u_n$") plt.title("Premières valeurs de $u_n$") pi/2 sum(valeurs_u) somme_serie = pi/2 somme_partielle = sum(valeurs_u) erreur_relative = abs(somme_partielle - somme_serie) / somme_serie erreur_relative valeurs_n = np.arange(10, 1000) valeurs_u = u(valeurs_n) valeurs_equivalents = 1 / (valeurs_n (valeurs_n + 1)) plt.figure() plt.plot(valeurs_n, valeurs_u / valeurs_equivalents, "-") plt.xlabel("Entier $n$") plt.title(r"Valeurs de $u_n / \frac{1}{n(n+1)}$") from math import ceil, sqrt, pi def Se(e, delta=1e-5, borne_sur_n_0=10000): borne_sur_n_1 = int(ceil(1 + sqrt(delta)/2.0)) borne_sur_n = max(borne_sur_n_0, borne_sur_n_1) somme_partielle = 0 for n in range(0, borne_sur_n + 1): somme_partielle += e(n) * u(n) return somme_partielle def e010101(n): return 1 if n % 2 == 0 else 0 delta = 1e-5 Se010101 = Se(e010101, delta) print("Pour delta =", delta, "on a Se010101(delta) ~=", round(Se010101, 5)) def inverse_Se(x, n): assert 0 < x < pi/2.0, "Erreur : x doit être entre 0 et pi/2 strictement." print("Je vous laisse chercher.") raise NotImplementedError from random import random def pile(proba): True si pile, False si face (false, face, facile à retenir). return random() < proba def En(n, p): lance = pile(p) for i in range(n - 1): nouveau_lance = pile(p) if lance and nouveau_lance: return False nouveau_lance = lance return True import numpy as np lances = [ En(2, 0.5) for _ in range(100) ] np.bincount(lances) def pn(n, p, nbSimulations=100000): return np.mean([ En(n, p) for _ in range(nbSimulations) ]) pn(2, 0.5) pn(4, 0.5) pn(4, 0.1) pn(4, 0.9) pn(6, 0.2) pn(20, 0.2) pn(100, 0.2) from math import floor, log, pi delta = 1e-5 def f(x): if x == 0: return 0 borne_sur_n = int(floor(log((6/pi*2 delta), abs(x)) - 1)) somme_partielle = 0 for n in range(1, borne_sur_n + 1): somme_partielle += xn / n2 return somme_partielle for x in [-0.75, -0.5, 0.25, 0, 0.25, 0.5, 0.75]: print("Pour x =", x, "\tf(x) =", round(f(x), 5)) from scipy import integrate def g(x): def h(t): return log(1 - t) / t integrale, erreur = integrate.quad(h, 0, x) return integrale import numpy as np import matplotlib.pyplot as plt domaine = np.linspace(-0.99, 0.99, 1000) valeurs_f = [f(x) for x in domaine] valeurs_g = [g(x) for x in domaine] plt.figure() plt.plot(domaine, valeurs_f, "+-", label="$f(x)$", markevery=50) plt.plot(domaine, valeurs_g, "+-", label="$g(x)$", markevery=50) plt.legend() plt.grid() plt.title("Représentation de $f(x)$ et $g(x)$") plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: A continuación mostramos los paquetes que usaremos regularmente para tratar datos, pandas, numpy, matplotlib. Al ser un programa en Python, se pueden importar paquetes que seguirán siendo válidos hasta el final del notebook. Step2: Lo siguiente hace que los gráficos se muestren inline. Para figuras pequeñas se puede utilizar unas figuras interactivas que permiten zoom, usando %maplotlib nbagg. Step3: Numpy Step4: Numpy permite generar y procesar arrays de datos de forma muy eficiente. A continuación se muestran algunos ejemplos Step5: También arrays multidimensionales Step6: Se pueden aplicar funciones sobre todo el array o matriz, y el resultado será una matriz idéntica con el operador aplicado. Similar a lo que ocurre con la operación map de algunos lenguajes de programación (incluído Python) Step7: También se pueden filtrar los elementos de un array o matriz que cumplan una condición. Para eso se utiliza el operador de indización ([]) con una expresión booleana. Step8: ¿Por qué usar Numpy? Step9: numpy tiene infinidad de funciones, por lo que sería interesante darse una vuelta por su documentación Step10: Pandas Step11: Se puede hacer plot también de una columna contra otra. Step12: Valores incompletos. Si no se establecen, se pone a NaN (not a number). Step13: fillna() permite cambiar el valor de los datos faltantes. Step14: A continuación se muestra un ejemplo de uso de Pandas para leer datos y procesarlos en un Dataframe. Step15: De la fecha, extraer sólo la fecha (no la hora, que no nos interesa). Step16: Añadimos una columna de todo "1" para especificar que cada pregunta cuenta como 1. Step17: A los Dataframe de Pandas también se les puede aplicar operaciones de agregación, como groupby o sum. Finalmente, la funcion plot() permite mostrar los datos en un gráfico. Step18: A continuación comprobamos con la página de la Wikipedia cuándo apareció el lenguaje Swift Step19: A continuación se muestra cómo ubicar posiciones en un mapa con el paquete folium. Se muestra también cómo acceder a distintas posiciones del Dataframe con iloc, loc, etc. Step20: El paquete folium permite generar mapas de posiciones. El siguiente ejemplo centra un mapa en Mula y pone un marcador con su nombre	<ASSISTANT_TASK:> Python Code: !uname -a %lsmagic import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib %matplotlib inline matplotlib.style.use('ggplot') from IPython.display import YouTubeVideo YouTubeVideo('o8fmjaW9a0A') # Yes, it can also embed youtube videos. a = np.array([4,5,6]) print(a.shape) print(a[0]) a[0] = 9 print (a) np.arange(10) np.arange(1,20) a = np.zeros((2,2)) print (a) a.ndim a.dtype b = np.random.random((2,2)) print (b) a = np.random.random((2,2)) print(a) print (a >= .5) print (a[a >= .5]) %%capture timeit_output %timeit l1 = range(1,1000) %timeit l2 = np.arange(1,1000) print(timeit_output) x = np.array([[1,2],[3,4]]) print (np.sum(x)) # Compute sum of all elements; prints "10" print (np.sum(x, axis=0)) # Compute sum of each column; prints "[4 6]" print (np.sum(x, axis=1)) # Compute sum of each row; prints "[3 7]" x * 2 x ** 2 x = np.arange(0, 3 * np.pi, 0.1) y = np.sin(x) plt.subplot() # Plot the points using matplotlib plt.plot(x, y) plt.show() plt.subplot(211) plt.plot(range(12)) plt.subplot(212, facecolor='y') plt.plot(range(100)) plt.show() # Compute the x and y coordinates for points on sine and cosine curves x = np.arange(0, 3 * np.pi, 0.1) y_sin = np.sin(x) y_cos = np.cos(x) # Plot the points using matplotlib plt.plot(x, y_sin) plt.plot(x, y_cos) plt.xlabel('x axis label') plt.ylabel('y axis label') plt.title('Sine and Cosine') plt.legend(['Sine', 'Cosine']) plt.show() ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000)) ts ts.describe() ts = ts.cumsum() ts.plot(); df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index, columns=list('ABCD')) df = df.cumsum() df.plot(); df3 = pd.DataFrame(np.random.randn(1000, 2), columns=['B', 'C']).cumsum() df3['A'] = pd.Series(list(range(len(df3)))) df3.plot(x='A', y='B'); d = {'one' : pd.Series([1., 2., 3.], index=['a', 'b', 'c']), 'two' : pd.Series([1., 2., 3., 4.], index=['a', 'b', 'c', 'd'])} df = pd.DataFrame(d) df df.fillna(0) pd.DataFrame(d, index=['d', 'b', 'a']) pd.DataFrame(d, index=['d', 'b', 'a'], columns=['two', 'three']) df = pd.read_csv('https://github.com/dsevilla/bdge/raw/master/intro/swift-question-dates.txt.gz', header=None, names=['date'], compression='gzip', parse_dates=['date'], index_col='date') df df.index = df.index.date df['Count'] = 1 df accum = df.groupby(df.index).sum() accum # Los 30 primeros registros que tengan un número de preguntas mayor que 20 por día. accum = accum[accum.Count > 20][:30] accum accum[accum.Count > 30][:30].plot.bar() !pip install lxml dfwiki = pd.read_html('https://en.wikipedia.org/wiki/Swift_(programming_language)',attrs={'class': 'infobox vevent'}) dfwiki[0] firstdate = dfwiki[0][1][4] firstdate from dateutil.parser import parse dt = parse(firstdate.split(';')[0]) print (dt.date().isoformat()) print (accum.index[0].isoformat()) assert dt.date().isoformat() == accum.index[0].isoformat() # cargar municipios y mostrarlos en el mapa df = pd.read_csv('https://github.com/dsevilla/bdge/raw/master/intro/municipios-2017.csv.gz',header=0,compression='gzip') df.head() df.iloc[0] df.iloc[0].NOMBRE_ACTUAL df.loc[:,'NOMBRE_ACTUAL'] df.iloc[:,0] df.PROVINCIA df[df.PROVINCIA == 'A Coruña'] mula = df[df.NOMBRE_ACTUAL == 'Mula'].iloc[0] mula (mula_lat,mula_lon) = (mula.LATITUD_ETRS89, mula.LONGITUD_ETRS89) (mula_lat,mula_lon) !pip install folium import folium map = folium.Map(location=[mula_lat, mula_lon],zoom_start=10) folium.Marker(location = [mula_lat, mula_lon], popup="{} ({} habitantes)".format(mula.NOMBRE_ACTUAL,mula.POBLACION_MUNI)).add_to(map) map <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Importing dependencies Step3: Visualize data Step4: Interactive pandas Dataframe Step5: Grid and potential field Step6: From potential field to block Step8: Combining potential fields Step9: This potential field gives the following block Step10: Combining both potential field where the first potential field is younger than the second we can obtain the following structure. Step11: Side note	<ASSISTANT_TASK:> Python Code: from IPython.display import HTML HTML('''<script> code_show=true; function code_toggle() { if (code_show){ $('div.input').hide(); } else { $('div.input').show(); } code_show = !code_show } $( document ).ready(code_toggle); </script> <form action="javascript:code_toggle()"><input type="submit" value="Click here to toggle on/off the raw code."></form>''') # Importing import importlib import theano.tensor as T import sys, os sys.path.append("/home/bl3/PycharmProjects/GeMpy/GeMpy") import pandas as pn import GeMpy_core import Visualization import numpy as np importlib.reload(GeMpy_core) os.environ['CUDA_LAUNCH_BLOCKING'] = '1' np.set_printoptions(precision = 4, linewidth= 300, suppress = True) import matplotlib.pyplot as plt from matplotlib import cm from IPython.display import set_matplotlib_formats set_matplotlib_formats('pdf', 'png') plt.rcParams['savefig.dpi'] = 75 plt.rcParams['figure.autolayout'] = False plt.rcParams['figure.figsize'] = 10, 6 plt.rcParams['axes.labelsize'] = 18 plt.rcParams['axes.titlesize'] = 20 plt.rcParams['font.size'] = 16 plt.rcParams['lines.linewidth'] = 2.0 plt.rcParams['lines.markersize'] = 8 plt.rcParams['legend.fontsize'] = 14 import seaborn as sns # This sets reasonable defaults for font size for # a figure that will go in a paper sns.set_context("paper") # Set the font to be serif, rather than sans sns.set(font='Arial') # Make the background white, and specify the # specific font family sns.set_style("white") import qgrid qgrid.nbinstall(overwrite=True) # copies javascript dependencies to your /nbextensions folder %matplotlib inline # Setting extend, grid and compile # Setting the extent test = GeMpy_core.GeMpy() test.import_data([0,10,0,10,0,10]) # ========================= # DATA GENERATION IN PYTHON # ========================= # Layers coordinates layer_1 = np.array([[0.5,4,7], [2,4,6.5], [4,4,7], [5,4,6]])#-np.array([5,5,4]))/8+0.5 layer_2 = np.array([[3,4,5], [6,4,4],[8,4,4], [7,4,3], [1,4,6]]) layers = np.asarray([layer_1,layer_2]) # Foliations coordinates dip_pos_1 = np.array([7,4,7])#- np.array([5,5,4]))/8+0.5 dip_pos_2 = np.array([2.,4,4]) # Dips dip_angle_1 = float(15) dip_angle_2 = float(340) dips_angles = np.asarray([dip_angle_1, dip_angle_2], dtype="float64") # Azimuths azimuths = np.asarray([90,90], dtype="float64") # Polarity polarity = np.asarray([1,1], dtype="float64") # Pandas Dataframe with the interfaces data test.Data.Interfaces = pn.DataFrame( data = {"X" :np.append(layer_1[:, 0],layer_2[:,0]), "Y" :np.append(layer_1[:, 1],layer_2[:,1]), "Z" :np.append(layer_1[:, 2],layer_2[:,2]), "formation" : np.append( np.tile("Layer 1", len(layer_1)), np.tile("Layer 2", len(layer_2)))}) # Pandas Dataframe with the Foliations data test.Data.Foliations = pn.DataFrame( data = {"X" :np.append(dip_pos_1[0],dip_pos_2[0]), "Y" :np.append(dip_pos_1[ 1],dip_pos_2[1]), "Z" :np.append(dip_pos_1[ 2],dip_pos_2[2]), "azimuth" : azimuths, "dip" : dips_angles, "polarity" : polarity, "formation" : ["Layer 1", "Layer 2"]}) # Creation of the formations (to be deprecated) test.Data.formations = test.Data.Interfaces["formation"].unique() # Calculation of the pola gradient from dip azimuth and polarity test.Data.calculate_gradient() # Set defautl series test.Data.set_series() # Method to be sure all objects get updated test.update_data() # The following code is for the visualization of labels of the input data (yet to be implemented) # ---------------------------------------------------------------------------------------------- def annotate_plot(frame, label_col, x, y, kwargs): Annotate the plot of a given DataFrame using one of its columns Should be called right after a DataFrame or series plot method, before telling matplotlib to show the plot. Parameters ---------- frame : pandas.DataFrame plot_col : str The string identifying the column of frame that was plotted label_col : str The string identifying the column of frame to be used as label kwargs: Other key-word args that should be passed to plt.annotate Returns ------- None Notes ----- After calling this function you should call plt.show() to get the results. This function only adds the annotations, it doesn't show them. import matplotlib.pyplot as plt # Make sure we have pyplot as plt for label, x, y in zip(frame[label_col], frame[x], frame[y]): plt.annotate(label, xy=(x+0.2, y+0.15), kwargs) inter_labels =[r'${\bf{x}}_{\alpha \, 0}^1$', r'${\bf{x}}_{\alpha \, 1}^1$', r'${\bf{x}}_{\alpha \, 2}^1$', r'${\bf{x}}_{\alpha \, 3}^1$', r'${\bf{x}}_{\alpha \, 0}^2$', r'${\bf{x}}_{\alpha \, 1}^2$', r'${\bf{x}}_{\alpha \, 2}^2$', r'${\bf{x}}_{\alpha \, 3}^2$', r'${\bf{x}}_{\alpha \, 4}^2$'] foli_labels =[r'${\bf{x}}_{\beta \,{0}}$', r'${\bf{x}}_{\beta \,{1}}$'] test.Data.Interfaces['labels'] = pn.Series(inter_labels) test.Data.Foliations['labels'] = pn.Series(foli_labels) # Plot and table test.Plot.plot_data() annotate_plot(test.Data.Interfaces, 'labels','X', 'Z', size = 'x-large') annotate_plot(test.Data.Foliations, 'labels','X', 'Z', size = 'x-large') test.Data.Interfaces import qgrid qgrid.show_grid(test.Data.Interfaces) test.create_grid() test.set_interpolator(u_grade=0, verbose = 0) test.Plot.plot_potential_field(4, direction='y', colorbar = True, cmap = 'magma') #test.Interpolator.DK; from ipywidgets import widgets from ipywidgets import interact def cov_cubic_f(r,a = 6, c_o = 1): if r <= a: return c_o(1-7(r/a)*2+35/4(r/a)*3-7/2(r/a)*5+3/4(r/a)*7) else: return 0 def cov_cubic_d1_f(r,a = 6., c_o = 1): SED_dips_dips = r f = c_o return (f ((-14 /a ** 2) + 105 / 4 * SED_dips_dips / a ** 3 - 35 / 2 * SED_dips_dips 3 / a 5 + 21 / 4 * SED_dips_dips 5 / a 7)) def cov_cubic_d2_f(r, a = 6, c_o = 1): SED_dips_dips = r f = c_o return 7f(9r5-20a*2r*3+15a*4r-4a5)/(2a*7) def plot_potential_var(a = 10, c_o = 1, nugget_effect = 0): x = np.linspace(0,12,50) y = [cov_cubic_f(i, a = a, c_o = c_o) for i in x] fig = plt.figure() ax1 = fig.add_subplot(121) ax1.plot(x,c_o-np.asarray(y)+nugget_effect) plt.hlines(0,0,12, linestyles = "--") plt.title("Variogram") plt.margins(0,0.1) ax2 = fig.add_subplot(122) ax2.plot(x,np.asarray(y)) ax2.scatter(0,nugget_effect+c_o) plt.title("Covariance Function") plt.tight_layout() plt.margins(0,0.1) plt.suptitle('$C_Z(r)$', y = 1.08, fontsize=15, fontweight='bold') def plot_potential_direction_var( a = 10, c_o = 1, nugget_effect = 0): x = np.linspace(0,12,50) y = np.asarray([cov_cubic_d1_f(i, a = a, c_o = c_o) for i in x]) fig = plt.figure() ax1 = fig.add_subplot(121) ax1.plot(x,c_o-np.asarray(y)+nugget_effect) plt.title("Variogram") plt.margins(0,0.1) ax2 = fig.add_subplot(122) ax2.plot(x,np.asarray(y)) #ax2.scatter(0,c_o) plt.title("Cross-Covariance Function") plt.tight_layout() plt.margins(0,0.1) plt.suptitle('$C\'_Z / r$', y = 1.08, fontsize=15, fontweight='bold') def plot_directionU_directionU_var(a = 10, c_o = 1, nugget_effect = 0): x = np.linspace(0.01,12,50) d1 = np.asarray([cov_cubic_d1_f(i, a = a, c_o = c_o) for i in x]) d2 = np.asarray([cov_cubic_d2_f(i, a = a, c_o = c_o) for i in x]) y = -(d2) # (0.5x2)/(x2)* fig = plt.figure() ax1 = fig.add_subplot(121) ax1.plot(x,c_o-np.asarray(y)+nugget_effect) plt.title("Variogram") plt.margins(0,0.1) ax2 = fig.add_subplot(122) ax2.plot(x,np.asarray(y)) ax2.scatter(0,nugget_effect+y[0], s = 20) plt.title("Covariance Function") plt.tight_layout() plt.margins(0,0.1) plt.suptitle('$C_{\partial {Z}/ \partial x, \, \partial {Z}/ \partial x}(h_x)$' , y = 1.08, fontsize=15) def plot_directionU_directionV_var(a = 10, c_o = 1, nugget_effect = 0): x = np.linspace(0.01,12,50) d1 = np.asarray([cov_cubic_d1_f(i, a = a, c_o = c_o) for i in x]) d2 = np.asarray([cov_cubic_d2_f(i, a = a, c_o = c_o) for i in x]) y = -(d2-d1) # (0.5x2)/(x2) fig = plt.figure() ax1 = fig.add_subplot(121) ax1.plot(x,c_o-np.asarray(y)+nugget_effect) plt.title("Variogram") plt.margins(0,0.1) ax2 = fig.add_subplot(122) ax2.plot(x,np.asarray(y)) ax2.scatter(0,nugget_effect+y[0], s = 20) plt.title("Covariance Function") plt.tight_layout() plt.margins(0,0.1) plt.suptitle('$C_{\partial {Z}/ \partial x, \, \partial {Z}/ \partial y}(h_x,h_y)$' , y = 1.08, fontsize=15) def plot_all(a = 10, c_o = 1, nugget_effect = 0): plot_potential_direction_var(a, c_o, nugget_effect) plot_directionU_directionU_var(a, c_o, nugget_effect) plot_directionU_directionV_var(a, c_o, nugget_effect) test.Interpolator.compute_block_model() test.Plot.plot_block_section() # Setting extend, grid and compile # Setting the extent two_pot = GeMpy_core.GeMpy() two_pot.import_data([0,10,0,10,0,10]) # Data Generation layer_1 = np.array([[0.5,4,7], [2,4,6.5], [4,4,7], [5,4,6]])#-np.array([5,5,4]))/8+0.5 layer_2 = np.array([[3,4,5], [6,4,4],[8,4,4], [7,4,3], [1,4,6]]) layer_3 = np.array([[2,4,3], [8,4,2], [9,4,3]]) dip_pos_1 = np.array([7,4,7])#- np.array([5,5,4]))/8+0.5 dip_pos_2 = np.array([2.,4,4]) dip_pos_3 = np.array([1,4,1]) dip_angle_1 = float(15) dip_angle_2 = float(340) dip_angle_3 = float(80) dips_angles = np.asarray([dip_angle_1, dip_angle_2, dip_angle_3], dtype="float64") layers = np.asarray([layer_1,layer_2, layer_3]) azimuths = np.asarray([90,90, 90], dtype="float64") polarity = np.asarray([1,1, 1], dtype="float64") two_pot.Data.Interfaces = pn.DataFrame(data = {"X" :np.hstack((layer_1[:, 0],layer_2[:,0], layer_3[:,0])), "Y" :np.hstack((layer_1[:, 1],layer_2[:,1], layer_3[:,1])), "Z" :np.hstack((layer_1[:, 2],layer_2[:,2], layer_3[:,2])), "formation" : np.hstack((np.tile("Layer 1", len(layer_1)), np.tile("Layer 2", len(layer_2)), np.tile("Layer 3", len(layer_3))))}) two_pot.Data.Foliations = pn.DataFrame(data = {"X" :np.hstack((dip_pos_1[0], dip_pos_2[0], dip_pos_3[0])), "Y" :np.hstack((dip_pos_1[ 1],dip_pos_2[1], dip_pos_3[1])), "Z" :np.hstack((dip_pos_1[ 2],dip_pos_2[2], dip_pos_3[2])), "azimuth" : azimuths, "dip" : dips_angles, "polarity" : polarity, "formation" : ["Layer 1", "Layer 2", 'Layer 3']}) inter_labels =[r'${\bf{x}}_{\alpha \, 0}^1$', r'${\bf{x}}_{\alpha \, 1}^1$', r'${\bf{x}}_{\alpha \, 2}^1$', r'${\bf{x}}_{\alpha \, 3}^1$', r'${\bf{x}}_{\alpha \, 0}^2$', r'${\bf{x}}_{\alpha \, 1}^2$', r'${\bf{x}}_{\alpha \, 2}^2$', r'${\bf{x}}_{\alpha \, 3}^2$', r'${\bf{x}}_{\alpha \, 4}^2$', r'${\bf{x}}_{\alpha \, 0}^1$', r'${\bf{x}}_{\alpha \, 1}^1$', r'${\bf{x}}_{\alpha \, 2}^1$'] foli_labels =[r'${\bf{x}}_{\beta \,{0}}$', r'${\bf{x}}_{\beta \,{1}}$', r'${\bf{x}}_{\beta \,{0}}$'] two_pot.Data.Interfaces['labels'] = pn.Series(inter_labels) two_pot.Data.Foliations['labels'] = pn.Series(foli_labels) two_pot.Data.formations = two_pot.Data.Interfaces["formation"].unique() two_pot.Data.calculate_gradient() two_pot.Data.set_series({'younger': ('Layer 1', 'Layer 2'), 'older': 'Layer 3'}, order = ['younger', 'older']) two_pot.update_data() def annotate_plot(frame, label_col, x, y, kwargs): Annotate the plot of a given DataFrame using one of its columns Should be called right after a DataFrame or series plot method, before telling matplotlib to show the plot. Parameters ---------- frame : pandas.DataFrame plot_col : str The string identifying the column of frame that was plotted label_col : str The string identifying the column of frame to be used as label kwargs: Other key-word args that should be passed to plt.annotate Returns ------- None Notes ----- After calling this function you should call plt.show() to get the results. This function only adds the annotations, it doesn't show them. import matplotlib.pyplot as plt # Make sure we have pyplot as plt for label, x, y in zip(frame[label_col], frame[x], frame[y]): plt.annotate(label, xy=(x+0.2, y+0.15), kwargs) serie_to_plot = 'older' two_pot.Plot.plot_data(series = serie_to_plot) annotate_plot(two_pot.Data.Interfaces[two_pot.Data.Interfaces['series'] == serie_to_plot] , 'labels','X', 'Z', size = 'x-large') annotate_plot(two_pot.Data.Foliations[two_pot.Data.Foliations['series'] == serie_to_plot], 'labels','X', 'Z', size = 'x-large') two_pot.create_grid() two_pot.set_interpolator(u_grade=0, verbose = 0) two_pot.Plot.plot_potential_field(4, n_pf=1, direction='y', colorbar = True, cmap = 'magma') # Reset the block two_pot.Interpolator.block.set_value(np.zeros_like(two_pot.Grid.grid[:,0])) two_pot.Interpolator.compute_block_model(series_number=[1]) two_pot.Plot.plot_block_section() # Reset the block two_pot.Interpolator.block.set_value(np.zeros_like(two_pot.Grid.grid[:,0])) two_pot.Interpolator.compute_block_model(series_number=[0,1]) two_pot.Plot.plot_block_section() plot_potential_var(10,102 / 14 / 3 , 0.01) plot_all(10,102 / 14 / 3 , 0.01) # 0**2 /14/3 <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The binomial distribution is closely related to the normal distribution (aka Gaussian distribution) Step2: Could we figure this out analytically? Step3: How can we use the mean and standard deviation to estimate the probability?	<ASSISTANT_TASK:> Python Code: import random results = [] for trial in xrange(10000): heads = 0 for i in xrange(100): flip = random.randint(0,1) if (flip == 0): heads += 1 results.append(heads) print results[1:10] import matplotlib.pyplot as plt plt.figure() plt.hist(results) plt.show() ## Plot the histogram using integer values by creating more bins plt.figure() plt.hist(results, bins=range(100)) plt.title("Using integer values") plt.show() ## Plot the density function, notice bars sum to exactly 1 ## Also make the plot bigger plt.figure(figsize=(15,6)) plt.hist(results, bins=range(100), normed=True) plt.title("coin flip densities") plt.show() flips_mean = float(sum(results)) / len(results) print flips_mean ## the numpy package has lots of useful routines: http://www.numpy.org/ import numpy as np mean = np.mean(results) print mean ## we could code standard deviation by hand, but numpy makes it easier stdev=np.std(results) print stdev ## Overlay a normal distribution on top of the coin flip data plt.figure(figsize=(15,6)) count, bins, patches = plt.hist(results, bins=range(100), normed=True, label="coin flip histogram") plt.plot(bins, 1/(stdev * np.sqrt(2 * np.pi)) * np.exp( - (bins - mean)*2 / (2 stdev*2) ), linewidth=3, color='red', label="normal distribution") plt.title("Coin flip densities with normal distribution overlay") plt.legend() plt.show() prob_heads = .5 num_flips = 100 num_heads = 25 prob_flips = np.math.factorial(num_flips) / \ (np.math.factorial(num_heads) np.math.factorial(num_flips-num_heads)) * \ (prob_heads*num_heads) ((1-prob_heads)*(num_flips-num_heads)) print "The probability of seeing %d heads in %d flips is %.015f" % (num_heads, num_flips, prob_flips) ## Another super useful package is scipy import scipy.stats sp_prob = scipy.stats.binom.pmf(num_heads, num_flips, prob_heads) print "scipy computed it as %0.15f" % sp_prob ## normal approximatation print scipy.stats.norm(50, 5).pdf(25) ## Overlay a normal distribution on top of the coin flip data plt.figure(figsize=(15,6)) count, bins, patches = plt.hist(results, bins=range(100), normed=True, label="coin flip histogram") plt.plot(bins, scipy.stats.binom.pmf(bins, num_flips, prob_heads),linewidth=3, color='red', label="binomial distribution") plt.plot(bins, scipy.stats.norm(50,5).pdf(bins),linewidth=3, color='green', linestyle='--', label="normal distribution") plt.title("Coin flip densities with normal distribution overlay") plt.legend() plt.show() expected_mean = num_flips prob_heads expected_stdev = np.math.sqrt(num_flips * prob_heads * (1 - prob_heads)) print "In %d flips, with a probability %.02f" % (num_flips, prob_heads) print "The expected frequency is %.02f +/- %.02f" % (expected_mean, expected_stdev) print "The observed frequency was %0.2f +/- %0.2f" % (mean, stdev) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: x1 and x2 have spectral peaks at 40 Hz Step2: Spectral Granger Causality Steps Step3: Compare with nitime version Step4: Non-parametric version Steps Step5: Wilson spectral matrix factorizaion	<ASSISTANT_TASK:> Python Code: time_extent = (0, .250) num_trials = 500 sampling_frequency = 200 num_time_points = ((time_extent[1] - time_extent[0]) * sampling_frequency) + 1 time = np.linspace(time_extent[0], time_extent[1], num=num_time_points, endpoint=True) signal_shape = (len(time), num_trials) np.random.seed(2) def simulate_arma_model(ar_coefficients, ma_coefficients=None, signal_shape=(100,1), sigma=1, axis=0, num_burnin_samples=10): ar = np.r_[1, -ar_coefficients] # add zero-lag and negate if ma_coefficients is None: ma = np.asarray([1]) else: ma = np.r_[1, ma_coefficients] # add zero-lag # Add burnin samples to shape signal_shape = list(signal_shape) signal_shape[axis] += num_burnin_samples # Get arma process white_noise = np.random.normal(0, sigma, size=signal_shape) signal = scipy.signal.lfilter(ma, ar, white_noise, axis=axis) # Return non-burnin samples slc = [slice(None)] * len(signal_shape) slc[axis] = slice(num_burnin_samples, signal_shape[axis], 1) return signal[slc] ar1 = np.array([.55, -0.70]) x1 = simulate_arma_model(ar1, signal_shape=signal_shape, sigma=1, num_burnin_samples=sampling_frequency) arima_model.ARMA(x1[:, 0], (2,0)).fit(trend='nc', disp=0).summary() ar2 = np.array([.56, -0.75]) x2 = simulate_arma_model(ar2, signal_shape=signal_shape, sigma=2, num_burnin_samples=sampling_frequency) arima_model.ARMA(x2[:, 0], (2,0)).fit(trend='nc', disp=0).summary() x2[1:, :] = 0.60 * x1[:-1, :] psd1 = spectral.multitaper_power_spectral_density(x1, sampling_frequency=sampling_frequency, time_halfbandwidth_product=1, desired_frequencies=[0, 100]) psd2 = spectral.multitaper_power_spectral_density(x2, sampling_frequency=sampling_frequency, time_halfbandwidth_product=1, desired_frequencies=[0, 100]) fig, axes = plt.subplots(1,2, figsize=(4,3), sharex=True, sharey=True) psd1.plot(ax=axes[0], legend=False) axes[0].set_ylabel('Power') axes[0].set_title('x1') axes[0].axvline(40, color='black', linestyle=':') psd2.plot(ax=axes[1], legend=False) axes[1].axvline(40, color='black', linestyle=':') axes[1].set_title('x2') plt.tight_layout() # Step 1 centered_x1 = spectral._subtract_mean(x1) centered_x2 = spectral._subtract_mean(x2) x = np.concatenate((centered_x1[..., np.newaxis], centered_x2[..., np.newaxis]), axis=-1) num_lfps = x.shape[-1] # Step 2 order = 3 fit = [alg.MAR_est_LWR(x[:, trial, :].T, order) for trial in np.arange(x1.shape[1])] # A shape: order-1 x num_lfps x num_lfps # cov shape: num_lfps x num_lfps # Step 3 Sigma = np.mean([trial_fit[1] for trial_fit in fit], axis=0) # Step 4 A = np.mean([trial_fit[0] for trial_fit in fit], axis=0) # Step 5 pad = 0 number_of_time_samples = int(num_time_points) next_exponent = spectral._nextpower2(number_of_time_samples) number_of_fft_samples = max( 2 ** (next_exponent + pad), number_of_time_samples) half_of_fft_samples = number_of_fft_samples//2 - 1 A_0 = np.concatenate((np.eye(num_lfps)[np.newaxis, :, :], A)).reshape((order, -1)) B = np.zeros((A_0.shape[-1], half_of_fft_samples), dtype='complex') for coef_ind in