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: SASE1 Step2: We are interested in fast, i.e. pulse-resolved data from the instrument source SA1_XTD2_XGM/DOOCS Step3: We are particularly interested in data for quantity "intensityTD". The xarray DataArray class is suited for work with axis-labeled data, and the karabo_data method get_array() serves the purpose of shaping a 2D array of that type from pulse-resolved data (which is originally stored "flat" in terms of pulses Step4: Next, we will plot a portion of the data in two dimensions, taking the first 1500 trains for the x-Axis and the first 30 pulses per train for the y-Axis (1500, 30). Because the Matplotlib convention takes the slow axis to be y, we have to transpose to (30, 1500) Step5: The pattern tells us what was done in this experiment Step6: Accordingly for the odd "off" pulses Step7: Now we can calculate the ratio of averages for every train - data types like numpy ndarray or xarray DataArray may be just divided "as such", a shortcut notation for dividing every corresponding element - and plot. Step8: Moreover, the relative error of this ratio can be calculated by multiplicative error propagation as the square root of the sum of squared relative errors (enumerator and denominator), and from it the absolute error. The Numpy functions "sqrt" and "square" applied to array-like structures perform these operations element-wise, so the entire calculation can be conveniently done using the arrays as arguments, and we obtain individual errors for every train in the end. Step9: We can as well plot the suppression ratio values with individual error bars according to the respective absolute error. Here, we restrict ourselves to the first 50 trains for clarity Step10: Finally, we draw a histogram of suppression ratio values Step11: We see that there is a suppression of signal from odd pulses to approximately 4% of the intensity of even pulses. Step12: The difference here is that the selection scheme (indexing and slicing) shifts by one with respect to SASE1 data Step13: The suppression ratio calculation and its plot Step14: The error calculation with (selective) plot Step15: The histogram Step16: Here, suppression of signal for even "off" pulses is to approximately 0.5% of intensity from odd "on" pulses. The "suppression factor" is almost 10 times the value of SASE1. However, the relative error of these values is larger as well, as can be seen in the error-bar plot. For the smaller quantities, it is ~ 100% (!).
<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt import numpy as np import xarray as xr from karabo_data import RunDirectory sa1_data = RunDirectory('/gpfs/exfel/exp/XMPL/201750/p700000/raw/r0008') sa1_data.info() sa1_data.keys_for_source('SA1_XTD2_XGM/XGM/DOOCS:output') sa1_flux = sa1_data.get_array('SA1_XTD2_XGM/XGM/DOOCS:output', 'data.intensityTD') print(sa1_flux) fig = plt.figure(figsize=(10, 6)) ax = fig.add_subplot(1, 1, 1) image = ax.imshow(sa1_flux[:1500, :30].transpose(), origin='lower', cmap='inferno') ax.set_title('SASE1 XTD2 XGM intensity (fast)') fig.colorbar(image, orientation='horizontal') ax.set_xlabel('train index') ax.set_ylabel('pulseIndex') ax.set_aspect(15) sa1_mean_on = np.mean(sa1_flux[:, :20:2], axis=1) sa1_stddev_on = np.std(sa1_flux[:, :20:2], axis=1) print(sa1_mean_on) sa1_mean_off = np.mean(sa1_flux[:, 1:21:2], axis=1) sa1_stddev_off = np.std(sa1_flux[:, 1:21:2], axis=1) print(sa1_mean_off) sa1_suppression = sa1_mean_off / sa1_mean_on fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) ax.plot(sa1_suppression.coords['trainId'].values, sa1_suppression) ax.set_xlabel('train identifier') ax.ticklabel_format(style='plain', useOffset=False) plt.xticks(rotation=60) ax.set_ylabel('suppression') sa1_rel_error = np.sqrt(np.square(sa1_stddev_off / sa1_mean_off) + np.square(sa1_stddev_on / sa1_mean_on)) sa1_abs_error = sa1_rel_error * sa1_suppression fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) ax.errorbar(sa1_suppression.coords['trainId'].values[:50], sa1_suppression[:50], yerr=sa1_abs_error[:50], fmt='ro') ax.set_xlabel('train identifier') ax.ticklabel_format(style='plain', useOffset=False) plt.xticks(rotation=60) ax.set_ylabel('suppression') fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) _ = ax.hist(sa1_suppression, bins=50) ax.set_xlabel('suppression') ax.set_ylabel('frequency') sa3_data = RunDirectory('/gpfs/exfel/exp/XMPL/201750/p700000/raw/r0009') sa3_data.info() sa3_flux = sa3_data.get_array('SA3_XTD10_XGM/XGM/DOOCS:output', 'data.intensityTD') print(sa3_flux.shape) fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) image = ax.imshow(sa3_flux[:1500, :30].transpose(), origin='lower', cmap='inferno') ax.set_title('SASE3 XTD10 XGM intensity (fast)') fig.colorbar(image, orientation='horizontal') ax.set_xlabel('train index') ax.set_ylabel('pulseIndex') ax.set_aspect(15) sa3_mean_on = np.mean(sa3_flux[:, 1:21:2], axis=1) sa3_stddev_on = np.std(sa3_flux[:, 1:21:2], axis=1) print(sa3_mean_on) sa3_mean_off = np.mean(sa3_flux[:, :20:2], axis=1) sa3_stddev_off = np.std(sa3_flux[:, :20:2], axis=1) print(sa3_mean_off) sa3_suppression = sa3_mean_off / sa3_mean_on fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) ax.plot(sa3_suppression.coords['trainId'].values, sa3_suppression) ax.set_xlabel('train identifier') ax.ticklabel_format(style='plain', useOffset=False) plt.xticks(rotation=60) ax.set_ylabel('suppression') sa3_rel_error = np.sqrt(np.square(sa3_stddev_off / sa3_mean_off) + np.square(sa3_stddev_on / sa3_mean_on)) sa3_abs_error = sa3_rel_error * sa3_suppression fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) ax.errorbar(sa1_suppression.coords['trainId'].values[:50], sa3_suppression[:50], yerr=sa3_abs_error[:50], fmt='ro') ax.set_xlabel('train identifier') ax.ticklabel_format(style='plain', useOffset=False) plt.xticks(rotation=60) ax.set_ylabel('suppression') fig = plt.figure(figsize=(8, 6)) ax = fig.add_subplot(1, 1, 1) _ = ax.hist(sa3_suppression, bins=50) ax.set_xlabel('suppression') ax.set_ylabel('frequency') sa1_on_all = np.array(sa1_flux[:, :20:2]).flatten() sa1_on_all.shape sa1_mean_on_overall = np.mean(sa1_on_all) sa1_stddev_on_overall = np.std(sa1_on_all) sa1_off_all = np.array(sa1_flux[:, 1:21:2]).flatten() sa1_off_all.shape sa1_mean_off_overall = np.mean(sa1_off_all) sa1_stddev_off_overall = np.std(sa1_off_all) sa1_suppression_overall = sa1_mean_off_overall / sa1_mean_on_overall sa1_rel_error_overall = np.sqrt(np.square(sa1_stddev_off_overall / sa1_mean_off_overall) + \ np.square(sa1_stddev_on_overall / sa1_mean_on_overall)) sa1_abs_error_overall = sa1_rel_error_overall * sa1_suppression_overall print('SA1 suppression ratio =', sa1_suppression_overall, '\u00b1', sa1_abs_error_overall) sa3_on_all = np.array(sa3_flux[:, 1:21:2]).flatten() sa3_on_all.shape sa3_mean_on_overall = np.mean(sa3_on_all) sa3_stddev_on_overall = np.std(sa3_on_all) sa3_off_all = np.array(sa3_flux[:, :20:2]).flatten() sa3_off_all.shape sa3_mean_off_overall = np.mean(sa3_off_all) sa3_stddev_off_overall = np.std(sa3_off_all) sa3_suppression_overall = sa3_mean_off_overall / sa3_mean_on_overall sa3_rel_error_overall = np.sqrt(np.square(sa3_stddev_off_overall / sa3_mean_off_overall) + \ np.square(sa3_stddev_on_overall / sa3_mean_on_overall)) sa3_abs_error_overall = sa3_rel_error_overall * sa3_suppression_overall print('SA3 suppression ratio =', sa3_suppression_overall, '\u00b1', sa3_abs_error_overall) <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: Challenges
<ASSISTANT_TASK:> Python Code: from mcpi import minecraft mc = minecraft.Minecraft.create(ip, port, my_name) # send a chat message mc..... # teleport mc.player.getPos() # returns a Vec3 instance; could also get pitch/orientation of player mv.player.setPos(pos_vector) # place blocks from mcpi import block mc.setBlock(x, y, z, block.STONE) mv.setBlocks(x0, y0, z0, x1, y1, z2, block.STONE) # detect blocks mc.getBlock(x, y, z) mc.getBlocks(x0, y0, z0, x1, y1, z1) # clear all the things mc.setBlocks(0, 0, 4, 100, 100, 100, block.AIR) # introduce writing and using functions wall() tower(height) sphere(radius) pyramid(width, height) house() lava(x, y, z) water(x, y z) # create your own teleporter by watching for the player stepping on a certain block, then changing their position <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 a = tf.constant( [[0.3232, -0.2321, 0.2332, -0.1231, 0.2435, 0.6728], [0.2323, -0.1231, -0.5321, -0.1452, 0.5435, 0.1722], [0.9823, -0.1321, -0.6433, 0.1231, 0.023, 0.0711]] ) def g(a): return tf.argmin(a,axis=0) result = g(a.__copy__()) <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 pandas as pd df = pd.DataFrame([[1,1,0,1],[0,0,0,0],[1,0,0,1],[0,1,0,0],[1,1,0,1]],columns=['A','B','C','D']) def g(df): return df.loc[(df.sum(axis=1) != 0), (df.sum(axis=0) != 0)] result = g(df.copy()) <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 new Google Cloud Storage Bucket for ML model exports Step2: Setup parameters for notebook scheduling Step3: Locating the CSV files Step4: Use tf.data to read the CSV files Step5: Add data transformations and build the new DNN Step6: Visualize the DNN model layers Step7: Train the model Step8: Visualize the Model Loss Curves Step9: Evaluate over the full validation dataset Step10: Although we get RMSE of around 10 (your answer will be different due to random seeds), remember that we trained on a really small subset of the data. We need a larger training dataset before making decisions about this model. Step11: However, this is not realistic, because we can't expect client code to have a model object in memory. We'll have to export our model to a file, and expect client code to instantiate the model from that exported file. Step12: Serve the model on Cloud AI Platform Step13: In this notebook, we have looked at how to implement a custom Keras model using feature columns.
<ASSISTANT_TASK:> Python Code: %%bash export PROJECT=$(gcloud config list project --format "value(core.project)") echo "Your current GCP Project Name is: "$PROJECT import os, json, math, shutil import datetime import numpy as np import logging # SET TF ERROR LOG VERBOSITY logging.getLogger("tensorflow").setLevel(logging.ERROR) import tensorflow as tf print(tf.version.VERSION) PROJECT = "your-gcp-project-here" # REPLACE WITH YOUR PROJECT NAME REGION = "us-central1" # REPLACE WITH YOUR BUCKET REGION e.g. us-central1 # Do not change these os.environ["PROJECT"] = PROJECT os.environ["REGION"] = REGION os.environ["BUCKET"] = PROJECT # DEFAULT BUCKET WILL BE PROJECT ID if PROJECT == "your-gcp-project-here": print("Don't forget to update your PROJECT name! Currently:", PROJECT) %%bash ## Create new ML GCS bucket if it doesn't exist already... exists=$(gsutil ls -d | grep -w gs://${PROJECT}-ml/) if [ -n "$exists" ]; then echo -e "Bucket exists, let's not recreate it." else echo "Creating a new GCS bucket." gsutil mb -l ${REGION} gs://${PROJECT}-ml echo -e "\nHere are your current buckets:" gsutil ls fi # Note that this cell is special. It's got a tag (you can view tags by clicking on the wrench icon on the left menu in Jupyter) # These are parameters that we will configure so that we can schedule this notebook DATADIR = '../../data' OUTDIR = './trained_model' NBUCKETS = 10 # for feature crossing TRAIN_BATCH_SIZE = 32 NUM_TRAIN_EXAMPLES = 10000 * 5 # remember the training dataset repeats, so this will wrap around NUM_EVALS = 5 # evaluate this many times NUM_EVAL_EXAMPLES = 10000 # enough to get a reasonable sample, but no so much that it slows down if DATADIR[:5] == 'gs://': !gsutil ls $DATADIR/*.csv else: !ls -l $DATADIR/*.csv CSV_COLUMNS = ['fare_amount', 'pickup_datetime', 'pickup_longitude', 'pickup_latitude', 'dropoff_longitude', 'dropoff_latitude', 'passenger_count', 'key'] LABEL_COLUMN = 'fare_amount' DEFAULTS = [[0.0],['na'],[0.0],[0.0],[0.0],[0.0],[0.0],['na']] def features_and_labels(row_data): for unwanted_col in ['key']: # keep the pickup_datetime! row_data.pop(unwanted_col) label = row_data.pop(LABEL_COLUMN) return row_data, label # features, label # load the training data def load_dataset(pattern, batch_size=1, mode=tf.estimator.ModeKeys.EVAL): pattern = '{}/{}'.format(DATADIR, pattern) dataset = (tf.data.experimental.make_csv_dataset(pattern, batch_size, CSV_COLUMNS, DEFAULTS) .map(features_and_labels) # features, label ) if mode == tf.estimator.ModeKeys.TRAIN: print("Repeating training dataset indefinitely") dataset = dataset.shuffle(1000).repeat() dataset = dataset.prefetch(1) # take advantage of multi-threading; 1=AUTOTUNE return dataset def parse_datetime(s): if type(s) is not str: s = s.numpy().decode('utf-8') # if it is a Tensor return datetime.datetime.strptime(s, "%Y-%m-%d %H:%M:%S %Z") for s in ['2012-07-05 14:18:00 UTC']: print(s) for ts in [parse_datetime(s), parse_datetime(tf.constant(s))]: # as string, as tensor print(ts.weekday()) DAYS = ['Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat'] print(DAYS[ts.weekday()]) ## Add transformations def euclidean(params): lon1, lat1, lon2, lat2 = params londiff = lon2 - lon1 latdiff = lat2 - lat1 return tf.sqrt(londiff*londiff + latdiff*latdiff) DAYS = ['Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat'] def get_dayofweek(s): ts = parse_datetime(s) return DAYS[ts.weekday()] @tf.function def dayofweek(ts_in): return tf.map_fn( lambda s: tf.py_function(get_dayofweek, inp=[s], Tout=tf.string), ts_in ) @tf.function def fare_thresh(x): return 60 * tf.keras.activations.relu(x) def transform(inputs, NUMERIC_COLS, STRING_COLS): print("BEFORE TRANSFORMATION") print("INPUTS:", inputs.keys()) # Pass-through columns transformed = inputs.copy() del transformed['pickup_datetime'] feature_columns = { colname: tf.feature_column.numeric_column(colname) for colname in NUMERIC_COLS } # scale the lat, lon values to be in 0, 1 if True: for lon_col in ['pickup_longitude', 'dropoff_longitude']: # in range -70 to -78 transformed[lon_col] = tf.keras.layers.Lambda( lambda x: (x+78)/8.0, name='scale_{}'.format(lon_col) )(inputs[lon_col]) for lat_col in ['pickup_latitude', 'dropoff_latitude']: # in range 37 to 45 transformed[lat_col] = tf.keras.layers.Lambda( lambda x: (x-37)/8.0, name='scale_{}'.format(lat_col) )(inputs[lat_col]) # add Euclidean distance. Doesn't have to be accurate calculation because NN will calibrate it if True: transformed['euclidean'] = tf.keras.layers.Lambda(euclidean, name='euclidean')([ inputs['pickup_longitude'], inputs['pickup_latitude'], inputs['dropoff_longitude'], inputs['dropoff_latitude'] ]) feature_columns['euclidean'] = tf.feature_column.numeric_column('euclidean') # hour of day from timestamp of form '2010-02-08 09:17:00+00:00' if True: transformed['hourofday'] = tf.keras.layers.Lambda( lambda x: tf.strings.to_number(tf.strings.substr(x, 11, 2), out_type=tf.dtypes.int32), name='hourofday' )(inputs['pickup_datetime']) feature_columns['hourofday'] = tf.feature_column.indicator_column( tf.feature_column.categorical_column_with_identity('hourofday', num_buckets=24)) if False: # https://buganizer.corp.google.com/issues/137795281 # day of week is hard because there is no TensorFlow function for date handling transformed['dayofweek'] = tf.keras.layers.Lambda( lambda x: dayofweek(x), name='dayofweek_pyfun' )(inputs['pickup_datetime']) transformed['dayofweek'] = tf.keras.layers.Reshape((), name='dayofweek')(transformed['dayofweek']) feature_columns['dayofweek'] = tf.feature_column.indicator_column( tf.feature_column.categorical_column_with_vocabulary_list( 'dayofweek', vocabulary_list = DAYS)) if True: # https://buganizer.corp.google.com/issues/135479527 # featurecross lat, lon into nxn buckets, then embed nbuckets = NBUCKETS latbuckets = np.linspace(0, 1, nbuckets).tolist() lonbuckets = np.linspace(0, 1, nbuckets).tolist() b_plat = tf.feature_column.bucketized_column(feature_columns['pickup_latitude'], latbuckets) b_dlat = tf.feature_column.bucketized_column(feature_columns['dropoff_latitude'], latbuckets) b_plon = tf.feature_column.bucketized_column(feature_columns['pickup_longitude'], lonbuckets) b_dlon = tf.feature_column.bucketized_column(feature_columns['dropoff_longitude'], lonbuckets) ploc = tf.feature_column.crossed_column([b_plat, b_plon], nbuckets * nbuckets) dloc = tf.feature_column.crossed_column([b_dlat, b_dlon], nbuckets * nbuckets) pd_pair = tf.feature_column.crossed_column([ploc, dloc], nbuckets ** 4 ) feature_columns['pickup_and_dropoff'] = tf.feature_column.embedding_column(pd_pair, 100) print("AFTER TRANSFORMATION") print("TRANSFORMED:", transformed.keys()) print("FEATURES", feature_columns.keys()) return transformed, feature_columns def rmse(y_true, y_pred): return tf.sqrt(tf.reduce_mean(tf.square(y_pred - y_true))) def build_dnn_model(): # input layer is all float except for pickup_datetime which is a string STRING_COLS = ['pickup_datetime'] NUMERIC_COLS = set(CSV_COLUMNS) - set([LABEL_COLUMN, 'key']) - set(STRING_COLS) print(STRING_COLS) print(NUMERIC_COLS) inputs = { colname : tf.keras.layers.Input(name=colname, shape=(), dtype='float32') for colname in NUMERIC_COLS } inputs.update({ colname : tf.keras.layers.Input(name=colname, shape=(), dtype='string') for colname in STRING_COLS }) # transforms transformed, feature_columns = transform(inputs, NUMERIC_COLS, STRING_COLS) dnn_inputs = tf.keras.layers.DenseFeatures(feature_columns.values())(transformed) # two