np.arange(A_0.shape[-1]): normalized_freq, B[coef_ind, :] = scipy.signal.freqz(A_0[:, coef_ind], worN=half_of_fft_samples) B = B.reshape((num_lfps, num_lfps, half_of_fft_samples)) H = np.zeros_like(B) for freq_ind in np.arange(half_of_fft_samples): H[:, :, freq_ind] = np.linalg.inv(B[:, :, freq_ind]) freq = (normalized_freq * sampling_frequency) / (2 * np.pi) # Step 6 S = np.zeros_like(H) for freq_ind in np.arange(H.shape[-1]): S[:, :, freq_ind] = np.linalg.multi_dot( [H[:, :, freq_ind], Sigma, H[:, :, freq_ind].conj().transpose()]) S = np.abs(S) I12 = -np.log(1 - ((Sigma[0, 0] - Sigma[0, 1]*2 / Sigma[1, 1]) np.abs(H[1, 0])2) / S[1, 1]) # I12 = np.log( S[1, 1] / (S[1,1] - (Sigma[0, 0] - Sigma[0, 1]2 / Sigma[1, 1]) * np.abs(H[1, 0])2)) I21 = -np.log(1 - ((Sigma[1, 1] - Sigma[0, 1]2 / Sigma[0, 0]) * np.abs(H[0, 1])*2) / S[0, 0]) plt.plot(freq, I12, label='x1 → x2') plt.plot(freq, I21, label='x2 → x1') plt.xlabel('Frequencies (Hz)') plt.ylabel('Granger Causality') plt.legend(); order = 3 fit = [alg.MAR_est_LWR(x[:, trial, :].T, order) for trial in np.arange(x1.shape[1])] Sigma = np.mean([trial_fit[1] for trial_fit in fit], axis=0) A = np.mean([trial_fit[0] for trial_fit in fit], axis=0) normalized_freq, f_x2y, f_y2x, f_xy, Sw = alg.granger_causality_xy(A, Sigma, n_freqs=number_of_fft_samples) freq = (normalized_freq sampling_frequency) / (2 * np.pi) plt.plot(freq, f_x2y, label='x1 → x2') plt.plot(freq, f_y2x, label='x2 → x1') plt.xlabel('Frequencies (Hz)') plt.ylabel('Granger Causality') plt.legend(); # Step 1 def get_complex_spectrum(data, sampling_frequency=1000, time_halfbandwidth_product=3, pad=0, tapers=None, frequencies=None, freq_ind=None, number_of_fft_samples=None, number_of_tapers=None, desired_frequencies=None): complex_spectrum = spectral._multitaper_fft( tapers, spectral._center_data(data), number_of_fft_samples, sampling_frequency) return np.nanmean(complex_spectrum[freq_ind, :, :], axis=(1, 2)).squeeze() data = [x1, x2] num_signals = len(data) time_halfbandwidth_product = 1 tapers, number_of_fft_samples, frequencies, freq_ind = spectral._set_default_multitaper_parameters( number_of_time_samples=data[0].shape[0], sampling_frequency=sampling_frequency, time_halfbandwidth_product=time_halfbandwidth_product) complex_spectra = [get_complex_spectrum( signal, sampling_frequency=sampling_frequency, time_halfbandwidth_product=time_halfbandwidth_product, tapers=tapers, frequencies=frequencies, freq_ind=freq_ind, number_of_fft_samples=number_of_fft_samples) for signal in data] S = np.stack([np.conj(complex_spectrum1) * complex_spectrum2 for complex_spectrum1, complex_spectrum2 in itertools.product(complex_spectra, repeat=2)]) S = S.reshape((num_signals, num_signals, num_frequencies)) A0 = np.random.normal(size=(num_signals, 1000)) A0 = np.dot(A0, A0.T) / 1000; A0 = np.linalg.cholesky(A0).T num_two_sided_frequencies = 2 * num_frequencies - 1 Psi = np.zeros((num_signals, num_signals, num_two_sided_frequencies), dtype=complex) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Reading and Preprocessing the Images with OpenCV Step2: Building a Convnet in Keras	<ASSISTANT_TASK:> Python Code: data = pd.read_csv('data/driving_log.csv', header=None, names=['center', 'left', 'right', 'angle', 'throttle', 'break', 'speed']) print(data.ix[0].center) data.sample() def img_id(path): return path.split('/IMG/')[1] image_paths = data.center.apply(img_id).values.tolist() image_paths[:5] # y_all = data[['angle', 'throttle']].values y_all = data.angle.values n_samples = y_all.shape[0] print("Training Model with {} Samples".format(n_samples)) def read_image(path): img = cv2.imread(path, cv2.IMREAD_COLOR) img = img[40:160, 0:320] ## Cropping top section of image, just useless noise # img = cv2.imread(path, cv2.IMREAD_GRAYSCALE) # img = np.expand_dims(img, axis=2) return img[:,:,::-1] X_all = np.ndarray((n_samples, ROWS, COLS, CHANNELS), dtype=np.uint8) for i, path in enumerate(image_paths): DIR+path img = read_image(DIR+path) X_all[i] = img print(X_all.shape) for img in X_all[:3]: plt.imshow(img) plt.show() X_train, X_test, y_train, y_test = train_test_split( X_all, y_all, test_size=0.20, random_state=23) def fit_gen(data, batch_size): while 1: x = np.ndarray((batch_size, ROWS, COLS, CHANNELS), dtype=np.uint8) y = np.zeros(batch_size) i=0 for line in data.iterrows(): path = line[1].center.split('/IMG/')[1] x[i] = read_image(DIR+path) y[i] = line[1].angle i+=1 if i == batch_size: i=0 yield (x, y) x = np.ndarray((batch_size, ROWS, COLS, CHANNELS), dtype=np.uint8) y = np.zeros(batch_size) def rmse(y_true, y_pred): return K.sqrt(K.mean(K.square(y_pred - y_true), axis=-1)) def get_model(): lr = 0.0001 weight_init='glorot_normal' opt = RMSprop(lr) loss = 'mean_squared_error' model = Sequential() model.add(BatchNormalization(mode=2, axis=1, input_shape=(ROWS, COLS, CHANNELS))) model.add(Convolution2D(3, 3, 3, init=weight_init, border_mode='valid', activation='relu', input_shape=(ROWS, COLS, CHANNELS))) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(9, 3, 3, init=weight_init, border_mode='valid', activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(18, 3, 3, init=weight_init, border_mode='valid', activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(32, 3, 3, init=weight_init, border_mode='valid', activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Flatten()) model.add(Dense(80, activation='relu', init=weight_init)) # model.add(Dropout(0.5)) model.add(Dense(15, activation='relu', init=weight_init)) model.add(Dropout(0.25)) model.add(Dense(1, init=weight_init, activation='linear')) model.compile(optimizer=opt, loss=loss) return model model = get_model() model.summary() nb_epoch = 30 batch_size = 64 ### Creating Validation Data X_train, X_test, y_train, y_test = train_test_split( X_all, y_all, test_size=0.20, random_state=23) # Callbacks early_stopping = EarlyStopping(monitor='val_loss', patience=8, verbose=1, mode='auto') save_weights = ModelCheckpoint('new_model.h5', monitor='val_loss', save_best_only=True) model.fit_generator(fit_gen(data, 32), samples_per_epoch=data.shape[0], nb_epoch=nb_epoch, validation_data=(X_test, y_test), callbacks=[save_weights, early_stopping]) model.fit(X_all, y_all, batch_size=batch_size, nb_epoch=nb_epoch, validation_data=(X_test, y_test), verbose=1, shuffle=True, callbacks=[save_weights, early_stopping]) preds = model.predict(X_test, verbose=1) print( "Test MSE: {}".format(mean_squared_error(y_test, preds))) print( "Test RMSE: {}".format(np.sqrt(mean_squared_error(y_test, preds)))) js = model.to_json() with open('model.json', 'w') as outfile: json.dump(js, outfile) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Create Noisy Data Step2: Model Fitting Step3: Two-peaks model Step4: Fit results from an lmfit Model can be inspected with Step5: This is good for peeking at the results. However, Step6: A summary of the one-peak model fit Step7: Tidy Step8: Let's see the results for a single dataset Step9: or for a single parameter across datasets Step10: Note that there is a much larger error in fitting p2_center Step11: Augment Step12: Let's see the results for a single dataset Step13: Plotting a single dataset is simplified compared to a manual plot Step14: But keep in mind that, for a single dataset, we could Step15: However, things become much more interesting when we want to plot multiple Step16: Comparison of one- or two-peaks models Step17: Then we perfom a facet plot with seaborn	<ASSISTANT_TASK:> Python Code: %matplotlib inline %config InlineBackend.figure_format='retina' # for hi-dpi displays import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns from lmfit import Model import lmfit print('lmfit: %s' % lmfit.__version__) sns.set_style('whitegrid') import pybroom as br N = 20 x = np.linspace(-10, 10, 101) peak1 = lmfit.models.GaussianModel(prefix='p1_') peak2 = lmfit.models.GaussianModel(prefix='p2_') model = peak1 + peak2 #params = model.make_params(p1_amplitude=1.5, p2_amplitude=1, # p1_sigma=1, p2_sigma=1) Y_data = np.zeros((N, x.size)) Y_data.shape for i in range(Y_data.shape[0]): Y_data[i] = model.eval(x=x, p1_center=-1, p2_center=2, p1_sigma=0.5, p2_sigma=1.5, p1_height=1, p2_height=0.5) Y_data += np.random.randn(*Y_data.shape)/10 plt.plot(x, Y_data.T, '-k', alpha=0.1); model1 = lmfit.models.GaussianModel() Results1 = [model1.fit(y, x=x) for y in Y_data] params = model.make_params(p1_center=0, p2_center=3, p1_sigma=0.5, p2_sigma=1, p1_amplitude=1, p2_amplitude=2) Results = [model.fit(y, x=x, params=params) for y in Y_data] #print(Results[0].fit_report()) #Results[0].params.pretty_print() dg = br.glance(Results, var_names='dataset') dg.drop('model', 1).drop('message', 1).head() dg1 = br.glance(Results1, var_names='dataset') dg1.drop('model', 1).drop('message', 1).head() dt = br.tidy(Results, var_names='dataset') dt.query('dataset == 0') dt.query('name == "p1_center"').head() dt.query('name == "p1_center"')['value'].std() dt.query('name == "p2_center"')['value'].std() dt.query('name == "p1_center"')['value'].hist() dt.query('name == "p2_center"')['value'].hist(ax=plt.gca()); da = br.augment(Results, var_names='dataset') da1 = br.augment(Results1, var_names='dataset') r = Results[0] da.query('dataset == 0').head() da0 = da.query('dataset == 0') plt.plot('x', 'data', data=da0, marker='o', ls='None') plt.plot('x', "Model(gaussian, prefix='p1_')", data=da0, lw=2, ls='--') plt.plot('x', "Model(gaussian, prefix='p2_')", data=da0, lw=2, ls='--') plt.plot('x', 'best_fit', data=da0, lw=2); plt.legend() Results[0].plot_fit(); grid = sns.FacetGrid(da.query('dataset < 6'), col="dataset", hue="dataset", col_wrap=3) grid.map(plt.plot, 'x', 'data', marker='o', ls='None', ms=3, color='k') grid.map(plt.plot, 'x', "Model(gaussian, prefix='p1_')", ls='--') grid.map(plt.plot, 'x', "Model(gaussian, prefix='p2_')", ls='--') grid.map(plt.plot, "x", "best_fit"); da['model'] = 'twopeaks' da1['model'] = 'onepeak' da_tot = pd.concat([da, da1], ignore_index=True) grid = sns.FacetGrid(da_tot.query('dataset < 6'), col="dataset", hue="model", col_wrap=3) grid.map(plt.plot, 'x', 'data', marker='o', ls='None', ms=3, color='k') grid.map(plt.plot, "x", "best_fit") grid.add_legend(); <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Create A Simple Object	<ASSISTANT_TASK:> Python Code: import datetime class Regiment(object): def __init__(self, date=datetime.datetime.now()): self.date = date def __repr__(self): return date def __str__(self): return str(date) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Step 2 Step2: Step 3 Step3: Retrieving a DataFrame	<ASSISTANT_TASK:> Python Code: from pydrill.client import PyDrill #Open a connection to Drill drill = PyDrill(host='localhost', port=8047) #Verify the connection is active, throw an error if not. if not drill.is_active(): raise ImproperlyConfigured('Please run Drill first') #Execute query in Drill query_result = drill.query(''' SELECT JobTitle, AVG( CAST( LTRIM( AnnualSalary, '$' ) AS FLOAT) ) AS avg_salary, COUNT( DISTINCT name ) AS number FROM dfs.drillworkshop.`*.csvh` GROUP BY JobTitle Order By avg_salary DESC LIMIT 10 ''') #Iterate through the rows. for row in query_result: print( row ) df = query_result.to_dataframe() df.head() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Image Classification Step2: Explore the Data Step5: Implement Preprocess Functions Step8: One-hot encode Step10: Randomize Data Step12: Check Point Step18: Build the network Step21: Convolution and Max Pooling Layer Step24: Flatten Layer Step27: Fully-Connected Layer Step30: Output Layer Step33: Create Convolutional Model Step34: Train the Neural Network Step37: x = np.zeros((100,2,1,5)) Step39: Show Stats Step40: Hyperparameters Step42: Train on a Single CIFAR-10 Batch Step45: Checkpoint	<ASSISTANT_TASK:> Python Code: DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE from urllib.request import urlretrieve from os.path import isfile, isdir from tqdm import tqdm import problem_unittests as tests import tarfile cifar10_dataset_folder_path = 'cifar-10-batches-py' # Use Floyd's cifar-10 dataset if present floyd_cifar10_location = '/input/cifar-10/python.tar.gz' if isfile(floyd_cifar10_location): tar_gz_path = floyd_cifar10_location else: tar_gz_path = 'cifar-10-python.tar.gz' class DLProgress(tqdm): last_block = 0 def hook(self, block_num=1, block_size=1, total_size=None): self.total = total_size self.update((block_num - self.last_block) * block_size) self.last_block = block_num if not isfile(tar_gz_path): with DLProgress(unit='B', unit_scale=True, miniters=1, desc='CIFAR-10 Dataset') as pbar: urlretrieve( 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz', tar_gz_path, pbar.hook) if not isdir(cifar10_dataset_folder_path): with tarfile.open(tar_gz_path) as tar: tar.extractall() tar.close() tests.test_folder_path(cifar10_dataset_folder_path) %matplotlib inline %config InlineBackend.figure_format = 'retina' import helper import numpy as np # Explore the dataset batch_id = 2 sample_id = 18 helper.display_stats(cifar10_dataset_folder_path, batch_id, sample_id) from skimage import color # def to_hsi(x): # r = x[:,:,:,0] # g = x[:,:,:,1] # b = x[:,:,:,2] # theta = np.acos((0.5 * ((r-g) + (r-b))) / (((r-g)*2) + (r-b ))) def normalize(x): Normalize a list of sample image data in the range of 0 to 1 : x: List of image data. The image shape is (32, 32, 3) : return: Numpy array of normalize data x = x / 255.0 for i in range(x.shape[0]): x[i,:,:,:] = color.rgb2hsv(x[i,:,:,:]) return x DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_normalize(normalize) def one_hot_encode(x): One hot encode a list of sample labels. Return a one-hot encoded vector for each label. : x: List of sample Labels : return: Numpy array of one-hot encoded labels m = (x.shape[0] if hasattr(x, 'shape') else len(x)) rv = np.zeros((m, 10)) rv[range(m),x] = 1 return rv DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_one_hot_encode(one_hot_encode) %%time DON'T MODIFY ANYTHING IN THIS CELL # Preprocess Training, Validation, and Testing Data helper.preprocess_and_save_data(cifar10_dataset_folder_path, normalize, one_hot_encode) DON'T MODIFY ANYTHING IN THIS CELL import pickle import problem_unittests as tests import helper # Load the Preprocessed Validation data valid_features, valid_labels = pickle.load(open('preprocess_validation.p', mode='rb')) import tensorflow as tf def neural_net_image_input(image_shape): Return a Tensor for a batch of image input : image_shape: Shape of the images : return: Tensor for image input. tensor_shape = tuple([None] + list(image_shape)) return tf.placeholder(tf.float32, shape=tensor_shape, name='x') def neural_net_label_input(n_classes): Return a Tensor for a batch of label input : n_classes: Number of classes : return: Tensor for label input. return tf.placeholder(tf.float32, shape=(None,n_classes), name='y') def neural_net_keep_prob_input(): Return a Tensor for keep probability : return: Tensor for keep probability. return tf.placeholder(tf.float32, name='keep_prob') def neural_net_learn_rate_input(): Return a Tensor for keep probability : return: Tensor for keep probability. return tf.placeholder(tf.float32, name='learn_rate') DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tf.reset_default_graph() tests.test_nn_image_inputs(neural_net_image_input) tests.test_nn_label_inputs(neural_net_label_input) tests.test_nn_keep_prob_inputs(neural_net_keep_prob_input) def conv2d_maxpool(x_tensor, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides): Apply convolution then max pooling to x_tensor :param x_tensor: TensorFlow Tensor :param conv_num_outputs: Number of outputs for the convolutional layer :param conv_ksize: kernal size 2-D Tuple for the convolutional layer :param conv_strides: Stride 2-D Tuple for convolution :param pool_ksize: kernal size 2-D Tuple for pool :param pool_strides: Stride 2-D Tuple for pool : return: A tensor that represents convolution and max pooling of x_tensor conv_ksize = list(conv_ksize) conv_strides = list(conv_strides) pool_ksize = list(pool_ksize) pool_strides = list(pool_strides) conv_num_inputs = int(x_tensor.shape[3]) conv_weights = tf.Variable(tf.truncated_normal( conv_ksize + [conv_num_inputs,conv_num_outputs], stddev=0.01)) conv_strides = [1] + conv_strides + [1] rv = tf.nn.conv2d(x_tensor, conv_weights, conv_strides, 'SAME') conv_bias = tf.Variable(tf.zeros(rv.shape[1:])) rv = tf.nn.relu(rv + conv_bias) pool_ksize = [1] + pool_ksize + [1] pool_strides = [1] + pool_strides + [1] rv = tf.nn.max_pool(rv, pool_ksize, pool_strides, 'SAME') return rv DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_con_pool(conv2d_maxpool) def flatten(x_tensor): Flatten x_tensor to (Batch Size, Flattened Image Size) : x_tensor: A tensor of size (Batch Size, ...), where ... are the image dimensions. : return: A tensor of size (Batch Size, Flattened Image Size). return tf.contrib.layers.flatten(x_tensor) DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_flatten(flatten) def fully_conn(x_tensor, num_outputs): Apply a fully connected layer to x_tensor using weight and bias : x_tensor: A 2-D tensor where the first dimension is batch size. : num_outputs: The number of output that the new tensor should be. : return: A 2-D tensor where the second dimension is num_outputs. dimensions = [int(x_tensor.shape[1]), num_outputs] weights = tf.Variable(tf.truncated_normal(dimensions, stddev=0.01)) bias = tf.Variable(tf.zeros(num_outputs)) return tf.nn.relu(tf.matmul(x_tensor, weights) + bias) DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_fully_conn(fully_conn) def output(x_tensor, num_outputs): Apply a output layer to x_tensor using weight and bias : x_tensor: A 2-D tensor where the first dimension is batch size. : num_outputs: The number of output that the new tensor should be. : return: A 2-D tensor where the second dimension is num_outputs. # TODO: Implement Function dimensions = [int(x_tensor.shape[1]), num_outputs] weights = tf.Variable(tf.truncated_normal(dimensions, stddev=0.01)) bias = tf.Variable(tf.zeros(num_outputs)) return tf.matmul(x_tensor, weights) + bias DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_output(output) def conv_net(x, keep_prob): Create a convolutional neural network model : x: Placeholder tensor that holds image data. : keep_prob: Placeholder tensor that hold dropout keep probability. : return: Tensor that represents logits # TODO: Apply 1, 2, or 3 Convolution and Max Pool layers # Play around with different number of outputs, kernel size and stride # Function Definition from Above: # conv2d_maxpool(x_tensor, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides) #with tf.device('/gpu:0'): x_tensor = x x_tensor = conv2d_maxpool(x_tensor, 128, [8,8], [1,1], [2,2], [1,1]) x_tensor = conv2d_maxpool(x_tensor, 128, [4,4], [2,2], [2,2], [2,2]) x_tensor = tf.nn.dropout(x_tensor, keep_prob) #with tf.device('/gpu:1'): x_tensor = conv2d_maxpool(x_tensor, 64, [4,4], [1,1], [2,2], [2,2]) # TODO: Apply a Flatten Layer # Function Definition from Above: # flatten(x_tensor) x_tensor = flatten(x_tensor) # TODO: Apply 1, 2, or 3 Fully Connected Layers # Play around with different number of outputs # Function Definition from Above: # fully_conn(x_tensor, num_outputs) x_tensor = tf.nn.dropout(fully_conn(x_tensor, 512), keep_prob) x_tensor = fully_conn(x_tensor, 256) x_tensor = tf.nn.dropout(fully_conn(x_tensor, 256), keep_prob) # TODO: Apply an Output Layer # Set this to the number of classes # Function Definition from Above: # output(x_tensor, num_outputs) x_tensor = output(x_tensor, 10) # TODO: return output return x_tensor DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE ############################## ## Build the Neural Network ## ############################## # Remove previous weights, bias, inputs, etc.. tf.reset_default_graph() # Inputs # x = (neural_net_image_input((32, 32, 3)), neural_net_image_input((32, 32, 3))) x = neural_net_image_input((32, 32, 3)) y = neural_net_label_input(10) keep_prob = neural_net_keep_prob_input() learn_rate = neural_net_learn_rate_input() # Model logits = [] with tf.variable_scope(tf.get_variable_scope()): logits.append(conv_net(x, keep_prob)) logits = tf.concat(logits, 0) # Name logits Tensor, so that is can be loaded from disk after training logits = tf.identity(logits, name='logits') # Loss and Optimizer cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y)) optimizer = tf.train.AdamOptimizer(learning_rate=learn_rate).minimize(cost) # Accuracy correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32), name='accuracy') tests.test_conv_net(conv_net) # def split(t,n=2): # if n == 1: return (t,) # dimSize = int(t.shape[0]) # partSize = dimSize/n # maxIdx = int(partSize) # rv = [t[:maxIdx,...]] # for i in range(n-2): # myMin = int(maxIdx) # nextMax = min(dimSize,float(maxIdx)+partSize) # myMax = int(nextMax) # rv.append(t[myMin:myMax,...]) # maxIdx = nextMax # rv.append(t[int(maxIdx):,...]) # return tuple(rv) def train_neural_network(session, optimizer, keep_probability, feature_batch, label_batch, epoch=0): Optimize the session on a batch of images and labels : session: Current TensorFlow session : optimizer: TensorFlow optimizer function : keep_probability: keep probability : feature_batch: Batch of Numpy image data : label_batch: Batch of Numpy label data if epoch < 125: learning_rate=0.001 elif epoch < 175: learning_rate=0.0003 elif epoch < 225: learning_rate=0.0001 else: learning_rate=0.00003 session.run(optimizer, feed_dict={x: feature_batch, y: label_batch, learn_rate: learning_rate, keep_prob: keep_probability}) DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_train_nn(train_neural_network) import datetime def print_stats(session, feature_batch, label_batch, cost, accuracy): Print information about loss and validation accuracy : session: Current TensorFlow session : feature_batch: Batch of Numpy image data : label_batch: Batch of Numpy label data : cost: TensorFlow cost function : accuracy: TensorFlow accuracy function # TODO: Implement Function train_cost, train_acc = session.run((cost, accuracy), feed_dict={x: feature_batch, y: label_batch, keep_prob: 1.0}) valid_cost, valid_acc = session.run((cost, accuracy), feed_dict={x: valid_features, y: valid_labels, keep_prob: 1.0}) print("Training loss: {0:.02}, accuracy: {1:.02}".format(train_cost, train_acc)) print(datetime.datetime.now(),"Validation loss: {0:.02}, accuracy: {1:.02}".format(valid_cost, valid_acc)) return valid_acc # TODO: Tune Parameters epochs = 250 batch_size = 256 keep_probability = 0.4 import matplotlib.pyplot as plt %matplotlib inline fig, axis = plt.subplots(figsize=(13,13)) axis.plot(val_accuracy) DON'T MODIFY ANYTHING IN THIS CELL save_model_path = './image_classification' full_val_accuracy = [] print('Training...') with tf.Session() as sess: # Initializing the variables sess.run(tf.global_variables_initializer()) # Training cycle for epoch in range(epochs): # Loop over all batches n_batches = 5 for batch_i in range(1, n_batches + 1): for batch_features, batch_labels in helper.load_preprocess_training_batch(batch_i, batch_size): train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels, epoch) print('Epoch {:>2}, CIFAR-10 Batch {}: '.format(epoch + 1, batch_i), end='') full_val_accuracy.append(print_stats(sess, batch_features, batch_labels, cost, accuracy)) # Save Model saver = tf.train.Saver() save_path = saver.save(sess, save_model_path) import matplotlib.pyplot as plt %matplotlib inline import numpy as np fig, axis = plt.subplots(figsize=(13,13)) axis.plot(np.array(range(len(full_val_accuracy)))/5, full_val_accuracy) DON'T MODIFY ANYTHING IN THIS CELL %matplotlib inline %config InlineBackend.figure_format = 'retina' import tensorflow as tf import pickle import helper import random # Set batch size if not already set try: if batch_size: pass except NameError: batch_size = 64 save_model_path = './image_classification' n_samples = 4 top_n_predictions = 3 def test_model(): Test the saved model against the test dataset test_features, test_labels = pickle.load(open('preprocess_test.p', mode='rb')) loaded_graph = tf.Graph() with tf.Session(graph=loaded_graph) as sess: # Load model loader = tf.train.import_meta_graph(save_model_path + '.meta') loader.restore(sess, save_model_path) # file_writer = tf.summary.FileWriter('tensorboard', sess.graph) # Get Tensors from loaded model loaded_x = loaded_graph.get_tensor_by_name('x:0') loaded_y = loaded_graph.get_tensor_by_name('y:0') loaded_keep_prob = loaded_graph.get_tensor_by_name('keep_prob:0') loaded_logits = loaded_graph.get_tensor_by_name('logits:0') loaded_acc = loaded_graph.get_tensor_by_name('accuracy:0') # Get accuracy in batches for memory limitations test_batch_acc_total = 0 test_batch_count = 0 for test_feature_batch, test_label_batch in helper.batch_features_labels(test_features, test_labels, batch_size): test_batch_acc_total += sess.run( loaded_acc, feed_dict={loaded_x: test_feature_batch, loaded_y: test_label_batch, loaded_keep_prob: 1.0}) test_batch_count += 1 print('Testing Accuracy: {}\n'.format(test_batch_acc_total/test_batch_count)) # Print Random Samples random_test_features, random_test_labels = tuple(zip(*random.sample(list(zip(test_features, test_labels)), n_samples))) random_test_predictions = sess.run( tf.nn.top_k(tf.nn.softmax(loaded_logits), top_n_predictions), feed_dict={loaded_x: random_test_features, loaded_y: random_test_labels, loaded_keep_prob: 1.0}) helper.display_image_predictions(random_test_features, random_test_labels, random_test_predictions) test_model() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Crear un entorno Step2: Notebooks Step3: Como véis, no hay puntos y coma al final de cada sentencia, le basta con fin de línea. Y en vez de printf usa print, que es mucho más sencillo. Step4: Visualizando datos Step5: Un ejemplo más completo Step6: Haciendo uso de Machine Learning Step7: Primero pintamos los puntos Step8: Aplicamos k-means Step9: Detectando criterio para abordar orquídeas	<ASSISTANT_TASK:> Python Code: #from IPython.display import HTML #HTML('''<script> #code_show=true; #function code_toggle() { # if (code_show){ # $('div.input').hide(); # } else { # $('div.input').show(); # }# # code_show = !code_show #} #$( ocument ).ready(code_toggle); #</script> #The raw code for this IPython notebook is by default hidden for easier reading. #To toggle on/off the raw code, click <a href="javascript:code_toggle()">here</a>.''') from IPython.display import YouTubeVideo YouTubeVideo("qb7FT68tcA8") print("Hola a todos") sumcars = 0 sumwords = 0 for word in ['hola', 'a', 'todos']: print("Frase: ", word) sumcars += len(word) sumwords += 1 print("Se han mostrado ", sumwords, " palabras y ", sumwords, " caracteres") %pylab inline import matplotlib import matplotlib.pyplot as plt import numpy as np x = np.arange(30) plt.plot(x, x2) # example with a legend and latex symbols fig, ax = plt.subplots() ax.plot(x, x2, label=r"$y = \alpha^2$") ax.plot(x, x**3, label=r"$y = \alpha^3$") ax.legend(loc=2) # upper left corner ax.set_xlabel(r'$\alpha$', fontsize=18) ax.set_ylabel(r'$y$', fontsize=18) ax.set_title('Ejemplo más completo'); import sklearn.datasets import sklearn.cluster import matplotlib.pyplot as plot # Creamos los puntos n = 1000 k = 4 # Generate fake data data, labels = sklearn.datasets.make_blobs( n_samples=n, n_features=2, centers=k) plot.scatter(data[:, 0], data[:, 1]) # scikit-learn kmeans = sklearn.cluster.KMeans(k, max_iter=300) kmeans.fit(data) means = kmeans.cluster_centers_ plot.scatter(data[:, 0], data[:, 1], c=labels) plot.scatter(means[:, 0], means[:, 1], linewidths=2, color='r') plot.show() import seaborn as sns iris = sns.load_dataset("iris") g = sns.PairGrid(iris, hue="species") g.map(plt.scatter); g = g.add_legend() from sklearn import datasets # load the iris dataset iris = datasets.load_iris() # start with the first two features: sepal length (cm) and sepal width (cm) X = iris.data[:100,:2] # save the target values as y y = iris.target[:100] # Define bounds on the X and Y axes X_min, X_max = X[:,0].min()-.5, X[:,0].max()+.5 y_min, y_max = X[:,1].min()-.5, X[:,1].max()+.5 for target in set(y): x = [X[i,0] for i in range(len(y)) if y[i]==target] z = [X[i,1] for i in range(len(y)) if y[i]==target] plt.scatter(x,z,color=['red','blue'][target], label=iris.target_names[:2][target]) plt.xlabel('Sepal Length') plt.ylabel('Sepal Width') plt.xlim(X_min,X_max) plt.ylim(y_min,y_max) plt.title('Scatter Plot of Sepal Length vs. Sepal Width') plt.legend(iris.target_names[:2], loc='lower right') plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Next, generate some data to use for our fitting and plotting. This generates the same dataset as in the AstroML demo. Step2: Component Number Selection Step3: Cross-Validation Step4: We can see here that the cross-validation test prefers the maximum number of components (10) that we allowed for the model (and in fact, the score continues to rise as more components are added beyond 10). This is a result of the particular dataset being fit Step5: Saving to and Reading from a File Step6: Once the model is saved, it can be read into an XDGMM object using the read_model() function, or a new XDGMM object can be initialized directly from the saved model file. Note that if both a filename and model parameters are passed to the constructor, the parameters saved in the file will override those passed by the user. Step7: Sampling from the Model Step8: Conditioning the Model Step9: Note how the number of components in the conditioned model is the same as in the original joint model, but that the weights of the components have changed, and the mu array is now 1-dimensional (since $y$ has been conditioned out). Step10: As expected, the conditioning results are the same. Labels will also be saved to and read from files when the save_model() and read_model() functions are used. Step11: If we sample 1000 points from this conditional distribution, we would get something like this Step12: Conditional Prediction	<ASSISTANT_TASK:> Python Code: %matplotlib inline import numpy as np from matplotlib import pyplot as plt from xdgmm import XDGMM from sklearn.model_selection import validation_curve from sklearn.model_selection import ShuffleSplit from demo_plots import * ''' Due to AstroML still using the deprecated GMM class from scikit-learn (instead of GaussianMixture), this demo will throw numerous errors whenever the XDGMM object calls an AstroML method, such as fit. The lines below will suppress these warnings; comment them out to see everything. This XDGMM class has been updated to use GaussianMixture instead of GMM when necessary, but since it uses an AstroML XDGMM object to store and manipulate the model, it is dependent on AstroML. These warnings will continue to occur until the XDGMM class from AstroML has been updated. ''' import warnings warnings.filterwarnings('ignore') N = 2000 np.random.seed(0) # generate the true data x_true = (1.4 + 2 * np.random.random(N)) ** 2 y_true = 0.1 * x_true 2 # add scatter to "true" distribution dx = 0.1 + 4. / x_true 2 dy = 0.1 + 10. / x_true ** 2 x_true += np.random.normal(0, dx, N) y_true += np.random.normal(0, dy, N) # add noise to get the "observed" distribution dx = 0.2 + 0.5 * np.random.random(N) dy = 0.2 + 0.5 * np.random.random(N) x = x_true + np.random.normal(0, dx) y = y_true + np.random.normal(0, dy) # stack the results for computation X = np.vstack([x, y]).T Xerr = np.zeros(X.shape + X.shape[-1:]) diag = np.arange(X.shape[-1]) Xerr[:, diag, diag] = np.vstack([dx 2, dy 2]).T # Instantiate an XDGMM model: xdgmm = XDGMM() # Define the range of component numbers, and get ready to compute the BIC for each one: param_range = np.array([1,2,3,4,5,6,7,8,9,10]) # Loop over component numbers, fitting XDGMM model and computing the BIC: bic, optimal_n_comp, lowest_bic = xdgmm.bic_test(X, Xerr, param_range) plot_bic(param_range, bic, optimal_n_comp) param_range = np.array([1,2,3,4,5,6,7,8,9,10]) shuffle_split = ShuffleSplit(3, test_size=0.3,random_state=0) train_scores,test_scores = validation_curve(xdgmm, X=X, y=Xerr, param_name="n_components", param_range=param_range, n_jobs=3, cv=shuffle_split, verbose=1) train_scores_mean = np.mean(train_scores, axis=1) train_scores_std = np.std(train_scores, axis=1) test_scores_mean = np.mean(test_scores, axis=1) test_scores_std = np.std(test_scores, axis=1) plot_val_curve(param_range, train_scores_mean, train_scores_std, test_scores_mean, test_scores_std) xdgmm.n_components = optimal_n_comp xdgmm = xdgmm.fit(X, Xerr) xdgmm.save_model('demo_model.fit') # Read model into an existing XDGMM object xdgmm.read_model('demo_model.fit') # Initialize a new XDGMM object using the model xdgmm2 = XDGMM(filename='demo_model.fit') # Comparison --- the arrays should be the same. print xdgmm.weights print xdgmm2.weights sample = xdgmm.sample(N) plot_sample(x_true, y_true, x, y, sample, xdgmm) cond_X = np.array([np.nan, 1.5]) cond_Xerr = np.array([0.0,0.05]) cond_xdgmm = xdgmm.condition(X_input = cond_X,Xerr_input = cond_Xerr) # Compare the conditioned model to the original: print xdgmm.weights print cond_xdgmm.weights print "\n" print xdgmm.mu print cond_xdgmm.mu # First, set the labels in the XDGMM object xdgmm.labels = np.array(['x','y']) # The dictionary can pass either floats or tuples cond_dict = {'y':(1.5,0.05)} cond_xdgmm2 = xdgmm.condition(X_dict = cond_dict) # Print the weights and means of the new model. print cond_xdgmm2.weights print cond_xdgmm2.mu print cond_xdgmm2.labels plot_cond_model(xdgmm, cond_xdgmm, 1.5) cond_sample = cond_xdgmm.sample(1000) y = np.ones(1000)*1.5 plot_cond_sample(cond_sample,y) # Simulate a dataset: true_sample = xdgmm.sample(1000) true_x = true_sample[:,0] y = true_sample[:,1] # Predict x values given y values: predicted_x = np.array([]) for this_y in y: # Specify y-conditioning to apply to P(x,y): on_this = np.array([np.nan,this_y]) # Compute conditional PDF P(x\|y): cond_gmm = xdgmm.condition(on_this) # Draw a sample x value from this PDF, and add it to the growing list predicted_x = np.append(predicted_x, cond_gmm.sample()) # Plot the two datasets, to compare the true x and the predicted x: plot_conditional_predictions(y, true_x, predicted_x) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Introduction Step2: Mini-summary Step3: Mini-summary Step4: Mini-summary Step5: Mini-summary Step6: Mini-summary Step7: Mini-summary	<ASSISTANT_TASK:> Python Code: %matplotlib inline import sys # system module import numpy as np # scientific computing import pandas as pd # data package import matplotlib as mpl import matplotlib.pyplot as plt # graphics module #Step 1: Input Data import pandas as pd #Use pandas to read data into Python from our computers. path = '/Users/Haley/Desktop/Final_Project_Data.xlsx' #Read data with the complete path sheet1 = pd.read_excel(path, sheetname='Civilian Labor Force by Sex', skip_footer =7, index_col = 0) print('Data types:\n\n', sheet1.dtypes,sep='') print('Dimensions:', sheet1.shape) sheet1.head() #Step 2: Draw graphs fig, ax = plt.subplots(2, 1, figsize=(8,8)) # create fig and ax objects sheet11 = sheet1[['Number of women in the civilian labor force (in thousands)', 'Number of men in the civilian labor force (in thousands)']] sheet11.plot(ax=ax[0], kind='line', # line plot color=['red', 'green'], # line color alpha=0.65) ax[0].legend(['Number of women in the civilian labor force', 'Number of men in the civilian labor force'], fontsize=8, loc=0) ax[0].set_ylabel('Number in the civlian force in thousands') ax[0].set_xlabel('Date') ax[0].set_ylim(0) ax[0].set_title('Civilian Labor Force by Sex (1948-2015)', fontsize=14, loc='left') sheet12=sheet1[['Share of the civilian labor force who are women (percent)', 'Share of the civilian labor force who are men (percent)']] sheet12.plot(ax=ax[1], kind='line', # line plot color=['red', 'green'], # line color alpha=0.65) ax[1].legend(['% of women in the civilian labor force', '% of men in the civilian labor force'], fontsize=8, loc=0) ax[1].set_ylabel('% in the civlian force') ax[1].set_xlabel('Date') ax[1].set_ylim(0) ax[0].spines["top"].set_visible(False) ax[0].spines["bottom"].set_visible(False) ax[0].spines["right"].set_visible(False) ax[0].spines["left"].set_visible(False) ax[1].spines["top"].set_visible(False) ax[1].spines["bottom"].set_visible(False) ax[1].spines["right"].set_visible(False) ax[1].spines["left"].set_visible(False) #Step 1: Input Data sheet2 = pd.read_excel(path, sheetname='Labor Force Participation Rate', skiprows = 1, index_col = 0, usecols =(range(3)) #only need the first three cols ) sheet2 #Step 2: Draw a graph plt.plot(sheet2.index, sheet2['All Women']) plt.plot(sheet2.index, sheet2['All Men']) plt.title('Labor Force Partipation Rate by Sex', fontsize=14, loc='left') # add title plt.ylabel('Labor Force Participation Rate') # y axis label plt.xlabel('Year') # y axis label #Step 1: Input Data sheet3 = pd.read_excel(path, sheetname='Median annual earnings by sex', skiprows = 2, index_col = 0, usecols =(range(3)) #only need the first three cols ) sheet3 #To do list #Draw a line graph #calculate the difference in year 1960 and the difference in year 2014 #Step 2: Draw a graph sheet3.plot(title='Median Annual Earnings by Sex', color=['r','g']) #Step 1: Input Data sheet4 = pd.read_excel(path, sheetname='Participation Rate by Edu Sex', skip_footer = 6, index_col = 0 ) sheet4=sheet4[['Women','Men']] #Step 2: Draw a graph sheet4.plot(figsize=(17,6), ylim=(0,100), kind='bar', color=['red','g'],alpha=0.5, title='Participation Rate by Edu Sex') #Step 1: Input Data sheet5 = pd.read_excel(path, sheetname='Employed parents by status', skip_footer = 4, skiprows=1, index_col = 0, #usecols=['Age of youngest child','Percent of total employed of mothers','Percent of total employed of fathers'] # sheet5["Type"] == 'Full-time' ) sheet16 = sheet5[sheet5['Type'] == 'Full-time'] sheet16 sheet17 = sheet5[sheet5['Type'] == 'Part-time'] sheet17 fig, ax = plt.subplots(2, 1, figsize=(14,14)) # create fig and ax objects sheet16.plot(ax=ax[0], kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax[0].legend(['Mothers', 'Fathers'], fontsize=10, loc='center') ax[0].set_ylabel('Percent of total employed') ax[0].set_xlabel('Age of youngest child') ax[0].set_ylim(0) ax[0].set_title('Employed parents by full-time status, sex and age of youngest child, 2015 annual averages', fontsize=10, loc='left') sheet17.plot(ax=ax[1], kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax[1].legend(['Mothers', 'Fathers'], fontsize=10, loc='center') ax[1].set_ylabel('Percent of total employed') ax[1].set_xlabel('Age of youngest child') ax[1].set_ylim(0) ax[1].set_title('Employed parents by part-time status, sex and age of youngest child, 2015 annual averages', fontsize=10, loc='left') ax[0].spines["top"].set_visible(False) ax[0].spines["right"].set_visible(False) ax[0].spines["left"].set_visible(False) ax[1].spines["top"].set_visible(False) ax[1].spines["left"].set_visible(False) fig, ax = plt.subplots(figsize=(12,4)) sheet16.plot(ax=ax, kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax.set_ylabel('Employment rates') ax.set_xlabel('Age of the youngest child') ax.set_ylim(0) ax.set_title('Employment Rate of parents', fontsize=14) ax.legend(fontsize=8, loc=0) ax.spines["top"].set_visible(False) #Step 1: Input Data sheet6 = pd.read_excel(path, sheetname='Unemployment Rate of parents', skip_footer = 4, index_col = 0) sheet6 #Step 2: Draw a graph fig, ax = plt.subplots(figsize=(12,4)) sheet6.plot(ax=ax, kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax.set_ylabel('Unemployment rates') ax.set_xlabel('Age of the youngest child') ax.set_ylim(0) ax.set_title('Unemployment Rate of parents', fontsize=14) ax.legend(fontsize=8, loc=0) ax.spines["top"].set_visible(False) #if column == "under 3 years": # y_pos += 0.5 #Step 1: Import Data sheet7 = pd.read_excel(path, sheetname='Table 8B Important', skiprows = 3, skip_footer = 4, index_col = 0) sheet71=sheet7[['Men.1','Women.1']] sheet71 = sheet71.rename(columns={'Men.1': 'Men', 'Women.1': 'Women'}) sheet71=sheet71.iloc[[4, 5, 6, 13, 12,16], :] sheet71 #Step 2: Draw a graph fig, ax = plt.subplots(figsize=(12,4)) sheet71.plot(ax=ax, kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax.set_ylabel('Average Hours per Day ') ax.set_ylim(0) ax.set_title('American Use of Time by Sex When the Youngest Child is Under 6', fontsize=14) ax.legend(['Men', 'Women'],fontsize=8, loc='best') ax.spines["top"].set_visible(False) #Step 1: Import Data sheet7 = pd.read_excel(path, sheetname='Table 8B Important', skiprows = 3, skip_footer = 4, index_col = 0) sheet72=sheet7[['Men.2','Women.2']] sheet72 = sheet72.rename(columns={'Men.2': 'Men', 'Women.2': 'Women'}) sheet72=sheet72.iloc[[4, 5, 6, 13, 12,16], :] sheet72 #Step 2: Draw a graph fig, ax = plt.subplots(figsize=(12,4)) sheet72.plot(ax=ax, kind='bar', # line plot color=['purple', 'yellow'], # line color alpha=0.5, width=0.4) ax.set_ylabel('Average Hours per Day ') ax.set_ylim(0) ax.set_title('American Use of Time by Sex When the Youngest Child is Between 6 to 17', fontsize=14) ax.legend(['Men', 'Women'],fontsize=8, loc='best') ax.spines["top"].set_visible(False) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Once Alascan is instantiated and finished running, we can plot the results. The plotScan_interactive function by default, outputs the results in an html file and opens it up in your browser. However, if you are using a notebook to view it, you can display the plot inline by passing the argument display_output='notebook' to the function. Here we display it in the notebook so that it's easier to view alongside the code. Step2: The plotScan_interactive function displays a bar plot similar to plotScan but now hovering over specific bars displays the corresponding asssociation/solvation free energy values. Additionally, clicking and dragging in the plot allows you to zoom in a subset of values. The plotly modebar in the top right has additional options such as zoom, autoscale and saving as a static image.	<ASSISTANT_TASK:> Python Code: from aesop import Alascan, plotScan_interactive, plotNetwork_interactive path_apbs = 'path\to\executable\apbs' path_coulomb = 'path\to\executable\coulomb' path_pdb2pqr = 'path\to\executable\pdb2pqr' jobname = 'alascan' pdbfile = 'barnase_barstar.pdb' selstr = ['chain A', 'chain B'] alascan = Alascan(pdb=pdbfile, pdb2pqr_exe=path_pdb2pqr, apbs_exe=path_apbs, coulomb_exe=path_coulomb, jobname=jobname, selstr=selstr, minim=False) alascan = Alascan(pdb=pdbfile, jobname=jobname, selstr=selstr) alascan.run() plotScan_interactive(alascan,display_output='notebook') #If you are not using a notebook to run your code then use the code below instead: #plotScan_interactive(alascan) plotNetwork_interactive(alascan,display_output='notebook') #If you are not using a notebook to run your code then use the code below instead: #plotNetwork_interactive(alascan) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Download the Cincinnati 311 (Non-Emergency) Service Requests data Step2: Parse the 1st record Step3: Implement a class that parses and cleans a Cincinnati 311 data record	<ASSISTANT_TASK:> Python Code: from Cincinnati311CSVDataParser import Cincinnati311CSVDataParser from csv import DictReader import os import re import urllib2 data_dir = "./Data" csv_file_path = os.path.join(data_dir, "cincinnati311.csv") if not os.path.exists(csv_file_path): if not os.path.exists(data_dir): os.mkdir(data_dir) url = 'https://data.cincinnati-oh.gov/api/views' +\ '/4cjh-bm8b/rows.csv?accessType=DOWNLOAD' response = urllib2.urlopen(url) html = response.read() with open(csv_file_path, 'wb') as h_file: h_file.write(html) h_file = open("./Data/cincinnati311.csv", "r") fieldnames = [re.sub("_", "", elem.lower())\ for elem in h_file.readline().rstrip().split(',')] readerobj = DictReader(h_file, fieldnames) print readerobj.next() h_file.close() # head -n 3 cincinnati311.csv > sample.csv h_file = open("./Data/sample.csv", "r") parserobj = Cincinnati311CSVDataParser(h_file) for record in parserobj: print record h_file.close() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Problema Prático 4.6 Step2: Exemplo 4.7 Step3: Problema Prático 4.7 Step4: Teorema de Thèvenin Step5: Problema Prático 4.8 Step6: Exemplo 4.9 Step7: Problema Prático 4.9 Step8: Exemplo 4.10 Step9: Problema Prático 4.10	<ASSISTANT_TASK:> Python Code: print("Exemplo 4.6") #trasforma fonte 1 (corrente -> tensao) #vs1 = isR = 12V #Req em serie entre 4 e 2 #Req1 = 4 + 2 = 6 #transforma fonte 2 (tensao -> corrente) #is2 = 12/3 = 4A #transforma fonte 1 (tensao -> corrente) #is1 = 12/6 = 2A #Req paralelo entre 6 e 3 #Req2 = 63/(6 + 3) = 2 #fonte resultante #ir = is2 - is1 = 4 - 2 = 2A #transforma fonte 2 (corrente -> tensao) #vs2 = Req2ir = 2 2 = 4V #divisor tensao #v0 = vs28/(8 + Req2) v0 = 48/(8 + 2) print("Tensao v0",v0,"V") print("Problema Prático 4.6") #Req serie 4 e 1 = 5 #Req paralelo 6 e 3 = 2 #transforma fonte 1 (corrente -> tensao) #vs1 = Ris1 = 52 = 10V #soma fonte 1 e 2 = 5 + 10 = 15V #transforma fonte soma (tensao -> corrente) #is = 15/2 = 7,5A #Req paralelo 5 e 2 = 10/7 #soma fonte corrente = 7,5 + 3 = 10,5 A #divisor corrente i0 = 10.5(10/7)/((10/7) + 7) print("Corrente i0:",i0,"A") print("Exemplo 4.7") #transforma fonte 1 (tensao -> corrente) #is1 = 6/2 = 3 A #transforma fonte dep. (corrente -> tensao) #vs_dep = 0.25Vx 4 = Vx #soma fonte dep. e fonte 2 = 18 + Vx #Req paralelo 2 e 2 = 1 #transforma fontes soma (tensao -> corrente) #is_soma = 18/4 + Vx/4 #soma fontes = 18/4 + Vx/4 + 3 = 30/4 + Vx/4 = (30 + Vx)/4 #transforma fontes soma (corrente -> tensao) #fonte resultante = ((30 + Vx)/4)4 = 30 + Vx #LKT #(30 + Vx) - 4ix - Vx = 0 #ix = (30 + Vx)/5 = 6 + Vx/5 #30 - 24 - 4Vx/5 = 0 vx = 65/4 print("Tensão Vx",vx,"V") print("Problema Prático 4.7") #transforma fonte dep. (tensao -> corrente) #is_dep = 2ix/5 #soma fontes = 0.024 - 2ix #divisor corrente #ix = (24m - 2ix)5/(5 + 10) #ix = (0.12 - 10ix)/15 #ix + 2ix/3 = 0.008 #5ix/3 = 0.008 ix = 0.0083/5 print("Corrente ix:",ix,"A") print("Exemplo 4.8") #Req1 = 412/(4 + 12) = 48/16 = 3 #Rth = 3 + 1 = 4 #transforma fonte 1 (tensao -> corrente) #is1 = 32/4 = 8 A #soma fontes = 8 + 2 = 10 A #ix = 104/(4 + 12) = 40/16 = 5/2 #Vab = 12(5/2) = 30 = Vth Vth = 30 Rth = 4 Rl = 6 Il = Vth/(Rl + Rth) print("Para RL = 6, Corrente:",Il,"A") Rl = 16 Il = Vth/(Rl + Rth) print("Para RL = 6, Corrente:",Il,"A") Rl = 36 Il = Vth/(Rl + Rth) print("Para RL = 6, Corrente:",Il,"A") print("Problema Prático 4.8") #Req1 = 6 + 6 = 12 #Rth = Req14/(Req1 + 4) = 48/16 = 3 Rth = 3 #Superposicao Vsource #Vab1 = Vs4/(4 + 6 + 6) = 124/16 = 3V #Superposicao Csource #Iab = Is6/(4 + 6 + 6) = 26/16 = 3/4 #Vab2 = Iab4 = 3V #Vth = Vab1 + Vab2 Vth = 6 I = Vth/(Rth + 1) print("Tensao Vth:",Vth,"V") print("Resistencia Rth:",Rth) print("Corrente I:",I,"A") print("Exemplo 4.9") import numpy as np #Descobrir Rth - desliga fontes indep., nao se alteram fontes dep. #Aplicar tensao vo arbitraria entre terminais a b #vo = 1 V #Analise de malhas #-2Vx + 2(i1 - i2) = 0 #Vx = i1 - i2 #Vx = -4i2 #i1 + 3i2 = 0 #-Vx + 2(i2 - i1) + 6(i2 - i3) = 0 #2i2 - 2i1 + 6i2 - 6i3 = Vx #-3i1 + 9i2 - 6i3 = 0 #-i1 + 3i2 - 2i3 = 0 #Vo + 6(i3 - i2) + 2i3 = 0 #6i3 - 6i2 + 2i3 = -1 #-6i2 + 8i3 = -1 coef = np.matrix("1 3 0;-1 3 -2;0 -6 8") res = np.matrix("0;0;-1") I = np.linalg.inv(coef)res #i3 = -i0 io = -I[2] #Rth = Vo/io Rth = 1/io print("Resistencia Rth:",float(Rth)) #Descobrir Vth #Analise de tensao em terminais a b #Analise de Malhas #i1 = 5 A #-2Vx + 2(i2 - i3) = 0 #Vx = i2 - i3 #Vx = 4(5 - i3) = 20 - 4i3 #i2 + 3i3 = 20 #4(i3 - 5) + 2(i3 - i2) + 6i3 = 0 #4i3 +2i3 - 2i2 + 6i3 = 20 #-2i2 + 12i3 = 20 #-i2 + 6i3 = 10 coef = np.matrix("1 3;-1 6") res = np.matrix("20;10") I = np.linalg.inv(coef)res Vth = 6I[1] print("Tensão Vth:",float(Vth),"V") print("Problema Prático 4.9") #Descobrir Rth #Vo = 1V #Analise Nodal #i1 - Ix/2 = 0 #v1/5 - Ix/2 = 0 #Ix = (v1 - 1)/3 #v1/5 - (v1 - 1)/6 = 0 #v1/5 - v1/6 = -1/6 #v1/30 = -1/6 #v1 = -5 #Ix = (v1 - 1)/3 = -6/3 = -2 A #i2 = 1/4 A #io = -Ix + i2 = 9/4 A #Rth = 1/(9/4) = 4/9 Rth = 4/9 print("Resistencia Rth:",Rth) #Descobrir Vth #Analise de Malhas #-6 + 5i1 + 3Ix + 4Ix = 0 #5i1 + 7Ix = 6 #3Ix/2 + i1 = Ix #Ix/2 + i1 = 0 #2i1 + Ix = 0 coef = np.matrix("5 7;2 1") res = np.matrix("6;0") I = np.linalg.inv(coef)res Ix = float(I[1]) Vth = 4Ix print("Tensão Vth:",Vth,"V") print("Exemplo 4.10") #vab = -vo = -1 V #i1 = 1/4 A #ix = 1/2 A #i0 = 2ix - ix - i1 = 1 - 1/2 - 1/4 = 1/4 A #Rth = -1/(1/4) = -4 Rth = -4 print("Resistencia Rth:", Rth) print("Tensao Vth:",0,"V") print("Problema Prático 4.10") #iab = 1 A #-vx + 10i1 + 4vx + 15(i1 - iab) = 0 #3vx + 25i1 - 15iab = 0 #vx = -5i1 #-15i1 + 25i1 = 15 #10i1 = 15 #i1 = 1,5 A = 3/2 A #vx = -5i1 = -7,5 V = -15/2 V #vdep = 4vx = -30V #vab = vo = 15(i1 - iab) = 15/2 = 7,5V #Rth = vo/(-iab) = -7,5 Rth = -7.5 print("Tensao Vth:",0,"V") print("Resistencia Rth",Rth) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: This distribution was generated using 100,000 random data points with zero mean ($\mu = 0$) and unit variance ($\sigma^2 = 1$). Thus, the true ATE is zero, meaning there is no treatment effect, and we see that the histogram is centered around that value. We can also see the variation around zero. We'll discuss this next. Step2: We could also use NumPy's built-in standard deviation method. Step3: This can be expressed in terms of potential outcomes (Gerber and Green, 2012) Step4: Let's set our $N$ and $m$ variables. Step5: Next, we'll generate some data from a normal distribution. In the first example, the treatment, t, and the control, c, will be centered at 5. We'll combine the treatment and control arrays. Step6: The experimental test statistic is Step7: Here, we should expect a high $p$-value. Step8: Using the data from [7], we find that the permuted test statistics are as extreme as the experimental test statistic 65% of the time. This means, we don't have enough evidence to say that the experimental test statistic is different from zero. Step9: The new experimental test statistic is Step10: Because the values are actually different, the $p$-value should be low.	<ASSISTANT_TASK:> Python Code: import numpy as np import pandas as pd import matplotlib as mpl import matplotlib.pyplot as plt %matplotlib inline mpl.style.use('ggplot') mpl.rc('savefig', dpi=100) np.random.seed(42) # data mu, sigma = 0, 1 x = mu + sigma * np.random.randn(100000) # plot pd.Series(x).plot(kind='hist', bins=50, color='#000000', alpha=0.5, normed=True) # plot options plt.title('Sampling Distribution Example') plt.xlabel('ATE Estimates') plt.ylabel('Density') plt.tick_params(axis='both', top='off', bottom='off', left='off', right='off') (((x - x.mean()) 2).mean()) 0.5 x.std() from code.permutation import permutation_test N, m = 50, 25 np.random.seed(42) t = np.random.normal(loc=5, size=m) c = np.random.normal(loc=5, size=N-m) outcomes = np.append(t, c) t.mean() - c.mean() permutation_test(outcomes, m) np.random.seed(42) t = np.random.normal(loc=6, size=m) c = np.random.normal(loc=5, size=N-m) outcomes = np.append(t, c) t.mean() - c.mean() permutation_test(outcomes, m) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: 2. Tokenize name into (surname, title, first name and maiden name) Step2: 2.1 Extract features from Title variable Step3: It seems we can extract some info from title Step4: 3 Examine marriages / sibling relationships Step5: Initialize data structures for algorithm Step6: 1. Extract marriages in greedy fashion. Assume is_married has no fp ( might have actually	<ASSISTANT_TASK:> Python Code: train = pd.read_csv("data/train.csv") train["dataset"] = "train" train.head() test = pd.read_csv("data/test.csv") test["dataset"] = "test" test.head() #Combine both datasets to predict families train = train.append(test) train.set_index(train["PassengerId"],inplace=True) name_tokenizer = re.compile(r"^(?P<surname>[^,]+), (?P<title>[A-Z a-z]+?)\. (?P<f_name>[A-Z a-z.]+)?(?P<maiden_name>$[A-Za-z .]