hidden layers of [32, 8] just in like the BQML DNN h1 = tf.keras.layers.Dense(32, activation='relu', name='h1')(dnn_inputs) h2 = tf.keras.layers.Dense(8, activation='relu', name='h2')(h1) if False: # https://buganizer.corp.google.com/issues/136476088 # final output would normally have a linear activation because this is regression # However, we know something about the taxi problem (fares are +ve and tend to be below $60). # Use that here. (You can verify by running this query): # SELECT APPROX_QUANTILES(fare_amount, 100) FROM serverlessml.cleaned_training_data output = tf.keras.layers.Dense(1, activation=fare_thresh, name='fare')(h2) else: output = tf.keras.layers.Dense(1, name='fare')(h2) model = tf.keras.models.Model(inputs, output) model.compile(optimizer='adam', loss='mse', metrics=[rmse, 'mse']) return model model = build_dnn_model() print(model.summary()) tf.keras.utils.plot_model(model, 'dnn_model.png', show_shapes=False, rankdir='LR') trainds = load_dataset('taxi-train*', TRAIN_BATCH_SIZE, tf.estimator.ModeKeys.TRAIN) evalds = load_dataset('taxi-valid*', 1000, tf.estimator.ModeKeys.EVAL).take(NUM_EVAL_EXAMPLES//10000) # evaluate on 1/10 final evaluation set steps_per_epoch = NUM_TRAIN_EXAMPLES // (TRAIN_BATCH_SIZE * NUM_EVALS) shutil.rmtree('{}/checkpoints/'.format(OUTDIR), ignore_errors=True) checkpoint_path = '{}/checkpoints/taxi'.format(OUTDIR) cp_callback = tf.keras.callbacks.ModelCheckpoint(checkpoint_path, save_weights_only=True, verbose=1) history = model.fit(trainds, validation_data=evalds, epochs=NUM_EVALS, steps_per_epoch=steps_per_epoch, verbose=2, # 0=silent, 1=progress bar, 2=one line per epoch callbacks=[cp_callback]) # plot import matplotlib.pyplot as plt nrows = 1 ncols = 2 fig = plt.figure(figsize=(10, 5)) for idx, key in enumerate(['loss', 'rmse']): ax = fig.add_subplot(nrows, ncols, idx+1) plt.plot(history.history[key]) plt.plot(history.history['val_{}'.format(key)]) plt.title('model {}'.format(key)) plt.ylabel(key) plt.xlabel('epoch') plt.legend(['train', 'validation'], loc='upper left'); evalds = load_dataset('taxi-valid*', 1000, tf.estimator.ModeKeys.EVAL).take(NUM_EVAL_EXAMPLES//1000) model.evaluate(evalds) model.predict({ 'pickup_longitude': tf.convert_to_tensor([-73.982683]), 'pickup_latitude': tf.convert_to_tensor([40.742104]), 'dropoff_longitude': tf.convert_to_tensor([-73.983766]), 'dropoff_latitude': tf.convert_to_tensor([40.755174]), 'passenger_count': tf.convert_to_tensor([3.0]), 'pickup_datetime': tf.convert_to_tensor(['2010-02-08 09:17:00 UTC'], dtype=tf.string), }, steps=1) import shutil, os, datetime OUTPUT_DIR = os.path.join(OUTDIR, 'export/savedmodel') if OUTPUT_DIR[:5] != 'gs://': shutil.rmtree(OUTPUT_DIR, ignore_errors=True) EXPORT_PATH = os.path.join(OUTPUT_DIR, datetime.datetime.now().strftime('%Y%m%d%H%M%S')) tf.saved_model.save(model, EXPORT_PATH) # with default serving function !saved_model_cli show --tag_set serve --signature_def serving_default --dir {EXPORT_PATH} !find {EXPORT_PATH} os.environ['EXPORT_PATH'] = EXPORT_PATH %%bash PROJECT=${PROJECT} BUCKET=${PROJECT}-ml REGION=us-east1 MODEL_NAME=taxifare VERSION_NAME=v2 if [[ $(gcloud ai-platform models list --format='value(name)' | grep $MODEL_NAME) ]]; then echo "$MODEL_NAME already exists" else # create model echo "Creating $MODEL_NAME" gcloud ai-platform models create --regions=$REGION $MODEL_NAME fi if [[ $(gcloud ai-platform versions list --model $MODEL_NAME --format='value(name)' | grep $VERSION_NAME) ]]; then echo "Deleting already existing $MODEL_NAME:$VERSION_NAME ... " gcloud ai-platform versions delete --model=$MODEL_NAME $VERSION_NAME echo "Please run this cell again if you don't see a Creating message ... " sleep 10 fi # create model echo "Creating $MODEL_NAME:$VERSION_NAME" gcloud ai-platform versions create --model=$MODEL_NAME $VERSION_NAME --async \ --framework=tensorflow --python-version=3.7 --runtime-version=1.15 \ --origin=$EXPORT_PATH --staging-bucket=gs://$BUCKET %%writefile repro.json {"pickup_longitude": -73.982683, "pickup_latitude": 40.742104, "dropoff_longitude": -73.983766, "dropoff_latitude": 40.755174, "passenger_count": 3.0, "pickup_datetime": "2010-02-08 09:17:00 UTC"} !gcloud ai-platform predict --model taxifare --json-instances repro.json --version v2 <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: ์„œ์‹ ์žˆ๋Š” print ๋ฌธ Step2: ์•„๋ž˜์™€ ๊ฐ™์ด ์ธ๋ฑ์‹ฑ์„ ์ด์šฉํ•˜๋Š” Step3: ๋ฌธ์ž์—ด ํ™œ์šฉ Step4: range ํ•จ์ˆ˜ Step5: ํŒŒ์ด์ฌ 2.x ๋ฒ„์ „์—์„œ๋Š” range์™€ ๊ฑฐ์˜ ๋™์ผํ•œ ์—ญํ• ์„ ์ˆ˜ํ–‰ํ•˜์ง€๋งŒ ๋ฆฌ์ŠคํŠธ ์ „์ฒด๋ฅผ ๋ณด์—ฌ์ฃผ์ง€ ์•Š๋Š” xrange๊ฐ€ ์žˆ๋‹ค. Step6: ์ฃผ์˜ Step7: range ํ•จ์ˆ˜ ์ธ์ž Step8: range ํ•จ์ˆ˜๋Š” for๋ฌธ์—์„œ ์œ ์šฉํ•˜๊ฒŒ ํ™œ์šฉ๋œ๋‹ค. Step9: ๋‹จ์ˆœํ•œ ์นด์šดํŠธ ์—ญํ• ์„ ์ˆ˜ํ–‰ํ•˜๋Š” ์šฉ๋„๋กœ rangeํ•จ์ˆ˜๋ฅผ ํ™œ์šฉํ•  ์ˆ˜๋„ ์žˆ๋‹ค. Step10: C ๋˜๋Š” Java ์–ธ์–ด์—์„œ์™€๋Š” ๋‹ฌ๋ฆฌ ํŒŒ์ด์ฌ์—์„œ๋Š” for๋ฌธ์—์„œ ์‚ฌ์šฉ๋˜๋Š” ๋ณ€์ˆ˜๋Š” ์ง€์—ญ๋ณ€์ˆ˜๊ฐ€ ์•„๋‹˜์— ์ฃผ์˜ํ•  ๊ฒƒ. Step11: range ํ•จ์ˆ˜ ํ™œ์šฉ Step12: ์—ฐ์Šต Step13: ์—ฐ์Šต Step14: ์—ฐ์Šต Step15: while ๋ฌธ ๋ฃจํ”„ Step16: ์˜ˆ์ œ Step17: ์—ฐ์Šต๋ฌธ์ œ Step18: [0.0, 0.1, 0.2, 0.3, ..., 0.9, 1.0]์„ ๊ธฐ๋Œ€ํ•˜์˜€์ง€๋งŒ ๋‹ค๋ฅด๊ฒŒ ๋‚˜์™”๋‹ค. n_divide ํ•จ์ˆ˜๋ฅผ ์•„๋ž˜์™€ ๊ฐ™์ด ์ฝ”๋”ฉํ•ด ๋ณด์ž.
<ASSISTANT_TASK:> Python Code: animals = ['cat', 'dog', 'mouse'] for x in animals: print("This is the {}.".format(x)) for x in animals: print("{}!, this is the {}.".format("Hi", x)) for x in animals: print("{1}!, you are {0}.".format("animals", x)) for letter in "Hello World": print(letter) a = range(10) a b = xrange(10) b a[5] b[5] a[2:6] c0 = range(4) c0 c1 = range(1, 4) c1 c2 = range(1, 10, 2) c2 for i in range(6): print("the square of {} is {}").format(i, i ** 2) for i in range(5): print("printing five times") i def range_double(x): z = [] for y in range(x): z.append(y*2) return z range_double(4) def skip13(a, b): result = [] for k in range (a,b): if k == 13: pass # ์•„๋ฌด ๊ฒƒ๋„ ํ•˜์ง€ ์•Š์Œ else: result.append(k) return result skip13(1, 20) q = [] def add(name): q.append(name) def next(): return q.pop(0) def show(): for i in q: print(i) def length(): return len(q) add("SeungMin") q add("Jisung") q.pop(1) q next() add("Park") add("Kim") q show() length() next() add("Hwang") show() next() show() def iterate(f, x, n): a = x for i in range(n): a = f(a) return a # ๋ฐ˜ ๋‚˜๋ˆ„๊ธฐ๋ฅผ ์›ํ•˜๋Š” ๋งŒํผ ๋ฐ˜๋ณตํ•˜๊ณ ์ž ํ•˜๋ฉด f ์ธ์ž์— ์•„๋ž˜ divide_2 ํ•จ์ˆ˜๋ฅผ ์ž…๋ ฅํ•˜๋ฉด ๋œ๋‹ค. def divide_2(x): return x/2.0 iterate(divide_2, 64, 3) x = 64 while x > 1: x = x/2 print(x) eps = 1.0 while eps + 1 > 1: eps = eps / 2.0 eps + 1 > 1 # print("A very small epsilon is {}.".format(eps)) def n_divide(n): a = [] for i in range(n+1): d = 1-(float(n-i)/n) a.append(d) return a n_divide(10) def n_divide1(n): a = [] for i in range(n+1): d = (float(i)/n) a.append(d) return a n_divide1(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: Let's see which free resources are readily available. And then let's have a closer look at Shakespeare's Hamlet (to pretent we are literature freaks). Step2: Regular Expressions Step3: And which of them actually start with "wre"? Step4: Find all words that start with "T" or "t", end with "r" and have exactly 3 other characters in the middle. To implement the "T" or "t" we use a character class specified by the brackets []. [Tt]matches either "T" or "t". Step5: Did Shakespeare use any numbers (written as digits?) For macthing all the digits, we could similarly use [0123456789] or [0-9], but using the abbreviation \dis much more convenient. Step6: And is there something that starts with z and ends with g? Step7: In the last example we can not be sure whether there is definitely nothing or whether we got the regular expression wrong. To find out which one is the case, create a string you know should match and test your expression there.
<ASSISTANT_TASK:> Python Code: import nltk, re from nltk import word_tokenize # NOTE if the data (corpora, example files) is not yet downloaded, this needs to be done first # nltk.download() print(nltk.corpus.gutenberg.fileids()) hamlet = nltk.corpus.gutenberg.words('shakespeare-hamlet.txt') print(len(hamlet)) [w for w in hamlet if re.search('wre', w)] [w for w in hamlet if re.search('^wre', w)] [w for w in hamlet if re.search('^[Tt]\w{5,5}r$', w)] [w for w in hamlet if re.search('\d', w)] [w for w in hamlet if re.search('^z.*g$', w)] [w for w in ["zarhhg","zhang","zg","42"] if re.search('^z.*g$', w)] <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 --&gt; Software Properties Step13: 2.2. Code Version Step14: 2.3. Code Languages Step15: 3. Key Properties --&gt; 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 --&gt; Timestep Framework --&gt; 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 --&gt; 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 --&gt; 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 --&gt; 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 --&gt; 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 --&gt; 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 --&gt; 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', 'ncc', 'noresm2-mh', '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: ๆ‰พๅ‡บๅœ–็‰‡็š„็ถฒๅ€ Step2: Q Step3: ๅฆ‚ไฝ•ๆ›้ ? Step4: ้–‹ๅง‹ๅ›žๅœˆไพ†ๆŠ“ๅœ–ๅง Step5: ๅทฒ็ถ“ๅฏไปฅๆŠ“ไบ†๏ผŒ้‚„ๆœ‰ไป€้บผๅ•้กŒ๏ผŸ Step6: ็พๅœจไพ†ๅปบ็ซ‹ไธ€ๅ€‹ไป‹้ข Step7: ๆ“‹ๆމๆ›ดๅคšๅปฃๅ‘Š Step8: ๅˆฉ็”จ thread
<ASSISTANT_TASK:> Python Code: import spynner import os, sys from IPython.display import display, Image # ็”จ spynner ๆ‰“้–‹็€่ฆฝๅ™จ browser = spynner.Browser(debug_level=spynner.ERROR, debug_stream=sys.stderr) browser.show() # ๅ‘Š่จด browser๏ผŒ่ฆๅฎƒไน‹ๅพŒไธ่ฆ้šฑ่บซ # ๅœจ ?????? ๅกซๅ…ฅ้ฉ็•ถ็ถฒๅ€ base_url = 'http://v.??????.com/online/comic-7340.html?ch=' book_no = 54 browser.load( base_url+str(book_no)) browser.load_jquery(True) # spynner ๅ…งๅปบๆœ‰ jquery๏ผŒ็”จ้€™ๅ€‹ method ่ผ‰ๅ…ฅ๏ผŒๆฏ”่ผƒๆ–นไพฟใ€‚ img_url = browser.runjs('$("#TheImg").attr("src")') print(img_url) Image(img_url, width=200) # ็•ถ็„ถไธ็”จ jquery ไนŸๅฏไปฅ browser.runjs('document.getElementById("TheImg").getAttribute("src")') img_data = browser.download(img_url) # jpg ๆช”ๆกˆๅ…งๅฎน with open("cover.jpg", 'wb') as jpg_file: jpg_file.write(img_data) Image(data=img_data, width=200) #็ธฝๅ…ฑ้ ๆ•ธ total_pages = int(browser.runjs('ps')) total_pages for page in range(1, 1+total_pages): browser.load("{}{}-{}".format(base_url, book_no, page)) img_url = browser.runjs('document.getElementById("TheImg").getAttribute("src")') print(page, img_url) with open("{}-{}.jpg".format(book_no, page), "wb") as f: browser.download(img_url, outfd=f) print("File saved in", os.getcwd()) from PySide.QtWebKit import QWebSettings # ็”จไพ†่จญๅฎš QtWebKit # ๅˆฉ็”จ import ipywidgets as W # ่จญๅฎšไธ่‡ชๅ‹•้กฏ็คบๅœ–็‰‡ settings = browser.webview.settings() settings.setAttribute(QWebSettings.AutoLoadImages, False) # ๅฏไปฅ็œ‹ๅˆฐ็€่ฆฝๅ™จไธฆไธๆœƒ่ฎ€้€ฒๅœ–็‰‡ total_pages = int(browser.runjs('ps')) for page in range(1, 1+10): browser.load("{}{}-{}".format(base_url, book_no, page)) img_url = browser.runjs('document.getElementById("TheImg").getAttribute("src")') print(page, img_url) # ๅปบ็ซ‹ Image Widget ็”จไพ†้กฏ็คบๅœ–็‰‡้ ่ฆฝ img = W.Image() img.width = 300 # ้กฏ็คบไธ‹่ผ‰้€ฒๅบฆ็š„ Progress bar progress = W.IntProgress(min=1, value=1, max=total_pages) display(img) display(progress) dir_name = os.path.join("download", "{:02d}".format(book_no)) if not os.path.exists(dir_name): os.makedirs(dir_name) print("Download to {}".format(os.path.join(os.getcwd(), dir_name))) sys.stdout.flush() # ้–‹ๅง‹ไธ‹่ผ‰ for page in range(1, total_pages+1): # ๅ–ๅพ— image url browser.load("{}{}-{}".format(base_url, book_no, page)) img_url = browser.runjs('document.getElementById("TheImg").getAttribute("src")') # ไธ‹่ผ‰ๅœ–็‰‡ fn = os.path.join(dir_name, "{:03d}.jpg".format(page)) with open(fn, "wb") as f: browser.download(img_url, outfd=f) # ๆ›ดๆ–ฐ Widget ็š„็‹€ๆ…‹ progress.description = "%d/%d"%(page, total_pages) progress.value = page img.value = Image(filename=fn).data from PySide.QtNetwork import QNetworkAccessManager, QNetworkRequest # ๆŽงๅˆถ browser ็š„็ถฒ่ทฏ้€ฃ็ทš from PySide.QtCore import QUrl # Qt ็š„ Url ้กžๅˆฅ # ้—œๆމไน‹ๅ‰็š„ browser browser.close() browser = spynner.Browser(debug_level=spynner.ERROR, debug_stream=sys.stderr) # ๅปบ็ซ‹ไธ€ๅ€‹ webview # ๆˆ‘ๅ€‘ไธ่จญๅฎš AutoLoadImages=False, ไฝ†ๅขžๅŠ ไธ€ไบ›ๅ…ถไป–่จญๅฎš # ้€™่ฃกไธฆไธๆ˜ฏ้‡้ปž๏ผŒไฝ†้ฉๅˆๆˆ‘ๅ€‘็š„ๆ‡‰็”จ browser.create_webview() settings = browser.webview.settings() # settings.setAttribute(QWebSettings.AutoLoadImages, False) settings.setAttribute(QWebSettings.JavaEnabled, False) # ไธ้œ€่ฆ Java settings.setAttribute(QWebSettings.DnsPrefetchEnabled, True) # ่ฉฆ่‘—็ฏ€็œ Dns ่Šฑ็š„ๆ™‚้–“ settings.setAttribute(QWebSettings.PrivateBrowsingEnabled, True) # ไธ้œ€่ฆ็€่ฆฝ็ด€้Œ„ # ๅปบ็ซ‹ไธ€ๅ€‹็ฉบ็š„ url BLANK_REQUEST = QNetworkRequest(QUrl()) # ๅปบ็ซ‹ไธ€ๅ€‹็ฉบ็š„ๅœ–็‰‡ url DUMMY_IMG_REQUEST = QNetworkRequest(QUrl("data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=")) # ๅ› ็‚บๅช้œ€่ฆ็”จไธ€ๆฌก๏ผŒๅฏไปฅๅ–ๅ€‹ๅˆ่‡ญๅˆ้•ท็š„ๅๅญ— class EightComicNetworkAccessManager(QNetworkAccessManager): # ๅช้œ€่ฆๅ–ไปฃ createRequest ้€™ๅ€‹ method ๅณๅฏ def createRequest(self, op, request, device=None): url = str(request.url().toString()) # ๅƒๆ•ธๅพˆๅคš๏ผŒไฝ†ๅชๅ– url ๅฐฑๅค ็”จ if 'comic' not in url[:20]: # ็”จๅพˆ้†œ็š„ๆ–นๅผไพ†ๅˆคๆ–ท้ž 8comic ็ถฒ็ซ™็š„ url # ็”จ็ฉบ็š„ url ๅ–ไปฃๅŽŸๆœฌ็š„ url return QNetworkAccessManager.createRequest(self, self.GetOperation, BLANK_REQUEST) elif not url.endswith('js') and not url.endswith('css') and '.html' not in url: # ๅ‡กๆ˜ฏ .js .css .html ไน‹ๅค–็š„๏ผŒ้ƒฝ็”จ็ฉบ็š„ๅœ–็‰‡ url ๅ–ไปฃๅŽŸๆœฌ็š„ url return QNetworkAccessManager.createRequest(self, self.GetOperation, DUMMY_IMG_REQUEST) else: # ๅ‚ณๅ›žๅŽŸๆœฌ็š„ url return QNetworkAccessManager.createRequest(self, op, request, device) # ่จญๅฎš browser ็š„ NetworkAccessManager browser.webpage.setNetworkAccessManager(EightComicNetworkAccessManager()) browser.show() browser.load(base_url+str(book_no)) total_pages = int(browser.runjs('ps')) %%timeit -n 1 -r 1 # ๅปบ็ซ‹ Image Widget ็”จไพ†้กฏ็คบๅœ–็‰‡้ ่ฆฝ img = W.Image() img.width = 300 # ้กฏ็คบไธ‹่ผ‰้€ฒๅบฆ็š„ Progress bar progress = W.IntProgress(min=1, value=1, max=total_pages) display(img) display(progress) dir_name = os.path.join("download", "{:02d}".format(book_no)) if not os.path.exists(dir_name): os.makedirs(dir_name) print("Download to {}".format(os.path.join(os.getcwd(), dir_name))) sys.stdout.flush() # ้–‹ๅง‹ไธ‹่ผ‰ for page in range(1, total_pages+1): # ๅ–ๅพ— image url browser.load("{}{}-{}".format(base_url, book_no, page)) img_url = browser.runjs('document.getElementById("TheImg").getAttribute("src")') # ไธ‹่ผ‰ๅœ–็‰‡ fn = os.path.join(dir_name, "{:03d}.jpg".format(page)) with open(fn, "wb") as f: browser.download(img_url, outfd=f) # ๆ›ดๆ–ฐ Widget ็š„็‹€ๆ…‹ progress.description = "%d/%d"%(page, total_pages) progress.value = page img.value = Image(filename=fn).data from urllib.request import urlopen from multiprocessing.pool import ThreadPool %%timeit -n 1 -r 1 book_no = 63 browser.load(base_url+str(book_no)) total_pages = int(browser.runjs('ps')) def save_img(img_url, page): fn = os.path.join(dir_name, "{:03d}.jpg".format(page)) with urlopen(img_url) as img_src: with open(fn, "wb") as f: f.write(img_src.read()) # ๆ›ดๆ–ฐ widget ็š„็‹€ๆ…‹ progress.value += 1 progress.description = "img: %d/%d"%(progress.value, total_pages) img.value = "<img src='{}' height=300 />".format(fn) # ๅปบ็ซ‹ Image Widget ็”จไพ†้กฏ็คบๅœ–็‰‡้ ่ฆฝ img = W.HTML() # ้กฏ็คบไธ‹่ผ‰้€ฒๅบฆ็š„ Progress bar progress = W.IntProgress(min=1, value=1, max=total_pages) display(progress) display(img) dir_name = os.path.join("download", "{:02d}".format(book_no)) if not os.path.exists(dir_name): os.makedirs(dir_name) print("Download to {}".format(os.path.join(os.getcwd(), dir_name))) sys.stdout.flush() pool = ThreadPool(5) for page in range(1, total_pages+1): # ๅ–ๅพ— image url browser.load("{}{}-{}".format(base_url, book_no, page)) img_url = browser.runjs('document.getElementById("TheImg").getAttribute("src")') pool.apply_async(save_img, (img_url, page)) pool.close() pool.join() <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: Logistic regression analysis Step2: Now we will load our sample data and create a 'Alcabuse' variable from 'Dalc' and 'Walc' (weekday and weekend alcohol consumption level, respectively) and make it a binary variable by calling it alcohol abuse if a student scores more than 8 on drinking alcohol in a week. The dataset was retrieved from here but slightly modified to better illustrate our purpose. Step3: The hypothesis we want to test is Step4: Interpreting logistic model coefficients for prediction Step5: Plotting the predictions of the model Step6: Interpreting coefficients as odds Step7: Cross-validation Step8: 2. Fit the model on the training dataset Step9: 3. Calculate predictions on the test dataset Step10: 4. Calculate accuracy of the predictions Step11: Question Step12: Accuracy, sensitivity, and specificity are all affected if we change the cutoff value to .7 Step13: Regularization Step14: How do we determine the penalty value? Step15: Now let's create a plot showing how well each alpha value performs across cross-validation folds Step16: Ridge regression Step17: The points on the left vertical axis (the left ends of the lines) are the ordinary least squares regression values.
<ASSISTANT_TASK:> Python Code: %matplotlib inline import numpy as np import pandas as pd import matplotlib.pyplot as plt import statsmodels.formula.api as smf import seaborn as sns from IPython.display import display, HTML # Plot a sigmoid function plt.figure(figsize=(5,5)) # open a figure base and determine the size (width, height) def sigmoid(t): # Define the sigmoid function return (1/(1 + np.e**(-t))) plot_range = np.arange(-6, 6, 0.1) # range of x values to plot y_values = sigmoid(plot_range) # Plot curve plt.plot(plot_range, # X-axis range y_values, # Predicted values color="red",linewidth=3) plt.title("Example of a sigmoid function",fontsize=18) plt.ylabel("Probability",fontsize=16) # Load the data df = pd.read_csv('../Data/student-mat.csv') df['Alcabuse']=0 df.loc[df['Dalc']+df['Walc'] >=8,'Alcabuse']=1 # Let's call it abuse if more than 8 alcohol consumption per week logm = smf.logit('Alcabuse ~ freetime',data=df).fit() print(logm.summary()) x = 5 print('x = %i' %x) # x print('b0 = %f' %logm.params[0]) # b0 print('b1 = %f' %logm.params[1]) # b1 palcabuse = sigmoid(logm.params[0] + logm.params[1] * x) print('palcabuse = %f' %palcabuse) print('If a student has %i hours of free time per week, then he has %.2f %% probability of alcohol abuse' % (x,palcabuse*100)) # Note that we had to use double percent sign %% to print % # because a single % is reserved for printing inline numbers as in %i or %.2f # Plot model fit xs = np.arange(min(df.freetime)-1,max(df.freetime)+1,0.1) ys = np.array([sigmoid(logm.params[0] + logm.params[1] * x) for x in xs]) plt.figure(figsize=(8,4)) plt.plot(xs,ys,linewidth=3) jitter = np.random.random(len(df.Alcabuse))/5 ys_outcomes = np.abs((df.Alcabuse==1)-0.01-jitter) alpha = 0.7 plt.plot(df.freetime[df.Alcabuse == 1], ys_outcomes[df.Alcabuse ==1], 'b.', alpha=alpha) plt.plot(df.freetime[df.Alcabuse == 0], ys_outcomes[df.Alcabuse ==0], 'r.', alpha=alpha) plt.xlabel("Freetime",fontsize=16) plt.ylabel("Probability of being an alcohol abuser",fontsize=16) plt.title("Predicting alcohol abuse by free time",fontsize=18) odd1 = sigmoid(logm.params[0] + logm.params[1] * 5) / (1-sigmoid(logm.params[0] + logm.params[1] * 5)) odd2 = sigmoid(logm.params[0] + logm.params[1] * 4) / (1-sigmoid(logm.params[0] + logm.params[1] * 4)) dodds = odd1/odd2 print('A student with 5hrs of free time compared to a student with 4 is %.2f times more likely to be an alcohol abuser' %dodds) from sklearn.cross_validation import train_test_split np.random.seed(12345678) # set the random number generator seed to get consistent results trainratio = .6 train, test = train_test_split(df, train_size=trainratio, random_state=1) print('train-test ratio %.2f' %(float(len(train))/(len(train)+len(test)))) # We run the model on the train dataset logmt = smf.logit('Alcabuse ~ freetime + goout',data=train).fit() print(logmt.summary()) ytestpred = logmt.predict(test) np.round(ytestpred,2) cutoff = .5 # Calculate accuracy for train ytrainpred = logmt.predict(train) ytrainpred[ytrainpred>=cutoff] =1 ytrainpred[ytrainpred<cutoff] =0 accs_train = pd.crosstab(ytrainpred,train["Alcabuse"]) # Calculate accuracy for test ytestpred = logmt.predict(test) ytestpred[ytestpred>=cutoff] =1 ytestpred[ytestpred<cutoff] =0 accs_test = pd.crosstab(ytestpred,test["Alcabuse"]) # Overall accuracy print('Overall Accuracy in Training set : %.2f ' %((accs_train[0][0]+accs_train[1][1])/float(train.shape[0]))) print('overall Accuracy in Testing set : %.2f ' %((accs_test[0][0]+accs_test[1][1])/float(test.shape[0]))) # Sensitivity and false negatives print('Training') display(accs_train) print('') print('sensitivity : %.2f ' %(float(accs_train[1][1])/(accs_train[1][1]+accs_train[1][0]))) print('false negative : %.2f ' %(float(accs_train[1][0])/(accs_train[1][1]+accs_train[1][0]))) print('specificity : %.2f ' %(float(accs_train[0][0])/(accs_train[0][0]+accs_train[0][1]))) print('false positives : %.2f ' %(float(accs_train[0][1])/(accs_train[0][0]+accs_train[0][1]))) # Specificity and false positives print('\n') print('Test') display(accs_test) print('\n') print('sensitivity : %.2f ' %(float(accs_test[1][1])/(accs_test[1][1]+accs_test[1][0]))) print('false negative : %.2f ' %(float(accs_test[1][0])/(accs_test[1][1]+accs_test[1][0]))) print('specificity : %.2f ' %(float(accs_test[0][0])/(accs_test[0][0]+accs_test[0][1]))) print('false positives : %.2f ' %(float(accs_test[0][1])/(accs_test[0][0]+accs_test[0][1]))) ytestpred = logmt.predict(test) cutoff = .7 ytestpred[ytestpred>=cutoff] =1 ytestpred[ytestpred<cutoff] =0 accs = pd.crosstab(ytestpred,test["Alcabuse"]) # Overall accuracy print ('overall accuracy : %.2f ' %((accs[0][0]+accs[1][1])/float(test.shape[0]))) # Sensitivity and false negatives print('') print('sensitivity : %.2f ' %(float(accs[1][1])/(accs[1][1]+accs[1][0]))) print('false negative : %.2f ' %(float(accs[1][0])/(accs[1][1]+accs[1][0]))) # Specificity and false positives print('') print('specificity : %.2f ' %(float(accs[0][0])/(accs[0][0]+accs[0][1]))) print('false positives : %.2f ' %(float(accs[0][1])/(accs[0][0]+accs[0][1]))) display(accs) df['AlcSum']=df['Dalc']+df['Walc'] # We have a lot of features to choose from df.keys() # Make a model with all the feature variables formula = 'AlcSum ~ school+sex+age+address+famsize+Pstatus+Medu+\ Fedu+Mjob+Fjob+reason+guardian+traveltime+\ studytime+failures+schoolsup+famsup+paid+activities+nursery+higher+\ internet+romantic+famrel+freetime+goout+health+absences+G1+G2+G3' # Generate a design matrix with the formula # This automatically generates separate regressors for categorical variables. from patsy import dmatrices y, X = dmatrices(formula_like=formula, data=df, return_type='dataframe') # Ridge if L1_wt = 0 , Lasso if L1_wt = 1 penalty = .036 regm = smf.OLS(y,X).fit_regularized(method='coord_descent', maxiter=1000, alpha=penalty, L1_wt=1.0) print regm.summary() from sklearn.linear_model import LassoCV, LassoLarsCV, LassoLarsIC import time # LassoLarsIC: least angle regression with BIC/AIC criterion model_bic = LassoLarsIC(criterion='bic') model_bic.fit(X, y) alpha_bic_ = model_bic.alpha_ model_aic = LassoLarsIC(criterion='aic') model_aic.fit(X, y) alpha_aic_ = model_aic.alpha_ def plot_ic_criterion(model, name, value, color): alpha_ = model.alpha_ alphas_ = model.alphas_ criterion_ = model.criterion_ plt.plot(-np.log10(alphas_), criterion_, '--', color=color, linewidth=3, label='%s criterion' % name) plt.axvline(-np.log10(alpha_), color=color, linewidth=3, label='%s estimate alpha: %.3f' %(name,value) ) plt.xlabel('-log(alpha)',fontsize=16) plt.ylabel('Model Fit Criterion',fontsize=16) plt.figure(figsize=(15,5)) plot_ic_criterion(model_aic, 'AIC', alpha_aic_ , 'b') plot_ic_criterion(model_bic, 'BIC', alpha_bic_ , 'r') plt.legend() plt.title('Information-criterion for model selection',fontsize=18) # LassoCV: coordinate descent y, X = dmatrices(formula_like=formula, data=df, return_type='dataframe') # Compute paths print("Computing regularization path using the coordinate descent lasso...") t1 = time.time() model = LassoCV(cv=5).fit(X, y) t_lasso_cv = time.time() - t1 # Display results m_log_alphas = -np.log10(model.alphas_) # Display results plt.figure(figsize=(15,5)) plt.plot(m_log_alphas, model.mse_path_, ':') plt.plot(m_log_alphas, model.mse_path_.mean(axis=-1), 'k', label='Average across the folds', linewidth=2) plt.axvline(-np.log10(model.alpha_), linestyle='--', color='k', label='CV estimate alpha: %.3f' %model.alpha_ ) plt.legend() plt.xlabel('-log(alpha)',fontsize=16) plt.ylabel('Mean square error',fontsize=16) plt.title('Mean square error on each fold: coordinate descent',fontsize=18) plt.axis('tight') from sklearn import linear_model y, X = dmatrices(formula_like=formula, data=df, return_type='dataframe') n_alphas = 200 alphas = np.logspace(-2, 6, n_alphas) # Get optimal lambda clf = linear_model.RidgeCV(alphas=alphas) clf.fit(X,y) aestim = clf.alpha_ # Estimated regularization param # Get paths clf = linear_model.Ridge(fit_intercept=False) coefs = [] for a in alphas: clf.set_params(alpha=a) clf.fit(X, y) coefs.append(clf.coef_) ############################################################################### # Display results plt.figure(figsize=(15,8)) ax = plt.gca() ax.plot(alphas, np.squeeze(coefs)) ax.set_xscale('log') plt.axvline(aestim, linestyle='--', color='k', label='alpha: CV estimate') plt.legend() plt.xlabel('Lambda',fontsize=16) plt.ylabel('Weights',fontsize=16) plt.title('Ridge coefficients as a function of the regularization',fontsize=18) plt.axis('tight') clf = linear_model.Ridge(fit_intercept=False) a = aestim clf.set_params(alpha=a) clf.fit(X, y) np.round(clf.coef_,3) # Ridge if L1_wt = 0 , Lasso if L1_wt = 1 penalty = aestim regm = smf.OLS(y,X).fit_regularized(method='coord_descent', maxiter=1000, alpha=penalty, L1_wt=0) print regm.summary() <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: Poner NFQ en un mapa Step2: Leer un archivo Excel
<ASSISTANT_TASK:> Python Code: import pandas as pd import numpy as np from sklearn import linear_model from matplotlib import pylab as plt plt.style.use('bmh') %matplotlib notebook wine = pd.read_csv('data/winequality-white.csv',delimiter=';') wine.describe() fig = plt.figure(2) ax = [fig.add_subplot(3,4,i) for i in range(1,12)] models = [linear_model.LinearRegression() for i in range(11)] for column, model in zip(wine.columns, models): model.fit(wine['quality'].reshape(-1,1), wine[column].as_matrix().reshape(-1,1)) for qual, group in wine.groupby('quality'): for column, axis in zip(group.columns, ax): axis.plot(qual, group[column].mean(), 'ob') axis.set_title(column + ' (avg)', fontsize=10) qual = np.arange(3,10) for model, axi in zip(models, ax): axi.plot(qual, model.coef_[0][0]*qual + model.intercept_, 'r--', linewidth=4, label='Regression') axi.legend(fontsize=6) fig.tight_layout() import folium madrid = folium.Map(location=[40.429857, -3.685812], tiles="Stamen toner", zoom_start=15) nfqsolutions = folium.Marker([40.429857, -3.685812], popup='NFQ Solutions') madrid.add_children(nfqsolutions) madrid.save('madrid.html') madrid with pd.ExcelFile('./data/winequality-white.xls') as xls: wines = pd.read_excel(xls, 'Sheet1') wines.describe() <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: Wiki Talk Comments Toxicity Prediction Step2: Note that depending on when you run the cell below, you may receive a warning about the default version of TensorFlow in Colab switching to TensorFlow 2.X soon. You can safely ignore that warning as this notebook was designed to be compatible with TensorFlow 1.X and 2.X. Step3: Though TFCO is compatible with eager and graph execution, this notebook assumes that eager execution is enabled by default. To ensure that nothing breaks, eager execution will be enabled in the cell below. Step4: Hyper-parameters Step5: Load and pre-process dataset Step6: The comment column contains the discussion comments and is_toxic column indicates whether or not a comment is annotated as toxic. Step7: Next, we tokenize the textual comments using the Tokenizer provided by Keras. We use the training set comments alone to build a vocabulary of tokens, and use them to convert all the comments into a (padded) sequence of tokens of the same length. Step8: Finally, we identify comments related to certain sensitive topic groups. We consider a subset of the <a href="https Step9: We then create separate group membership matrices for the train, test and validation sets, where the rows correspond to comments, the columns correspond to the four sensitive groups, and each entry is a boolean indicating whether the comment contains a term from the topic group. Step10: As shown below, all four topic groups constitute only a small fraction of the overall dataset, and have varying proportions of toxic comments. Step11: We see that only 1.3% of the dataset contains comments related to sexuality. Among them, 37% of the comments have been annotated as being toxic. Note that this is significantly larger than the overall proportion of comments annotated as toxic. This could be because the few comments that used those identity terms did so in pejorative contexts. As mentioned above, this could cause our model to disporportionately misclassify comments as toxic when they include those terms. Since this is the concern, we'll make sure to look at the False Positive Rate when we evaluate the model's performance. Step12: We use the downloaded GloVe embeddings to create an embedding matrix, where the rows contain the word embeddings for the tokens in the Tokenizer's vocabulary. Step13: We are now ready to specify the Keras layers. We write a function to create a new model, which we will invoke whenever we wish to train a new model. Step14: We also define a method to set random seeds. This is done to ensure reproducible results. Step15: Fairness indicators Step16: Train unconstrained model Step17: Note Step18: Having trained the unconstrained model, we plot various evaluation metrics for the model on the test set. Step19: As explained above, we are concentrating on the false positive rate. In their current version (0.1.2), Fairness Indicators select false negative rate by default. After running the line below, go ahead and deselect false_negative_rate and select false_positive_rate to look at the metric we are interested in. Step20: While the overall false positive rate is less than 2%, the false positive rate on the sexuality-related comments is significantly higher. This is because the sexuality group is very small in size, and has a disproportionately higher fraction of comments annotated as toxic. Hence, training a model without constraints results in the model believing that sexuality-related terms are a strong indicator of toxicity. Step21: We instantiate a new model, and compute predictions for minibatches from the two streams. Step22: We then set up a constrained optimization problem with the error rate as the objective and with constraints on the per-group false positive rate. Step23: We are ready to train the model. We maintain a separate counter for the two minibatch streams. Every time we perform a gradient update, we will have to copy the minibatch contents from the first stream to the tensors features_tensor and labels_tensor, and the minibatch contents from the second stream to the tensors features_tensor_sen, labels_tensor_sen and groups_tensor_sen. Step24: Having trained the constrained model, we plot various evaluation metrics for the model on the test set. Step25: As with last time, remember to select false_positive_rate.