+$)?") name_tokens = ["surname","title","f_name","maiden_name"] for name_tk in name_tokens: train[name_tk] = train.Name.apply(lambda x: name_tokenizer.match(x).group(name_tk)) test[name_tk] = test.Name.apply(lambda x: name_tokenizer.match(x).group(name_tk)) train.head(n=5) print train.groupby(["title","Sex"]).size() #Encode special title following this logic train.has_special_title = train.title.apply(lambda x: x not in ["Mr","Mrs","Miss","Mme","Mlle","Master"]) def is_married(couple_rows): are_married=False if couple_rows.irow(0).Sex != couple_rows.irow(1).Sex: #Get who is the husband and whose the wife man = couple_rows.irow(0) if couple_rows.irow(0).Sex == "male" else couple_rows.irow(1) woman = couple_rows.irow(0) if couple_rows.irow(0).Sex == "female" else couple_rows.irow(1) #Marriage tests marriage_tests = {} marriage_tests["same_f_name"] = woman.f_name is not None and woman.f_name in man.f_name marriage_tests["consistent_title"] = woman.title not in ("Miss","Mlle") and man.title != "Master" marriage_tests["same_ticket"] = woman.Ticket == man.Ticket marriage_tests["same_pclass"] = woman.Pclass == man.Pclass marriage_tests["legal_age"] = (woman.title in ("Mme","Mrs") or woman.Age >= 10) and man.Age > 10 marriage_tests["consistent_SibSp"] = (woman.SibSp > 0 and man.SibSp > 0) or (woman.SibSp == man.SibSp) are_married = marriage_tests["same_f_name"] and marriage_tests["legal_age"] or ( ) consistency_checks = ( marriage_tests["consistent_title"] and marriage_tests["legal_age"] and marriage_tests["same_pclass"] and marriage_tests["same_ticket"] and marriage_tests["consistent_SibSp"]) if are_married and not consistency_checks: failed_tests = ", ".join("{}:{}".format(x,marriage_tests[x]) for x in marriage_tests if not marriage_tests[x]) print "WARNING: Sketchy marriage: {}".format(failed_tests) print couple_rows print return are_married #Data structures - sets to keep track which ones have already been assigned married_people = set() people_with_parents = set() links_to_assign = train[["SibSp","Parch"]] #Matches a couple with the Max amount of kids they can have #Which is the min(husband.Parch, wife.Parch) marriages_table = {} #Subset only people who have spouses/siblings on the boat train_sibsp = train.ix[ train.SibSp > 0] #People grouped by surname surname_groups = train_sibsp.groupby("surname").groups for surname in surname_groups: surname_rows = surname_groups[surname] couples = itertools.combinations(surname_rows,2) for cpl in couples: cpl_rows = train_sibsp.ix[list(cpl)] if is_married(cpl_rows): #Make sure we're not marrying somebody twice :p assert cpl[0] not in married_people,"{} is already married :/".format(cpl[0]) assert cpl[1] not in married_people,"{} is already married :/".format(cpl[1]) #add couples to married set married_people.add(cpl[0]) married_people.add(cpl[1]) marriages_table[cpl] = min(links_to_assign.ix[cpl[0]]["Parch"], links_to_assign.ix[cpl[1]]["Parch"] ) #print # break marriages_table train.ix[list((26,1066))] train.ix[ (train.SibSp > 0) \| (train.Parch > 0) ].shape train <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The station number and date range we are interested in are part of the URL that we use to communicate with the web services. The specific file we receive when the read_csv command runs doesn't exist -- when our script requests the data, the server reads the URL to see what we want, pulls data from a database, packages it, and passes it on to us. The API (the protocol that governs the communication between machines) establishes the "formula" for writing the URL. As long as we follow that formula (and request data that exists), the server will provide it for us. Step2: Python dictionaries to URLs {.callout} Step3: Just like there is the Numpy library for matrices and Pandas for tabular data, there is a Python library that provides a simple interface for accessing resources through URLs (take a look at the most popular package repository Step4: This is not the most elegant way to write the URL but it accomplishes the job! To clean things up a bit, we can replace the values we want to be able to change with variables Step5: We can now combine it with the rest of our code Step6: Creating Functions Step7: The function definition opens with the word def, which is followed by the name of the function and a parenthesized list of parameter names. The body of the function — the statements that are executed when it runs — is indented below the definition line, typically by four spaces. Step8: The boiling point of water in Kelvin should be 373.15 K, not 273.15 K! Step9: 5 divided by 9 should be 0.5556, but when we ask Python 2 to divide to integers, it returns an integer! If we want to want to keep the fractional part of the division, we need to convert one or the other number to floating point Step10: You can also turn an integer into a float by casting Step11: Casting {.challenge} Step12: Composing Functions Step13: What about converting Fahrenheit to Celsius? We could write out the formula, but we don’t need to. Instead, we can compose the two functions we have already created Step14: This is our first taste of how larger programs are built Step15: We can make another function plot_discharge to compose to plot and save the figures Step16: The function plot_discharge produces output that is visible to us but has no return statement because it doesn't need to give anything back when it is called. Step17: Now that these three functions exist, we can rewrite our previous code in a much simpler script Step18: Testing and Documenting Step19: There’s a better way, though. If the first thing in a function is a string that isn’t assigned to a variable, that string is attached to the function as its documentation. A string like this is called a docstring (one set of quotes for single line strings, three sets for multi-line strings!) Step20: This is better because we can now ask Python’s built-in help system to show us the documentation for the function Step21: Defining Defaults Step22: As this example shows, parameters are matched up from left to right, and any that haven’t been given a value explicitly get their default value. We can override this behavior by naming the value as we pass it in	<ASSISTANT_TASK:> Python Code: import pandas as pd import matplotlib.pyplot as plt %matplotlib inline new_column_names = ['Agency', 'Station', 'OldDateTime', 'Timezone', 'Discharge_cfs', 'Discharge_stat', 'Stage_ft', 'Stage_stat'] url = 'http://waterservices.usgs.gov/nwis/iv/?format=rdb&sites=09380000&startDT=2016-01-01&endDT=2016-01-10&parameterCd=00060,00065' data = pd.read_csv(url, header=1, sep='\t', comment='#', names = new_column_names) data['DateTime'] = pd.to_datetime(data['OldDateTime']) new_station_name = "0" + str(data['Station'].unique()[0]) data['Station'] = new_station_name data.plot(x='DateTime', y='Discharge_cfs', title='Station ' + new_station_name) plt.xlabel('Time') plt.ylabel('Discharge (cfs)') plt.savefig('data/discharge_' + new_station_name + '.png') plt.show() url_root = 'http://waterservices.usgs.gov/nwis/iv/?' # root of URL url_1 = 'format=' + 'rdb' # file format url_2 = 'sites=' + '09380000' # station number url_3 = 'startDT=' + '2016-01-01' # start date url_4 = 'endDT=' + '2016-01-10' # end date url_5 = 'parameterCd=' + '00060,00065' # data fields url = url_root + url_1 + '&' + url_2 + '&' + url_3 + '&' + url_4 + '&' + url_5 print url url_dict = {} # create an empty dictionary url_dict['format'] = 'rdb' url_dict['sites'] = '09380000' url_dict['startDT'] = '2016-01-01' url_dict['endDT'] = '2016-01-10' url_dict['parameterCd'] = ['00060','00065'] print url_dict import urllib # need to set the parameter doseq to 1 to handle the list in url_dict['parameterCd'] url_parameters = urllib.urlencode(url_dict, doseq=1) print url_root + url_parameters this_station = '09380000' startDate = '2016-01-01' endDate = '2016-01-10' url_root = 'http://waterservices.usgs.gov/nwis/iv/?' url_1 = 'format=' + 'rdb' url_2 = 'sites=' + this_station url_3 = 'startDT=' + startDate url_4 = 'endDT=' + endDate url_5 = 'parameterCd=' + '00060,00065' url = url_root + url_1 + '&' + url_2 + '&' + url_3 + '&' + url_4 + '&' + url_5 print url import pandas as pd import matplotlib.pyplot as plt %matplotlib inline ########## change these values ########### this_station = '09380000' startDate = '2016-01-01' endDate = '2016-01-10' ########################################## # create the URL url_root = 'http://waterservices.usgs.gov/nwis/iv/?' url_1 = 'format=' + 'rdb' url_2 = 'sites=' + this_station url_3 = 'startDT=' + startDate url_4 = 'endDT=' + endDate url_5 = 'parameterCd=' + '00060,00065' url = url_root + url_1 + '&' + url_2 + '&' + url_3 + '&' + url_4 + '&' + url_5 # import the data new_column_names = ['Agency', 'Station', 'OldDateTime', 'Timezone', 'Discharge_cfs', 'Discharge_stat', 'Stage_ft', 'Stage_stat'] data = pd.read_csv(url, header=1, sep='\t', comment='#', names = new_column_names) # fix formatting data['DateTime'] = pd.to_datetime(data['OldDateTime']) new_station_name = "0" + str(data['Station'].unique()[0]) data['Station'] = new_station_name # plot and save figure data.plot(x='DateTime', y='Discharge_cfs', title='Station ' + new_station_name) plt.xlabel('Time') plt.ylabel('Discharge (cfs)') plt.savefig('data/discharge_' + new_station_name + '.png') plt.show() def fahr_to_kelvin(temp): return ((temp - 32) * (5/9)) + 273.15 print 'freezing point of water:', fahr_to_kelvin(32) print 'boiling point of water:', fahr_to_kelvin(212) 5/9 print 'two integers:', 5/9 print '5.0/9:', 5.0/9 print '5/9.0:', 5/9.0 float(5)/9 def fahr_to_kelvin(temp): return ((temp - 32) * (5./9)) + 273.15 print 'freezing point of water:', fahr_to_kelvin(32) print 'boiling point of water:', fahr_to_kelvin(212) def kelvin_to_celsius(temp_k): return temp_k - 273.15 print 'absolute zero in Celsius:', kelvin_to_celsius(0.0) def fahr_to_celsius(temp_f): temp_k = fahr_to_kelvin(temp_f) temp_c = kelvin_to_celsius(temp_k) return temp_c print 'freezing point of water in Celsius:', fahr_to_celsius(32.0) def import_streamgage_data(url): new_column_names = ['Agency', 'Station', 'OldDateTime', 'Timezone', 'Discharge_cfs', 'Discharge_stat', 'Stage_ft', 'Stage_stat'] data = pd.read_csv(url, header=1, sep='\t', comment='#', names = new_column_names) # fix formatting data['DateTime'] = pd.to_datetime(data['OldDateTime']) new_station_name = "0" + str(data['Station'].unique()[0]) data['Station'] = new_station_name return data def plot_discharge(data): data.plot(x='DateTime', y='Discharge_cfs', title='Station ' + new_station_name) plt.xlabel('Time') plt.ylabel('Discharge (cfs)') plt.savefig('data/discharge_' + new_station_name + '.png') plt.show() def generate_URL(station, startDT, endDT): url_root = 'http://waterservices.usgs.gov/nwis/iv/?' url_1 = 'format=' + 'rdb' url_2 = 'sites=' + station url_3 = 'startDT=' + startDT url_4 = 'endDT=' + endDT url_5 = 'parameterCd=' + '00060,00065' url = url_root + url_1 + '&' + url_2 + '&' + url_3 + '&' + url_4 + '&' + url_5 return url ########## change these values ########### this_station = '09380000' startDate = '2016-01-01' endDate = '2016-01-10' ########################################## url = generate_URL(this_station, startDate, endDate) data = import_streamgage_data(url) plot_discharge(data) # plot_discharge(data): take a DataFrame containing streamgage data, plot the discharge and save a figure to file. def plot_discharge(data): data.plot(x='DateTime', y='Discharge_cfs', title='Station ' + new_station_name) plt.xlabel('Time') plt.ylabel('Discharge (cfs)') plt.savefig('data/discharge_' + new_station_name + '.png') plt.show() def plot_discharge(data): ''' Take a DataFrame containing streamgage data, plot the discharge and save a figure to file. ''' data.plot(x='DateTime', y='Discharge_cfs', title='Station ' + new_station_name) plt.xlabel('Time') plt.ylabel('Discharge (cfs)') plt.savefig('data/discharge_' + new_station_name + '.png') plt.show() help(plot_discharge) def display(a=1, b=2, c=3): print 'a:', a, 'b:', b, 'c:', c print 'no parameters:' display() print 'one parameter:' display(55) print 'two parameters:' display(55, 66) print('only setting the value of c') display(c=77) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Download wikipedia dump files Step2: Convert two wikipedia dump files Step3: Initial training Step4: Japanese new idol group, "Babymetal", weren't known worldwide in 2010, so that the word, "babymetal", is not in oldmodel vocaburary. Step5: Online update Step6: Model Comparison Step7: After online training, the word, "babymetal", is added in model. This word is simillar with rock and metal bands. Step8: The word, "Zootopia", become disney movie through the years.	<ASSISTANT_TASK:> Python Code: from gensim.corpora.wikicorpus import WikiCorpus from gensim.models.word2vec import Word2Vec, LineSentence from pprint import pprint from copy import deepcopy from multiprocessing import cpu_count %%bash wget https://dumps.wikimedia.org/archive/2010/2010-11/enwiki/20101011/enwiki-20101011-pages-articles.xml.bz2 wget https://dumps.wikimedia.org/enwiki/20160820/enwiki-20160820-pages-articles.xml.bz2 old, new = [WikiCorpus('enwiki-{}-pages-articles.xml.bz2'.format(ymd)) for ymd in ['20101011', '20160820']] def write_wiki(wiki, name, titles = []): with open('{}.wiki'.format(name), 'wb') as f: wiki.metadata = True for text, (page_id, title) in wiki.get_texts(): if title not in titles: f.write(b' '.join(text)+b'\n') titles.append(title) return titles old_titles = write_wiki(old, 'old') all_titles = write_wiki(new, 'new', old_titles) oldwiki, newwiki = [LineSentence(f+'.wiki') for f in ['old', 'new']] %%time model = Word2Vec(oldwiki, min_count = 0, workers=cpu_count()) # model = Word2Vec.load('oldmodel') oldmodel = deepcopy(model) oldmodel.save('oldmodel') try: print(oldmodel.most_similar('babymetal')) except KeyError as e: print(e) %%time model.build_vocab(newwiki, update=True) model.train(newwiki, total_examples=model.corpus_count, epochs=model.iter) model.save('newmodel') # model = Word2Vec.load('newmodel') for m in ['oldmodel', 'model']: print('The vocabulary size of the', m, 'is', len(eval(m).wv.vocab)) try: pprint(model.most_similar('babymetal')) except KeyError as e: print(e) w = 'zootopia' for m in ['oldmodel', 'model']: print('The count of the word,'+w+', is', eval(m).wv.vocab[w].count, 'in', m) pprint(eval(m).most_similar(w)) print('') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: TicTaeToe 게임 Step2: TicTaeToe게임을 간단 버젼으로 구현한 것으로 사용자가 먼저 착수하여 승부를 겨루게 됩니다.	<ASSISTANT_TASK:> Python Code: # 운영체제 !ver # 현재 위치 및 하위 디렉토리 구조 !dir # 파이선 버전 !python --version # 가상환경 버전 !virtualenv --version # 존재하는 가상환경 목록 !workon # 가상환경 kookmin1에 진입 # workon kookmin1 # 가상환경 kookmin1에 설치된 패키지 # 데이터 분석 : numpy, pandas # 시각화 : matplotlib !pip freeze from IPython.display import Image Image(filename='images/TicTaeToe.png') # %load TicTaeToe.py import sys import random # 게임 방범 설명 print("출처: http://www.practicepython.org") print("==================================") print("가로, 세로, 대각선 방향으로 ") print("세점을 먼저 이어 놓으면 이기는") print("게임으로 사용자(U)와 Computer(C)가") print("번갈아 놓습니다.") print("==================================\n") # 3 x 3 정보를 담기 위한 저장소 선언 # 0 은 초기 상태 # 1 은 사용자가 선택한 곳 # 2 는 컴퓨터가 선택한 곳 dim=3 list4 = [0,0,0,0,0,0,0,0,0] # 사용자 안내를 위한 박스를 그리고 그 안에 번호 넣기 def graph(): k = 1 for i in range(dim+1): print(" ---"dim) for j in range(dim): if (i < dim): print("\| "+str(k), end=" ") k = k + 1 if (i != 3): print("\|") # 사용자 또는 컴퓨터가 수를 둘때 마다, # 누가 이겼는지 체크 def game_wins(list4): #print(list4) for i in range(dim): #checks to see if you win in a column if list4[i] == list4[i+3] == list4[i+6] == 1: print("You Won") elif list4[i] == list4[i+3] == list4[i+6] == 2: print("You Lost") #checks to see if you win in a row if list4[dimi] == list4[dimi+1] == list4[dimi+2] == 1: print ("You Won") elif list4[dimi] == list4[dimi+1] == list4[dimi+2] == 2: print("You Lost") #checks to see if you win in a diagonal if list4[0] == list4[4] == list4[8] == 1: print ("You Won") elif list4[0] == list4[4] == list4[8] == 2: print("You Lost") if list4[2] == list4[4] == list4[6] == 1: print ("You Won") elif list4[2] == list4[4] == list4[6] == 2: print("You Lost") # 사용자 안내를 위한 박스를 그리고 그 안에 번호 또는 둔 수 표기 def graph_pos(list4): for idx in range(len(list4)): if (idx % 3 == 0): print(" ---"dim) if (list4[idx] == 0): print("\| "+str(idx+1), end=" ") elif (list4[idx] == 1): print("\| "+"U", end=" ") else: print("\| "+"C", end=" ") if (idx % 3 == 2): print("\|") print("\n") # 게임 시작 go = input("Play TicTaeToe? Enter, or eXit?") if (go == 'x' or go == 'X'): sys.exit(0) graph() print("\n") while(1): # 보드게임이 승부가 날때까지 무한 반복 # 빈곳 선택 pos = int(input("You : ")) - 1 while (pos < 0 or pos > 8 or list4[pos] != 0): pos = int(input("Again : ")) - 1 list4[pos] = 1 # 보드를 갱신하여 그리고, 승부 체크 graph_pos(list4) game_wins(list4) # 컴퓨터 차례로, 빈곳을 랜덤하게 선택하여 List에 저장 pos = random.randrange(9) while (list4[pos] != 0): pos = random.randrange(9) print("Computer : " + str(pos+1)) list4[pos] = 2 # 보드를 갱신하여 그리고, 승부 체크 graph_pos(list4) game_wins(list4) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Step 2 create your request Step2: Step 3 set the coordinates for your request (for instance, let us choose Curiosity landing site) Step3: Step 4 retrieve fields from the Mars Climate Database (all fields are stored in the req object) Step4: Step 5 print requested results Step5: Main atmospheric variables Step6: Shortcut Step7: The extvar number can also be used to inquire a specific variable (see Fortran sources). Step8: Another way to inquire for a specific variable is through a string. Step9: Print all field Step10: 1D slices Step11: ... and for several variables Step12: Request seasonal cycle (this takes a longer time) Step13: It is a good place here to remind you that any field stored in the Mars Climate Database is inside the req object. Step14: 1D slices Step15: 2D mapping Step16: You can also use the method htmlmap2d that will create a PNG file with your figure in it. This is the function actually used in the online MCD interface. Step17: Adding wind vectors can be done with the incwind argument. Step18: NB Step19: NB Step20: advanced diagnostics Step21: Zonal average Step22: Zonal average Step23: see difference with following case	<ASSISTANT_TASK:> Python Code: from mcd import mcd # This line configures matplotlib to show figures embedded in the notebook. %matplotlib inline req = mcd() req.lat = -4.6 # latitude req.lon = 137.4 # longitude req.loct = 15. # local time req.xz = 1. # vertical coordinate req.xdate = 150.6 # areocentric longitude req.update() req.printcoord() req.printmeanvar() req.printmcd() req.printextvar(22) req.printextvar("tsurf") req.printallextvar() req.diurnal() req.plot1d("t") req.plot1d(["t","p","u","v"]) req.xzs = -3500. req.xze = 15000. req.zkey = 2 req.lat = 25. req.lon = 195. req.loct = 4.2 req.xdate = 140. req.profile(nd=50) req.plot1d("t") tpot = req.temptab((610./req.prestab)*(1.0/3.9)) print tpot req = mcd() req.diurnal() req.getascii("t",filename="diurnal.txt") %cat diurnal.txt ; rm -rf diurnal.txt test = mcd() test.loct = 15. test.xz = 10000. test.map2d("t") test.htmlmap2d("t") test.map2d("t",incwind=True) test.map2d(["t","u"]) figname = test.getnameset()+'.png' print figname test = mcd() test.xz = 50000. test.lat = 20. test.locts = 0. test.locte = 24. test.lons = -180. test.lone = +180. test.htmlplot2d("tsurf",figname="hov.png") test = mcd() test.zonmean = True test.lats = -90. test.late = 90. test.htmlplot2d("u",figname="zonm.png") test = mcd() test.zonmean = True test.lats = -90. test.late = 90. test.xdates = 0. test.xdatee = 360. test.htmlplot2d("h2ovap",figname="zonmm.png") test.zonmean = False test.lon = 0. test.htmlplot2d("h2ovap",figname="hovls.png") <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description:	<ASSISTANT_TASK:> Python Code: import tensorflow as tf seed_x = 10 ### return the tensor as variable 'result' def g(seed_x): tf.random.set_seed(seed_x) return tf.random.uniform(shape=(10,), minval=1, maxval=5, dtype=tf.int32) result = g(seed_x) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: A 3d arrow is designed as a right cone and a disk as its base. We define the standard cone, as the cone of vertex, Vert(0,0, headsize), and angle theta between the symmetry axis, Oz, and any generatrice Step2: Place a 3d arrow along a line, starting from a point on that line, called origin below Step3: Parameterize the Moebius strip and define it as a Plotly surface Step4: Define a unicolor colorscale, to plot the cones and disks defining the 3d arrows Step5: The following function returns the Plotly traces that represent a 3d arrow Step6: Define the normals along the central circle, i.e. the curve corresponding to v=0 in the Moebius strip parameterization Step7:	<ASSISTANT_TASK:> Python Code: import numpy as np import plotly.graph_objects as go def arrow3d(headsize, theta): r = headsizenp.tan(theta) u = np.linspace(0,2np.pi, 60) v = np.linspace(0, 1, 15) U,V = np.meshgrid(u,v) #parameterization of the standard cone x = rVnp.cos(U) y = rVnp.sin(U) z = headsize(1-V) cone = np.stack((x,y,z)) #shape(3, m, n) w = np.linspace(0, r, 10) u, w = np.meshgrid(u,w) #parameterization of the base disk xx = wnp.cos(u) yy = wnp.sin(u) zz = np.zeros(w.shape) disk = np.stack((xx,yy,zz)) return cone, disk def place_arrow3d(start, end, headsize, theta): # Move the standard arrow to a position in the 3d space, # which is computed from the inputted data # start = array of shape (3,) = the starting point of the arrow's support line # end = array of shape(3, ) = the end point of the segment of line # headsize # theta=the angle between the symmetry axis and a generatrice epsilon=1.0e-04 # any coordinate less than epsilon is considered 0 cone, disk = arrow3d(headsize, theta)#get the standard cone arr_dir = end-start# the arrow direction if np.linalg.norm(arr_dir) > epsilon: #define a right orthonormal basis (u1, u2, u3), with u3 the unit vector of the arrow_dir u3 = arr_dir/np.linalg.norm(arr_dir) origin = end-headsize u3 #the point where the arrow starts on the supp line a, b, c = u3 if abs(a) > epsilon or abs(b) > epsilon: v1 = np.array([-b, a, 0])# v1 orthogonal to u3 u1 = v1/np.linalg.norm(v1) else: u1 = np.array([1., 0, 0]) u2 = np.cross(u3, u1)# this def ensures that the orthonormal basis is a right one T = np.vstack((u1, u2, u3)).T #Transformation T, T(e_i)=u_i, to be applied to the standard cone cone = np.einsum('ji, imn -> jmn', T, cone)#Transform the standard cone disk = np.einsum('ji, imn -> jmn', T, disk)#Transform the cone base cone = np.apply_along_axis(lambda a, v: a+v, 0, cone, origin)#translate the cone; #dir translation, v=vec(O,origin) disk = np.apply_along_axis(lambda a, v: a+v, 0, disk, origin)# translate the cone base return origin, cone, disk else: return (0, ) u = np.linspace(0, 2np.pi, 36) v = np.linspace(-0.5, 0.5, 10) u, v = np.meshgrid(u,v) tp = 1+vnp.cos(u/2.) x = tpnp.cos(u) y = tpnp.sin(u) z = vnp.sin(u/2.) fig= go.Figure(go.Surface( x=x, y=y, z=z, colorscale="balance", colorbar=dict(thickness=20, len=0.6))) pl_c = [[0.0, 'rgb(179, 56, 38)'], [1.0, 'rgb(179, 56, 38)']] def get_normals(start, origin, cone, disk, colorscale=pl_c): tr_cone=go.Surface( x=cone[0, :, :], y=cone[1, :, :], z=cone[2, :, :], colorscale=colorscale, showscale=False) tr_disk=go.Surface( x=disk[0, :, :], y=disk[1, :, :], z=disk[2, :, :], colorscale=colorscale, showscale=False) tr_line=go.Scatter3d( x=[start[0], origin[0]], y=[start[1], origin[1]], z=[start[2], origin[2]], mode='lines', line=dict(width=3, color='rgb(60, 9, 17)') ) return [tr_line, tr_cone, tr_disk] #return a list that is concatenated to data u = np.linspace(0, 2np.pi, 24) xx = np.cos(u) yy = np.sin(u) zz = np.zeros(xx.shape) starters = np.vstack((xx,yy,zz)).T a = 0.3 #Normal coordinates Nx = 2np.cos(u)np.sin(u/2) Ny = np.cos(u/2)-np.cos(3u/2) Nz = -2np.cos(u) ends = starters+a*np.vstack((Nx,Ny, Nz)).T for j in range(ends.shape[0]): arr=place_arrow3d(starters[j], ends[j], 0.15, np.pi/15) if len(arr)==3:# get normals at the regular points on a surface, i.e. where \|\|Normalvector\|\| not = 0 fig.add_traces(get_normals(starters[j], arr[0], arr[1], arr[2])) fig.update_layout(title_text='<br>A vector field along the central circle of the Moebius strip', title_x=0.5, font_family='Balto', width=675, height=675, showlegend=False, scene=dict(camera_eye=dict(x=1.65, y=1.65, z=0.75), aspectmode='data')) from IPython.core.display import HTML def css_styling(): styles = open("./custom.css", "r").read() return HTML(styles) css_styling() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: TASK Step2: TASK Step3: TASK Step4: TASK Step5: TASK Step6: TASK Step7: TASK Step8: TASK Step9: TASK Step10: TASK Step11: TASK Step12: TASK	<ASSISTANT_TASK:> Python Code: # CODE HERE import pandas as pd df = pd.read_csv('bank.csv') # CODE HERE df.head() # CODE HERE df['age'].mean() # CODE HERE df['age'].idxmin() df.iloc[503]['marital'] # CODE HERE df['job'].nunique() # CODE HERE df['job'].value_counts() #CODE HERE # Many, many ways to do this one! Here is just one way: 100*df['marital'].value_counts()['married']/len(df) # df['marital].value_counts() df['default code'] = df['default'].map({'no':0,'yes':1}) df.head() # CODE HERE df['marital code'] = df['marital'].apply(lambda status: status[0]) df.head() # CODE HERE df['duration'].max() # CODE HERE df[df['job']=='unemployed']['education'].value_counts() # CODE HERE df[df['job']=='unemployed']['age'].mean() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Document Authors Step2: Document Contributors Step3: Document Publication Step4: Document Table of Contents Step5: 1.2. Model Name Step6: 1.3. Scheme Scope Step7: 1.4. Basic Approximations Step8: 1.5. Prognostic Variables Form Step9: 1.6. Number Of Tracers Step10: 1.7. Family Approach Step11: 2. Key Properties --> Software Properties Step12: 2.2. Code Version Step13: 2.3. Code Languages Step14: 3. Key Properties --> Timestep Framework Step15: 3.2. Split Operator Advection Timestep Step16: 3.3. Split Operator Physical Timestep Step17: 3.4. Integrated Timestep Step18: 3.5. Integrated Scheme Type Step19: 4. Key Properties --> Meteorological Forcings Step20: 4.2. Variables 2D Step21: 4.3. Frequency Step22: 5. Key Properties --> Resolution Step23: 5.2. Canonical Horizontal Resolution Step24: 5.3. Number Of Horizontal Gridpoints Step25: 5.4. Number Of Vertical Levels Step26: 5.5. Is Adaptive Grid Step27: 6. Key Properties --> Tuning Applied Step28: 6.2. Global Mean Metrics Used Step29: 6.3. Regional Metrics Used Step30: 6.4. Trend Metrics Used Step31: 7. Transport Step32: 7.2. Scheme Step33: 7.3. Mass Conservation Scheme Step34: 7.4. Convention Step35: 8. Emissions Step36: 8.2. Method Step37: 8.3. Sources Step38: 8.4. Prescribed Climatology Step39: 8.5. Prescribed Climatology Emitted Species Step40: 8.6. Prescribed Spatially Uniform Emitted Species Step41: 8.7. Interactive Emitted Species Step42: 8.8. Other Emitted Species Step43: 8.9. Other Method Characteristics Step44: 9. Concentrations Step45: 9.2. Prescribed Lower Boundary Step46: 9.3. Prescribed Upper Boundary Step47: 9.4. Prescribed Fields Mmr Step48: 9.5. Prescribed Fields Mmr Step49: 10. Optical Radiative Properties Step50: 11. Optical Radiative Properties --> Absorption Step51: 11.2. Dust Step52: 11.3. Organics Step53: 12. Optical Radiative Properties --> Mixtures Step54: 12.2. Internal Step55: 12.3. Mixing Rule Step56: 13. Optical Radiative Properties --> Impact Of H2o Step57: 13.2. Internal Mixture Step58: 14. Optical Radiative Properties --> Radiative Scheme Step59: 14.2. Shortwave Bands Step60: 14.3. Longwave Bands Step61: 15. Optical Radiative Properties --> Cloud Interactions Step62: 15.2. Twomey Step63: 15.3. Twomey Minimum Ccn Step64: 15.4. Drizzle Step65: 15.5. Cloud Lifetime Step66: 15.6. Longwave Bands Step67: 16. Model Step68: 16.2. Processes Step69: 16.3. Coupling Step70: 16.4. Gas Phase Precursors Step71: 16.5. Scheme Type Step72: 16.6. Bulk Scheme Species	<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'test-institute-3', 'sandbox-1', 'aerosol') # Set as follows: DOC.set_author("name", "email") # TODO - please enter value(s) # Set as follows: DOC.set_contributor("name", "email") # TODO - please enter value(s) # Set publication status: # 0=do not publish, 1=publish. DOC.set_publication_status(0) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.model_overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.model_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.scheme_scope') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "troposhere" # "stratosphere" # "mesosphere" # "mesosphere" # "whole atmosphere" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.basic_approximations') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.prognostic_variables_form') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "3D mass/volume ratio for aerosols" # "3D number concenttration for aerosols" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.number_of_tracers') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.family_approach') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.software_properties.repository') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.software_properties.code_version') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.software_properties.code_languages') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.timestep_framework.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Uses atmospheric chemistry time stepping" # "Specific timestepping (operator splitting)" # "Specific timestepping (integrated)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.timestep_framework.split_operator_advection_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.timestep_framework.split_operator_physical_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.timestep_framework.integrated_timestep') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.timestep_framework.integrated_scheme_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Explicit" # "Implicit" # "Semi-implicit" # "Semi-analytic" # "Impact solver" # "Back Euler" # "Newton Raphson" # "Rosenbrock" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.meteorological_forcings.variables_3D') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.meteorological_forcings.variables_2D') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.meteorological_forcings.frequency') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.resolution.name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.resolution.canonical_horizontal_resolution') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.resolution.number_of_horizontal_gridpoints') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.resolution.number_of_vertical_levels') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.resolution.is_adaptive_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.tuning_applied.