<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. #@title pip installs !pip install git+https://github.com/google-research/tensorflow_constrained_optimization !pip install git+https://github.com/tensorflow/fairness-indicators #@title Import Modules import io import os import shutil import sys import tempfile import time import urllib import zipfile import apache_beam as beam from IPython.display import display from IPython.display import HTML import numpy as np import pandas as pd import tensorflow as tf import tensorflow.keras as keras from tensorflow.keras import layers from tensorflow.keras.preprocessing import sequence from tensorflow.keras.preprocessing import text import tensorflow_constrained_optimization as tfco import tensorflow_model_analysis as tfma import fairness_indicators as fi from tensorflow_model_analysis.addons.fairness.view import widget_view from tensorflow_model_analysis.model_agnostic_eval import model_agnostic_evaluate_graph from tensorflow_model_analysis.model_agnostic_eval import model_agnostic_extractor from tensorflow_model_analysis.model_agnostic_eval import model_agnostic_predict as agnostic_predict #@title Enable Eager Execution and Print Versions if tf.__version__ < "2.0.0": tf.enable_eager_execution() print("Eager execution enabled.") else: print("Eager execution enabled by default.") print("TensorFlow " + tf.__version__) print("TFMA " + tfma.__version__) print("FI " + fi.version.__version__) hparams = { "batch_size": 128, "cnn_filter_sizes": [128, 128, 128], "cnn_kernel_sizes": [5, 5, 5], "cnn_pooling_sizes": [5, 5, 40], "constraint_learning_rate": 0.01, "embedding_dim": 100, "embedding_trainable": False, "learning_rate": 0.005, "max_num_words": 10000, "max_sequence_length": 250 } toxicity_data_url = ("https://github.com/conversationai/unintended-ml-bias-analysis/" "raw/e02b9f12b63a39235e57ba6d3d62d8139ca5572c/data/") data_train = pd.read_csv(toxicity_data_url + "wiki_train.csv") data_test = pd.read_csv(toxicity_data_url + "wiki_test.csv") data_vali = pd.read_csv(toxicity_data_url + "wiki_dev.csv") data_train.head() labels_train = data_train["is_toxic"].values.reshape(-1, 1) * 1.0 labels_test = data_test["is_toxic"].values.reshape(-1, 1) * 1.0 labels_vali = data_vali["is_toxic"].values.reshape(-1, 1) * 1.0 tokenizer = text.Tokenizer(num_words=hparams["max_num_words"]) tokenizer.fit_on_texts(data_train["comment"]) def prep_text(texts, tokenizer, max_sequence_length): # Turns text into into padded sequences. text_sequences = tokenizer.texts_to_sequences(texts) return sequence.pad_sequences(text_sequences, maxlen=max_sequence_length) text_train = prep_text(data_train["comment"], tokenizer, hparams["max_sequence_length"]) text_test = prep_text(data_test["comment"], tokenizer, hparams["max_sequence_length"]) text_vali = prep_text(data_vali["comment"], tokenizer, hparams["max_sequence_length"]) terms = { 'sexuality': ['gay', 'lesbian', 'bisexual', 'homosexual', 'straight', 'heterosexual'], 'gender identity': ['trans', 'transgender', 'cis', 'nonbinary'], 'religion': ['christian', 'muslim', 'jewish', 'buddhist', 'catholic', 'protestant', 'sikh', 'taoist'], 'race': ['african', 'african american', 'black', 'white', 'european', 'hispanic', 'latino', 'latina', 'latinx', 'mexican', 'canadian', 'american', 'asian', 'indian', 'middle eastern', 'chinese', 'japanese']} group_names = list(terms.keys()) num_groups = len(group_names) def get_groups(text): # Returns a boolean NumPy array of shape (n, k), where n is the number of comments, # and k is the number of groups. Each entry (i, j) indicates if the i-th comment # contains a term from the j-th group. groups = np.zeros((text.shape[0], num_groups)) for ii in range(num_groups): groups[:, ii] = text.str.contains('|'.join(terms[group_names[ii]]), case=False) return groups groups_train = get_groups(data_train["comment"]) groups_test = get_groups(data_test["comment"]) groups_vali = get_groups(data_vali["comment"]) print("Overall label proportion = %.1f%%" % (labels_train.mean() * 100)) group_stats = [] for ii in range(num_groups): group_proportion = groups_train[:, ii].mean() group_pos_proportion = labels_train[groups_train[:, ii] == 1].mean() group_stats.append([group_names[ii], "%.2f%%" % (group_proportion * 100), "%.1f%%" % (group_pos_proportion * 100)]) group_stats = pd.DataFrame(group_stats, columns=["Topic group", "Group proportion", "Label proportion"]) group_stats zip_file_url = "http://nlp.stanford.edu/data/glove.6B.zip" zip_file = urllib.request.urlopen(zip_file_url) archive = zipfile.ZipFile(io.BytesIO(zip_file.read())) embeddings_index = {} glove_file = "glove.6B.100d.txt" with archive.open(glove_file) as f: for line in f: values = line.split() word = values[0].decode("utf-8") coefs = np.asarray(values[1:], dtype="float32") embeddings_index[word] = coefs embedding_matrix = np.zeros((len(tokenizer.word_index) + 1, hparams["embedding_dim"])) num_words_in_embedding = 0 for word, i in tokenizer.word_index.items(): embedding_vector = embeddings_index.get(word) if embedding_vector is not None: num_words_in_embedding += 1 embedding_matrix[i] = embedding_vector def create_model(): model = keras.Sequential() # Embedding layer. embedding_layer = layers.Embedding( embedding_matrix.shape[0], embedding_matrix.shape[1], weights=[embedding_matrix], input_length=hparams["max_sequence_length"], trainable=hparams['embedding_trainable']) model.add(embedding_layer) # Convolution layers. for filter_size, kernel_size, pool_size in zip( hparams['cnn_filter_sizes'], hparams['cnn_kernel_sizes'], hparams['cnn_pooling_sizes']): conv_layer = layers.Conv1D( filter_size, kernel_size, activation='relu', padding='same') model.add(conv_layer) pooled_layer = layers.MaxPooling1D(pool_size, padding='same') model.add(pooled_layer) # Add a flatten layer, a fully-connected layer and an output layer. model.add(layers.Flatten()) model.add(layers.Dense(128, activation='relu')) model.add(layers.Dense(1)) return model def set_seeds(): np.random.seed(121212) tf.compat.v1.set_random_seed(212121) def create_examples(labels, predictions, groups, group_names): # Returns tf.examples with given labels, predictions, and group information. examples = [] sigmoid = lambda x: 1/(1 + np.exp(-x)) for ii in range(labels.shape[0]): example = tf.train.Example() example.features.feature['toxicity'].float_list.value.append( labels[ii][0]) example.features.feature['prediction'].float_list.value.append( sigmoid(predictions[ii][0])) # predictions need to be in [0, 1]. for jj in range(groups.shape[1]): example.features.feature[group_names[jj]].bytes_list.value.append( b'Yes' if groups[ii, jj] else b'No') examples.append(example) return examples def evaluate_results(labels, predictions, groups, group_names): # Evaluates fairness indicators for given labels, predictions and group # membership info. examples = create_examples(labels, predictions, groups, group_names) # Create feature map for labels, predictions and each group. feature_map = { 'prediction': tf.io.FixedLenFeature([], tf.float32), 'toxicity': tf.io.FixedLenFeature([], tf.float32), } for group in group_names: feature_map[group] = tf.io.FixedLenFeature([], tf.string) # Serialize the examples. serialized_examples = [e.SerializeToString() for e in examples] BASE_DIR = tempfile.gettempdir() OUTPUT_DIR = os.path.join(BASE_DIR, 'output') with beam.Pipeline() as pipeline: model_agnostic_config = agnostic_predict.ModelAgnosticConfig( label_keys=['toxicity'], prediction_keys=['prediction'], feature_spec=feature_map) slices = [tfma.slicer.SingleSliceSpec()] for group in group_names: slices.append( tfma.slicer.SingleSliceSpec(columns=[group])) extractors = [ model_agnostic_extractor.ModelAgnosticExtractor( model_agnostic_config=model_agnostic_config), tfma.extractors.slice_key_extractor.SliceKeyExtractor(slices) ] metrics_callbacks = [ tfma.post_export_metrics.fairness_indicators( thresholds=[0.5], target_prediction_keys=['prediction'], labels_key='toxicity'), tfma.post_export_metrics.example_count()] # Create a model agnostic aggregator. eval_shared_model = tfma.types.EvalSharedModel( add_metrics_callbacks=metrics_callbacks, construct_fn=model_agnostic_evaluate_graph.make_construct_fn( add_metrics_callbacks=metrics_callbacks, config=model_agnostic_config)) # Run Model Agnostic Eval. _ = ( pipeline | beam.Create(serialized_examples) | 'ExtractEvaluateAndWriteResults' >> tfma.ExtractEvaluateAndWriteResults( eval_shared_model=eval_shared_model, output_path=OUTPUT_DIR, extractors=extractors, compute_confidence_intervals=True ) ) fairness_ind_result = tfma.load_eval_result(output_path=OUTPUT_DIR) # Also evaluate accuracy of the model. accuracy = np.mean(labels == (predictions > 0.0)) return fairness_ind_result, accuracy def plot_fairness_indicators(eval_result, title): fairness_ind_result, accuracy = eval_result display(HTML("<center><h2>" + title + " (Accuracy = %.2f%%)" % (accuracy * 100) + "</h2></center>")) widget_view.render_fairness_indicator(fairness_ind_result) def plot_multi_fairness_indicators(multi_eval_results): multi_results = {} multi_accuracy = {} for title, (fairness_ind_result, accuracy) in multi_eval_results.items(): multi_results[title] = fairness_ind_result multi_accuracy[title] = accuracy title_str = "<center><h2>" for title in multi_eval_results.keys(): title_str+=title + " (Accuracy = %.2f%%)" % (multi_accuracy[title] * 100) + "; " title_str=title_str[:-2] title_str+="</h2></center>" # fairness_ind_result, accuracy = eval_result display(HTML(title_str)) widget_view.render_fairness_indicator(multi_eval_results=multi_results) # Set random seed for reproducible results. set_seeds() # Optimizer and loss. optimizer = tf.keras.optimizers.Adam(learning_rate=hparams["learning_rate"]) loss = lambda y_true, y_pred: tf.keras.losses.binary_crossentropy( y_true, y_pred, from_logits=True) # Create, compile and fit model. model_unconstrained = create_model() model_unconstrained.compile(optimizer=optimizer, loss=loss) model_unconstrained.fit( x=text_train, y=labels_train, batch_size=hparams["batch_size"], epochs=2) scores_unconstrained_test = model_unconstrained.predict(text_test) eval_result_unconstrained = evaluate_results( labels_test, scores_unconstrained_test, groups_test, group_names) plot_fairness_indicators(eval_result_unconstrained, "Unconstrained") # Set random seed. set_seeds() # Features tensors. batch_shape = (hparams["batch_size"], hparams['max_sequence_length']) features_tensor = tf.Variable(np.zeros(batch_shape, dtype='int32'), name='x') features_tensor_sen = tf.Variable(np.zeros(batch_shape, dtype='int32'), name='x_sen') # Labels tensors. batch_shape = (hparams["batch_size"], 1) labels_tensor = tf.Variable(np.zeros(batch_shape, dtype='float32'), name='labels') labels_tensor_sen = tf.Variable(np.zeros(batch_shape, dtype='float32'), name='labels_sen') # Groups tensors. batch_shape = (hparams["batch_size"], num_groups) groups_tensor_sen = tf.Variable(np.zeros(batch_shape, dtype='float32'), name='groups_sen') # Create model, and separate prediction functions for the two streams. # For the predictions, we use a nullary function returning a Tensor to support eager mode. model_constrained = create_model() def predictions(): return model_constrained(features_tensor) def predictions_sen(): return model_constrained(features_tensor_sen) epsilon = 0.02 # Desired false-positive rate threshold. # Set up separate contexts for the two minibatch streams. context = tfco.rate_context(predictions, lambda:labels_tensor) context_sen = tfco.rate_context(predictions_sen, lambda:labels_tensor_sen) # Compute the objective using the first stream. objective = tfco.error_rate(context) # Compute the constraint using the second stream. # Subset the examples belonging to the "sexuality" group from the second stream # and add a constraint on the group's false positive rate. context_sen_subset = context_sen.subset(lambda: groups_tensor_sen[:, 0] > 0) constraint = [tfco.false_positive_rate(context_sen_subset) <= epsilon] # Create a rate minimization problem. problem = tfco.RateMinimizationProblem(objective, constraint) # Set up a constrained optimizer. optimizer = tfco.ProxyLagrangianOptimizerV2( optimizer=tf.keras.optimizers.Adam(learning_rate=hparams["learning_rate"]), num_constraints=problem.num_constraints) # List of variables to optimize include the model weights, # and the trainable variables from the rate minimization problem and # the constrained optimizer. var_list = (model_constrained.trainable_weights + list(problem.trainable_variables) + optimizer.trainable_variables()) # Indices of sensitive group members. protected_group_indices = np.nonzero(groups_train.sum(axis=1))[0] num_examples = text_train.shape[0] num_examples_sen = protected_group_indices.shape[0] batch_size = hparams["batch_size"] # Number of steps needed for one epoch over the training sample. num_steps = int(num_examples / batch_size) start_time = time.time() # Loop over minibatches. for batch_index in range(num_steps): # Indices for current minibatch in the first stream. batch_indices = np.arange( batch_index * batch_size, (batch_index + 1) * batch_size) batch_indices = [ind % num_examples for ind in batch_indices] # Indices for current minibatch in the second stream. batch_indices_sen = np.arange( batch_index * batch_size, (batch_index + 1) * batch_size) batch_indices_sen = [protected_group_indices[ind % num_examples_sen] for ind in batch_indices_sen] # Assign features, labels, groups from the minibatches to the respective tensors. features_tensor.assign(text_train[batch_indices, :]) labels_tensor.assign(labels_train[batch_indices]) features_tensor_sen.assign(text_train[batch_indices_sen, :]) labels_tensor_sen.assign(labels_train[batch_indices_sen]) groups_tensor_sen.assign(groups_train[batch_indices_sen, :]) # Gradient update. optimizer.minimize(problem, var_list=var_list) # Record and print batch training stats every 10 steps. if (batch_index + 1) % 10 == 0 or batch_index in (0, num_steps - 1): hinge_loss = problem.objective() max_violation = max(problem.constraints()) elapsed_time = time.time() - start_time sys.stdout.write( "\rStep %d / %d: Elapsed time = %ds, Loss = %.3f, Violation = %.3f" % (batch_index + 1, num_steps, elapsed_time, hinge_loss, max_violation)) scores_constrained_test = model_constrained.predict(text_test) eval_result_constrained = evaluate_results( labels_test, scores_constrained_test, groups_test, group_names) plot_fairness_indicators(eval_result_constrained, "Constrained") multi_results = { 'constrained':eval_result_constrained, 'unconstrained':eval_result_unconstrained, } plot_multi_fairness_indicators(multi_eval_results=multi_results) <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: Transformation classes Step2: PSDEstimator Step3: Source power comodulation (SPoC) Step4: Decoding over time Step5: You can retrieve the spatial filters and spatial patterns if you explicitly Step6: Temporal generalization Step7: Plot the full (generalization) matrix
<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib.pyplot as plt from sklearn.pipeline import make_pipeline from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression import mne from mne.datasets import sample from mne.decoding import (SlidingEstimator, GeneralizingEstimator, Scaler, cross_val_multiscore, LinearModel, get_coef, Vectorizer, CSP) data_path = sample.data_path() raw_fname = data_path + '/MEG/sample/sample_audvis_raw.fif' tmin, tmax = -0.200, 0.500 event_id = {'Auditory/Left': 1, 'Visual/Left': 3} # just use two raw = mne.io.read_raw_fif(raw_fname, preload=True) # The subsequent decoding analyses only capture evoked responses, so we can # low-pass the MEG data. Usually a value more like 40 Hz would be used, # but here low-pass at 20 so we can more heavily decimate, and allow # the examlpe to run faster. The 2 Hz high-pass helps improve CSP. raw.filter(2, 20) events = mne.find_events(raw, 'STI 014') # Set up pick list: EEG + MEG - bad channels (modify to your needs) raw.info['bads'] += ['MEG 2443', 'EEG 053'] # bads + 2 more # Read epochs epochs = mne.Epochs(raw, events, event_id, tmin, tmax, proj=True, picks=('grad', 'eog'), baseline=(None, 0.), preload=True, reject=dict(grad=4000e-13, eog=150e-6), decim=10) epochs.pick_types(meg=True, exclude='bads') # remove stim and EOG X = epochs.get_data() # MEG signals: n_epochs, n_meg_channels, n_times y = epochs.events[:, 2] # target: Audio left or right # Uses all MEG sensors and time points as separate classification # features, so the resulting filters used are spatio-temporal clf = make_pipeline(Scaler(epochs.info), Vectorizer(), LogisticRegression(solver='lbfgs')) scores = cross_val_multiscore(clf, X, y, cv=5, n_jobs=1) # Mean scores across cross-validation splits score = np.mean(scores, axis=0) print('Spatio-temporal: %0.1f%%' % (100 * score,)) csp = CSP(n_components=3, norm_trace=False) clf = make_pipeline(csp, LogisticRegression(solver='lbfgs')) scores = cross_val_multiscore(clf, X, y, cv=5, n_jobs=1) print('CSP: %0.1f%%' % (100 * scores.mean(),)) # Fit CSP on full data and plot csp.fit(X, y) csp.plot_patterns(epochs.info) csp.plot_filters(epochs.info, scalings=1e-9) # We will train the classifier on all left visual vs auditory trials on MEG clf = make_pipeline(StandardScaler(), LogisticRegression(solver='lbfgs')) time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc', verbose=True) scores = cross_val_multiscore(time_decod, X, y, cv=5, n_jobs=1) # Mean scores across cross-validation splits scores = np.mean(scores, axis=0) # Plot fig, ax = plt.subplots() ax.plot(epochs.times, scores, label='score') ax.axhline(.5, color='k', linestyle='--', label='chance') ax.set_xlabel('Times') ax.set_ylabel('AUC') # Area Under the Curve ax.legend() ax.axvline(.0, color='k', linestyle='-') ax.set_title('Sensor space decoding') clf = make_pipeline(StandardScaler(), LinearModel(LogisticRegression(solver='lbfgs'))) time_decod = SlidingEstimator(clf, n_jobs=1, scoring='roc_auc', verbose=True) time_decod.fit(X, y) coef = get_coef(time_decod, 'patterns_', inverse_transform=True) evoked = mne.EvokedArray(coef, epochs.info, tmin=epochs.times[0]) joint_kwargs = dict(ts_args=dict(time_unit='s'), topomap_args=dict(time_unit='s')) evoked.plot_joint(times=np.arange(0., .500, .100), title='patterns', **joint_kwargs) # define the Temporal generalization object time_gen = GeneralizingEstimator(clf, n_jobs=1, scoring='roc_auc', verbose=True) scores = cross_val_multiscore(time_gen, X, y, cv=5, n_jobs=1) # Mean scores across cross-validation splits scores = np.mean(scores, axis=0) # Plot the diagonal (it's exactly the same as the time-by-time decoding above) fig, ax = plt.subplots() ax.plot(epochs.times, np.diag(scores), label='score') ax.axhline(.5, color='k', linestyle='--', label='chance') ax.set_xlabel('Times') ax.set_ylabel('AUC') ax.legend() ax.axvline(.0, color='k', linestyle='-') ax.set_title('Decoding MEG sensors over time') fig, ax = plt.subplots(1, 1) im = ax.imshow(scores, interpolation='lanczos', origin='lower', cmap='RdBu_r', extent=epochs.times[[0, -1, 0, -1]], vmin=0., vmax=1.) ax.set_xlabel('Testing Time (s)') ax.set_ylabel('Training Time (s)') ax.set_title('Temporal generalization') ax.axvline(0, color='k') ax.axhline(0, color='k') plt.colorbar(im, ax=ax) <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: PCAs Step2: Standardizing Step3: 1 - Eigendecomposition - Computing Eigenvectors and Eigenvalues Step4: eigendecomposition on the covariance matrix Step5: Correlation Matrix Step6: Eigendecomposition of the raw data based on the correlation matrix Step7: 2 - Selecting Principal Components Step8: Projection Matrix Step9: 3 - Projection Onto the New Feature Space Step10: import mca Step11: TODO
<ASSISTANT_TASK:> Python Code: %run "../Functions/1. Google form analysis.ipynb" binarized = getAllBinarized() score = np.dot(binarized,np.ones(len(binarized.columns))) dimensions = binarized.shape[1] dimensions binarized['class'] = 'default' # split data table into data X and class labels y X = binarized.iloc[:,0:dimensions].values y = binarized.iloc[:,dimensions].values from sklearn.preprocessing import StandardScaler X_std = StandardScaler().fit_transform(X) mean_vec = np.mean(X_std, axis=0) cov_mat = (X_std - mean_vec).T.dot((X_std - mean_vec)) / (X_std.shape[0]-1) print('Covariance matrix \n%s' %cov_mat) print('NumPy covariance matrix: \n%s' %np.cov(X_std.T)) cov_mat = np.cov(X_std.T) eig_vals, eig_vecs = np.linalg.eig(cov_mat) #print('Eigenvectors \n%s' %eig_vecs) print('\nEigenvalues \n%s' %eig_vals) cor_mat1 = np.corrcoef(X_std.T) eig_vals, eig_vecs = np.linalg.eig(cor_mat1) #print('Eigenvectors \n%s' %eig_vecs) print('\nEigenvalues \n%s' %eig_vals) u,s,v = np.linalg.svd(X_std.T) s for ev in eig_vecs: np.testing.assert_array_almost_equal(1.0, np.linalg.norm(ev)) print('Everything ok!') # Make a list of (eigenvalue, eigenvector) tuples eig_pairs = [(np.abs(eig_vals[i]), eig_vecs[:,i]) for i in range(len(eig_vals))] # Sort the (eigenvalue, eigenvector) tuples from high to low eig_pairs.sort() eig_pairs.reverse() # Visually confirm that the list is correctly sorted by decreasing eigenvalues print('Eigenvalues in descending order:') for i in eig_pairs: print(i[0]) tot = sum(eig_vals) var_exp = [(i / tot)*100 for i in sorted(eig_vals, reverse=True)] cum_var_exp = np.cumsum(var_exp) with plt.style.context('seaborn-whitegrid'): plt.figure(figsize=(6, 4)) plt.bar(range(dimensions), var_exp, alpha=0.5, align='center', label='individual explained variance') plt.step(range(dimensions), cum_var_exp, where='mid', label='cumulative explained variance') plt.ylabel('Explained variance ratio') plt.xlabel('Principal components') plt.legend(loc='best') plt.tight_layout() var_exp[:5] cum_var_exp[:5] matrix_w = np.hstack((eig_pairs[0][1].reshape(dimensions,1), eig_pairs[1][1].reshape(dimensions,1))) print('Matrix W:\n', matrix_w) gform.columns colors = ('blue','red','green','magenta','cyan','purple','yellow','black','white') len(colors) Y = X_std.dot(matrix_w) with plt.style.context('seaborn-whitegrid'): plt.figure(figsize=(6, 4)) ax = plt.subplot(111) plt.scatter(Y[:, 0], Y[:, 1]) plt.xlabel('Principal Component 1') plt.ylabel('Principal Component 2') plt.title("base PCA") plt.show() # classNames is a tuple def classifyAndPlot(classNames, classes, title = '', rainbow = False): defaultClassName = '' sampleSize = 0 for classIndex in range(0, len(classes)): sampleSize += len(classes[classIndex]) if(sampleSize < gform.shape[0]): if(len(classNames) == len(classes) + 1): defaultClassName = classNames[-1] else: defaultClassName = 'other' classNames.append(defaultClassName) for labelIndex in binarized.index: i = int(labelIndex[len('corrections'):]) isUserSet = False for classIndex in range(0, len(classes)): if(gform.iloc[i][localplayerguidkey] in classes[classIndex].values): binarized.loc[labelIndex,'class'] = classNames[classIndex] isUserSet = True if not isUserSet: if not (defaultClassName in classNames): print("unexpected error: check the exhaustiveness of the provided classes") binarized.loc[labelIndex,'class'] = defaultClassName y = binarized.iloc[:,dimensions].values with plt.style.context('seaborn-whitegrid'): plt.figure(figsize=(6, 4)) ax = plt.subplot(111) colors = ('blue','red','green','magenta','cyan','purple','yellow','black','white') if (rainbow or len(classNames) > len(colors)): colors = plt.cm.rainbow(np.linspace(1, 0, len(classNames))) colors = colors[:len(classNames)] for lab, col in zip(classNames,colors): plt.scatter(Y[y==lab, 0], Y[y==lab, 1], label=lab, c=col) plt.xlabel('Principal Component 1') plt.ylabel('Principal Component 2') # source https://stackoverflow.com/questions/4700614/how-to-put-the-legend-out-of-the-plot # Put a legend to the right of the current axis ax.legend(loc='center left', bbox_to_anchor=(1, 0.5)) if(len(title) > 0): plt.title(title) plt.show() answered = binarized[binarized['Guess: the bacterium would glow yellow...'] == 1] indices = answered.index.map(lambda label: int(label[len('corrections'):])) surveys = gform.iloc[indices][localplayerguidkey] #classifyAndPlot(['guessed', 'did not'], [surveys]) title = 'test title' rainbow = True alreadyDefaultClassName = True classNames = ['guessed', 'did not'] classes = [surveys] # classNames is a tuple #def classifyAndPlot(classNames, classes, title = '', rainbow = False): defaultClassName = '' sampleSize = 0 for classIndex in range(0, len(classes)): sampleSize += len(classes[classIndex]) if(sampleSize < gform.shape[0]): if(len(classNames) == len(classes) + 1): defaultClassName = classNames[-1] else: defaultClassName = 'other' classNames.append(defaultClassName) for labelIndex in binarized.index: i = int(labelIndex[len('corrections'):]) isUserSet = False for classIndex in range(0, len(classes)): if(gform.iloc[i][localplayerguidkey] in classes[classIndex].values): binarized.loc[labelIndex,'class'] = classNames[classIndex] isUserSet = True if not isUserSet: if not (defaultClassName in classNames): print("unexpected error: check the exhaustiveness of the provided classes") binarized.loc[labelIndex,'class'] = defaultClassName y = binarized.iloc[:,dimensions].values with plt.style.context('seaborn-whitegrid'): plt.figure(figsize=(6, 4)) ax = plt.subplot(111) colors = ('blue','red','green','magenta','cyan','purple','yellow','black','white') if (rainbow or len(classNames) > len(colors)): colors = plt.cm.rainbow(np.linspace(1, 0, len(classNames))) colors = colors[:len(classNames)] for lab, col in zip(classNames,colors): plt.scatter(Y[y==lab, 0], Y[y==lab, 1], label=lab, c=col) plt.xlabel('Principal Component 1') plt.ylabel('Principal Component 2') # source https://stackoverflow.com/questions/4700614/how-to-put-the-legend-out-of-the-plot # Put a legend to the right of the current axis ax.legend(loc='center left', bbox_to_anchor=(1, 0.5)) if(len(title) > 0): plt.title(title) plt.show() answered = binarized[binarized['Guess: the bacterium would glow yellow...'] == 1] indices = answered.index.map(lambda label: int(label[len('corrections'):])) surveys = gform.iloc[indices][localplayerguidkey] classifyAndPlot(['guessed', 'did not'], [surveys]) classifyAndPlot(['biologist', 'other'], [getSurveysOfBiologists(gform, True)[localplayerguidkey]], title = 'biologists and non-biologists') classifyAndPlot(['gamer', 'other'], [getSurveysOfGamers(gform, True)[localplayerguidkey]], title = 'gamers and non-gamers') classNames = [] classes = [] for answer in gform['Are you interested in biology?'].value_counts().index: classNames.append(answer) classes.append(gform[gform['Are you interested in biology?'] == answer][localplayerguidkey]) classNames.append('other') classifyAndPlot(classNames, classes, rainbow = True, title = 'interest in biology') #np.plot(score) classNames = [] classes = [] for thisScore in np.unique(score): classNames.append(thisScore) index = np.where(score == thisScore)[0] classes.append( gform.loc[index][localplayerguidkey]) classifyAndPlot(classNames, classes, rainbow = True, title = 'score') classNames = [] classes = [] question = 'How old are you?' for answer in np.sort(gform[question].unique()): classNames.append(answer) classes.append(gform[gform[question] == answer][localplayerguidkey]) classifyAndPlot(classNames, classes, rainbow = True, title = 'age') gform.columns[:5] # questions to avoid: #0 Timestamp #3 Age #40 Remarks #41 ID from itertools import chain questionRange = chain(range(1,3), range(4,40), range(42,44)) for questionIndex in questionRange: question = gform.columns[questionIndex] classNames = [] classes = [] for answer in gform[question].value_counts().index: classNames.append(answer) classes.append(gform[gform[question] == answer][localplayerguidkey]) classifyAndPlot(classNames, classes, title = question, rainbow = False) eig_vals eig_vecs[0] maxComponentIndex = np.argmax(abs(eig_vecs[0])) binarized.columns[maxComponentIndex] sum(eig_vecs[0]*eig_vecs[0]) eig_vecs[0] sortedIndices = [] descendingWeights = np.sort(abs(eig_vecs[0]))[::-1] for sortedComponent in descendingWeights: sortedIndices.append(np.where(abs(eig_vecs[0]) == sortedComponent)[0][0]) sortedQuestions0 = pd.DataFrame(index = descendingWeights, data = binarized.columns[sortedIndices]) sortedQuestions0 def accessFirst(a): return a[0] sortedQuestionsLastIndex = 10 array1 = np.arange(sortedQuestionsLastIndex+1.)/(sortedQuestionsLastIndex + 1.) sortedQuestionsLastIndex+1,\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Accent(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Dark2(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Paired(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Pastel1(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Pastel2(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Set1(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Set2(array1)))),\ len(np.unique(np.apply_along_axis(accessFirst, 1, cm.Set3(array1)))),\ from matplotlib import cm def displayQuestionsContributions(\ sortedQuestions,\ title = "Contributions of questions to component",\ sortedQuestionsLastIndex = 10\ ): colors=cm.Set3(np.arange(sortedQuestionsLastIndex+1.)/(sortedQuestionsLastIndex + 1.)) sortedQuestionsLabelsArray = np.append(sortedQuestions.values.flatten()[:sortedQuestionsLastIndex], 'others') sortedQuestionsValuesArray = np.append(sortedQuestions.index[:sortedQuestionsLastIndex], sum(sortedQuestions.index[sortedQuestionsLastIndex:])) fig1, ax1 = plt.subplots() ax1.pie(sortedQuestionsValuesArray, labels=sortedQuestionsLabelsArray, autopct='%1.1f%%', startangle=100, colors = colors) ax1.axis('equal') # cf https://matplotlib.org/users/customizing.html plt.rcParams['patch.linewidth'] = 0 plt.rcParams['text.color'] = '#2b2b2b' plt.title(title) plt.tight_layout() plt.show() displayQuestionsContributions(sortedQuestions0, sortedQuestionsLastIndex = 10, title = 'Contributions of questions to component 1') sum(sortedQuestions0.index**2) sortedIndices = [] descendingWeights = np.sort(abs(eig_vecs[1]))[::-1] for sortedComponent in descendingWeights: sortedIndices.append(np.where(abs(eig_vecs[1]) == sortedComponent)[0][0]) sortedQuestions1 = pd.DataFrame(index = descendingWeights, data = binarized.columns[sortedIndices]) sortedQuestions1 displayQuestionsContributions(sortedQuestions1, sortedQuestionsLastIndex = 10, title = 'Contributions of questions to component 2') sum(sortedQuestions1.index**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: Better ML Engineering with ML Metadata Step2: Install and import TFX Step3: Import packages Step4: Check the TFX, and MLMD versions. Step5: Download the dataset Step6: Create an InteractiveContext Step7: Construct the TFX Pipeline Step8: Instantiate and run the StatisticsGen Component Step9: Instantiate and run the SchemaGen Component Step10: Instantiate and run the Trainer Component Step11: Run the Trainer component. Step12: Evaluate and push the model Step13: Running the TFX pipeline populates the MLMD Database. In the next section, you use the MLMD API to query this database for metadata information. Step14: Create some helper functions to view the data from the MD store. Step15: First, query the MD store for a list of all its stored ArtifactTypes. Step16: Next, query all PushedModel artifacts. Step17: Query the MD store for the latest pushed model. This tutorial has only one pushed model. Step18: One of the first steps in debugging a pushed model is to look at which trained model is pushed and to see which training data is used to train that model. Step19: Query the parent artifacts for the pushed model. Step20: Query the properties for the model. Step21: Query the upstream artifacts for the model. Step22: Get the training data the model trained with. Step23: Now that you have the training data that the model trained with, query the database again to find the training step (execution). Query the MD store for a list of the registered execution types. Step24: The training step is the ExecutionType named tfx.components.trainer.component.Trainer. Traverse the MD store to get the trainer run that corresponds to the pushed model.
<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. try: import colab !pip install --upgrade pip except: pass !pip install -q -U tfx import os import tempfile import urllib import pandas as pd import tensorflow_model_analysis as tfma from tfx.orchestration.experimental.interactive.interactive_context import InteractiveContext from tfx import v1 as tfx print('TFX version: {}'.format(tfx.__version__)) import ml_metadata as mlmd print('MLMD version: {}'.format(mlmd.__version__)) DATA_PATH = 'https://raw.githubusercontent.com/tensorflow/tfx/master/tfx/examples/penguin/data/labelled/penguins_processed.csv' _data_root = tempfile.mkdtemp(prefix='tfx-data') _data_filepath = os.path.join(_data_root, "penguins_processed.csv") urllib.request.urlretrieve(DATA_PATH, _data_filepath) interactive_context = InteractiveContext() example_gen = tfx.components.CsvExampleGen(input_base=_data_root) interactive_context.run(example_gen) statistics_gen = tfx.components.StatisticsGen( examples=example_gen.outputs['examples']) interactive_context.run(statistics_gen) infer_schema = tfx.components.SchemaGen( statistics=statistics_gen.outputs['statistics'], infer_feature_shape=True) interactive_context.run(infer_schema) # Define the module file for the Trainer component trainer_module_file = 'penguin_trainer.py' %%writefile {trainer_module_file} # Define the training algorithm for the Trainer module file import os from typing import List, Text import tensorflow as tf from tensorflow import keras from tfx import v1 as tfx from tfx_bsl.public import tfxio from tensorflow_metadata.proto.v0 import schema_pb2 # Features used for classification - culmen length and depth, flipper length, # body mass, and species. _LABEL_KEY = 'species' _FEATURE_KEYS = [ 'culmen_length_mm', 'culmen_depth_mm', 'flipper_length_mm', 'body_mass_g' ] def _input_fn(file_pattern: List[Text], data_accessor: tfx.components.DataAccessor, schema: schema_pb2.Schema, batch_size: int) -> tf.data.Dataset: return data_accessor.tf_dataset_factory( file_pattern, tfxio.TensorFlowDatasetOptions( batch_size=batch_size, label_key=_LABEL_KEY), schema).repeat() def _build_keras_model(): inputs = [keras.layers.Input(shape=(1,), name=f) for f in _FEATURE_KEYS] d = keras.layers.concatenate(inputs) d = keras.layers.Dense(8, activation='relu')(d) d = keras.layers.Dense(8, activation='relu')(d) outputs = keras.layers.Dense(3)(d) model = keras.Model(inputs=inputs, outputs=outputs) model.compile( optimizer=keras.optimizers.Adam(1e-2), loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=[keras.metrics.SparseCategoricalAccuracy()]) return model def run_fn(fn_args: tfx.components.FnArgs): schema = schema_pb2.Schema() tfx.utils.parse_pbtxt_file(fn_args.schema_path, schema) train_dataset = _input_fn( fn_args.train_files, fn_args.data_accessor, schema, batch_size=10) eval_dataset = _input_fn( fn_args.eval_files, fn_args.data_accessor, schema, batch_size=10) model = _build_keras_model() model.fit( train_dataset, epochs=int(fn_args.train_steps / 20), steps_per_epoch=20, validation_data=eval_dataset, validation_steps=fn_args.eval_steps) model.save(fn_args.serving_model_dir, save_format='tf') trainer = tfx.components.Trainer( module_file=os.path.abspath(trainer_module_file), examples=example_gen.outputs['examples'], schema=infer_schema.outputs['schema'], train_args=tfx.proto.TrainArgs(num_steps=100), eval_args=tfx.proto.EvalArgs(num_steps=50)) interactive_context.run(trainer) _serving_model_dir = os.path.join(tempfile.mkdtemp(), 'serving_model/penguins_classification') eval_config = tfma.EvalConfig( model_specs=[ tfma.ModelSpec(label_key='species', signature_name='serving_default') ], metrics_specs=[ tfma.MetricsSpec(metrics=[ tfma.MetricConfig( class_name='SparseCategoricalAccuracy', threshold=tfma.MetricThreshold( value_threshold=tfma.GenericValueThreshold( lower_bound={'value': 0.6}))) ]) ], slicing_specs=[tfma.SlicingSpec()]) evaluator = tfx.components.Evaluator( examples=example_gen.outputs['examples'], model=trainer.outputs['model'], schema=infer_schema.outputs['schema'], eval_config=eval_config) interactive_context.run(evaluator) pusher = tfx.components.Pusher( model=trainer.outputs['model'], model_blessing=evaluator.outputs['blessing'], push_destination=tfx.proto.PushDestination( filesystem=tfx.proto.PushDestination.Filesystem( base_directory=_serving_model_dir))) interactive_context.run(pusher) connection_config = interactive_context.metadata_connection_config store = mlmd.MetadataStore(connection_config) # All TFX artifacts are stored in the base directory base_dir = connection_config.sqlite.filename_uri.split('metadata.sqlite')[0] def display_types(types): # Helper function to render dataframes for the artifact and execution types table = {'id': [], 'name': []} for a_type in types: table['id'].append(a_type.id) table['name'].append(a_type.name) return pd.DataFrame(data=table) def display_artifacts(store, artifacts): # Helper function to render dataframes for the input artifacts table = {'artifact id': [], 'type': [], 'uri': []} for a in artifacts: table['artifact id'].append(a.id) artifact_type = store.get_artifact_types_by_id([a.type_id])[0] table['type'].append(artifact_type.name) table['uri'].append(a.uri.replace(base_dir, './')) return pd.DataFrame(data=table) def display_properties(store, node): # Helper function to render dataframes for artifact and execution properties table = {'property': [], 'value': []} for k, v in node.properties.items(): table['property'].append(k) table['value'].append( v.string_value if v.HasField('string_value') else v.int_value) for k, v in node.custom_properties.items(): table['property'].append(k) table['value'].append( v.string_value if v.HasField('string_value') else v.int_value) return pd.DataFrame(data=table) display_types(store.get_artifact_types()) pushed_models = store.get_artifacts_by_type("PushedModel") display_artifacts(store, pushed_models) pushed_model = pushed_models[-1] display_properties(store, pushed_model) def get_one_hop_parent_artifacts(store, artifacts): # Get a list of artifacts within a 1-hop of the artifacts of interest artifact_ids = [artifact.id for artifact in artifacts] executions_ids = set( event.execution_id for event in store.get_events_by_artifact_ids(artifact_ids) if event.type == mlmd.proto.Event.OUTPUT) artifacts_ids = set( event.artifact_id for event in store.get_events_by_execution_ids(executions_ids) if event.type == mlmd.proto.Event.INPUT) return [artifact for artifact in store.get_artifacts_by_id(artifacts_ids)] parent_artifacts = get_one_hop_parent_artifacts(store, [pushed_model]) display_artifacts(store, parent_artifacts) exported_model = parent_artifacts[0] display_properties(store, exported_model) model_parents = get_one_hop_parent_artifacts(store, [exported_model]) display_artifacts(store, model_parents) used_data = model_parents[0] display_properties(store, used_data) display_types(store.get_execution_types()) def find_producer_execution(store, artifact): executions_ids = set( event.execution_id for event in store.get_events_by_artifact_ids([artifact.id]) if event.type == mlmd.proto.Event.OUTPUT) return store.get_executions_by_id(executions_ids)[0] trainer = find_producer_execution(store, exported_model) display_properties(store, trainer) <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: Donc attention aux nom donnรฉ aux paramรชtres formels, il peut รชtre aussi utile de se premunir contre des fautes, en utilisant la commande try qui permet la gestion des exceptions Step2: Chaรฎnes et Listes Step3: En cherchant une solution plus dรฉtaillรฉ, on peut inclure un test conditionnel Step4: On peut รฉgalement utiliser une dรฉclaration comme try on appelle cela un catch Step5: Les chaines de caractรจres, sont d'abord utiles pour retravailler la prรฉsentation d'un tableau Step6: dans cet exemple on va faire l'appel Step7: Erreurs classiques sur les listes Step8: Visualisation d'un phรฉnomรจne physique