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.tuning_applied.global_mean_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.tuning_applied.regional_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.key_properties.tuning_applied.trend_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.transport.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.transport.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Uses Atmospheric chemistry transport scheme" # "Specific transport scheme (eulerian)" # "Specific transport scheme (semi-lagrangian)" # "Specific transport scheme (eulerian and semi-lagrangian)" # "Specific transport scheme (lagrangian)" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.transport.mass_conservation_scheme') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Uses Atmospheric chemistry transport scheme" # "Mass adjustment" # "Concentrations positivity" # "Gradients monotonicity" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.transport.convention') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Uses Atmospheric chemistry transport scheme" # "Convective fluxes connected to tracers" # "Vertical velocities connected to tracers" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.method') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Prescribed (climatology)" # "Prescribed CMIP6" # "Prescribed above surface" # "Interactive" # "Interactive above surface" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.sources') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Vegetation" # "Volcanos" # "Bare ground" # "Sea surface" # "Lightning" # "Fires" # "Aircraft" # "Anthropogenic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.prescribed_climatology') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant" # "Interannual" # "Annual" # "Monthly" # "Daily" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.prescribed_climatology_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.prescribed_spatially_uniform_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.interactive_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.other_emitted_species') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.emissions.other_method_characteristics') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.concentrations.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.concentrations.prescribed_lower_boundary') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.concentrations.prescribed_upper_boundary') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.concentrations.prescribed_fields_mmr') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.concentrations.prescribed_fields_mmr') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.absorption.black_carbon') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.absorption.dust') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.absorption.organics') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.mixtures.external') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.mixtures.internal') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.mixtures.mixing_rule') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.impact_of_h2o.size') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.impact_of_h2o.internal_mixture') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.radiative_scheme.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.radiative_scheme.shortwave_bands') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.radiative_scheme.longwave_bands') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.twomey') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.twomey_minimum_ccn') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.drizzle') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.cloud_lifetime') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.optical_radiative_properties.cloud_interactions.longwave_bands') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.processes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Dry deposition" # "Sedimentation" # "Wet deposition (impaction scavenging)" # "Wet deposition (nucleation scavenging)" # "Coagulation" # "Oxidation (gas phase)" # "Oxidation (in cloud)" # "Condensation" # "Ageing" # "Advection (horizontal)" # "Advection (vertical)" # "Heterogeneous chemistry" # "Nucleation" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.coupling') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Radiation" # "Land surface" # "Heterogeneous chemistry" # "Clouds" # "Ocean" # "Cryosphere" # "Gas phase chemistry" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.gas_phase_precursors') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "DMS" # "SO2" # "Ammonia" # "Iodine" # "Terpene" # "Isoprene" # "VOC" # "NOx" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.scheme_type') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Bulk" # "Modal" # "Bin" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.aerosol.model.bulk_scheme_species') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Sulphate" # "Nitrate" # "Sea salt" # "Dust" # "Ice" # "Organic" # "Black carbon / soot" # "SOA (secondary organic aerosols)" # "POM (particulate organic matter)" # "Polar stratospheric ice" # "NAT (Nitric acid trihydrate)" # "NAD (Nitric acid dihydrate)" # "STS (supercooled ternary solution aerosol particule)" # "Other: [Please specify]" # TODO - please enter value(s) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: matplotlib Step2: Next, we want to make sure that the plots that we create are displayed in this notebook. To achieve this we have to issue a command to be interpretted by Jupyter -- called a magic command. A magic command is preceded by a % character. Magics are not Python and will create errs if used outside of the Jupyter notebook Step3: A quick matplotlib example Step4: The plot function Step5: Example Step6: Example Step7: Example Step8: Example Step9: Figures, axes, and subplots Step10: In the previous example the figure() function creates a new figure and add_subplot() puts a new axis on the figure. The command fig.add_subplot(1,1,1) means divide the figure fig into a 1 by 1 grid and assign the first component of that grid to the variable ax1. Step11: Example Step12: Exporting figures to image files	<ASSISTANT_TASK:> Python Code: # Define T and g T = 40 y0 =50 g = 0 # Compute yT using the direct approach and print # Initialize a 1-dimensional array called y that has T+1 zeros # Set the initial value of y to equal y0 # Use a for loop to update the values of y one at a time # Print the final value in the array y # Import matplotlib.pyplot # Magic command for the Jupyter Notebook # Import numpy as np # Create an array of x values from -6 to 6 # Create a variable y equal to the sin of x # Use the plot function to plot the # Add a title and axis labels # Use the help function to see the documentation for plot # Create an array of x values from -6 to 6 # Create a variable y equal to the x squared # Use the plot function to plot the line # Add a title and axis labels # Add grid # Create an array of x values from -6 to 6 # Create y variables # Use the plot function to plot the lines # Add a title and axis labels # Set axis limits # legend # Add grid # Set betas # Create x values # create epsilon values from the standard normal distribution # create y # plot # Add a title and axis labels # Set axis limits # Add grid # Create an array of x values from -6 to 6 # Create y variables # Use the plot function to plot the lines # Add a title and axis labels # Add grid # legend # Create data # Create a new figure # Create axis # Plot # Add grid # Create data # Create a new figure # Create axis 1 and plot with title # Create axis 2 and plot with title # Create data # Create a new figure # Create axis 1 and plot with title # Create axis 2 and plot with title # Create axis 3 and plot with title # Create axis 4 and plot with title # Adjust margins # Create data x = np.arange(-6,6,0.001) y = np.sin(x) # Create a new figure, axis, and plot fig = plt.figure() ax1 = fig.add_subplot(1,1,1) ax1.plot(x,y,lw=3,alpha = 0.6) ax1.grid() # Save plt.savefig('fig_econ129_class04_sine.png',dpi=120) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: gpu info Step2: Understand the input Step3: Kernel Info from the single stream Step4: model 3 cuda streams Step5: start kernel from beginning Step6: set the h2d start for all the cuda streams Step7: merge all the cuda stream trace together Step8: start algorithm Step9: start algo	<ASSISTANT_TASK:> Python Code: %load_ext autoreload %autoreload 2 import warnings import pandas as pd import numpy as np import os import sys # error msg, add the modules import operator # sorting from math import * import matplotlib.pyplot as plt sys.path.append('../../') import cuda_timeline import read_trace import avgblk import cke from model_param import * #from df_util import * warnings.filterwarnings("ignore", category=np.VisibleDeprecationWarning) gtx950 = DeviceInfo() gtx950.sm_num = 6 gtx950.sharedmem_per_sm = 49152 gtx950.reg_per_sm = 65536 gtx950.maxthreads_per_sm = 2048 # init SM resources SM_resList, SM_traceList = init_gpu(gtx950) #SM_resList[0] SM_traceList[0] trace_s1 = 'trace_s1_5m.csv' df_trace_s1 = read_trace.Trace2dataframe(trace_s1) trace_s2 = 'trace_s2_5m.csv' df_trace_s2 = read_trace.Trace2dataframe(trace_s2) trace_s3 = 'trace_s3_5m.csv' df_trace_s3 = read_trace.Trace2dataframe(trace_s3) df_trace_s1 cuda_timeline.plot_trace(df_trace_s1) cuda_timeline.plot_trace(df_trace_s2) cuda_timeline.plot_trace(df_trace_s3) # extract kernel info from trace # warning: currently lmted to one kernel kernel = read_trace.GetKernelInfo(df_trace_s1, gtx950) Dump_kernel_info(kernel) # for each stream, have a dd for each kernel stream_kernel_list = [] stream_num = 3 for sid in range(stream_num): #print sid # key will be the kernel order # value will be the kernel info kern_dd = {} kern_dd[0] = Copy_kernel_info(kernel) stream_kernel_list.append(kern_dd) Dump_kernel_info(stream_kernel_list[0][0]) df_s1_trace_timing = read_trace.Get_timing_from_trace(df_trace_s1) df_s1 = read_trace.Reset_starting(df_s1_trace_timing) df_s1 # find when to start the stream and update the starting pos for the trace H2D_H2D_OVLP_TH = 3.158431 df_cke_list = cke.init_trace_list(df_s1, stream_num = stream_num, h2d_ovlp_th = H2D_H2D_OVLP_TH) df_cke_list[0] df_cke_list[1] df_cke_list[2] df_all_api = cke.init_sort_api_with_extra_cols(df_cke_list) df_all_api # stream_id list stream_list = [float(x) for x in range(stream_num)] # pick the 1st sleep api df_all_api, r1, r1_stream = cke.pick_first_sleep(df_all_api) df_all_api = SetWake(df_all_api, r1) df_all_api = UpdateCell(df_all_api, r1, 'current_pos', get_rowinfo(df_all_api, r1)['start']) df_all_api = UpdateCell(df_all_api, r1, 'pred_end', get_rowinfo(df_all_api, r1)['end']) print('row {}, stream-id {}'.format(r1, r1_stream)) stream_queue = [] stream_queue.append(r1_stream) ## conconcurrency cc = 1.0 # extract api calls from other streams df_other = df_all_api.loc[df_all_api.stream_id <> r1_stream] other_stream_ids = list(df_other.stream_id.unique()) other_stream_num = len(other_stream_ids) for i in range(other_stream_num): df_other, r2, r2_stream = cke.pick_first_sleep(df_other) print('row {}, stream-id {}'.format(r2, r2_stream)) df_all_api = SetWake(df_all_api, r2) df_all_api = UpdateCell(df_all_api, r2, 'current_pos', get_rowinfo(df_all_api, r2)['start']) df_all_api = UpdateCell(df_all_api, r2, 'pred_end', get_rowinfo(df_all_api, r2)['end']) #--------------- # if r1 and r2 are from the same stream, break the iteration, and finish r1 #--------------- if r1_stream == r2_stream: break # when they are not the same stream, check whether there is concurrency #----------------------- # move the current_pos to the starting of coming api r2, and update r1 status #----------------------- df_all_api = cke.StartNext_byType(df_all_api, [r1, r2]) #----------------------------- # if one call is done, continue the next round #----------------------------- if cke.CheckRowDone(df_all_api, [r1, r2]): continue whichType = cke.CheckType(df_all_api, r1, r2) # check whether the same api print whichType if whichType == None: # run noconflict pass elif whichType in ['h2d', 'd2h']: # data transfer in the same direction cc = cc + 1 df_all_api = cke.Predict_transferOvlp(df_all_api, [r1, r2], ways = cc) break else: # concurrent kernel: todo pass break # other_stream_list = cke.find_unique_streams(df_other) # find the 1st sleep api that is other stream # if there is overlapping, we start ovlp mode, if not finish r1, start current # go through each # rest_stream_list = [x for x in stream_list if x <> r1_stream] # print rest_stream_list # for sid in rest_stream_list: # df_stream = df_all_api.loc[df_all_api.stream_id == sid] df_all_api # # # run above count = 0 # break_count = 7 break_count = 7 while not cke.AllDone(df_all_api): count = count + 1 #if count == break_count: break #----------------------- # pick two api to model #----------------------- df_all_api, r1, r2 = cke.PickTwo(df_all_api) #if count == break_count: break #----------------------- # check the last api or not #----------------------- last_api = False if r1 == None and r2 == None: last_api = True if last_api == True: # go directly updating the last wake api df_all_api = cke.UpdateStream_lastapi(df_all_api) break #----------------------- # move the current_pos to the starting of coming api r2, and update r1 status #----------------------- df_all_api = cke.StartNext_byType(df_all_api, [r1, r2]) #if count == break_count: break #----------------------------- # if one call is done, continue the next round #----------------------------- if cke.CheckRowDone(df_all_api, r1, r2): continue #if count == break_count: break #----------------------------- # when all calls are active #----------------------------- #----------------------------- # check whether the two calls are kerns, if yes #----------------------------- whichType = cke.CheckType(df_all_api, r1, r2) # check whether the same api if whichType == None: df_all_api = cke.Predict_noConflict(df_all_api, r1, r2) elif whichType in ['h2d', 'd2h']: # data transfer in the same direction df_all_api = cke.Predict_transferOvlp(df_all_api, r1, r2, ways = 2.0) else: # concurrent kernel: todo print('run cke model') #cke.model_2cke(df_all_api, r1, r2) #if count == break_count: break r1_sid, r1_kid =cke.FindStreamAndKernID(df_all_api, r1) #print('r1_stream_id {} , r1_kernel_id {}'.format(r1_sid, r1_kid)) r2_sid, r2_kid =cke.FindStreamAndKernID(df_all_api, r2) #print('r2_stream_id {} , r2_kernel_id {}'.format(r2_sid, r2_kid)) r1_start_ms = cke.GetStartTime(df_all_api, r1) r2_start_ms = cke.GetStartTime(df_all_api, r2) #print r1_start_ms #print r2_start_ms #print('before:') #print('r1 start :{} r2 start : {}'.format(stream_kernel_list[r1_sid][r1_kid].start_ms, # stream_kernel_list[r2_sid][r2_kid].start_ms)) stream_kernel_list[0][0].start_ms = r1_start_ms stream_kernel_list[1][0].start_ms = r2_start_ms #print('after:') #print('r1 start :{} r2 start : {}'.format(stream_kernel_list[r1_sid][r1_kid].start_ms, # stream_kernel_list[r2_sid][r2_kid].start_ms)) #Dump_kern_info(stream_kernel_list[r1_sid][r1_kid]) #Dump_kern_info(stream_kernel_list[r2_sid][r2_kid]) kernels_ = [] kernels_.append(stream_kernel_list[r1_sid][r1_kid]) kernels_.append(stream_kernel_list[r2_sid][r2_kid]) SM_resList, SM_traceList = avgblk.cke_model(gtx950, SM_resList, SM_traceList, kernels_) # find the kernel execution time from the sm trace table result_kernel_runtime_dd = avgblk.Get_KernTime(SM_traceList) #print result_kernel_runtime_dd result_r1_start = result_kernel_runtime_dd[0][0] result_r1_end = result_kernel_runtime_dd[0][1] result_r2_start = result_kernel_runtime_dd[1][0] result_r2_end = result_kernel_runtime_dd[1][1] # r1 will be the 1st in dd, r2 will be the 2nd df_all_api.set_value(r1, 'pred_end', result_r1_end) df_all_api.set_value(r2, 'pred_end', result_r2_end) # Warning: it is better to have a pred_start # Warning: but we care about the end timing for now #if count == break_count: break # check any of r1 and r2 has status done. if done, go to next rangeT = cke.Get_pred_range(df_all_api) print rangeT #if count == break_count: break extra_conc = cke.Check_cc_by_time(df_all_api, rangeT) # check whether there is conc during the rangeT print('extra_conc {}'.format(extra_conc)) #if count == break_count: break if extra_conc == 0: if whichType in ['h2d', 'd2h']: df_all_api = cke.Update_wake_transferOvlp(df_all_api, rangeT, ways = 2.0) elif whichType == 'kern': df_all_api = cke.Update_wake_kernOvlp(df_all_api) else: # no overlapping df_all_api = cke.Update_wake_noConflict(df_all_api, rangeT) #if count == break_count: break # check if any api is done, and update the timing for the other apis in that stream df_all_api = cke.UpdateStreamTime(df_all_api) #if count == break_count: break else: # todo : when there is additional overlapping pass # if count == break_count: # break df_all_api df_2stream_trace df_s1 # # run above # <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: To create a Series we need to set the column (using usecols) to use and set the parameter squeeze to True. Step2: If the input file has only 1 column we don't need to provide the usecols argument. Step3: On Series we can perform classic python operation using Built-In Functions!	<ASSISTANT_TASK:> Python Code: import pandas as pd asd = pd.read_csv("data/input.csv") print type(asd) asd.head() # This is a Dataframe because we have multiple columns! data = pd.read_csv("data/input.csv", usecols=["name"], squeeze=True) print type(data) data.head() data.index data = pd.read_csv("data/input_with_one_column.csv", squeeze=True) print type(data) # HEAD print data.head(2), "\n" # TAIL print data.tail() list(data) dict(data) max(data) min(data) dir(data) type(data) sorted(data) data = pd.read_csv("data/input_with_two_column.csv", index_col="name", squeeze=True) data.head() data[["Alex", "asd"]] data["Alex":"Vale"] <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Contents Step2: All these traveling weather systems tend to move warm, moist air poleward and cold, dry air equatorward. There is thus a net poleward energy transport. Step3: At each timestep, the warm temperatures get cooler (at the equator) while the cold polar temperatures get warmer! Step4: <a id='section4'></a> Step5: We're going to plot the data and the best fit line, but also another line using these values Step6: Discuss these curves... Step7: The albedo increases markedly toward the poles. Step8: Of course we are not fitting all the details of the observed albedo curve. But we do get the correct global mean a reasonable representation of the equator-to-pole gradient in albedo. Step9: Example EBM using climlab Step10: The upshot Step11: When $D=0$, every latitude is in radiative equilibrium and the heat transport is zero. As we have already seen, this gives an equator-to-pole temperature gradient much too high.	<ASSISTANT_TASK:> Python Code: # Ensure compatibility with Python 2 and 3 from __future__ import print_function, division from IPython.display import YouTubeVideo YouTubeVideo('As85L34fKYQ') %matplotlib inline import numpy as np import matplotlib.pyplot as plt import climlab from climlab import constants as const # First define an initial temperature field # that is warm at the equator and cold at the poles # and varies smoothly with latitude in between from climlab.utils import legendre sfc = climlab.domain.zonal_mean_surface(num_lat=90, water_depth=10.) lat = sfc.lat.points initial = 12. - 40. * legendre.P2(np.sin(np.deg2rad(lat))) fig, ax = plt.subplots() ax.plot(lat, initial) ax.set_xlabel('Latitude') ax.set_ylabel('Temperature (deg C)') ## Set up the climlab diffusion process # make a copy of initial so that it remains unmodified Ts = climlab.Field(np.array(initial), domain=sfc) # thermal diffusivity in W/m*2/degC D = 0.55 # create the climlab diffusion process # setting the diffusivity and a timestep of ONE MONTH d = climlab.dynamics.MeridionalHeatDiffusion(name='Diffusion', state=Ts, D=D, timestep=const.seconds_per_month) print( d) # We are going to step forward one month at a time # and store the temperature each time niter = 5 temp = np.zeros((Ts.size, niter+1)) temp[:, 0] = np.squeeze(Ts) for n in range(niter): d.step_forward() temp[:, n+1] = np.squeeze(Ts) # Now plot the temperatures fig,ax = plt.subplots() ax.plot(lat, temp) ax.set_xlabel('Latitude') ax.set_ylabel('Temperature (deg C)') ax.legend(range(niter+1)) x = np.linspace(-1,1) fig,ax = plt.subplots() ax.plot(x, legendre.P2(x)) ax.set_title('$P_2(x)$') import xarray as xr ## The NOAA ESRL server is shutdown! January 2019 ncep_url = "http://www.esrl.noaa.gov/psd/thredds/dodsC/Datasets/ncep.reanalysis.derived/" ncep_Ts = xr.open_dataset( ncep_url + "surface_gauss/skt.sfc.mon.1981-2010.ltm.nc", decode_times=False) #url = 'http://apdrc.soest.hawaii.edu:80/dods/public_data/Reanalysis_Data/NCEP/NCEP/clima/' #ncep_Ts = xr.open_dataset(url + 'surface_gauss/skt') lat_ncep = ncep_Ts.lat; lon_ncep = ncep_Ts.lon print( ncep_Ts) Ts_ncep_annual = ncep_Ts.skt.mean(dim=('lon','time')) ncep_ulwrf = xr.open_dataset( ncep_url + "other_gauss/ulwrf.ntat.mon.1981-2010.ltm.nc", decode_times=False) ncep_dswrf = xr.open_dataset( ncep_url + "other_gauss/dswrf.ntat.mon.1981-2010.ltm.nc", decode_times=False) ncep_uswrf = xr.open_dataset( ncep_url + "other_gauss/uswrf.ntat.mon.1981-2010.ltm.nc", decode_times=False) #ncep_ulwrf = xr.open_dataset(url + "other_gauss/ulwrf") #ncep_dswrf = xr.open_dataset(url + "other_gauss/dswrf") #ncep_uswrf = xr.open_dataset(url + "other_gauss/uswrf") OLR_ncep_annual = ncep_ulwrf.ulwrf.mean(dim=('lon','time')) ASR_ncep_annual = (ncep_dswrf.dswrf - ncep_uswrf.uswrf).mean(dim=('lon','time')) from scipy.stats import linregress slope, intercept, r_value, p_value, std_err = linregress(Ts_ncep_annual, OLR_ncep_annual) print( 'Best fit is A = %0.0f W/m2 and B = %0.1f W/m2/degC' %(intercept, slope)) # More standard values A = 210. B = 2. fig, ax1 = plt.subplots(figsize=(8,6)) ax1.plot( Ts_ncep_annual, OLR_ncep_annual, 'o' , label='data') ax1.plot( Ts_ncep_annual, intercept + slope Ts_ncep_annual, 'k--', label='best fit') ax1.plot( Ts_ncep_annual, A + B * Ts_ncep_annual, 'r--', label='B=2') ax1.set_xlabel('Surface temperature (C)', fontsize=16) ax1.set_ylabel('OLR (W m$^{-2}$)', fontsize=16) ax1.set_title('OLR versus surface temperature from NCEP reanalysis', fontsize=18) ax1.legend(loc='upper left') ax1.grid() days = np.linspace(1.,50.)/50 * const.days_per_year Qann_ncep = climlab.solar.insolation.daily_insolation(lat_ncep, days ).mean(dim='day') albedo_ncep = 1 - ASR_ncep_annual / Qann_ncep albedo_ncep_global = np.average(albedo_ncep, weights=np.cos(np.deg2rad(lat_ncep))) print( 'The annual, global mean planetary albedo is %0.3f' %albedo_ncep_global) fig,ax = plt.subplots() ax.plot(lat_ncep, albedo_ncep) ax.grid(); ax.set_xlabel('Latitude') ax.set_ylabel('Albedo'); # Add a new curve to the previous figure a0 = albedo_ncep_global a2 = 0.25 ax.plot(lat_ncep, a0 + a2 * legendre.P2(np.sin(np.deg2rad(lat_ncep)))) fig # Some imports needed to make and display animations from IPython.display import HTML from matplotlib import animation def setup_figure(): templimits = -20,32 radlimits = -340, 340 htlimits = -6,6 latlimits = -90,90 lat_ticks = np.arange(-90,90,30) fig, axes = plt.subplots(3,1,figsize=(8,10)) axes[0].set_ylabel('Temperature (deg C)') axes[0].set_ylim(templimits) axes[1].set_ylabel('Energy budget (W m$^{-2}$)') axes[1].set_ylim(radlimits) axes[2].set_ylabel('Heat transport (PW)') axes[2].set_ylim(htlimits) axes[2].set_xlabel('Latitude') for ax in axes: ax.set_xlim(latlimits); ax.set_xticks(lat_ticks); ax.grid() fig.suptitle('Diffusive energy balance model with annual-mean insolation', fontsize=14) return fig, axes def initial_figure(model): # Make figure and axes fig, axes = setup_figure() # plot initial data lines = [] lines.append(axes[0].plot(model.lat, model.Ts)[0]) lines.append(axes[1].plot(model.lat, model.ASR, 'k--', label='SW')[0]) lines.append(axes[1].plot(model.lat, -model.OLR, 'r--', label='LW')[0]) lines.append(axes[1].plot(model.lat, model.net_radiation, 'c-', label='net rad')[0]) lines.append(axes[1].plot(model.lat, model.heat_transport_convergence, 'g--', label='dyn')[0]) lines.append(axes[1].plot(model.lat, model.net_radiation+model.heat_transport_convergence, 'b-', label='total')[0]) axes[1].legend(loc='upper right') lines.append(axes[2].plot(model.lat_bounds, model.heat_transport)[0]) lines.append(axes[0].text(60, 25, 'Day 0')) return fig, axes, lines def animate(day, model, lines): model.step_forward() # The rest of this is just updating the plot lines[0].set_ydata(model.Ts) lines[1].set_ydata(model.ASR) lines[2].set_ydata(-model.OLR) lines[3].set_ydata(model.net_radiation) lines[4].set_ydata(model.heat_transport_convergence) lines[5].set_ydata(model.net_radiation+model.heat_transport_convergence) lines[6].set_ydata(model.heat_transport) lines[-1].set_text('Day {}'.format(int(model.time['days_elapsed']))) return lines # A model starting from isothermal initial conditions e = climlab.EBM_annual() e.Ts[:] = 15. # in degrees Celsius e.compute_diagnostics() # Plot initial data fig, axes, lines = initial_figure(e) ani = animation.FuncAnimation(fig, animate, frames=np.arange(1, 100), fargs=(e, lines)) HTML(ani.to_html5_video()) D = 0.1 model = climlab.EBM_annual(A=210, B=2, D=D, a0=0.354, a2=0.25) print( model) model.param model.integrate_years(10) fig, axes = plt.subplots(1,2, figsize=(12,4)) ax = axes[0] ax.plot(model.lat, model.Ts, label=('D = %0.1f' %D)) ax.plot(lat_ncep, Ts_ncep_annual, label='obs') ax.set_ylabel('Temperature (degC)') ax = axes[1] energy_in = np.squeeze(model.ASR - model.OLR) ax.plot(model.lat, energy_in, label=('D = %0.1f' %D)) ax.plot(lat_ncep, ASR_ncep_annual - OLR_ncep_annual, label='obs') ax.set_ylabel('Net downwelling radiation at TOA (W m$^{-2}$)') for ax in axes: ax.set_xlabel('Latitude'); ax.legend(); ax.grid(); def inferred_heat_transport( energy_in, lat_deg ): '''Returns the inferred heat transport (in PW) by integrating the net energy imbalance from pole to pole.''' from scipy import integrate from climlab import constants as const lat_rad = np.deg2rad( lat_deg ) return ( 1E-15 * 2 * np.math.pi * const.a*2 integrate.cumtrapz( np.cos(lat_rad)*energy_in, x=lat_rad, initial=0. ) ) fig, ax = plt.subplots() ax.plot(model.lat, inferred_heat_transport(energy_in, model.lat), label=('D = %0.1f' %D)) ax.set_ylabel('Heat transport (PW)') ax.legend(); ax.grid() ax.set_xlabel('Latitude') Darray = np.arange(0., 2.05, 0.05) model_list = [] Tmean_list = [] deltaT_list = [] Hmax_list = [] for D in Darray: ebm = climlab.EBM_annual(A=210, B=2, a0=0.354, a2=0.25, D=D) ebm.integrate_years(20., verbose=False) Tmean = ebm.global_mean_temperature() deltaT = np.max(ebm.Ts) - np.min(ebm.Ts) energy_in = np.squeeze(ebm.ASR - ebm.OLR) Htrans = inferred_heat_transport(energy_in, ebm.lat) Hmax = np.max(Htrans) model_list.append(ebm) Tmean_list.append(Tmean) deltaT_list.append(deltaT) Hmax_list.append(Hmax) color1 = 'b' color2 = 'r' fig = plt.figure(figsize=(8,6)) ax1 = fig.add_subplot(111) ax1.plot(Darray, deltaT_list, color=color1) ax1.plot(Darray, Tmean_list, 'b--') ax1.set_xlabel('D (W m$^{-2}$ K$^{-1}$)', fontsize=14) ax1.set_xticks(np.arange(Darray[0], Darray[-1], 0.2)) ax1.set_ylabel('$\Delta T$ (equator to pole)', fontsize=14, color=color1) for tl in ax1.get_yticklabels(): tl.set_color(color1) ax2 = ax1.twinx() ax2.plot(Darray, Hmax_list, color=color2) ax2.set_ylabel('Maximum poleward heat transport (PW)', fontsize=14, color=color2) for tl in ax2.get_yticklabels(): tl.set_color(color2) ax1.set_title('Effect of diffusivity on temperature gradient and heat transport in the EBM', fontsize=16) ax1.grid() ax1.plot([0.6, 0.6], [0, 140], 'k-'); %load_ext version_information %version_information numpy, scipy, matplotlib, xarray, climlab <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Exploring data file Step2: Ok.. Step3: Now we need to know the sampling rate Step4: So, the format seems to be 'hours Step5: That's pretty low. Step6: That's actually not bad! Step7: The first thing to note is that amplitude varies dramatically. Let's run it through a bandpass filter and take out all frequencies that definitely are not heart rate. Step8: Still low quality but at least the heart rate is quite visible now! Step9: That seems a reasonable result. By far the most peaks are marked correctly, and most peaksin noisy sections (low confidence) are simply rejected. Step10: Hmmm, not much luck yet, but an idea	<ASSISTANT_TASK:> Python Code: import numpy as np import heartpy as hp import pandas as pd import matplotlib.pyplot as plt df = pd.read_csv('raw_ppg.csv') df.keys() plt.figure(figsize=(12,6)) plt.plot(df['ppg'].values) plt.show() signal = df['ppg'].values[14500:20500] timer = df['timer'].values[14500:20500] plt.plot(signal) plt.show() timer[0:20] help(hp.get_samplerate_datetime) #Seems easy enough, right? Now let's determine the sample rate sample_rate = hp.get_samplerate_datetime(timer, timeformat = '%H:%M:%S.%f') print('sampling rate is: %.3f Hz' %sample_rate) from datetime import datetime #let's create a list 'newtimer' to house our datetime objects newtimer = [datetime.strptime(x, '%H:%M:%S.%f') for x in timer] #let's compute the real distances from entry to entry elapsed = [] for i in range(len(newtimer) - 1): elapsed.append(1 / ((newtimer[i+1] - newtimer[i]).microseconds / 1000000)) #and plot the results plt.figure(figsize=(12,4)) plt.plot(elapsed) plt.xlabel('Sample number') plt.ylabel('Actual sampling rate in Hz') plt.show() print('mean sampling rate: %.3f' %np.mean(elapsed)) print('median sampling rate: %.3f'%np.median(elapsed)) print('standard deviation: %.3f'%np.std(elapsed)) #Let's plot 4 minutes of the segment we selected to get a view #of what we're working with plt.figure(figsize=(12,6)) plt.plot(signal[0:int(240 * sample_rate)]) plt.title('original signal') plt.show() #Let's run it through a standard butterworth bandpass implementation to remove everything < 0.8 and > 3.5 Hz. filtered = hp.filter_signal(signal, [0.7, 3.5], sample_rate=sample_rate, order=3, filtertype='bandpass') #let's plot first 240 seconds and work with that! plt.figure(figsize=(12,12)) plt.subplot(211) plt.plot(signal[0:int(240 * sample_rate)]) plt.title('original signal') plt.subplot(212) plt.plot(filtered[0:int(240 * sample_rate)]) plt.title('filtered signal') plt.show() plt.figure(figsize=(12,6)) plt.plot(filtered[0:int(sample_rate * 60)]) plt.title('60 second segment of filtered signal') plt.show() #let's resample to ~100Hz as well #10Hz is low for the adaptive threshold analysis HeartPy uses from scipy.signal import resample resampled = resample(filtered, len(filtered) * 10) #don't forget to compute the new sampling rate new_sample_rate = sample_rate * 10 #run HeartPy over a few segments, fingers crossed, and plot results of each for s in [[0, 10000], [10000, 20000], [20000, 30000], [30000, 40000], [40000, 50000]]: wd, m = hp.process(resampled[s[0]:s[1]], sample_rate = new_sample_rate, high_precision=True, clean_rr=True) hp.plotter(wd, m, title = 'zoomed in section', figsize=(12,6)) hp.plot_poincare(wd, m) plt.show() for measure in m.keys(): print('%s: %f' %(measure, m[measure])) raw = df['ppg'].values plt.plot(raw) plt.show() import sys from scipy.signal import resample windowsize = 100 std = [] for i in range(len(raw) // windowsize): start = i * windowsize end = (i + 1) * windowsize sliced = raw[start:end] try: std.append(np.std(sliced)) except: print(i) plt.plot(std) plt.show() plt.plot(raw) plt.show() plt.plot(raw[0:(len(raw) // windowsize) * windowsize] - resample(std, len(std)windowsize)) plt.show() (len(raw) // windowsize) windowsize mx = np.max(raw) mn = np.min(raw) global_range = mx - mn windowsize = 100 filtered = [] for i in range(len(raw) // windowsize): start = i * windowsize end = (i + 1) * windowsize sliced = raw[start:end] rng = np.max(sliced) - np.min(sliced) if ((rng >= (0.5 * global_range)) or (np.max(sliced) >= 0.9 * mx) or (np.min(sliced) <= mn + (0.1 * mn))): for x in sliced: filtered.append(0) else: for x in sliced: filtered.append(x) plt.figure(figsize=(12,6)) plt.plot(raw) plt.show() plt.figure(figsize=(12,6)) plt.plot(filtered) plt.show() <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Echo client Step2: Usage Step3: Fibonacci example Step4: Nacci client Step5: Usage Step6: Exercise	<ASSISTANT_TASK:> Python Code: %%writefile echo.py #!/usr/bin/env python import zmq from zmq.eventloop import ioloop, zmqstream def echo(stream, message): stream.send_multipart(message) io_loop = ioloop.IOLoop() context = zmq.Context() socket = context.socket(zmq.ROUTER) stream = zmqstream.ZMQStream(socket, io_loop=io_loop) stream.on_recv_stream(echo) socket.bind('tcp://0.0.0.0:11235') io_loop.start() %%writefile client.py #!/usr/bin/env python import zmq context = zmq.Context() s = context.socket(zmq.DEALER) s.connect('tcp://127.0.0.1:11235') for i in range(10): s.send('Hello world') print(s.recv()) %%bash python client.py %%writefile fibo.py #!/usr/bin/env python import zmq from zmq.eventloop import ioloop, zmqstream def fibonacci(n): a, b = 0, 1 while n >= a: yield(a) a, b = b, a + b return def fibo(stream, message): n = int(message[1]) reply = [message[0]] + [str(n in [x for x in fibonacci(n)])] stream.send_multipart(reply) io_loop = ioloop.IOLoop() context = zmq.Context() socket = context.socket(zmq.ROUTER) stream = zmqstream.ZMQStream(socket, io_loop=io_loop) stream.on_recv_stream(fibo) socket.bind('tcp://0.0.0.0:11235') io_loop.start() %%writefile nacci.py #!/usr/bin/env python import zmq from random import randint context = zmq.Context() s = context.socket(zmq.DEALER) s.connect('tcp://127.0.0.1:11235') for i in range(15): n = randint(0,200) s.send(str(n)) print(str(n) + ' ' + s.recv()) %%bash python nacci.py %%writefile broker.py #!/usr/bin/env python import argparse import zmq from zmq.eventloop import ioloop, zmqstream clients = set() def action_register(message): address = message.split()[1].strip() if address in clients: return 'HOP' else: clients.add(address) return 'OK' def action_list(message): return ' '.join(clients) def handle(stream, message): addr, text = message print('BROKER: ' + text) action = text.split()[0].lower() try: reply = globals()['action_' + action](text) except KeyError: print('BROKER: Unknown action', action) reply = 'ERROR' stream.send_multipart((addr, reply)) io_loop = ioloop.IOLoop() context = zmq.Context() socket = context.socket(zmq.ROUTER) stream = zmqstream.ZMQStream(socket, io_loop=io_loop) stream.on_recv_stream(handle) parser = argparse.ArgumentParser() parser.add_argument('-b', '--bind-address', default='tcp://0.0.0.0:5555') if __name__ == '__main__': args = parser.parse_args() socket.bind(args.bind_address) io_loop.start() %%writefile cities.txt Barcelona Berlin Madrid New York Londres Igualada %%writefile hider.py #!/usr/bin/env python import argparse parser = argparse.ArgumentParser() parser.add_argument('-p', '--port', default='5556') parser.add_argument('-b', '--broker', default='tcp://127.0.0.1:5555') args = parser.parse_args() %%writefile seeker.py #!/usr/bin/env python import argparse parser = argparse.ArgumentParser() parser.add_argument('-b', '--broker', default='tcp://127.0.0.1:5555') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: NeoWS module Step2: You can also search by IAU number or SPK-ID (there is a faster neows.orbit_from_spk_id() function in that case, although) Step3: Since neows relies on Small-Body Database browser to get the SPK-ID given a body name, you can use the wildcards from that browser Step4: <div class="alert alert-info">Note that epoch is provided by the Web Service itself, so if you need orbit on another epoch, you have to propagate it Step5: Given that we are using NASA APIs, there is a maximum number of requests. If you want to make many requests, it is recommended getting a NASA API key. You can use your API key adding the api_key parameter to the function Step6: DASTCOM5 module Step7: Keep in mind that this function returns a list of orbits matching your string. This is made on purpose given that there are comets which have several records in the database (one for each orbit determination in history) what allow plots like this one Step8: While neows can only be used to get Orbit objects, dastcom5 can also provide asteroid and comet complete database. Step9: <div class="alert alert-info">Asteroid and comet parameters are not exactly the same (although they are very close) Step10: The number of Atira NEOs we use using this method is Step11: Which is consistent with the stats published by CNEOS Step12: We only need to get the 16 orbits from these 16 ndarrays. Step13: If we needed also the names of each asteroid, we could do Step14: <div class="alert alert-info">We knew beforehand that there are no `Atira` comets, only asteroids (comet orbits are usually more eccentric), but we could use the same method with `com_db` if we wanted.</div> Step15: Also, in this function, DASTCOM5 data (specially strings) is ready to use (decoded and improved strings, etc) Step16: Panda offers many functionalities, and can also be used in the same way as the ast_db and comet_db functions Step17: What? I said they can be used in the same way! Step18: So, rewriting our condition	<ASSISTANT_TASK:> Python Code: import matplotlib.pyplot as plt plt.ion() from astropy import time from poliastro.twobody.orbit import Orbit from poliastro.bodies import Earth from poliastro.plotting import OrbitPlotter from poliastro.neos import neows eros = neows.orbit_from_name('Eros') frame = OrbitPlotter() frame.plot(eros, label='Eros'); ganymed = neows.orbit_from_name('1036') # Ganymed IAU number amor = neows.orbit_from_name('2001221') # Amor SPK-ID eros = neows.orbit_from_spk_id('2000433') # Eros SPK-ID frame = OrbitPlotter() frame.plot(ganymed, label='Ganymed') frame.plot(amor, label='Amor') frame.plot(eros, label='Eros'); neows.orbit_from_name('alley') eros.epoch.iso epoch = time.Time(2458000.0, scale='tdb', format='jd') eros_november = eros.propagate(epoch) eros_november.epoch.iso neows.orbit_from_name('Toutatis', api_key='DEMO_KEY') from poliastro.neos import dastcom5 atira = dastcom5.orbit_from_name('atira')[0] # NEO wikipedia = dastcom5.orbit_from_name('wikipedia')[0] # Asteroid, but not NEO. frame = OrbitPlotter() frame.plot(atira, label='Atira (NEO)') frame.plot(wikipedia, label='Wikipedia (asteroid)'); halleys = dastcom5.orbit_from_name('1P') frame = OrbitPlotter() frame.plot(halleys[0], label='Halley') frame.plot(halleys[5], label='Halley') frame.plot(halleys[10], label='Halley') frame.plot(halleys[20], label='Halley') frame.plot(halleys[-1], label='Halley'); ast_db = dastcom5.asteroid_db() comet_db = dastcom5.comet_db() ast_db.dtype.names[:20] # They are more than 100, but that would be too much lines in this notebook :P aphelion_condition = 2 ast_db['A'] - ast_db['QR'] < 0.983 axis_condition = ast_db['A'] < 1.3 atiras = ast_db[aphelion_condition & axis_condition] len(atiras) from poliastro.twobody.orbit import Orbit from poliastro.bodies import Earth earth = Orbit.from_body_ephem(Earth) frame = OrbitPlotter() frame.plot(earth, label='Earth') for record in atiras['NO']: ss = dastcom5.orbit_from_record(record).to_icrs() frame.plot(ss, color="#666666") frame = OrbitPlotter() frame.plot(earth, label='Earth') for i in range(len(atiras)): record = atiras['NO'][i] label = atiras['ASTNAM'][i].decode().strip() # DASTCOM5 strings are binary ss = dastcom5.orbit_from_record(record).to_icrs() frame.plot(ss, label=label) db = dastcom5.entire_db() db.columns db[db.NAME == 'Halley'] # As you can see, Halley is the name of an asteroid too, did you know that? aphelion_condition = (2 * db['A'] - db['QR']) < 0.983 axis_condition = db['A'] < 1.3 atiras = db[aphelion_condition & axis_condition] len(atiras) len(atiras[atiras.A < 0]) axis_condition = (db['A'] < 1.3) & (db['A'] > 0) atiras = db[aphelion_condition & axis_condition] len(atiras) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: feature mapping Step2: regularized cost Step3: this is the same as the not regularized cost because we init theta as zeros... Step4: fit the parameters Step5: predict	<ASSISTANT_TASK:> Python Code: sns.set(context="notebook", style="ticks", font_scale=1.5) sns.lmplot('test1', 'test2', hue='accepted', data=df, size=6, fit_reg=False, scatter_kws={"s": 50} ) plt.title('Regularized Logistic Regression') x1 = np.array(df.test1) x2 = np.array(df.test2) data = lr.feature_mapping(x1, x2, power=6) print(data.shape) data.head() data.describe() theta = np.zeros(data.shape[1]) X = lr.feature_mapping(x1, x2, power=6, as_ndarray=True) print(X.shape) y = general.get_y(df) print(y.shape) lr.regularized_cost(theta, X, y, l=1) lr.regularized_gradient(theta, X, y) import scipy.optimize as opt print('init cost = {}'.format(lr.regularized_cost(theta, X, y))) res = opt.minimize(fun=lr.regularized_cost, x0=theta, args=(X, y), method='Newton-CG', jac=lr.regularized_gradient) res final_theta = res.x y_pred = lr.predict(X, final_theta) print(classification_report(y, y_pred)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: map() Step2: reduce() Step3: pipelining Step4: Ok, too easy, this is supposed to be a map & reduce tutorial... Step5: RDD Step6: flatMap() vs map() Step7: lambda functions Step8: filter() Step9: Exercise Step10: Exercise Step11: Exercise Step12: Exercise Step13: Which, as you all know, means "the state of being able to achieve honours". Step14: groupBy() Step15: reduceByKey Step16: Exercise Step17: Exercise Step18: DataFrame Step19: <a id='Pandas_interface'></a> Step20: Exercise Step22: <a id='SQL_interface'></a> Step23: Exercise	<ASSISTANT_TASK:> Python Code: import pyspark sc = pyspark.SparkContext('local[]') # We define our input l = range(10) l # We "upload" it as an RDD rdd = sc.parallelize(l) rdd # We define a map function def power_of_2(k): return 2k # And we apply it to our RDD rdd.map(power_of_2) # So we use collect() to retrieve all results. rdd.map(power_of_2).collect() ### WARNING ### # Never do that in real cases, or you will transfer ALL data to your browser, effectibly killing it. # What about summing, everything? # We define a reduce function def sum_everything(k1, k2): return k1 + k2 # And we apply the reduce operation rdd.reduce(sum_everything) # Or we can use the built in operation `sum` rdd.sum() # What if I wanted to compute the sum of the powers of 2? rdd.map(power_of_2).reduce(sum_everything) # or rdd.map(power_of_2).sum() # How can we count the number of elements in the array? rdd.count() def set_to_1(k): return 1 rdd.map(set_to_1).reduce(sum_everything) # Load all Shakespeare works import os shakespeare = sc.textFile(os.path.normpath('file:///../../resources/shakespeare.txt')) # Show the first lines shakespeare.take(10) # Get the longest line def keep_longest(k1, k2): if len(k1) > len(k2): return k1 else: return k2 shakespeare.reduce(keep_longest) # Compute the average line length def line_length(k): return len(k) shakespeare.map(line_length).sum() / shakespeare.count() # Split the text in words def split_in_words(k): return k.split() shakespeare.map(split_in_words).take(2) shakespeare.flatMap(split_in_words).take(15) shakespeare.flatMap( lambda k: k.split() # Split in words ).take(15) # Retrieve 10 words longer than 15 characters shakespeare.flatMap( lambda k: k.split() # Split in words ).filter( lambda k: len(k)>15 # Keep words longer than 15 characters ).take(10) %load -r 1-9 solutions/13_01_Big_Data.py %load -r 10-19 solutions/13_01_Big_Data.py %load -r 20-29 solutions/13_01_Big_Data.py %load -r 30-39 solutions/13_01_Big_Data.py words = shakespeare.flatMap( lambda k: k.split() # Split in words ).filter( lambda k: not (set('.,-') & set(k)) # Drop words with special characters ) words.groupBy(lambda k: k).take(10) # That method returns an iterable for each different word. This iterable contains a list of all the appearances of the word. # Lets print its contents tuples = words.groupBy(lambda k: k).take(5) for t in tuples: print(t[0], list(t[1])) # Now, to compute the number of appearances, we just have to count the elements in the iterator words.groupBy( lambda k: k ).map( lambda t: (t[0], len(list(t[1]))) ).take(5) # But this is VERY EXPENSIVE in terms of memory, # as all the word instances must be stored in a list before they can be counted. # We can do it much better! words.map( lambda w: (w, 1) ).take(10) words.map( lambda w: (w, 1) ).reduceByKey( lambda k1, k2: k1 + k2 ).take(10) %load -r 40-49 solutions/13_01_Big_Data.py %load -r 50-69 solutions/13_01_Big_Data.py %load -r 70-79 solutions/13_01_Big_Data.py from pyspark.sql import SQLContext sqlc = SQLContext(sc) gaia = sqlc.read.csv('../resources/gaia.csv.bz2', comment='#', header=True, inferSchema=True) gaia gaia.count() gaia.head(5) %matplotlib inline import pyspark.sql.functions as func g_hist = gaia.groupBy( ( func.floor(gaia.mag_g 10) / 10 ).alias('mag_g'), ).count().orderBy( 'mag_g' ) g_hist.take(10) g_hist.toPandas().set_index('mag_g').plot(loglog=True) %load -r 90-99 solutions/13_01_Big_Data.py sqlc.registerDataFrameAsTable(gaia, "gaia") g_hist = sqlc.sql( SELECT CAST(FLOOR(mag_g10)/10. AS FLOAT) AS mag_g, COUNT() AS `count` FROM gaia GROUP BY 1 ORDER BY 1 ) g_hist.take(10) g_hist.toPandas().set_index('mag_g').plot(loglog=True) %load -r 100-109 solutions/13_01_Big_Data.py <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Define an infinite integer set Step2: Test if interger value is in the set Step3: Test if another integer set is a subset Step4: Find the intersection of two IntegerSet objects Step5: Find the union of two IntegerSet objects Step6: We can also find unions and intersections of integer sets with ordinary Python sets, as long as these sets contain integer values Step7: The following line of code with cause the AttributeSetError exception Step8: Now, define objects of RegexSet Step9: Test if strings are matched by regex's defining our RegexSet objects Step10: Test if one regex set is a subset of another Step11: Find the intersection of two regex sets Step12: Find the union of two regex sets Step13: Subtract a finite set of strings from a regex set Step14: The result may be not extremely readable, but we can test it in the following way Step15: Now, we can also wrap Python set objects into FiniteSet class provided in ReGraph. Step16: It allows us to apply to them any set operations from the common interface of ReGraph’s attribute sets. For example Step17: ReGraph provides two special classes of attribute sets	<ASSISTANT_TASK:> Python Code: from math import inf import regraph.attribute_sets as atsets ints = atsets.IntegerSet({(0, 8), (11, inf)}) print(ints.contains(5)) print(ints.contains(9)) a = atsets.IntegerSet({(0, 3), (20, 30)}) print(a.issubset(ints)) b = atsets.IntegerSet({(0, 10)}) print(b.issubset(ints)) a_and_ints = a.intersection(ints) print(a_and_ints) b_and_ints = b.intersection(ints) print(b_and_ints) a_or_ints = a.union(ints) print(a_or_ints) b_or_ints = b.union(ints) print(b_or_ints) a.union({13, 14}) print(a) try: a.union({13, 14, "a"}) except Exception as e: print("Error message: ", e) print("Type: ", type(e)) words = atsets.RegexSet("[A-Za-z]+") integers = atsets.RegexSet("\d+") alphanums = atsets.RegexSet("[A-Za-z\d]+") print(words.match("42")) print(integers.match("42")) print(words.match("hello")) print(integers.match("hello")) print(integers.issubset(words)) print(integers.issubset(alphanums)) print(integers.intersection(words)) print(integers.intersection(alphanums)) print(integers.union(words)) print(words.difference({"hi", "bye"})) no_hi_bye = words.difference({"hi", "bye"}) print(no_hi_bye.match("hi")) print(no_hi_bye.match("bye")) print(no_hi_bye.match("afternoon")) a = atsets.FiniteSet({1, 2, 3}) int_regex = atsets.RegexSet("\d+") positive_integers = atsets.IntegerSet([(0, inf)]) print(a.issubset(int_regex)) print(a.issubset(positive_integers)) univ = atsets.UniversalSet() empty = atsets.EmptySet() print(univ.union(empty)) print(univ.intersection(empty)) a = atsets.FiniteSet({1, 2, 3}) print(a.issubset(univ)) print(a.issubset(empty)) print(univ.intersection(a)) print(univ.union(a)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step2: Euler's method Step4: The midpoint method is another numerical method for solving the above differential equation. In general it is more accurate than the Euler method. It uses the update equation Step6: You are now going to solve the following differential equation Step7: In the following cell you are going to solve the above ODE using four different algorithms	<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt import numpy as np import seaborn as sns from scipy.integrate import odeint from IPython.html.widgets import interact, fixed def solve_euler(derivs, y0, x): Solve a 1d ODE using Euler's method. Parameters ---------- derivs : function The derivative of the diff-eq with the signature deriv(y,x) where y and x are floats. y0 : float The initial condition y[0] = y(x[0]). x : np.ndarray, list, tuple The array of times at which of solve the diff-eq. Returns ------- y : np.ndarray Array of solutions y[i] = y(x[i]) # YOUR CODE HERE #raise NotImplementedError() y = np.empty_like(x) y[0] = y0 h = x[1] - x[0] for n in range (0, len(x) - 1): y[n + 1] = y[n] + h * derivs(y[n],x[n]) return y assert np.allclose(solve_euler(lambda y, x: 1, 0, [0,1,2]), [0,1,2]) def solve_midpoint(derivs, y0, x): Solve a 1d ODE using the Midpoint method. Parameters ---------- derivs : function The derivative of the diff-eq with the signature deriv(y,x) where y and x are floats. y0 : float The initial condition y[0] = y(x[0]). x : np.ndarray, list, tuple The array of times at which of solve the diff-eq. Returns ------- y : np.ndarray Array of solutions y[i] = y(x[i]) # YOUR CODE HERE #raise NotImplementedError() y = np.empty_like(x) y[0] = y0 h = x[1] - x[0] for n in range (0, len(x) - 1): # y[n + 1] = y[n] + h * ((derivs(y[n]+(h/2)) * derivs(y[n],x[n]), x[n]) * (y[n] + (h/2) * derivs(y[n],x[n]) + (h/2))) y[n+1] = y[n] + h * derivs(y[n] + h/2 * derivs(y[n],x[n]), x[n] + h/2) return y assert np.allclose(solve_midpoint(lambda y, x: 1, 0, [0,1,2]), [0,1,2]) def solve_exact(x): compute the exact solution to dy/dx = x + 2y. Parameters ---------- x : np.ndarray Array of x values to compute the solution at. Returns ------- y : np.ndarray Array of solutions at y[i] = y(x[i]). # YOUR CODE HERE #raise NotImplementedError() y = 0.25np.exp(2x) - 0.5x - 0.25 return y assert np.allclose(solve_exact(np.array([0,1,2])),np.array([0., 1.09726402, 12.39953751])) # YOUR CODE HERE # raise NotImplementedError() x = np.linspace(0,1.0,11) y = np.empty_like(x) y0 = y[0] def derivs(y, x): return x+2y plt.plot(solve_euler(derivs, y0, x), label = 'euler') plt.plot(solve_midpoint(derivs, y0, x), label = 'midpoint') plt.plot(solve_exact(x), label = 'exact') plt.plot(odeint(derivs, y0, x), label = 'odeint') assert True # leave this for grading the plots <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: To import the tensor module of PySINGA, run Step2: The ground-truth Step3: Generating the trainin data Step4: Training via SGD Step5: SINGA tensor module supports basic linear algebra operations, like + - * /, and advanced functions including axpy, gemm, gemv, and random function (e.g., Gaussian and Uniform). Step6: We can see that the learned line is becoming closer to the ground truth line (in blue color).	