<ASSISTANT_TASK:> Python Code: def tronquer_1( l ): return l[1:] l=[1,2,3] tronquer_1(l) def tronquer_liste( ma_liste ): try: return ma_liste[1:] except TypeError: print("Cette fonction n'accepte que des listes ou des chaรฎnes de caractรจres") l=[1,2,3] tronquer_liste(l) def extraire_avant_premier(s): return s[ : str.find(s,",") ] print( extraire_avant_premier("chat") ) ## cha def extraire_avant_premier(s): if str.find(s,",") == -1: return s return s[ : str.find(s,",") ] print( extraire_avant_premier("chat") ) ## Affiche chat def extraire_avant_premier(s): try: 1/(1+str.find(s,",")) return s[ : str.find(s,",") ] except ZeroDivisionError: return s print( extraire_avant_premier("chat, chien") ) ## Affiche chat def completer_2(s,n): return(s.ljust(n,' ')) Mon_Nom1 = 'DE SAINT-EXUPERY' Mon_Nom2 = 'CAMUS' #? Mon_Nom.ljust print(Mon_Nom1.ljust(25,' '),'present !') print(Mon_Nom2.ljust(25,' '),"c'est moi") #Les Delistes def tronquer_2(n): if n== []: return [] else: del n[0] return n liste_1 = [1,2,3] liste_2 = tronquer_2( liste_1 ) print( liste_1 ) ## affiche [2,3] print( liste_2 ) ## affiche [2,3] #Les Popistes def tronquer_2(a): if a == [] : return [] a.pop(0) return a liste_1 = [1,2,3] liste_2 = tronquer_2( liste_1 ) print( liste_1 ) ## affiche [2,3] print( liste_2 ) ## affiche [2,3] # -*- coding: utf-8 -*- import numpy as np # Constantes my0=4*np.pi*1e-7; # permeabilite du vide I0=-1; # intensitรฉ du courant # le courant circule de gauche a droite # Dimensions d=25*1e-3 # Diametre de la spire (m) r=d/2 # rayon de la spire (m) segments=100 # discretisation de la spire alpha = 2*np.pi/(segments-1) # discretisation de l'angle # initialisation de la spire x=[i*0 for i in range(segments)] y=[r*np.sin(i*alpha) for i in range(segments)] z=[-r*np.cos(i*alpha) for i in range(segments)] # Definition du sens du positif du courant : gauche -> droite # pour le calcul les longeurs sont exprimees en m x_spire=np.array([x]); y_spire=np.array([y]); z_spire=np.array([z]); %matplotlib inline #%%%%%%%%%%%%%%% Affichage de la spire en 3D %%%%%%%%%%%%%%%%# from mpl_toolkits.mplot3d import Axes3D import matplotlib.pyplot as plt import matplotlib.patches as patches fig = plt.figure() ax = fig.gca(projection='3d') #titre du graphe plt.title ('Simulation numerique d une spire', color='b') # spire plt.plot(y_spire [0], z_spire[0], 'g.', linewidth=1, label='spire') plt.plot(y_spire, z_spire, 'g.', linewidth=1) # vecteur champ magnetique Bx plt.plot(([0.003,0.003]),([0,0]),([-.05,0.05]), 'b-',label='axe de la spire',linewidth=1) plt.plot(([0.003,0.003]),([0,0]),([-.01,0.02]), 'm-',label='champ magnetique',linewidth=1) plt.plot([0.003],[0],[0.025], 'm', marker='^', linewidth=2) ax.text(0.004,0,0,'Bx', color='m') #courant plt.plot([0],[0.0125],[0], 'r', marker='<') ax.text(0,0.0125,0.01,'I', color='r') #legende du graphe plt.legend (loc='lower left', prop={'size':8}) plt.show() #%%%%%%%%%% Calcul du champ magnetique d apres Biot et Savart ndp=50 # Nombre de points # limites x xmin,xmax=-0.05,0.05 # limites y ymin, ymax=-0.05, 0.05 # limites z zmin, zmax=-0.05,0.05 dx=(xmax-xmin)/(ndp-1) #increment x dy=(ymax-ymin)/(ndp-1) # increment y dz=(zmax-zmin)/(ndp-1) # increment z #%%%%%%%%%%%%%%% Calcul magnetostatique %%%%%%%%%%%%%%%%%%%%%%%%%%%# bxf=np.zeros(ndp) # initialisation de la composante Bx du champ byf=np.zeros(ndp) # initialisation de la composante By du champ bzf=np.zeros(ndp) # initialisation de la composante Bz du champ I0f1=my0*I0/(4*np.pi) # Magnetostatique (on multiplie le courant #I0 par mu0/(4.pi)) # Integration du champ induit en un point de l'axe bleu # par le courant circulant sur chaque segment de la spire verte bfx,bfy,bfz=0,0,0 nseg=np.size(z_spire)-1 for i in range(ndp): #Initialisation des positions xM=(xmin+i*dx) yM,zM=0,0 #Initialisation des champs locaux bfx,bfy,bfz=0,0,0 R=np.array([xM,yM,zM]) # vecteur position sur # le point qui doit etre calcule # en integrant la contribution # de tous les courants le long # de la boucle verte for wseg in range(nseg): xs=x_spire[0][wseg] ys=y_spire[0][wseg] zs=z_spire[0][wseg] Rs=np.array([xs, ys, zs]) drsx=(x_spire[0][wseg+1]-x_spire[0][wseg]) drsy=(y_spire[0][wseg+1]-y_spire[0][wseg]) drsz=(z_spire[0][wseg+1]-z_spire[0][wseg]) drs=np.array([drsx, drsy, drsz]) #direction du courant Delta_R= Rs - R #vecteur entre l'รฉlement de spire et #le point oรน est calcul le champ Delta_Rdist=np.sqrt(Delta_R[0]**2+Delta_R[1]**2+Delta_R[2]**2) #Delta_Rdis2=Delta_Rdist**2 Delta_Rdis3=Delta_Rdist**3 b2=1.0/Delta_Rdis3 b12=I0f1*b2*(-1) # Produit vectoriel Delta_Rxdrs_x=Delta_R[1]*drsz-Delta_R[2]*drsy Delta_Rxdrs_y=Delta_R[2]*drsx-Delta_R[0]*drsz Delta_Rxdrs_z=Delta_R[0]*drsy-Delta_R[1]*drsx #Intรฉgration bfx=bfx+b12*Delta_Rxdrs_x bfy=bfy+b12*Delta_Rxdrs_y bfz=bfz+b12*Delta_Rxdrs_z # Il faut utiliser un champ defini comme 3 listes : # une liste pour chaque abscisse bxf[i]+=bfx byf[i]+=bfy bzf[i]+=bfz #%%%%%%%%%%% Modele Theorique %%%%%%%%%%%%%%%%%%# #r=d/2; # rayon de la spire en mm #r=r*1e-3; # rayon de la spire en m #valeur absolue de la composante Bx du champ magnetique en fonction de la position sur l axe de la spire bx_analytique=[abs(my0*I0)*(r)**2/(2*((r)**2+(x)**2)**(3/2)) for x in np.linspace(xmin, xmax, ndp, endpoint = True)] #%%%%%%%%%%% Visualisation %%%%%%%%%%%%%%%%%%%%%%%# #trace de la valeur absolue de la composante Bx du champ magnetique en fonction de x plt.plot(np.linspace(xmin, xmax, ndp, endpoint = True) , bxf,'bo') plt.plot(np.linspace(xmin, xmax, ndp, endpoint = True) , bx_analytique,'r-') plt.title ('Champ magnetique Bx le long de l axe Ox de la spire', color='b') plt.xlabel('position sur l axe Ox', color='b') plt.ylabel ('Bx', color='b') #etude de la composante bx1 du champ magnetique en differents points du plan xOy #initialisation du champ magnรฉtique bx1 bx1=0 by1=0 #Initialisation de l energie Em=0 Emf=0 #Indice pour les listes l=0 #ndp-1 intervalles ndp1=41 #### pour verification de Bx sur l'axe Ox avec yM,zM=0,0 ##BD seul cas ou la comparaison analytique est possible #### #initialisation des listes des coordonnees des points s = (ndp1,ndp1) xM1f=np.zeros(s) yM1f=np.zeros(s) #zM1f=np.zeros(ndp1*ndp1) u = np.zeros(s) X = np.zeros(s) Y = np.zeros(s) #initialisation de la liste des valeurs de la composante Bx1 en chaque point bx1f=np.zeros(s) #initialisation de la liste des valeurs de la composante By1 en chaque point by1f=np.zeros(s) #initialisation de la liste des valeurs de la composante By1 en chaque point bz1f=np.zeros(s) #calcul exact du coefficient b0 de l'integrale servant a calculer Bx #selon la formule: b0=mu0*I0*r/(2*pi) b0=2*10**(-7)*I0*r #coordonnees des points xM1f = np.linspace(-.03,.03,ndp1) yM1f = np.linspace(-.03,.03,ndp1) (X,Y) = np.meshgrid(xM1f,yM1f) #calcul de Bx1 en des points regulierement espaces du plan xoy autour de la spire ##BD Physiquement ce calcul doit s'appuyer sur un modele numerique car l'equation analytique est injustifiable des que l'on est excentre #Initialisation des positions xM, yM,zM=0,0,0 for i in range(ndp1): #Initialisation des champs locaux bfx,bfy,bfz=0,0,0 for j in range(ndp1): xM=X[i][j] yM=Y[i][j] #Initialisation des champs locaux bfx,bfy,bfz=0,0,0 R=np.array([xM,yM,zM]) # vecteur position sur # le point qui doit etre calcule # en integrant la contribution # de tous les courants le long # de la boucle verte for wseg in range(nseg): xs=x_spire[0][wseg] ys=y_spire[0][wseg] zs=z_spire[0][wseg] Rs=np.array([xs, ys, zs]) drsx=(x_spire[0][wseg+1]-x_spire[0][wseg]) drsy=(y_spire[0][wseg+1]-y_spire[0][wseg]) drsz=(z_spire[0][wseg+1]-z_spire[0][wseg]) drs=np.array([drsx, drsy, drsz]) #direction du courant Delta_R= Rs - R #vecteur entre l'รฉlement de spire et #le point oรน est calcul le champ Delta_Rdist=np.sqrt(Delta_R[0]**2+Delta_R[1]**2+Delta_R[2]**2) #Delta_Rdis2=Delta_Rdist**2 Delta_Rdis3=Delta_Rdist**3 b2=1.0/Delta_Rdis3 b12=I0f1*b2*(-1) # Produit vectoriel Delta_Rxdrs_x=Delta_R[1]*drsz-Delta_R[2]*drsy Delta_Rxdrs_y=Delta_R[2]*drsx-Delta_R[0]*drsz Delta_Rxdrs_z=Delta_R[0]*drsy-Delta_R[1]*drsx #Intรฉgration bfx=bfx+b12*Delta_Rxdrs_x bfy=bfy+b12*Delta_Rxdrs_y bfz=bfz+b12*Delta_Rxdrs_z # Il faut utiliser un champ defini comme 3 listes : # une liste pour chaque abscisse bx1f[i][j]+=bfx by1f[i][j]+=bfy bz1f[i][j]+=bfz #tracรฉ des vecteurs Bx en chaque point #tracรฉ des vecteurs B dans le plan xOy pour vรฉrifier les lignes de champ magnรฉtique q = plt.quiver(X,Y,bx1f,by1f,color='r') plt.title ('Cartographie des composantes Bx,By dans le plan xOy',color='b') plt.xlabel ('axe y',color='b') plt.ylabel ('axe x',color='b') 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: Load and Augment the Data Step2: Visualize a Batch of Training Data Step3: View an Image in More Detail Step4: Define the Network Architecture Step5: Specify Loss Function and Optimizer Step6: Train the Network Step7: Load the Model with the Lowest Validation Loss Step8: Test the Trained Network Step9: Visualize Sample Test Results
<ASSISTANT_TASK:> Python Code: import torch import numpy as np # check if CUDA is available train_on_gpu = torch.cuda.is_available() if not train_on_gpu: print('CUDA is not available. Training on CPU ...') else: print('CUDA is available! Training on GPU ...') from torchvision import datasets import torchvision.transforms as transforms from torch.utils.data.sampler import SubsetRandomSampler # number of subprocesses to use for data loading num_workers = 0 # how many samples per batch to load batch_size = 20 # percentage of training set to use as validation valid_size = 0.2 # convert data to a normalized torch.FloatTensor transform = transforms.Compose([ transforms.RandomHorizontalFlip(), # randomly flip and rotate transforms.RandomRotation(10), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) ]) # choose the training and test datasets train_data = datasets.CIFAR10('data', train=True, download=True, transform=transform) test_data = datasets.CIFAR10('data', train=False, download=True, transform=transform) # obtain training indices that will be used for validation num_train = len(train_data) indices = list(range(num_train)) np.random.shuffle(indices) split = int(np.floor(valid_size * num_train)) train_idx, valid_idx = indices[split:], indices[:split] # define samplers for obtaining training and validation batches train_sampler = SubsetRandomSampler(train_idx) valid_sampler = SubsetRandomSampler(valid_idx) # prepare data loaders (combine dataset and sampler) train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, sampler=train_sampler, num_workers=num_workers) valid_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, sampler=valid_sampler, num_workers=num_workers) test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, num_workers=num_workers) # specify the image classes classes = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'] import matplotlib.pyplot as plt %matplotlib inline # helper function to un-normalize and display an image def imshow(img): img = img / 2 + 0.5 # unnormalize plt.imshow(np.transpose(img, (1, 2, 0))) # convert from Tensor image # obtain one batch of training images dataiter = iter(train_loader) images, labels = dataiter.next() images = images.numpy() # convert images to numpy for display # plot the images in the batch, along with the corresponding labels fig = plt.figure(figsize=(25, 4)) # display 20 images for idx in np.arange(20): ax = fig.add_subplot(2, 20/2, idx+1, xticks=[], yticks=[]) imshow(images[idx]) ax.set_title(classes[labels[idx]]) rgb_img = np.squeeze(images[3]) channels = ['red channel', 'green channel', 'blue channel'] fig = plt.figure(figsize = (36, 36)) for idx in np.arange(rgb_img.shape[0]): ax = fig.add_subplot(1, 3, idx + 1) img = rgb_img[idx] ax.imshow(img, cmap='gray') ax.set_title(channels[idx]) width, height = img.shape thresh = img.max()/2.5 for x in range(width): for y in range(height): val = round(img[x][y],2) if img[x][y] !=0 else 0 ax.annotate(str(val), xy=(y,x), horizontalalignment='center', verticalalignment='center', size=8, color='white' if img[x][y]<thresh else 'black') import torch.nn as nn import torch.nn.functional as F # define the CNN architecture class Net(nn.Module): def __init__(self): super(Net, self).__init__() # convolutional layer (sees 32x32x3 image tensor) self.conv1 = nn.Conv2d(3, 16, 3, padding=1) # convolutional layer (sees 16x16x16 tensor) self.conv2 = nn.Conv2d(16, 32, 3, padding=1) # convolutional layer (sees 8x8x32 tensor) self.conv3 = nn.Conv2d(32, 64, 3, padding=1) # max pooling layer self.pool = nn.MaxPool2d(2, 2) # linear layer (64 * 4 * 4 -> 500) self.fc1 = nn.Linear(64 * 4 * 4, 500) # linear layer (500 -> 10) self.fc2 = nn.Linear(500, 10) # dropout layer (p=0.25) self.dropout = nn.Dropout(0.25) def forward(self, x): # add sequence of convolutional and max pooling layers x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = self.pool(F.relu(self.conv3(x))) # flatten image input x = x.view(-1, 64 * 4 * 4) # add dropout layer x = self.dropout(x) # add 1st hidden layer, with relu activation function x = F.relu(self.fc1(x)) # add dropout layer x = self.dropout(x) # add 2nd hidden layer, with relu activation function x = self.fc2(x) return x # create a complete CNN model = Net() print(model) # move tensors to GPU if CUDA is available if train_on_gpu: model.cuda() import torch.optim as optim # specify loss function (categorical cross-entropy) criterion = nn.CrossEntropyLoss() # specify optimizer optimizer = optim.SGD(model.parameters(), lr=0.01) # number of epochs to train the model n_epochs = 30 valid_loss_min = np.Inf # track change in validation loss for epoch in range(1, n_epochs+1): # keep track of training and validation loss train_loss = 0.0 valid_loss = 0.0 ################### # train the model # ################### model.train() for batch_idx, (data, target) in enumerate(train_loader): # move tensors to GPU if CUDA is available if train_on_gpu: data, target = data.cuda(), target.cuda() # clear the gradients of all optimized variables optimizer.zero_grad() # forward pass: compute predicted outputs by passing inputs to the model output = model(data) # calculate the batch loss loss = criterion(output, target) # backward pass: compute gradient of the loss with respect to model parameters loss.backward() # perform a single optimization step (parameter update) optimizer.step() # update training loss train_loss += loss.item()*data.size(0) ###################### # validate the model # ###################### model.eval() for batch_idx, (data, target) in enumerate(valid_loader): # move tensors to GPU if CUDA is available if train_on_gpu: data, target = data.cuda(), target.cuda() # forward pass: compute predicted outputs by passing inputs to the model output = model(data) # calculate the batch loss loss = criterion(output, target) # update average validation loss valid_loss += loss.item()*data.size(0) # calculate average losses train_loss = train_loss/len(train_loader.dataset) valid_loss = valid_loss/len(valid_loader.dataset) # print training/validation statistics print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format( epoch, train_loss, valid_loss)) # save model if validation loss has decreased if valid_loss <= valid_loss_min: print('Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...'.format( valid_loss_min, valid_loss)) torch.save(model.state_dict(), 'model_augmented.pt') valid_loss_min = valid_loss model.load_state_dict(torch.load('model_augmented.pt')) # track test loss test_loss = 0.0 class_correct = list(0. for i in range(10)) class_total = list(0. for i in range(10)) model.eval() # iterate over test data for batch_idx, (data, target) in enumerate(test_loader): # move tensors to GPU if CUDA is available if train_on_gpu: data, target = data.cuda(), target.cuda() # forward pass: compute predicted outputs by passing inputs to the model output = model(data) # calculate the batch loss loss = criterion(output, target) # update test loss test_loss += loss.item()*data.size(0) # convert output probabilities to predicted class _, pred = torch.max(output, 1) # compare predictions to true label correct_tensor = pred.eq(target.data.view_as(pred)) correct = np.squeeze(correct_tensor.numpy()) if not train_on_gpu else np.squeeze(correct_tensor.cpu().numpy()) # calculate test accuracy for each object class for i in range(batch_size): label = target.data[i] class_correct[label] += correct[i].item() class_total[label] += 1 # average test loss test_loss = test_loss/len(test_loader.dataset) print('Test Loss: {:.6f}\n'.format(test_loss)) for i in range(10): if class_total[i] > 0: print('Test Accuracy of %5s: %2d%% (%2d/%2d)' % ( classes[i], 100 * class_correct[i] / class_total[i], np.sum(class_correct[i]), np.sum(class_total[i]))) else: print('Test Accuracy of %5s: N/A (no training examples)' % (classes[i])) print('\nTest Accuracy (Overall): %2d%% (%2d/%2d)' % ( 100. * np.sum(class_correct) / np.sum(class_total), np.sum(class_correct), np.sum(class_total))) # obtain one batch of test images dataiter = iter(test_loader) images, labels = dataiter.next() images.numpy() # move model inputs to cuda, if GPU available if train_on_gpu: images = images.cuda() # get sample outputs output = model(images) # convert output probabilities to predicted class _, preds_tensor = torch.max(output, 1) preds = np.squeeze(preds_tensor.numpy()) if not train_on_gpu else np.squeeze(preds_tensor.cpu().numpy()) # plot the images in the batch, along with predicted and true labels fig = plt.figure(figsize=(25, 4)) for idx in np.arange(20): ax = fig.add_subplot(2, 20/2, idx+1, xticks=[], yticks=[]) imshow(images[idx]) ax.set_title("{} ({})".format(classes[preds[idx]], classes[labels[idx]]), color=("green" if preds[idx]==labels[idx].item() else "red")) <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 image above is captured and displayed by Jekyll. Step2: You can also remove only the code so that images and other output still show up. Step3: And here we'll only display a Pandas DataFrame. Again, this was generated with Python code Step4: You can configure the text that Textbooks with Jupyter uses for this by modifying your site's _config.yml file.
<ASSISTANT_TASK:> Python Code: from matplotlib import rcParams, cycler import matplotlib.pyplot as plt import numpy as np plt.ion() # Fixing random state for reproducibility np.random.seed(19680801) N = 10 data = [np.logspace(0, 1, 100) + np.random.randn(100) + ii for ii in range(N)] data = np.array(data).T cmap = plt.cm.coolwarm rcParams['axes.prop_cycle'] = cycler(color=cmap(np.linspace(0, 1, N))) from matplotlib.lines import Line2D custom_lines = [Line2D([0], [0], color=cmap(0.), lw=4), Line2D([0], [0], color=cmap(.5), lw=4), Line2D([0], [0], color=cmap(1.), lw=4)] fig, ax = plt.subplots(figsize=(10, 5)) lines = ax.plot(data) ax.legend(custom_lines, ['Cold', 'Medium', 'Hot']); thisvariable = "none of this should show up in the textbook" fig, ax = plt.subplots() x = np.random.randn(100) y = np.random.randn(100) ax.scatter(x, y, s=np.abs(x*100), c=x, cmap=plt.cm.coolwarm) ax.text(0, .5, thisvariable, fontsize=20, transform=ax.transAxes) ax.set_axis_off() # NO CODE thisvariable = "this plot *will* show up in the textbook." fig, ax = plt.subplots() x = np.random.randn(100) y = np.random.randn(100) ax.scatter(x, y, s=np.abs(x*100), c=x, cmap=plt.cm.coolwarm) ax.text(0, .5, thisvariable, fontsize=20, transform=ax.transAxes) ax.set_axis_off() # NO CODE import pandas as pd pd.DataFrame([['hi', 'there'], ['this', 'is'], ['a', 'DataFrame']], columns=['Word A', 'Word B']) import folium m = folium.Map( location=[45.372, -121.6972], zoom_start=12, tiles='Stamen Terrain' ) folium.Marker( location=[45.3288, -121.6625], popup='Mt. Hood Meadows', icon=folium.Icon(icon='cloud') ).add_to(m) folium.Marker( location=[45.3311, -121.7113], popup='Timberline Lodge', icon=folium.Icon(color='green') ).add_to(m) folium.Marker( location=[45.3300, -121.6823], popup='Some Other Location', icon=folium.Icon(color='red', icon='info-sign') ).add_to(m) 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: How we have a map of the world, with bright blue state borders. This isn't exactly what we want. Step2: Next, we'll plot some points on the map. Los Angeles and New York. Step3: Now we've plotted two points on the map. The 'c*' stands for cyan star.