<ASSISTANT_TASK:> Python Code: from __future__ import division from __future__ import print_function from builtins import range from past.utils import old_div %matplotlib inline import numpy as np import matplotlib.pyplot as plt from singa import tensor a, b = 3, 2 f = lambda x: a * x + b gx = np.linspace(0.,1,100) gy = [f(x) for x in gx] plt.plot(gx, gy, label='y=f(x)') plt.xlabel('x') plt.ylabel('y') plt.legend(loc='best') nb_points = 30 # generate training data train_x = np.asarray(np.random.uniform(0., 1., nb_points), np.float32) train_y = np.asarray(f(train_x) + np.random.rand(30), np.float32) plt.plot(train_x, train_y, 'bo', ms=7) def plot(idx, x, y): global gx, gy, axes # print the ground truth line axes[idx//5, idx%5].plot(gx, gy, label='y=f(x)') # print the learned line axes[idx//5, idx%5].plot(x, y, label='y=kx+b') axes[idx//5, idx%5].legend(loc='best') # set hyper-parameters max_iter = 15 alpha = 0.05 # init parameters k, b = 2.,0. # to plot the intermediate results fig, axes = plt.subplots(3, 5, figsize=(12, 8)) x = tensor.from_numpy(train_x) y = tensor.from_numpy(train_y) # sgd for idx in range(max_iter): y_ = x * k + b err = y_ - y loss = old_div(tensor.sum(err * err), nb_points) print('loss at iter %d = %f' % (idx, loss)) da1 = old_div(tensor.sum(err * x), nb_points) db1 = old_div(tensor.sum(err), nb_points) # update the parameters k -= da1 * alpha b -= db1 * alpha plot(idx, tensor.to_numpy(x), tensor.to_numpy(y_)) # to plot the intermediate results fig, axes = plt.subplots(3, 5, figsize=(12, 8)) x = tensor.from_numpy(train_x) y = tensor.from_numpy(train_y) # sgd for idx in range(max_iter): y_ = x * k + b err = y_ - y loss = old_div(tensor.sum(err * err), nb_points) print('loss at iter %d = %f' % (idx, loss)) da1 = old_div(tensor.sum(err * x), nb_points) db1 = old_div(tensor.sum(err), nb_points) # update the parameters k -= da1 * alpha b -= db1 * alpha plot(idx, tensor.to_numpy(x), tensor.to_numpy(y_)) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Fitting a decaying oscillation Step2: Now, using curve_fit to fit this model and determine the estimates and uncertainties for the parameters	<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt import numpy as np import scipy.optimize as opt # YOUR CODE HERE data = np.load('decay_osc.npz') tdata = data['tdata'] ydata = data['ydata'] dy = data['dy'] data.close plt.figure(figsize=(7,5)) plt.errorbar(tdata, ydata, dy, fmt='og', ecolor='gray') plt.xlabel('t') plt.ylabel('y') plt.grid(); assert True # leave this to grade the data import and raw data plot # YOUR CODE HERE def model(t, a, lamb, omega, delta): y = a * np.exp(-lamb * t)np.cos(omegat) + delta return y theta_best, theta_cov = opt.curve_fit(model, tdata, ydata, absolute_sigma=True) print('a = {0:.3f} +/- {1:.3f}'.format(theta_best[0], np.sqrt(theta_cov[0,0]))) print('lambda = {0:.3f} +/- {1:.3f}'.format(theta_best[1], np.sqrt(theta_cov[1,1]))) print('omega = {0:.3f} +/- {1:.3f}'.format(theta_best[2], np.sqrt(theta_cov[0,0]))) print('delta = {0:.3f} +/- {1:.3f}'.format(theta_best[3], np.sqrt(theta_cov[1,1]))) xfit = np.linspace(0,20) yfit = model(xfit, theta_best[0], theta_best[1], theta_best[2], theta_best[3]) plt.figure(figsize=(7,5)) plt.plot(xfit, yfit) plt.errorbar(tdata, ydata, dy, fmt='og', ecolor='gray') plt.xlabel('t') plt.ylabel('y') plt.grid(); assert True # leave this cell for grading the fit; should include a plot and printout of the parameters+errors <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Note that Step2: Those locations are also used in intermediate representation Step3: In miasm, each expression embeds its size. The location doesn't have a size. To use a location in IR code, you have to wrap it in the Miasm word ExprLoc	<ASSISTANT_TASK:> Python Code: # Import and create a locationDB from miasm.core.locationdb import LocationDB loc_db = LocationDB() print(repr(loc_db)) # Create a location with default attributes (no offset, no symbol name) loc_a = loc_db.add_location() print(loc_a) # Create a second location with an offset loc_b = loc_db.add_location(offset=112233) print(loc_b) # Add a location with a name loc_c = loc_db.add_location(name="main") # Add another alias name to this location loc_db.add_location_name(loc_c, "_main_") # Add another location loc_d = loc_db.add_location() # Display LocationDB print(loc_db) # Associate an offset to an existing location loc_db.set_location_offset(loc_a, 0x5678) print(loc_db) # Remove a name from an existing location loc_db.remove_location_name(loc_c, "_main_") print(loc_db) # Get the offset of a location hex(loc_db.get_location_offset(loc_a)) # Location with no offset print(loc_db.get_location_offset(loc_c)) # Display locations loc_db.pretty_str(loc_a) loc_db.pretty_str(loc_b) loc_db.pretty_str(loc_c) loc_db.pretty_str(loc_d) from miasm.analysis.binary import Container from miasm.analysis.machine import Machine # Create a LocationDB loc_db = LocationDB() # Create a container of bytes cont = Container.from_string( b"\x83\xf8\x10\x74\x07\x89\xc6\x0f\x47\xc3\xeb\x08\x89\xc8\xe8\x31\x33\x22\x11\x40\xc3", loc_db ) # Instantiate a x86 32 bit architecture machine = Machine("x86_32") # Instantiate a disassembler engine, using the previous bin_stream and its # associated location DB. mdis = machine.dis_engine(cont.bin_stream, loc_db=loc_db) # Run a recursive traversal disassembling from address 0 asmcfg = mdis.dis_multiblock(0) # Display each basic blocks for block in asmcfg.blocks: print(block) block = asmcfg.getby_offset(0) print(block) # The basic block is placed at a location, which can be retrieved using `.loc_key` print(block.loc_key) # We can add a name to this first location loc_db.add_location_name(block.loc_key, "entry") print(loc_db) # And we can re-display the block: print(block) # We will give an arbitrary name to location at offset 0xC loc_c = loc_db.get_offset_location(0xc) loc_db.add_location_name(loc_c, "quiche") print(block) # Get a lifter lifter = machine.lifter_model_call(loc_db) # Get the intermediate representation of the asmcfg ircfg = lifter.new_ircfg_from_asmcfg(asmcfg) # Get location at 0 loc_entry = loc_db.get_offset_location(0) # Get irblock at this location irblock = ircfg.blocks[loc_entry] # Display IRBlock print(irblock) # Get the irblock destination (IRDst value) dst = irblock.dst print(dst) print(repr(dst)) # It's an ExprCond. We retrieve here the possible values src1, src2 = dst.src1, dst.src2 print(repr(src1), repr(src2)) # Retrieve the location of the ExprLoc loc = src1.loc_key print(loc) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Now we can start to define the actual convolution code. We start by defining an object that represents a single layer of convolution that does the actual convolution operation followed by pooling over the output of that convolution. These layers will be stacked in the final model. Step2: This next method uses the convolution layer above to make a stack of them and adds a hidden layer followed by a logistic regression classification layer on top. Step3: This cell runs the model and allows you to play with a few hyperparameters. The ones below take about 1 to 2 minutes to run. Step4: For most convolution model it can be interesting to show what the trained filters look like. The code below does that from the parameters returned by the training function above. In this model there isn't much of an effect since the filters are 5x5 and we can't see much unfortunately. Step5: What can also be interesting is to draw the outputs of the filters for an example. This works somewhat better for this model. Step6: Some things you can try with this model	<ASSISTANT_TASK:> Python Code: import numpy import theano import theano.tensor as T from logistic_sgd import LogisticRegression from mlp import HiddenLayer from theano.tensor.signal import downsample from theano.tensor.nnet import conv class LeNetConvPoolLayer(object): def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, 2)): assert image_shape[1] == filter_shape[1] self.input = input # there are "num input feature maps * filter height * filter width" # inputs to each hidden unit fan_in = numpy.prod(filter_shape[1:]) # each unit in the lower layer receives a gradient from: # "num output feature maps * filter height * filter width" / pooling size fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) / numpy.prod(poolsize)) # initialize weights with random weights W_bound = numpy.sqrt(6. / (fan_in + fan_out)) self.W = theano.shared( numpy.asarray( rng.uniform(low=-W_bound, high=W_bound, size=filter_shape), dtype=theano.config.floatX ), borrow=True ) # the bias is a 1D tensor -- one bias per output feature map b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX) self.b = theano.shared(value=b_values, borrow=True) # convolve input feature maps with filters conv_out = conv.conv2d( input=input, filters=self.W, filter_shape=filter_shape, image_shape=image_shape ) # downsample each feature map individually, using maxpooling pooled_out = downsample.max_pool_2d( input=conv_out, ds=poolsize, ignore_border=True ) # add the bias term. Since the bias is a vector (1D array), we first # reshape it to a tensor of shape (1, n_filters, 1, 1). Each bias will # thus be broadcasted across mini-batches and feature map # width & height self.output = T.tanh(pooled_out + self.b.dimshuffle('x', 0, 'x', 'x')) # store parameters of this layer self.params = [self.W, self.b] import time import fuel from fuel.streams import DataStream from fuel.schemes import SequentialScheme from fuel.transformers import Cast fuel.config.floatX = theano.config.floatX = 'float32' def evaluate_lenet5(train, test, valid, learning_rate=0.1, n_epochs=200, nkerns=[20, 50], batch_size=500): rng = numpy.random.RandomState(23455) train_stream = DataStream.default_stream( train, iteration_scheme=SequentialScheme(train.num_examples, batch_size)) valid_stream = DataStream.default_stream( valid, iteration_scheme=SequentialScheme(valid.num_examples, batch_size)) test_stream = DataStream.default_stream( test, iteration_scheme=SequentialScheme(test.num_examples, batch_size)) x = T.tensor4('x') yi = T.imatrix('y') y = yi.reshape((yi.shape[0],)) # Construct the first convolutional pooling layer: # filtering reduces the image size to (28-5+1 , 28-5+1) = (24, 24) # maxpooling reduces this further to (24/2, 24/2) = (12, 12) # 4D output tensor is thus of shape (batch_size, nkerns[0], 12, 12) layer0 = LeNetConvPoolLayer( rng, input=x, image_shape=(batch_size, 1, 28, 28), filter_shape=(nkerns[0], 1, 5, 5), poolsize=(2, 2) ) # Construct the second convolutional pooling layer # filtering reduces the image size to (12-5+1, 12-5+1) = (8, 8) # maxpooling reduces this further to (8/2, 8/2) = (4, 4) # 4D output tensor is thus of shape (batch_size, nkerns[1], 4, 4) layer1 = LeNetConvPoolLayer( rng, input=layer0.output, image_shape=(batch_size, nkerns[0], 12, 12), filter_shape=(nkerns[1], nkerns[0], 5, 5), poolsize=(2, 2) ) # the HiddenLayer being fully-connected, it operates on 2D matrices of # shape (batch_size, num_pixels) (i.e matrix of rasterized images). # This will generate a matrix of shape (batch_size, nkerns[1] * 4 * 4), # or (500, 50 * 4 * 4) = (500, 800) with the default values. layer2_input = layer1.output.flatten(2) # construct a fully-connected sigmoidal layer layer2 = HiddenLayer( rng, input=layer2_input, n_in=nkerns[1] * 4 * 4, n_out=500, activation=T.tanh ) # classify the values of the fully-connected sigmoidal layer layer3 = LogisticRegression(input=layer2.output, n_in=500, n_out=10) # the cost we minimize during training is the NLL of the model cost = layer3.negative_log_likelihood(y) # create a function to compute the mistakes that are made by the model model_errors = theano.function( [x, yi], layer3.errors(y) ) # create a list of all model parameters to be fit by gradient descent params = layer3.params + layer2.params + layer1.params + layer0.params # create a list of gradients for all model parameters grads = T.grad(cost, params) # train_model is a function that updates the model parameters by # SGD Since this model has many parameters, it would be tedious to # manually create an update rule for each model parameter. We thus # create the updates list by automatically looping over all # (params[i], grads[i]) pairs. updates = [ (param_i, param_i - learning_rate * grad_i) for param_i, grad_i in zip(params, grads) ] train_model = theano.function( [x, yi], cost, updates=updates ) # early-stopping parameters patience = 10000 # look as this many examples regardless patience_increase = 2 # wait this much longer when a new best is found # a relative improvement of this much is considered significant improvement_threshold = 0.995 n_train_batches = (train.num_examples + batch_size - 1) // batch_size # go through this many minibatches before checking the network on # the validation set; in this case we check every epoch validation_frequency = min(n_train_batches, patience / 2) best_validation_loss = numpy.inf best_iter = 0 test_score = 0. start_time = time.clock() epoch = 0 iter = 0 done_looping = False while (epoch < n_epochs) and (not done_looping): epoch = epoch + 1 minibatch_index = 0 for minibatch in train_stream.get_epoch_iterator(): iter += 1 minibatch_index += 1 if iter % 100 == 0: print('training @ iter = ', iter) error = train_model(minibatch[0], minibatch[1]) if (iter + 1) % validation_frequency == 0: # compute zero-one loss on validation set validation_losses = [model_errors(vb[0], vb[1]) for vb in valid_stream.get_epoch_iterator()] this_validation_loss = numpy.mean(validation_losses) print('epoch %i, minibatch %i/%i, validation error %f %%' % (epoch, minibatch_index + 1, n_train_batches, this_validation_loss * 100.)) # if we got the best validation score until now if this_validation_loss < best_validation_loss: # improve patience if loss improvement is good enough if this_validation_loss < best_validation_loss * improvement_threshold: patience = max(patience, iter * patience_increase) # save best validation score and iteration number best_validation_loss = this_validation_loss best_iter = iter # test it on the test set test_losses = [ model_errors(tb[0], tb[1]) for tb in test_stream.get_epoch_iterator() ] test_score = numpy.mean(test_losses) print((' epoch %i, minibatch %i/%i, test error of ' 'best model %f %%') % (epoch, minibatch_index + 1, n_train_batches, test_score * 100.)) if patience <= iter: done_looping = True break end_time = time.clock() print('Optimization complete.') print('Best validation score of %f %% obtained at iteration %i, ' 'with test performance %f %%' % (best_validation_loss * 100., best_iter + 1, test_score * 100.)) print('The code ran for %.2fm' % ((end_time - start_time) / 60.)) # This is to make the pretty pictures in the cells below layer0_out = theano.function([x], layer0.output) layer1_out = theano.function([x], layer1.output) return params, layer0_out, layer1_out from fuel.datasets import MNIST train = MNIST(which_sets=('train',), subset=slice(0, 50000)) valid = MNIST(which_sets=('train',), subset=slice(50000, 60000)) test = MNIST(which_sets=('test',)) params, layer0_out, layer1_out = evaluate_lenet5(train, test, valid, learning_rate=0.1, n_epochs=10, nkerns=[10, 25], batch_size=50) %matplotlib inline import matplotlib.pyplot as plt from utils import tile_raster_images filts1 = params[6].get_value() filts2 = params[4].get_value() plt.clf() # Increase the size of the figure plt.gcf().set_size_inches(15, 10) # Make a grid for the two layers gs = plt.GridSpec(1, 2, width_ratios=[1, 25], height_ratios=[1, 1]) a = plt.subplot(gs[0]) b = plt.subplot(gs[1]) # Show the first layer filters (the small column) a.imshow(tile_raster_images(filts1.reshape(10, 25), img_shape=(5, 5), tile_shape=(10, 1), tile_spacing=(1,1)), cmap="Greys", interpolation="none") a.axis('off') # Show the second layer filters (the large block) b.imshow(tile_raster_images(filts2.reshape(250, 25), img_shape=(5, 5), tile_shape=(10, 25), tile_spacing=(1,1)), cmap="Greys", interpolation="none") b.axis('off') %matplotlib inline import matplotlib.pyplot as plt from utils import tile_raster_images # Grab some input examples from the test set (we cheat a bit here) sample = test.get_data(None, slice(0, 50))[0] # We will print this example amongst the batch example = 7 plt.gcf() # Increase the size of the figure plt.gcf().set_size_inches(15, 10) gs = plt.GridSpec(1, 3, width_ratios=[1, 1, 1], height_ratios=[1, 1, 1]) # Draw the input data a = plt.subplot(gs[0]) a.imshow(sample[example, 0], cmap="Greys", interpolation='none') a.axis('off') # Compute first layer output out0 = layer0_out(sample)[example] # Draw its output b = plt.subplot(gs[1]) b.imshow(tile_raster_images(out0.reshape(10, 144), img_shape=(12, 12), tile_shape=(5, 2), tile_spacing=(1, 1)), cmap="Greys", interpolation='none') b.axis('off') # Compute the second layer output out1 = layer1_out(sample)[example] # Draw it c = plt.subplot(gs[2]) c.imshow(tile_raster_images(out1.reshape(25, 16), img_shape=(4, 4), tile_shape=(5, 5), tile_spacing=(1, 1)), cmap="Greys", interpolation='none') c.axis('off') %load lenet.py <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Document Authors Step2: Document Contributors Step3: Document Publication Step4: Document Table of Contents Step5: 1.2. Model Name Step6: 1.3. Model Family Step7: 1.4. Basic Approximations Step8: 1.5. Prognostic Variables Step9: 2. Key Properties --> Seawater Properties Step10: 2.2. Eos Functional Temp Step11: 2.3. Eos Functional Salt Step12: 2.4. Eos Functional Depth Step13: 2.5. Ocean Freezing Point Step14: 2.6. Ocean Specific Heat Step15: 2.7. Ocean Reference Density Step16: 3. Key Properties --> Bathymetry Step17: 3.2. Type Step18: 3.3. Ocean Smoothing Step19: 3.4. Source Step20: 4. Key Properties --> Nonoceanic Waters Step21: 4.2. River Mouth Step22: 5. Key Properties --> Software Properties Step23: 5.2. Code Version Step24: 5.3. Code Languages Step25: 6. Key Properties --> Resolution Step26: 6.2. Canonical Horizontal Resolution Step27: 6.3. Range Horizontal Resolution Step28: 6.4. Number Of Horizontal Gridpoints Step29: 6.5. Number Of Vertical Levels Step30: 6.6. Is Adaptive Grid Step31: 6.7. Thickness Level 1 Step32: 7. Key Properties --> Tuning Applied Step33: 7.2. Global Mean Metrics Used Step34: 7.3. Regional Metrics Used Step35: 7.4. Trend Metrics Used Step36: 8. Key Properties --> Conservation Step37: 8.2. Scheme Step38: 8.3. Consistency Properties Step39: 8.4. Corrected Conserved Prognostic Variables Step40: 8.5. Was Flux Correction Used Step41: 9. Grid Step42: 10. Grid --> Discretisation --> Vertical Step43: 10.2. Partial Steps Step44: 11. Grid --> Discretisation --> Horizontal Step45: 11.2. Staggering Step46: 11.3. Scheme Step47: 12. Timestepping Framework Step48: 12.2. Diurnal Cycle Step49: 13. Timestepping Framework --> Tracers Step50: 13.2. Time Step Step51: 14. Timestepping Framework --> Baroclinic Dynamics Step52: 14.2. Scheme Step53: 14.3. Time Step Step54: 15. Timestepping Framework --> Barotropic Step55: 15.2. Time Step Step56: 16. Timestepping Framework --> Vertical Physics Step57: 17. Advection Step58: 18. Advection --> Momentum Step59: 18.2. Scheme Name Step60: 18.3. ALE Step61: 19. Advection --> Lateral Tracers Step62: 19.2. Flux Limiter Step63: 19.3. Effective Order Step64: 19.4. Name Step65: 19.5. Passive Tracers Step66: 19.6. Passive Tracers Advection Step67: 20. Advection --> Vertical Tracers Step68: 20.2. Flux Limiter Step69: 21. Lateral Physics Step70: 21.2. Scheme Step71: 22. Lateral Physics --> Momentum --> Operator Step72: 22.2. Order Step73: 22.3. Discretisation Step74: 23. Lateral Physics --> Momentum --> Eddy Viscosity Coeff Step75: 23.2. Constant Coefficient Step76: 23.3. Variable Coefficient Step77: 23.4. Coeff Background Step78: 23.5. Coeff Backscatter Step79: 24. Lateral Physics --> Tracers Step80: 24.2. Submesoscale Mixing Step81: 25. Lateral Physics --> Tracers --> Operator Step82: 25.2. Order Step83: 25.3. Discretisation Step84: 26. Lateral Physics --> Tracers --> Eddy Diffusity Coeff Step85: 26.2. Constant Coefficient Step86: 26.3. Variable Coefficient Step87: 26.4. Coeff Background Step88: 26.5. Coeff Backscatter Step89: 27. Lateral Physics --> Tracers --> Eddy Induced Velocity Step90: 27.2. Constant Val Step91: 27.3. Flux Type Step92: 27.4. Added Diffusivity Step93: 28. Vertical Physics Step94: 29. Vertical Physics --> Boundary Layer Mixing --> Details Step95: 30. Vertical Physics --> Boundary Layer Mixing --> Tracers Step96: 30.2. Closure Order Step97: 30.3. Constant Step98: 30.4. Background Step99: 31. Vertical Physics --> Boundary Layer Mixing --> Momentum Step100: 31.2. Closure Order Step101: 31.3. Constant Step102: 31.4. Background Step103: 32. Vertical Physics --> Interior Mixing --> Details Step104: 32.2. Tide Induced Mixing Step105: 32.3. Double Diffusion Step106: 32.4. Shear Mixing Step107: 33. Vertical Physics --> Interior Mixing --> Tracers Step108: 33.2. Constant Step109: 33.3. Profile Step110: 33.4. Background Step111: 34. Vertical Physics --> Interior Mixing --> Momentum Step112: 34.2. Constant Step113: 34.3. Profile Step114: 34.4. Background Step115: 35. Uplow Boundaries --> Free Surface Step116: 35.2. Scheme Step117: 35.3. Embeded Seaice Step118: 36. Uplow Boundaries --> Bottom Boundary Layer Step119: 36.2. Type Of Bbl Step120: 36.3. Lateral Mixing Coef Step121: 36.4. Sill Overflow Step122: 37. Boundary Forcing Step123: 37.2. Surface Pressure Step124: 37.3. Momentum Flux Correction Step125: 37.4. Tracers Flux Correction Step126: 37.5. Wave Effects Step127: 37.6. River Runoff Budget Step128: 37.7. Geothermal Heating Step129: 38. Boundary Forcing --> Momentum --> Bottom Friction Step130: 39. Boundary Forcing --> Momentum --> Lateral Friction Step131: 40. Boundary Forcing --> Tracers --> Sunlight Penetration Step132: 40.2. Ocean Colour Step133: 40.3. Extinction Depth Step134: 41. Boundary Forcing --> Tracers --> Fresh Water Forcing Step135: 41.2. From Sea Ice Step136: 41.3. Forced Mode Restoring	<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'ipsl', 'sandbox-3', 'ocean') # Set as follows: DOC.set_author("name", "email") # TODO - please enter value(s) # Set as follows: DOC.set_contributor("name", "email") # TODO - please enter value(s) # Set publication status: # 0=do not publish, 1=publish. DOC.set_publication_status(0) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.model_overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.model_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.model_family') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "OGCM" # "slab ocean" # "mixed layer ocean" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.basic_approximations') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Primitive equations" # "Non-hydrostatic" # "Boussinesq" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.prognostic_variables') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Potential temperature" # "Conservative temperature" # "Salinity" # "U-velocity" # "V-velocity" # "W-velocity" # "SSH" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.eos_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Linear" # "Wright, 1997" # "Mc Dougall et al." # "Jackett et al. 2006" # "TEOS 2010" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.eos_functional_temp') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Potential temperature" # "Conservative temperature" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.eos_functional_salt') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Practical salinity Sp" # "Absolute salinity Sa" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.eos_functional_depth') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Pressure (dbars)" # "Depth (meters)" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.ocean_freezing_point') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "TEOS 2010" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.ocean_specific_heat') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.seawater_properties.ocean_reference_density') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.bathymetry.reference_dates') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Present day" # "21000 years BP" # "6000 years BP" # "LGM" # "Pliocene" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.bathymetry.type') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.bathymetry.ocean_smoothing') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.bathymetry.source') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.nonoceanic_waters.isolated_seas') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.nonoceanic_waters.river_mouth') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.software_properties.repository') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.software_properties.code_version') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.software_properties.code_languages') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.canonical_horizontal_resolution') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.range_horizontal_resolution') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.number_of_horizontal_gridpoints') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.number_of_vertical_levels') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.is_adaptive_grid') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.resolution.thickness_level_1') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.tuning_applied.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.tuning_applied.global_mean_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.tuning_applied.regional_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.tuning_applied.trend_metrics_used') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.conservation.description') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.conservation.scheme') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Energy" # "Enstrophy" # "Salt" # "Volume of ocean" # "Momentum" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.conservation.consistency_properties') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.conservation.corrected_conserved_prognostic_variables') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.key_properties.conservation.was_flux_correction_used') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.discretisation.vertical.coordinates') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Z-coordinate" # "Z-coordinate" # "S-coordinate" # "Isopycnic - sigma 0" # "Isopycnic - sigma 2" # "Isopycnic - sigma 4" # "Isopycnic - other" # "Hybrid / Z+S" # "Hybrid / Z+isopycnic" # "Hybrid / other" # "Pressure referenced (P)" # "P" # "Z**" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.discretisation.vertical.partial_steps') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.discretisation.horizontal.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Lat-lon" # "Rotated north pole" # "Two north poles (ORCA-style)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.discretisation.horizontal.staggering') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Arakawa B-grid" # "Arakawa C-grid" # "Arakawa E-grid" # "N/a" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.grid.discretisation.horizontal.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Finite difference" # "Finite volumes" # "Finite elements" # "Unstructured grid" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.diurnal_cycle') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Via coupling" # "Specific treatment" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.tracers.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Leap-frog + Asselin filter" # "Leap-frog + Periodic Euler" # "Predictor-corrector" # "Runge-Kutta 2" # "AM3-LF" # "Forward-backward" # "Forward operator" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.tracers.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.baroclinic_dynamics.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Preconditioned conjugate gradient" # "Sub cyling" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.baroclinic_dynamics.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Leap-frog + Asselin filter" # "Leap-frog + Periodic Euler" # "Predictor-corrector" # "Runge-Kutta 2" # "AM3-LF" # "Forward-backward" # "Forward operator" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.baroclinic_dynamics.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.barotropic.splitting') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "split explicit" # "implicit" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.barotropic.time_step') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.timestepping_framework.vertical_physics.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.momentum.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Flux form" # "Vector form" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.momentum.scheme_name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.momentum.ALE') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.order') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.flux_limiter') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.effective_order') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.passive_tracers') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Ideal age" # "CFC 11" # "CFC 12" # "SF6" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.lateral_tracers.passive_tracers_advection') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.vertical_tracers.name') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.advection.vertical_tracers.flux_limiter') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Eddy active" # "Eddy admitting" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.operator.direction') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Horizontal" # "Isopycnal" # "Isoneutral" # "Geopotential" # "Iso-level" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.operator.order') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Harmonic" # "Bi-harmonic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.operator.discretisation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Second order" # "Higher order" # "Flux limiter" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.eddy_viscosity_coeff.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant" # "Space varying" # "Time + space varying (Smagorinsky)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.eddy_viscosity_coeff.constant_coefficient') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.eddy_viscosity_coeff.variable_coefficient') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.eddy_viscosity_coeff.coeff_background') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.momentum.eddy_viscosity_coeff.coeff_backscatter') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.mesoscale_closure') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.submesoscale_mixing') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.operator.direction') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Horizontal" # "Isopycnal" # "Isoneutral" # "Geopotential" # "Iso-level" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.operator.order') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Harmonic" # "Bi-harmonic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.operator.discretisation') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Second order" # "Higher order" # "Flux limiter" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_diffusity_coeff.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant" # "Space varying" # "Time + space varying (Smagorinsky)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_diffusity_coeff.constant_coefficient') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_diffusity_coeff.variable_coefficient') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_diffusity_coeff.coeff_background') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_diffusity_coeff.coeff_backscatter') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_induced_velocity.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "GM" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_induced_velocity.constant_val') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_induced_velocity.flux_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.lateral_physics.tracers.eddy_induced_velocity.added_diffusivity') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.details.langmuir_cells_mixing') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.tracers.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant value" # "Turbulent closure - TKE" # "Turbulent closure - KPP" # "Turbulent closure - Mellor-Yamada" # "Turbulent closure - Bulk Mixed Layer" # "Richardson number dependent - PP" # "Richardson number dependent - KT" # "Imbeded as isopycnic vertical coordinate" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.tracers.closure_order') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.tracers.constant') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.tracers.background') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.momentum.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant value" # "Turbulent closure - TKE" # "Turbulent closure - KPP" # "Turbulent closure - Mellor-Yamada" # "Turbulent closure - Bulk Mixed Layer" # "Richardson number dependent - PP" # "Richardson number dependent - KT" # "Imbeded as isopycnic vertical coordinate" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.momentum.closure_order') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.momentum.constant') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.boundary_layer_mixing.momentum.background') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.details.convection_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Non-penetrative convective adjustment" # "Enhanced vertical diffusion" # "Included in turbulence closure" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.details.tide_induced_mixing') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.details.double_diffusion') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.details.shear_mixing') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.tracers.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant value" # "Turbulent closure / TKE" # "Turbulent closure - Mellor-Yamada" # "Richardson number dependent - PP" # "Richardson number dependent - KT" # "Imbeded as isopycnic vertical coordinate" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.tracers.constant') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.tracers.profile') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.tracers.background') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.momentum.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant value" # "Turbulent closure / TKE" # "Turbulent closure - Mellor-Yamada" # "Richardson number dependent - PP" # "Richardson number dependent - KT" # "Imbeded as isopycnic vertical coordinate" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.momentum.constant') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.momentum.profile') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.vertical_physics.interior_mixing.momentum.background') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.free_surface.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.free_surface.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Linear implicit" # "Linear filtered" # "Linear semi-explicit" # "Non-linear implicit" # "Non-linear filtered" # "Non-linear semi-explicit" # "Fully explicit" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.free_surface.embeded_seaice') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.bottom_boundary_layer.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.bottom_boundary_layer.type_of_bbl') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Diffusive" # "Acvective" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.bottom_boundary_layer.lateral_mixing_coef') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.uplow_boundaries.bottom_boundary_layer.sill_overflow') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.surface_pressure') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.momentum_flux_correction') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers_flux_correction') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.wave_effects') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.river_runoff_budget') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.geothermal_heating') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.momentum.bottom_friction.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Linear" # "Non-linear" # "Non-linear (drag function of speed of tides)" # "Constant drag coefficient" # "None" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.momentum.lateral_friction.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Free-slip" # "No-slip" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.sunlight_penetration.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "1 extinction depth" # "2 extinction depth" # "3 extinction depth" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.sunlight_penetration.ocean_colour') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # Valid Choices: # True # False # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.sunlight_penetration.extinction_depth') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.fresh_water_forcing.from_atmopshere') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Freshwater flux" # "Virtual salt flux" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.fresh_water_forcing.from_sea_ice') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Freshwater flux" # "Virtual salt flux" # "Real salt flux" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocean.boundary_forcing.tracers.fresh_water_forcing.forced_mode_restoring') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: The Red Line is a subway that connects Cambridge and Boston, Massachusetts. When I was working in Cambridge I took the Red Line from Kendall Square to South Station and caught the commuter rail to Needham. During rush hour Red Line trains run every 7–8 minutes, on average. Step2: I'll convert them to minutes and use kde_from_sample to estimate the distribution. Step3: Here's what it looks like. Step4: The Update Step5: So here's the first update. Step6: Here's what the posterior distribution looks like. Step7: Because I am more likely to arrive during a longer gap, the distribution is shifted to the right. Step8: This shift is an example of the "inspection paradox", which I wrote an article about. Step9: make_elapsed_dist takes a hypothetical gap and an array of possible times. Step10: Here's an example that represents a uniform distribution from 0 to 0.6 minutes. Step11: The last element of the sequence is uniform from 0 to 20 minutes. Step12: Now we can use make_mixture to make a weighted mixture of uniform distributions, where the weights are the probabilities from posterior_z. Step13: The mean elapsed time is 4.4 minutes, half the posterior mean of z. Step14: With this likelihood, we can compute the posterior distribution of x. Step15: Here's what it looks like Step16: Based on the number of passengers, we think it has been about 5 minutes since the last train. Step17: Wait time Step18: Well, almost. That distribution contains some negative values, which are impossible. Step19: Based on the information so far, here are the distributions for x, y, and z, shown as CDFs. Step20: Because of rounding errors, posterior_y contains quantities that are not in posterior_x and posterior_z; that's why I plotted it as a CDF, and why it appears jaggy. Step21: I'll use this augmented sample to make a new estimate for the posterior distribution of z. Step22: Here's what it looks like. Step24: Now let's take the analysis from the previous sections and wrap it in a function. Step25: Given the number of passengers when we arrive at the station, it computes the posterior distribution of y. Step26: We can use it to compute the mean wait time and the probability of waiting more than 15 minutes. Step27: If we see 10 passengers, we expect to wait a little less than 5 minutes, and the chance of waiting more than 15 minutes is about 1%. Step28: Here's the mean wait as a function of the number of passengers. Step29: If there are no passengers on the platform when I arrive, I infer that I just missed a train; in that case, the expected wait time is the mean of augmented_posterior_z.	<ASSISTANT_TASK:> Python Code: # If we're running on Colab, install empiricaldist # https://pypi.org/project/empiricaldist/ import sys IN_COLAB = 'google.colab' in sys.modules if IN_COLAB: !pip install empiricaldist # Get utils.py import os if not os.path.exists('utils.py'): !wget https://github.com/AllenDowney/ThinkBayes2/raw/master/soln/utils.py from utils import set_pyplot_params set_pyplot_params() observed_gap_times = [ 428.0, 705.0, 407.0, 465.0, 433.0, 425.0, 204.0, 506.0, 143.0, 351.0, 450.0, 598.0, 464.0, 749.0, 341.0, 586.0, 754.0, 256.0, 378.0, 435.0, 176.0, 405.0, 360.0, 519.0, 648.0, 374.0, 483.0, 537.0, 578.0, 534.0, 577.0, 619.0, 538.0, 331.0, 186.0, 629.0, 193.0, 360.0, 660.0, 484.0, 512.0, 315.0, 457.0, 404.0, 740.0, 388.0, 357.0, 485.0, 567.0, 160.0, 428.0, 387.0, 901.0, 187.0, 622.0, 616.0, 585.0, 474.0, 442.0, 499.0, 437.0, 620.0, 351.0, 286.0, 373.0, 232.0, 393.0, 745.0, 636.0, 758.0, ] import numpy as np zs = np.array(observed_gap_times) / 60 from utils import kde_from_sample qs = np.linspace(0, 20, 101) pmf_z = kde_from_sample(zs, qs) from utils import decorate pmf_z.plot() decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of time between trains') likelihood = pmf_z.qs posterior_z = pmf_z * pmf_z.qs posterior_z.normalize() pmf_z.plot(label='prior', color='C5') posterior_z.plot(label='posterior', color='C4') decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of time between trains') pmf_z.mean(), posterior_z.mean() from empiricaldist import Pmf def make_elapsed_dist(gap, qs): qs = qs[qs <= gap] n = len(qs) return Pmf(1/n, qs) qs = posterior_z.qs pmf_seq = [make_elapsed_dist(gap, qs) for gap in qs] pmf_seq[3] pmf_seq[-1].plot() decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of wait time in 20 min gap') from utils import make_mixture pmf_x = make_mixture(posterior_z, pmf_seq) pmf_z.plot(label='prior gap', color='C5') posterior_z.plot(label='posterior gap', color='C4') pmf_x.plot(label='elapsed time', color='C1') decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of gap and elapsed times') posterior_z.mean(), pmf_x.mean() from scipy.stats import poisson lam = 2 num_passengers = 10 likelihood = poisson(lam * pmf_x.qs).pmf(num_passengers) posterior_x = pmf_x * likelihood posterior_x.normalize() pmf_x.plot(label='prior', color='C1') posterior_x.plot(label='posterior', color='C2') decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of time since last train') pmf_x.mean(), posterior_x.mean() posterior_y = Pmf.sub_dist(posterior_z, posterior_x) nonneg = (posterior_y.qs >= 0) posterior_y = Pmf(posterior_y[nonneg]) posterior_y.normalize() posterior_x.make_cdf().plot(label='posterior of x', color='C2') posterior_y.make_cdf().plot(label='posterior of y', color='C3') posterior_z.make_cdf().plot(label='posterior of z', color='C4') decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of elapsed time, wait time, gap') sample = posterior_z.sample(260) delays = [30, 40, 50] augmented_sample = np.append(sample, delays) qs = np.linspace(0, 60, 101) augmented_posterior_z = kde_from_sample(augmented_sample, qs) augmented_posterior_z.plot(label='augmented posterior of z', color='C4') decorate(xlabel='Time (min)', ylabel='PDF', title='Distribution of time between trains') qs = augmented_posterior_z.qs pmf_seq = [make_elapsed_dist(gap, qs) for gap in qs] pmf_x = make_mixture(augmented_posterior_z, pmf_seq) lam = 2 num_passengers = 10 def compute_posterior_y(num_passengers): Distribution of wait time based on `num_passengers`. likelihood = poisson(lam * qs).pmf(num_passengers) posterior_x = pmf_x * likelihood posterior_x.normalize() posterior_y = Pmf.sub_dist(augmented_posterior_z, posterior_x) nonneg = (posterior_y.qs >= 0) posterior_y = Pmf(posterior_y[nonneg]) posterior_y.normalize() return posterior_y posterior_y = compute_posterior_y(10) posterior_y.mean() 1 - posterior_y.make_cdf()(15) nums = np.arange(0, 37, 3) posteriors = [compute_posterior_y(num) for num in nums] mean_wait = [posterior_y.mean() for posterior_y in posteriors] import matplotlib.pyplot as plt plt.plot(nums, mean_wait) decorate(xlabel='Number of passengers', ylabel='Expected time until next train', title='Expected wait time based on number of passengers') prob_late = [1 - posterior_y.make_cdf()(15) for posterior_y in posteriors] plt.plot(nums, prob_late) decorate(xlabel='Number of passengers', ylabel='Probability of being late', title='Probability of being late based on number of passengers') <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Data Step2: 16.1 - Estimating the mean and standard deviation of a normal distribution Step3: Figure 16.3 Step4: 16.2 - Outliers and robust estimation Step5: Figure 16.9 Step6: 16.2 - Two Groups Step7: Figure 16.12	<ASSISTANT_TASK:> Python Code: import pandas as pd import numpy as np import pymc3 as pm import matplotlib.pyplot as plt import seaborn as sns import warnings warnings.filterwarnings("ignore", category=FutureWarning) from scipy.stats import norm, t from IPython.display import Image %matplotlib inline plt.style.use('seaborn-white') color = '#87ceeb' %load_ext watermark %watermark -p pandas,numpy,pymc3,matplotlib,seaborn,scipy df = pd.read_csv('data/TwoGroupIQ.csv', dtype={'Group':'category'}) df.info() df.head() # Mean and standard deviation df.groupby('Group').agg(['mean', 'std']) fg = sns.FacetGrid(df, col='Group', height=4) fg.map(sns.distplot, 'Score', kde=False, color='#87ceeb'); # We are only interested in the scores of group 'Smart Drug' y = df['Score'][df.Group == 'Smart Drug'] Image('images/fig16_2.png', width=300) with pm.Model() as model: mu = pm.Normal('mu', y.mean(), sd=y.std()) sigma = pm.Uniform('sigma', y.std()/1000, y.std()1000) # PyMC's Normal likelihood can take either precision or standard deviation as an argument. likelihood = pm.Normal('likelihood', mu, sd=sigma, observed=y) pm.model_to_graphviz(model) with model: trace = pm.sample(2000, cores=4, nuts_kwargs={'target_accept': 0.95}) pm.traceplot(trace); fig, [(ax1, ax2), (ax3, ax4)] = plt.subplots(2,2, figsize=(10,6)) font_d = {'size':16} # Upper left pm.plot_posterior(trace['mu'], point_estimate='mode', ref_val=100, ax=ax1, color=color) ax1.set_xlabel('$\mu$', fontdict=font_d) ax1.set_title('Mean', fontdict=font_d) # Upper right tr_len = len(trace) # Plot only 20 posterior prediction curves. n_curves = 20 # Create an index of length 20 with which we step through the trace. stepIdxVec = np.arange(0, tr_len, tr_len//n_curves) x_range = np.arange(y.min(), y.max()) x = np.tile(x_range.reshape(-1,1), (1,20)) ax2.hist(y, bins=25, density=True, color='steelblue') ax2.plot(x, norm.pdf(x, trace['mu'][stepIdxVec], trace['sigma'][stepIdxVec]), c=color) ax2.set_xlabel('y', fontdict=font_d) ax2.set_title('Data w. Post. Pred.\nN=63') [ax2.spines[spine].set_visible(False) for spine in ['left', 'right', 'top']] ax2.yaxis.set_visible(False) # Lower left pm.plot_posterior(trace['sigma'], point_estimate='mode', ref_val=15, ax=ax3, color=color) ax3.set_xlabel('$\sigma$', fontdict=font_d) ax3.set_title('Std. Dev.', fontdict=font_d) # Lower right pm.plot_posterior((trace['mu']-100)/trace['sigma'], point_estimate='mode', ref_val=0, ax=ax4, color=color) ax4.set_title('Effect Size', fontdict=font_d) ax4.set_xlabel('$(\mu - 100)/\sigma$', fontdict=font_d) plt.tight_layout(); with pm.Model() as model2: mu = pm.Normal('mu', y.mean(), sd=y.std()) sigma = pm.Uniform('sigma', y.std()/1000, y.std()1000) nu_minus1 = pm.Exponential('nu_minus1', 1/29) nu = pm.Deterministic('nu', nu_minus1+1) likelihood = pm.StudentT('likelihood', nu, mu, sd=sigma, observed=y) pm.model_to_graphviz(model2) with model2: trace2 = pm.sample(5000, cores=4, nuts_kwargs={'target_accept': 0.95}) pm.traceplot(trace2); fig, [(ax1, ax2), (ax3, ax4), (ax5, ax6)] = plt.subplots(3,2, figsize=(10,8)) # Upper left pm.plot_posterior(trace2['mu'], point_estimate='mode', ref_val=100, ax=ax1, color=color) ax1.set_xlabel('$\mu$', fontdict=font_d) ax1.set_title('Mean', fontdict=font_d) # Upper right tr_len = len(trace) n_curves = 20 stepIdxVec = np.arange(0, tr_len, tr_len//n_curves) x_range = np.arange(y.min(), y.max()) x = np.tile(x_range.reshape(-1,1), (1,20)) ax2.hist(y, bins=25, density=True, color='steelblue') ax2.plot(x, norm.pdf(x, trace2['mu'][stepIdxVec], trace2['sigma'][stepIdxVec]), c='#87ceeb') ax2.set_xlabel('y', fontdict=font_d) ax2.set_title('Data w. Post. Pred.') [ax2.spines[spine].set_visible(False) for spine in ['left', 'right', 'top']] ax2.yaxis.set_visible(False) # Middle left pm.plot_posterior(trace2['sigma'], point_estimate='mode', ref_val=15, ax=ax3, color=color) ax3.set_xlabel('$\sigma$', fontdict=font_d) ax3.set_title('Std. Dev.', fontdict=font_d) # Middle right pm.plot_posterior((trace2['mu']-100)/trace2['sigma'], point_estimate='mode', ref_val=0, ax=ax4, color=color) ax4.set_title('Effect Size', fontdict=font_d) ax4.set_xlabel('$(\mu - 100)/\sigma$', fontdict=font_d) # Lower left pm.plot_posterior(np.log10(trace2['nu']), point_estimate='mode', ax=ax5, color=color) ax5.set_title('Normality', fontdict=font_d) ax5.set_xlabel(r'log10($\nu$)', fontdict=font_d) plt.tight_layout(); ax6.set_visible(False) Image('images/fig16_11.png', width=400) grp_idx = df.Group.cat.codes.values grp_codes = df.Group.cat.categories n_grps = grp_codes.size with pm.Model() as model3: mu = pm.Normal('mu', df.Score.mean(), sd=df.Score.std(), shape=n_grps) sigma = pm.Uniform('sigma', df.Score.std()/1000, df.Score.std()1000, shape=n_grps) nu_minus1 = pm.Exponential('nu_minus1', 1/29) nu = pm.Deterministic('nu', nu_minus1+1) likelihood = pm.StudentT('likelihood', nu, mu[grp_idx], sd=sigma[grp_idx], observed=df.Score) pm.model_to_graphviz(model3) with model3: trace3 = pm.sample(5000, cores=4, nuts_kwargs={'target_accept': 0.95}) pm.traceplot(trace3); tr3_mu0 = trace3['mu'][:,0] tr3_mu1 = trace3['mu'][:,1] tr3_sigma0 = trace3['sigma'][:,0] tr3_sigma1 = trace3['sigma'][:,1] tr3_nu = np.log10(trace3['nu']) fig, axes = plt.subplots(5,2, figsize=(12, 12)) # Left column figs l_trace_vars = (tr3_mu0, tr3_mu1, tr3_sigma0, tr3_sigma1, tr3_nu) l_axes_idx = np.arange(5) l_xlabels = ('$\mu_0$', '$\mu_1$', '$\sigma_0$', '$\sigma_1$', r'log10($\nu$)') l_titles = ('Placebo Mean', 'Smart Drug Mean', 'Placebo Scale', 'Smart Drug Scale', 'Normality') for var, ax_i, xlabel, title in zip(l_trace_vars, l_axes_idx, l_xlabels, l_titles): pm.plot_posterior(var, point_estimate='mode', ax=axes[ax_i,0], color=color) axes[ax_i,0].set_xlabel(xlabel, font_d) axes[ax_i,0].set_title(title, font_d) # Right column figs tr_len = len(trace3) n_curves = 20 stepIdxVec = np.arange(0, tr_len, tr_len//n_curves) x_range = np.arange(df.Score.min(), df.Score.max()) x = np.tile(x_range.reshape(-1,1), (1,20)) # 1 axes[0,1].hist(df.Score[df.Group == 'Placebo'], bins=25, density=True, color='steelblue') axes[0,1].plot(x, t.pdf(x, loc=tr3_mu0[stepIdxVec], scale=tr3_sigma0[stepIdxVec], df=trace3['nu'][stepIdxVec]), c='#87ceeb') axes[0,1].set_xlabel('y', font_d) [axes[0,1].spines[spine].set_visible(False) for spine in ['left', 'right', 'top']] axes[0,1].yaxis.set_visible(False) axes[0,1].set_title('Data for Placebo w. Post. Pred.', font_d) # 2 axes[1,1].hist(df.Score[df.Group == 'Smart Drug'], bins=25, density=True, color='steelblue') axes[1,1].plot(x, t.pdf(x, loc=tr3_mu1[stepIdxVec], scale=tr3_sigma1[stepIdxVec], df=trace3['nu'][stepIdxVec]), c='#87ceeb') axes[1,1].set_xlabel('y', font_d) [axes[1,1].spines[spine].set_visible(False) for spine in ['left', 'right', 'top']] axes[1,1].yaxis.set_visible(False) axes[1,1].set_title('Data for Smart Drug w. Post. Pred.', font_d) # 3-5 r_vars = (tr3_mu1-tr3_mu0, tr3_sigma1-tr3_sigma0, (tr3_mu1-tr3_mu0)/np.sqrt((tr3_sigma02+tr3_sigma1*2)/2)) r_axes_idx = np.arange(start=2, stop=5) r_xlabels = ('$\mu_1 - \mu_0$', '$\sigma_1 - \sigma_0$', r'$\frac{(\mu_1-\mu_0)}{\sqrt{(\sigma_0^2+\sigma_1^2)/2}}$') r_titles = ('Difference of Means', 'Difference of Scales', 'Effect Size') for var, ax_i, xlabel, title in zip(r_vars, r_axes_idx, r_xlabels, r_titles): pm.plot_posterior(var, point_estimate='mode', ref_val=0, ax=axes[ax_i,1], color=color) axes[ax_i,1].set_xlabel(xlabel, font_d) axes[ax_i,1].set_title(title, font_d) plt.tight_layout(); <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step1: Computing the forward operator Step2: Visualizing the coregistration Step3: Compute Source Space Step4: The surface based source space src contains two parts, one for the left Step5: To compute a volume based source space defined with a grid of candidate Step6: To compute a volume based source space defined with a grid of candidate Step7: <div class="alert alert-info"><h4>Note</h4><p>Some sources may appear to be outside the BEM inner skull contour. Step8: Compute forward solution Step9: Note that the Step10: <div class="alert alert-danger"><h4>Warning</h4><p>Forward computation can remove vertices that are too close to (or outside) Step11: We can explore the content of fwd to access the numpy array that contains Step12: To extract the numpy array containing the forward operator corresponding to	<ASSISTANT_TASK:> Python Code: import os.path as op import mne from mne.datasets import sample data_path = sample.data_path() # the raw file containing the channel location + types sample_dir = op.join(data_path, 'MEG', 'sample',) raw_fname = op.join(sample_dir, 'sample_audvis_raw.fif') # The paths to Freesurfer reconstructions subjects_dir = op.join(data_path, 'subjects') subject = 'sample' plot_bem_kwargs = dict( subject=subject, subjects_dir=subjects_dir, brain_surfaces='white', orientation='coronal', slices=[50, 100, 150, 200]) mne.viz.plot_bem(plot_bem_kwargs) # The transformation file obtained by coregistration trans = op.join(sample_dir, 'sample_audvis_raw-trans.fif') info = mne.io.read_info(raw_fname) # Here we look at the dense head, which isn't used for BEM computations but # is useful for coregistration. mne.viz.plot_alignment(info, trans, subject=subject, dig=True, meg=['helmet', 'sensors'], subjects_dir=subjects_dir, surfaces='head-dense') src = mne.setup_source_space(subject, spacing='oct4', add_dist='patch', subjects_dir=subjects_dir) print(src) mne.viz.plot_bem(src=src, plot_bem_kwargs) sphere = (0.0, 0.0, 0.04, 0.09) vol_src = mne.setup_volume_source_space( subject, subjects_dir=subjects_dir, sphere=sphere, sphere_units='m', add_interpolator=False) # just for speed! print(vol_src) mne.viz.plot_bem(src=vol_src, plot_bem_kwargs) surface = op.join(subjects_dir, subject, 'bem', 'inner_skull.surf') vol_src = mne.setup_volume_source_space( subject, subjects_dir=subjects_dir, surface=surface, add_interpolator=False) # Just for speed! print(vol_src) mne.viz.plot_bem(src=vol_src, plot_bem_kwargs) fig = mne.viz.plot_alignment(subject=subject, subjects_dir=subjects_dir, surfaces='white', coord_frame='mri', src=src) mne.viz.set_3d_view(fig, azimuth=173.78, elevation=101.75, distance=0.30, focalpoint=(-0.03, -0.01, 0.03)) conductivity = (0.3,) # for single layer # conductivity = (0.3, 0.006, 0.3) # for three layers model = mne.make_bem_model(subject='sample', ico=4, conductivity=conductivity, subjects_dir=subjects_dir) bem = mne.make_bem_solution(model) fwd = mne.make_forward_solution(raw_fname, trans=trans, src=src, bem=bem, meg=True, eeg=False, mindist=5.0, n_jobs=1, verbose=True) print(fwd) print(f'Before: {src}') print(f'After: {fwd["src"]}') leadfield = fwd['sol']['data'] print("Leadfield size : %d sensors x %d dipoles" % leadfield.shape) fwd_fixed = mne.convert_forward_solution(fwd, surf_ori=True, force_fixed=True, use_cps=True) leadfield = fwd_fixed['sol']['data'] print("Leadfield size : %d sensors x %d dipoles" % leadfield.shape) <END_TASK>
<SYSTEM_TASK:> Given the following text description, write Python code to implement the functionality described below step by step <END_TASK> <USER_TASK:> Description: Step2: Get Authorization URL Step5: Create Authorization URL Helper Step6: Get Authorization Code Step7: Cut and paste that PIN here Step9: Get Access Token Step10: POST to that URL to get a response containing an access token Step11: It seems like the access token can only be created once and has a 10 year expiration time.	<ASSISTANT_TASK:> Python Code: import os DEN_CLIENT_ID = os.environ["DEN_CLIENT_ID"] DEN_CLIENT_SECRET = os.environ["DEN_CLIENT_SECRET"] import uuid def _get_state(): Get a unique id string. return str(uuid.uuid1()) _get_state() API_PROTOCOL = "https" API_LOCATION = "home.nest.com" from urlparse import SplitResult, urlunsplit from urllib import urlencode def _get_url(path, query, netloc=API_LOCATION): Get a URL for the given path and query. split = SplitResult(scheme=API_PROTOCOL, netloc=netloc, path=path, query=query, fragment="") return urlunsplit(split) def get_auth_url(client_id=DEN_CLIENT_ID): Get an authorization URL for the given client id. path = "login/oauth2" query = urlencode({"client_id": client_id, "state": _get_state()}) return _get_url(path, query) get_auth_url() !open "{get_auth_url()}" pin = "" def get_access_token_url(client_id=DEN_CLIENT_ID, client_secret=DEN_CLIENT_SECRET, code=pin): Get an access token URL for the given client id. path = "oauth2/access_token" query = urlencode({"client_id": client_id, "client_secret": client_secret, "code": code, "grant_type": "authorization_code"}) return _get_url(path, query, "api." + API_LOCATION) get_access_token_url() import requests r = requests.post(get_access_token_url()) print r.status_code assert r.status_code == requests.codes.OK r.json() access_token = r.json()["access_token"] access_token <END_TASK>

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.