<ASSISTANT_TASK:> Python Code: %matplotlib inline from mpl_toolkits.basemap import Basemap import matplotlib.pyplot as plt m = Basemap(projection='mill', llcrnrlat=-90, llcrnrlon=-180, urcrnrlat=90, urcrnrlon=180, resolution='l') m.drawcoastlines() m.drawcountries(linewidth=2) m.drawstates(color='b') m.bluemarble() m = Basemap(projection='mill', llcrnrlat=24.9493, llcrnrlon=-125.0011, urcrnrlat=49.5904, urcrnrlon=-66.9326, resolution='l') m.drawcoastlines() m.drawcountries(linewidth=1.5) m.drawstates(color='black') water_color = '#C1D2D2' continent_color = '#EBECEC' m = Basemap(projection='mill', llcrnrlat=24.5, llcrnrlon=-125.0011, urcrnrlat=49.5904, urcrnrlon=-66.9326, resolution='l') m.drawcoastlines() m.drawcountries(linewidth=1.5) m.drawstates(color='black') m.fillcontinents(color=continent_color, lake_color=water_color) m.drawmapboundary(fill_color=water_color) NYClat, NYClon = 40.7127, -74.0059 xpt, ypt = m(NYClon, NYClat) m.plot(xpt, ypt, 'c*', markersize=15, alpha=0.75) LAlat, LAlon = 34.05, -118.25 xpt, ypt = m(LAlon, LAlat) m.plot(xpt, ypt, 'g^', markersize=15, alpha=0.75) water_color = '#C1D2D2' continent_color = '#EBECEC' plt.figure(figsize=(12,6)) m = Basemap(projection='mill', llcrnrlat=24.5, llcrnrlon=-125.0011, urcrnrlat=49.5904, urcrnrlon=-66.9326, resolution='l') m.drawcoastlines() m.drawcountries(linewidth=1) m.drawstates(color='black') m.fillcontinents(color=continent_color, lake_color=water_color) m.drawmapboundary(fill_color=water_color) NYClat, NYClon = 40.7127, -74.0059 # xpt, ypt = m(NYClon, NYClat) # m.plot(xpt, ypt, 'c*', markersize=15, alpha=0.75) LAlat, LAlon = 34.05, -118.25 # xpt, ypt = m(LAlon, LAlat) # m.plot(xpt, ypt, 'g^', markersize=15, alpha=0.75) xpt, ypt = m([NYClon, LAlon], [NYClat, LAlat]) m.plot(xpt, ypt, 'g^', markersize=15, alpha=0.75) plt.savefig('us_test.png', bbox_inches='tight', pad_inches=0.0) <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 reload the data we generated in 1_notmnist.ipynb. Step2: Reformat into a shape that's more adapted to the models we're going to train Step3: We're first going to train a multinomial logistic regression using simple gradient descent. Step4: Let's run this computation and iterate Step5: Let's now switch to stochastic gradient descent training instead, which is much faster. Step6: Let's run it Step7: Problem
<ASSISTANT_TASK:> Python Code: # These are all the modules we'll be using later. Make sure you can import them # before proceeding further. from __future__ import print_function import numpy as np import tensorflow as tf from six.moves import cPickle as pickle from six.moves import range pickle_file = 'notMNIST.pickle' with open(pickle_file, 'rb') as f: save = pickle.load(f) train_dataset = save['train_dataset'] train_labels = save['train_labels'] valid_dataset = save['valid_dataset'] valid_labels = save['valid_labels'] test_dataset = save['test_dataset'] test_labels = save['test_labels'] del save # hint to help gc free up memory print('Training set', train_dataset.shape, train_labels.shape) print('Validation set', valid_dataset.shape, valid_labels.shape) print('Test set', test_dataset.shape, test_labels.shape) image_size = 28 num_labels = 10 def reformat(dataset, labels): dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32) # Map 0 to [1.0, 0.0, 0.0 ...], 1 to [0.0, 1.0, 0.0 ...] labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32) return dataset, labels train_dataset, train_labels = reformat(train_dataset, train_labels) valid_dataset, valid_labels = reformat(valid_dataset, valid_labels) test_dataset, test_labels = reformat(test_dataset, test_labels) print('Training set', train_dataset.shape, train_labels.shape) print('Validation set', valid_dataset.shape, valid_labels.shape) print('Test set', test_dataset.shape, test_labels.shape) # With gradient descent training, even this much data is prohibitive. # Subset the training data for faster turnaround. train_subset = 10000 graph = tf.Graph() with graph.as_default(): # Input data. # Load the training, validation and test data into constants that are # attached to the graph. tf_train_dataset = tf.constant(train_dataset[:train_subset, :]) tf_train_labels = tf.constant(train_labels[:train_subset]) tf_valid_dataset = tf.constant(valid_dataset) tf_test_dataset = tf.constant(test_dataset) # Variables. # These are the parameters that we are going to be training. The weight # matrix will be initialized using random valued following a (truncated) # normal distribution. The biases get initialized to zero. weights = tf.Variable( tf.truncated_normal([image_size * image_size, num_labels])) biases = tf.Variable(tf.zeros([num_labels])) # Training computation. # We multiply the inputs with the weight matrix, and add biases. We compute # the softmax and cross-entropy (it's one operation in TensorFlow, because # it's very common, and it can be optimized). We take the average of this # cross-entropy across all training examples: that's our loss. logits = tf.matmul(tf_train_dataset, weights) + biases loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels)) # Optimizer. # We are going to find the minimum of this loss using gradient descent. optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss) # Predictions for the training, validation, and test data. # These are not part of training, but merely here so that we can report # accuracy figures as we train. train_prediction = tf.nn.softmax(logits) valid_prediction = tf.nn.softmax( tf.matmul(tf_valid_dataset, weights) + biases) test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights) + biases) num_steps = 801 def accuracy(predictions, labels): return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1)) / predictions.shape[0]) with tf.Session(graph=graph) as session: # This is a one-time operation which ensures the parameters get initialized as # we described in the graph: random weights for the matrix, zeros for the # biases. tf.initialize_all_variables().run() print('Initialized') for step in range(num_steps): # Run the computations. We tell .run() that we want to run the optimizer, # and get the loss value and the training predictions returned as numpy # arrays. _, l, predictions = session.run([optimizer, loss, train_prediction]) if (step % 100 == 0): print('Loss at step %d: %f' % (step, l)) print('Training accuracy: %.1f%%' % accuracy( predictions, train_labels[:train_subset, :])) # Calling .eval() on valid_prediction is basically like calling run(), but # just to get that one numpy array. Note that it recomputes all its graph # dependencies. print('Validation accuracy: %.1f%%' % accuracy( valid_prediction.eval(), valid_labels)) print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels)) batch_size = 128 graph = tf.Graph() with graph.as_default(): # Input data. For the training data, we use a placeholder that will be fed # at run time with a training minibatch. tf_train_dataset = tf.placeholder(tf.float32, shape=(batch_size, image_size * image_size)) tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels)) tf_valid_dataset = tf.constant(valid_dataset) tf_test_dataset = tf.constant(test_dataset) # Variables. weights = tf.Variable( tf.truncated_normal([image_size * image_size, num_labels])) biases = tf.Variable(tf.zeros([num_labels])) # Training computation. logits = tf.matmul(tf_train_dataset, weights) + biases loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels)) # Optimizer. optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss) # Predictions for the training, validation, and test data. train_prediction = tf.nn.softmax(logits) valid_prediction = tf.nn.softmax( tf.matmul(tf_valid_dataset, weights) + biases) test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights) + biases) num_steps = 3001 with tf.Session(graph=graph) as session: tf.initialize_all_variables().run() print("Initialized") for step in range(num_steps): # Pick an offset within the training data, which has been randomized. # Note: we could use better randomization across epochs. offset = (step * batch_size) % (train_labels.shape[0] - batch_size) # Generate a minibatch. batch_data = train_dataset[offset:(offset + batch_size), :] batch_labels = train_labels[offset:(offset + batch_size), :] # Prepare a dictionary telling the session where to feed the minibatch. # The key of the dictionary is the placeholder node of the graph to be fed, # and the value is the numpy array to feed to it. feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels} _, l, predictions = session.run( [optimizer, loss, train_prediction], feed_dict=feed_dict) if (step % 500 == 0): print("Minibatch loss at step %d: %f" % (step, l)) print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels)) print("Validation accuracy: %.1f%%" % accuracy( valid_prediction.eval(), valid_labels)) print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels)) batch_size = 128 num_hidden_nodes = 1024 graph = tf.Graph() with graph.as_default(): # Input data. For the training data, we use a placeholder that will be fed # at run time with a training minibatch. tf_train_dataset = tf.placeholder(tf.float32, shape=(batch_size, image_size * image_size)) tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels)) tf_valid_dataset = tf.constant(valid_dataset) tf_test_dataset = tf.constant(test_dataset) # Variables. weights1 = tf.Variable( tf.truncated_normal([image_size * image_size, num_hidden_nodes])) biases1 = tf.Variable(tf.zeros([num_hidden_nodes])) weights2 = tf.Variable( tf.truncated_normal([num_hidden_nodes, num_labels])) biases2 = tf.Variable(tf.zeros([num_labels])) # Training computation. lay1_train = tf.nn.relu(tf.matmul(tf_train_dataset, weights1) + biases1) logits = tf.matmul(lay1_train, weights2) + biases2 loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels)) # Optimizer. optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss) # Predictions for the training, validation, and test data. train_prediction = tf.nn.softmax(logits) lay1_valid = tf.nn.relu(tf.matmul(tf_valid_dataset, weights1) + biases1) valid_prediction = tf.nn.softmax(tf.matmul(lay1_valid, weights2) + biases2) lay1_test = tf.nn.relu(tf.matmul(tf_test_dataset, weights1) + biases1) test_prediction = tf.nn.softmax(tf.matmul(lay1_test, weights2) + biases2) num_steps = 3001 with tf.Session(graph=graph) as session: tf.initialize_all_variables().run() print("Initialized") for step in range(num_steps): # Pick an offset within the training data, which has been randomized. # Note: we could use better randomization across epochs. offset = (step * batch_size) % (train_labels.shape[0] - batch_size) # Generate a minibatch. batch_data = train_dataset[offset:(offset + batch_size), :] batch_labels = train_labels[offset:(offset + batch_size), :] # Prepare a dictionary telling the session where to feed the minibatch. # The key of the dictionary is the placeholder node of the graph to be fed, # and the value is the numpy array to feed to it. feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels} _, l, predictions = session.run( [optimizer, loss, train_prediction], feed_dict=feed_dict) if (step % 500 == 0): print("Minibatch loss at step %d: %f" % (step, l)) print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels)) print("Validation accuracy: %.1f%%" % accuracy( valid_prediction.eval(), valid_labels)) print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels)) <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: Make The Datasets Step3: Because ScScore is trained on relative complexities, we want the X tensor in our dataset to have 3 dimensions (sample_id, molecule_id, features). The molecule_id dimension has size 2 because a sample is a pair of molecules. The label is 1 if the first molecule is more complex than the second molecule. The function create_dataset we introduce below pulls random pairs of SMILES strings out of a given list and ranks them according to this complexity measure. Step4: With our complexity ranker in place we can now construct our dataset. Let's start by randomly splitting the list of molecules into training and test sets. Step5: We'll featurize all our molecules with the ECFP fingerprint with chirality (matching the source paper), and will then construct our pairwise dataset using the function defined above. Step6: Now that we have our dataset created, let's train a ScScoreModel on this dataset. Step7: Model Performance Step8: Let's now plot the length of the smiles string of the molecule against the SaScore using matplotlib.
<ASSISTANT_TASK:> Python Code: !curl -Lo conda_installer.py https://raw.githubusercontent.com/deepchem/deepchem/master/scripts/colab_install.py import conda_installer conda_installer.install() !/root/miniconda/bin/conda info -e !pip install --pre deepchem import deepchem deepchem.__version__ import deepchem as dc tasks, datasets, transformers = dc.molnet.load_tox21(featurizer='Raw', splitter=None) molecules = datasets[0].X from rdkit import Chem import random from deepchem.feat import CircularFingerprint import numpy as np def create_dataset(fingerprints, smiles_lens, ds_size=100000): m1: list of np.Array fingerprints for molecules m2: list of int length of a molecules SMILES string returns: dc.data.Dataset for input into ScScore Model Dataset.X shape is (sample_id, molecule_id, features) Dataset.y shape is (sample_id,) values is 1 if the 0th index molecule is more complex 0 if the 1st index molecule is more complex X, y = [], [] all_data = list(zip(fingerprints, smiles_lens)) while len(y) < ds_size: i1 = random.randrange(0, len(smiles_lens)) i2 = random.randrange(0, len(smiles_lens)) m1 = all_data[i1] m2 = all_data[i2] if m1[1] == m2[1]: continue if m1[1] > m2[1]: y.append(1.0) else: y.append(0.0) X.append([m1[0], m2[0]]) return dc.data.NumpyDataset(np.array(X), np.expand_dims(np.array(y), axis=1)) molecule_ds = dc.data.NumpyDataset(np.array(molecules)) splitter = dc.splits.RandomSplitter() train_mols, test_mols = splitter.train_test_split(molecule_ds) n_features = 1024 featurizer = dc.feat.CircularFingerprint(size=n_features, radius=2, chiral=True) train_features = featurizer.featurize(train_mols.X) train_smiles_len = [len(Chem.MolToSmiles(x)) for x in train_mols.X] train_dataset = create_dataset(train_features, train_smiles_len) model = dc.models.ScScoreModel(n_features=n_features) model.fit(train_dataset, nb_epoch=20) import matplotlib.pyplot as plt %matplotlib inline mol_scores = model.predict_mols(test_mols.X) smiles_lengths = [len(Chem.MolToSmiles(x)) for x in test_mols.X] plt.figure(figsize=(20,16)) plt.scatter(smiles_lengths, mol_scores) plt.xlim(0,80) plt.xlabel("SMILES length") plt.ylabel("ScScore") 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: How to Get The Dataset Step2: Get rid of any rows that have nans in them Step3: Display the dtypes of your dset Step4: Coerce the Date feature (which is currently a string object) into real date, and confirm by displaying the dtypes again. This might be a slow executing process... Step5: Filter out the data so that it only contains samples that have a Date &gt; '2011-01-01', using indexing. Then, in a new figure, plot the crime incidents, as well as a new K-Means run's centroids.
<ASSISTANT_TASK:> Python Code: # .. your code here .. # .. your code here .. # .. your code here .. # .. your code here .. # .. your code here .. def doKMeans(df): # Let's plot your data with a '.' marker, a 0.3 alpha at the Longitude, # and Latitude locations in your dataset. Longitude = x, Latitude = y fig = plt.figure() ax = fig.add_subplot(111) ax.scatter(df.Longitude, df.Latitude, marker='.', alpha=0.3) # TODO: Filter `df` using indexing so it only contains Longitude and Latitude, # since the remaining columns aren't really applicable for this lab: # # .. your code here .. # TODO: Use K-Means to try and find seven cluster centers in this df. # Be sure to name your kmeans model `model` so that the printing works. # # .. your code here .. # Now we can print and plot the centroids: centroids = model.cluster_centers_ print(centroids) ax.scatter(centroids[:,0], centroids[:,1], marker='x', c='red', alpha=0.5, linewidths=3, s=169) plt.show() # Print & Plot your data doKMeans(df) # .. your code here .. # Print & Plot your data doKMeans(df) <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: Verify tables exist Step2: Create the baseline model Step3: REMINDER Step4: Lab Task #2 Step5: Resource for an explanation of the Regression Metrics.
<ASSISTANT_TASK:> Python Code: %%bash sudo pip freeze | grep google-cloud-bigquery==1.6.1 || \ sudo pip install google-cloud-bigquery==1.6.1 %%bigquery -- LIMIT 0 is a free query; this allows us to check that the table exists. SELECT * FROM babyweight.babyweight_data_train LIMIT 0 %%bigquery -- LIMIT 0 is a free query; this allows us to check that the table exists. SELECT * FROM babyweight.babyweight_data_eval LIMIT 0 %%bigquery CREATE OR REPLACE MODEL babyweight.baseline_model OPTIONS ( MODEL_TYPE=# TODO: Add model type, INPUT_LABEL_COLS=[# TODO: label column name], DATA_SPLIT_METHOD="NO_SPLIT") AS SELECT # TODO: Add features and label FROM # TODO: Add train table %%bigquery -- Information from model training SELECT * FROM ML.TRAINING_INFO(MODEL babyweight.baseline_model) %%bigquery SELECT * FROM ML.EVALUATE(MODEL # TODO: Add model name, ( SELECT # TODO: Add features and label FROM # TODO: Add eval table )) %%bigquery SELECT # TODO: Select just the calculated RMSE FROM ML.EVALUATE(MODEL # TODO: Add model name, ( SELECT # TODO: Add features and label FROM # TODO: Add eval 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: Now, I should be able to import $\delta$a$\delta$i Step2: I have turned the 1D folded SFS's from realSFS into $\delta$d$\delta$i format by hand according to the description in section 3.1 of the manual. I have left out the masking line from the input file. Step3: $\delta$a$\delta$i is detecting that the spectrum is folded (as given in the input file), but it is also automatically masking the 0th and 18th count category. This is a not a good behaviour. Step4: Single population statistics Step5: I have next added a masking line to the input file, setting it to '1' for the first position, i. e. the 0-count category. Step6: $\delta$a$\delta$i is issuing the following message when executing the above command Step7: I do not understand this warning from $\delta$a$\delta$i. The 18-count category is sensical for a folded spectrum with even sample size, so should not be masked. Anyway, I do not understand why $\delta$a$\delta$i is so reluctant to keep all positions, including the non-variable one. Step8: The function that returns $\pi$ produces the same output with or without the last count category masked ?! I think that is because even if the last count class (966.62...) is masked, it is still included in the calculation of $\pi$. However, there is no obvious unmasking in the pi function. Strange! Step9: This is the value of $\pi_{site}$ that I calculated previously and included in the first draft of the thesis. Step10: This is the same as the output of dadi's pi function on the same SFS. Step11: So, 1.6 million sites went into the ery spectrum. Step12: Apart from the incorrect small sample size correction by $\delta$a$\delta$i in case of folded spectra ($n$ refers to sampled sequences, not individuals), Gillespie's formula leads to a much higher estimate of $\pi_{site}$ than Wakeley's. Why is that? Step13: As can be seen from the insignificant difference (must be due to numerical inaccuracies) between the $\pi_{Wakeley}$ and the $\pi_{Gillespie}$ estimates, they are equivalent with the calculation for folded spectra given above as well as the correct small sample size correction. Beware Step14: I think for now it would be best to import unfolded spectra from realSFS and fold them if necessary in dadi. Step18: ML estimate of $\theta$ from 1D folded spectrum Step19: The counts in each frequency class should be Poisson distributed with rate equal to $E[\eta_i]$ as given above. The lowest frequency class has the highest rate and therefore also the highest variance Step20: The following function will take the file name of a file containing the flat 1D folded frequency spectrum of one population and plots it together with the best fitting neutral expectation. Step22: Univariate function minimizers or 1D scalar minimisation Step23: It would be interesting to know whether the cost function is convex or not. Step24: Within the specified bounds (the observed $\theta$, i. e. derived from the data, cannot lie outside these bounds), the cost function is convex. This is therefore an easy optimisation problem. See here for more details. Step25: The fitted values of $\theta$ are similar to the ones obtained above with the least_squares function. The estimates for ery deviate more than for par. Step26: Wow! Sympy is a replacement for Mathematica. There is also Sage, which may include even more functionality. Step28: Curve_fit is another function that can be used for optimization. Step29: I am not sure whether these standard errors (perr) are correct. It may be that it is assumed that errors are normally distributed, which they are not exactly in this case. They should be close to Poisson distributed (see Fu1995), which should be fairly similar to normal with such high expected values as here. Step30: There must be a way to get more than one bootstrap sample per call. Step31: It would be good to get the 5% and 95% quantiles from the bootstrap samples of each frequency class and add those intervals to the plot of the observed frequency spectrum and the fitted neutral spectrum. This would require to find a quantile function and to find out how to add lines to a plot with matplotlib. Step32: Marginalizing Step33: Note, that these marginalised 1D SFS's are not identical to the 1D SFS estimated directly with realSFS. This is because, for the estimation of the 2D SFS, realSFS has only taken sites that had data from at least 9 individuals in each population (see assembly.sh, lines 1423 onwards). Step34: These marginal unfolded spectra look similar in shape to the 1D folded spectra of each subspecies (see above). Step35: $\delta$a$\delta$i's pi function seems to calculate the correct value of $\pi$ for this unfolded spectrum. However, it is worrying that $\pi$ from this marginal spectrum is about 20 times larger than the one calculated from the directly estimated 1D folded spectrum (see above the $\pi$ calculated from the folded 1D spectrum). Step36: <font color="red">The sum over the marginalised 1D spectra should be the same as the sum over the 2D spectrum !</font> Step37: So, during the marginalisation the masking of data in the fixed categories (0, 36) is the problem, producing incorrectly marginalised counts in those masked categories. This is shown in the following Step38: This is very close to the estimate of $\pi$ derived from the folded 1D spectrum of ery! (see above) Step39: This is also nicely close to the estimate of $\pi_{site}$ of par from its folded 1D spectrum. Step40: Now, I am calculating Tajima's D from the ery marginal spectrum by hand in order to check whether $\delta$a$\delta$i is doing the right thing. Step41: $\delta$a$\delta$i seems to do the right thing. Note, that the estimate of Tajima's D from this marginal spectrum of ery is slightly different from the estimate derived from the folded 1D spectrum of ery (see /data3/claudius/Big_Data/ANGSD/SFS/SFS.Rmd). The folded 1D spectrum resulted in a Tajima's D estimate of $\sim$0.05, i. e. a difference of almost 0.1. Again, the 2D spectrum is based on only those sites for which there were at least 9 individiuals with data in both populations, whereas the 1D folded spectrum of ery included all sites for which there were 9 ery individuals with data (see line 1571 onwards in assembly.sh). Step42: My estimate from the folded 1D spectrum of par was -0.6142268 (see /data3/claudius/Big_Data/ANGSD/SFS/SFS.Rmd). Step43: The 2D spectrum contains counts from 60k sites that are variable in par or ery or both. Step44: This estimate of $F_{ST}$ according to Weir and Cockerham (1984) is well below the estimate of $\sim$0.3 from ANGSD according to Bhatia/Hudson (2013). Note, however, that this estimate showed a positive bias of around 0.025 in 100 permutations of population labels of individuals. Taking the positive bias into account, both estimates of $F_{ST}$ are quite similar. Step45: So, this is how the 2D SFS would look like if ery and par were not genetically differentiated. Step46: The $F_{ST}$ from the scrambled SFS is much lower than the $F_{ST}$ of the observed SFS. That should mean that there is significant population structure. However, the $F_{ST}$ from the scrambled SFS is not 0. I don't know why that is. Step47: Plotting Step48: The folded 2D spectrum is not a minor allele frequency spectrum as are the 1D folded spectra of ery and par. This is because an allele that is minor in one population can be the major allele in the other. What is not counted are the alleles that are major in both populations, i. e. the upper right corner. Step49: Let's use the formula (1.2) from Wakeley2009 to fold the 1D spectrum manually Step50: Here is how to flatten an array of arrays with list comprehension Step51: Set new mask for the folded spectrum Step52: The fold() function works correctly for 1D spectra, at least. How about 2D spectra? Step53: I am going to go through every step in the fold function of dadi Step54: With the variable length list of slice objects, one can generalise the reverse of arrays with any dimensions. Step55: Here, folding doesn't mask new cells. Step56: The transformation we have done with the upper-right diagonal 2D array above should be identical to projecting it across a vertical center line (creating an upper left triangular matrix) and then projecting it across a horizontal center line (creating the final lower left triangular matrix). Note, that this is not like mirroring the upper-right triangular 2D array across the 36-36 diagonal! Step57: SNP's with joint frequencies in the True cells are counted twice at the moment due to the folding and the fact that the sample sizes are even. Step58: These are the values in the diagonal before folding. Step59: These are the values that got added to the diagonal during folding. Comparing with the previous plot, one can see for instance that the value in the (0, 36) class got added to the value in the (36, 0) class and vice versa. The two frequency classes are equivalent, since it is arbitrary which allele we call minor in the total sample (of 72 gene copies). These SNP's are therefore counted twice.
<ASSISTANT_TASK:> Python Code: sys.path.insert(0, '/home/claudius/Downloads/dadi') sys.path import dadi dir(dadi) import pylab %matplotlib inline x = pylab.linspace(0, 4*pylab.pi, 1000) pylab.plot(x, pylab.sin(x), '-r') %%sh # this allows me to execute a shell command ls fs_ery = dadi.Spectrum.from_file('ERY.FOLDED.sfs.dadi_format') fs_ery # number of segregating sites fs_ery.data[1:].sum() fs_ery.pi() fs_ery = dadi.Spectrum.from_file('ERY.FOLDED.sfs.dadi_format', mask_corners=False) fs_ery fs_ery.pi() # Calcualting pi with the formula from Wakeley2009 n = 36 # 36 sequences sampled from 18 diploid individuals pi_Wakeley = (sum( [i*(n-i)*fs_ery[i] for i in range(1, n/2+1)] ) * 2.0 / (n*(n-1)))/pylab.sum(fs_ery.data) # note fs_ery.data gets the whole fs_ery list, including masked entries pi_Wakeley fs_ery.mask fs_ery.data # gets all data, including the masked one # Calculating pi with the formula from Gillespie: n = 18 p = pylab.arange(0, n+1)/float(n) p # Calculating pi with the formula from Gillespie: n / (n-1.0) * 2 * pylab.sum(fs_ery * p*(1-p)) # the sample size (n) that dadi stores in this spectrum object and uses as n in the pi function fs_ery.sample_sizes[0] # what is the total number of sites in the spectrum pylab.sum(fs_ery.data) # pi per site n / (n-1.0) * 2 * pylab.sum(fs_ery * p*(1-p)) / pylab.sum(fs_ery.data) # with correct small sample size correction 2 * n / (2* n-1.0) * 2 * pylab.sum(fs_ery * p*(1-p)) / pylab.sum(fs_ery.data) # Calculating pi with the formula from Gillespie: n = 18 p = pylab.arange(0, n+1)/float(n) p = p/2 # with a folded spectrum, we are summing over minor allele freqs only pi_Gillespie = 2*n / (2*n-1.0) * 2 * pylab.sum(fs_ery * p*(1-p)) / pylab.sum(fs_ery.data) pi_Gillespie pi_Wakeley - pi_Gillespie fs_ery.folded fs_par = dadi.Spectrum.from_file('PAR.FOLDED.sfs.dadi_format') pylab.plot(fs_ery, 'r', label='ery') pylab.plot(fs_par, 'g', label='par') pylab.legend() from scipy.optimize import least_squares def model(theta, eta, n): theta: scaled population mutation rate parameter [scalar] eta: the folded 1D spectrum, including 0-count cat. [list] n: number of sampled gene copies, i. e. 2*num_ind [scalar] returns a numpy array i = pylab.arange(1, eta.size) delta = pylab.where(i == n-i, 1, 0) return theta * 1/i + 1/(n-i) / (1 + delta) ?pylab.where # test i = pylab.arange(1, 19) n = 36 print i == n-i # print pylab.where(i == n-i, 1, 0) # get a theta estimate from pi: theta = pi_Wakeley * fs_ery.data.sum() print theta # print len(fs_ery) # model(theta, fs_ery, 36) def fun(theta, eta, n): return residuals between model and data return model(theta, eta, n) - eta[1:] def jac(theta, eta, n, test=False): creates a Jacobian matrix J = pylab.empty((eta.size-1, theta.size)) i = pylab.arange(1, eta.size, dtype=float) delta = pylab.where(i == n-i, 1, 0) num = 1/i + 1/(n-i) den = 1 + delta if test: print i print num print den J[:,0] = num / den return J # test jac(theta, fs_ery, 36, test=True) # starting value theta0 = theta # pi_Wakeley from above # sum over unmasked entries, i. e. without 0-count category, i. e. returns number of variable sites fs_ery.sum() # optimize res = least_squares(fun, x0=theta0, jac=jac, bounds=(0,fs_ery.sum()), kwargs={'eta': fs_ery, 'n': 36}, verbose=1) res.success ?least_squares print res.x print theta pylab.rcParams['figure.figsize'] = [12.0, 8.0] import matplotlib.pyplot as plt plt.rcParams['font.size'] = 14.0 i = range(1, len(fs_ery)) eta_model = model(res.x, eta=fs_ery, n=36) # get predicted values with optimal theta plt.plot(i, fs_ery[1:], "bo", label="data from ery") # plot observed spectrum ymax = max( fs_ery[1:].max(), eta_model.max() ) plt.axis([0, 19, 0, ymax*1.1]) # set axis range plt.xlabel("minor allele frequency (i)") plt.ylabel(r'$\eta_i$', fontsize='large', rotation='horizontal') plt.title("folded SFS of ery") plt.plot(i, eta_model, "go-", label="\nneutral model" + "\n" + r'$\theta_{opt} = $' + str(round(res.x, 1)) ) # plot model prediction with optimal theta plt.legend() #?plt.ylabel #print plt.rcParams fs_ery[1:].max() #?pylab os.getcwd() %%sh ls def plot_folded_sfs(filename, n, pop = ''): # read in spectrum from file data = open(filename, 'r') sfs = pylab.array( data.readline().split(), dtype=float ) data.close() # should close connection to file #return sfs # get starting value for theta from Watterson's theta S = sfs[1:].sum() T_total = sum([1.0/i for i in range(1, n)]) # onhe half the expected total length of the genealogy theta0 = S / T_total # see eq. 4.7 in Wakeley2009 # optimize res = least_squares(fun, x0=theta0, jac=jac, bounds=(0, sfs.sum()), kwargs={'eta': sfs, 'n': 36}, verbose=1) #print "Optimal theta per site is {0:.4f}".format(res.x[0]/sfs.sum()) #print res.x[0]/sfs.sum() #return theta0, res # plot plt.rcParams['font.size'] = 14.0 i = range(1, len(sfs)) eta_model = model(res.x, eta=sfs, n=36) # get predicted values with optimal theta plt.plot(i, sfs[1:], "rs", label="data of " + pop) # plot observed spectrum ymax = max( sfs[1:].max(), eta_model.max() ) plt.axis([0, 19, 0, ymax*1.1]) # set axis range plt.xlabel("minor allele frequency (i)") plt.ylabel(r'$\eta_i$', fontsize='large', rotation='horizontal') plt.title("folded SFS") plt.text(5, 10000, r"Optimal neutral $\theta$ per site is {0:.4f}".format(res.x[0]/sfs.sum())) plt.plot(i, eta_model, "go-", label="\nneutral model" + "\n" + r'$\theta_{opt} = $' + str(round(res.x, 1)) ) # plot model prediction with optimal theta plt.legend() plot_folded_sfs('PAR.FOLDED.sfs', n=36, pop='par') plot_folded_sfs('ERY.FOLDED.sfs', n=36, pop='ery') from scipy.optimize import minimize_scalar ?minimize_scalar # define cost function def f(theta, eta, n): return sum of squared deviations between model and data return sum( (model(theta, eta, n) - eta[1:])**2 ) # see above for definition of the 'model' function theta = pylab.arange(0, fs_ery.data[1:].sum()) # specify range of theta cost = [f(t, fs_ery.data, 36) for t in theta] plt.plot(theta, cost, 'b-', label='ery') plt.xlabel(r'$\theta$') plt.ylabel('cost') plt.title("cost function for ery") plt.legend(loc='best') ?plt.legend res = minimize_scalar(f, bounds = (0, fs_ery.data[1:].sum()), method = 'bounded', args = (fs_ery.data, 36)) res # number of segregating sites fs_par.data[1:].sum() res = minimize_scalar(f, bounds = (0, fs_par.data[1:].sum()), method = 'bounded', args = (fs_par.data, 36)) res from sympy import * x0 , x1 = symbols('x0 x1') init_printing(use_unicode=True) diff(0.5*(1-x0)**2 + (x1-x0**2)**2, x0) diff(0.5*(1-x0)**2 + (x1-x0**2)**2, x1) from scipy.optimize import curve_fit ?curve_fit def model(i, theta): i: indpendent variable, here minor SNP frequency classes theta: scaled population mutation rate parameter [scalar] returns a numpy array n = len(i) delta = pylab.where(i == n-i, 1, 0) return theta * 1/i + 1/(n-i) / (1 + delta) i = pylab.arange(1, fs_ery.size) popt, pcov = curve_fit(model, i, fs_ery.data[1:]) # optimal theta print popt perr = pylab.sqrt(pcov) perr print str(int(popt[0] - 1.96*perr[0])) + ' < ' + str(int(popt[0])) + ' < ' + str(int(popt[0] + 1.96*perr[0])) popt, pcov = curve_fit(model, i, fs_par.data[1:]) perr = pylab.sqrt(pcov) print str(int(popt[0] - 1.96*perr[0])) + ' < ' + str(int(popt[0])) + ' < ' + str(int(popt[0] + 1.96*perr[0])) %pwd % ll ! cat ERY.FOLDED.sfs.dadi_format fs_ery = dadi.Spectrum.from_file('ERY.FOLDED.sfs.dadi_format', mask_corners=False) fs_ery fs_ery.pop_ids = ['ery'] # get a Poisson sample from the observed spectrum fs_ery_param_boot = fs_ery.sample() fs_ery_param_boot fs_ery_param_boot.data %psource fs_ery.sample fs_ery_param_boot = pylab.array([fs_ery.sample() for i in range(100)]) # get the first 3 boostrap samples from the doubleton class fs_ery_param_boot[:3, 2] # read in the flattened 2D SFS EryPar_unfolded_2dsfs = dadi.Spectrum.from_file('EryPar.unfolded.2dsfs.dadi_format', mask_corners=True) # check dimension len(EryPar_unfolded_2dsfs[0,]) EryPar_unfolded_2dsfs.sample_sizes # add population labels EryPar_unfolded_2dsfs.pop_ids = ["ery", "par"] EryPar_unfolded_2dsfs.pop_ids # marginalise over par to get 1D SFS for ery fs_ery = EryPar_unfolded_2dsfs.marginalize([1]) # note the argument is an array with dimensions, one can marginalise over more than one dimension at the same time, # but that is only interesting for 3-dimensional spectra, which I don't have here fs_ery # marginalise over ery to get 1D SFS for par fs_par = EryPar_unfolded_2dsfs.marginalize([0]) fs_par # plot 1D spectra for each population pylab.plot(fs_par, 'g', label="par") pylab.plot(fs_ery, 'r', label="ery") pylab.legend() fs_ery.pi() / pylab.sum(fs_ery.data) fs_ery.data n = 36 # 36 sequences sampled from 18 diploid individuals pi_Wakeley = (sum( [i*(n-i)*fs_ery[i] for i in range(1, n)] ) * 2.0 / (n*(n-1))) pi_Wakeley = pi_Wakeley / pylab.sum(fs_ery.data) pi_Wakeley fs_par.pi() / pylab.sum(fs_par.data) pylab.sum(fs_par.data) pylab.sum(EryPar_unfolded_2dsfs.data) # from dadi's marginalise function: fs_ery.data sfs2d = EryPar_unfolded_2dsfs.copy() # this should get the marginal spectrum for ery ery_mar = [pylab.sum(sfs2d.data[i]) for i in range(0, len(sfs2d))] ery_mar # this should get the marginal spectrum for ery and then take the sum over it sum([pylab.sum(sfs2d.data[i]) for i in range(0, len(sfs2d))]) # look what happens if I include masking sum([pylab.sum(sfs2d[i]) for i in range(0, len(sfs2d))]) fs_ery.data - ery_mar sfs2d[0] pylab.sum(sfs2d[0]) # from dadi's marginalise function: fs_ery.data # dividing by the correct number of sites to get pi per site: fs_ery.pi() / pylab.sum(sfs2d.data) fs_par.pi() / pylab.sum(sfs2d.data) fs_ery.Watterson_theta() / pylab.sum(sfs2d.data) fs_ery.Tajima_D() fs_par.Tajima_D() n = 36 pi_Wakeley = (sum( [i*(n-i)*fs_ery.data[i] for i in range(1, n+1)] ) * 2.0 / (n*(n-1))) #/ pylab.sum(sfs2d.data) pi_Wakeley # number of segregating sites # this sums over all unmasked positions in the array pylab.sum(fs_ery) fs_ery.S() S = pylab.sum(fs_ery) theta_Watterson = S / pylab.sum(1.0 / (pylab.arange(1, n))) theta_Watterson # normalizing constant, see page 45 in Gillespie a1 = pylab.sum(1.0 / pylab.arange(1, n)) #print a1 a2 = pylab.sum(1.0 / pylab.arange(1, n)**2.0) #print a2 b1 = (n+1.0)/(3.0*(n-1)) #print b1 b2 = 2.0*(n**2 + n + 3)/(9.0*n*(n-1)) #print b2 c1 = b1 - (1.0/a1) #print c1 c2 = b2 - (n+2.0)/(a1*n) + a2/a1**2 #print c2 C = ((c1/a1)*S + (c2/(a1**2.0 + a2))*S*(S-1)) C = C**(1/2.0) ery_Tajimas_D = (pi_Wakeley - theta_Watterson) / C print '{0:.6f}'.format(ery_Tajimas_D) ery_Tajimas_D - fs_ery.Tajima_D() fs_par.Tajima_D() EryPar_unfolded_2dsfs.S() EryPar_unfolded_2dsfs.Fst() %psource EryPar_unfolded_2dsfs.scramble_pop_ids # plot the scrambled 2D SFS dadi.Plotting.plot_single_2d_sfs(EryPar_unfolded_2dsfs.scramble_pop_ids(), vmin=1) # get Fst for scrambled SFS EryPar_unfolded_2dsfs.scramble_pop_ids().Fst() # folding EryPar_folded_2dsfs = EryPar_unfolded_2dsfs.fold() EryPar_folded_2dsfs EryPar_folded_2dsfs.mask dadi.Plotting.plot_single_2d_sfs(EryPar_unfolded_2dsfs, vmin=1) dadi.Plotting.plot_single_2d_sfs(EryPar_folded_2dsfs, vmin=1) # unfolded spectrum from marginalisation of 2D unfolded spectrum fs_ery len(fs_ery) fs_ery.fold() fs_ery_folded = fs_ery.copy() # make a copy of the UNfolded spectrum n = len(fs_ery)-1 for i in range(len(fs_ery)): fs_ery_folded[i] += fs_ery[n-i] if i == n/2.0: fs_ery_folded[i] /= 2 fs_ery_folded[0:19] isinstance(fs_ery_folded, pylab.ndarray) mask = [True] mask.extend([False] * 18) mask.extend([True] * 18) print mask print sum(mask) mask = [True] * 37 for i in range(len(mask)): if i > 0 and i < 19: mask[i] = False print mask print sum(mask) mask = [[True], [False] * 18, [True] * 18] print mask print [elem for a in mask for elem in a] fs_ery_folded.mask = mask fs_ery_folded.folded = True fs_ery_folded - fs_ery.fold() EryPar_unfolded_2dsfs.sample_sizes EryPar_unfolded_2dsfs._total_per_entry() # copy the unfolded 2D spectrum for folding import copy sfs2d_folded = copy.deepcopy(EryPar_unfolded_2dsfs) n = len(sfs2d_folded)-1 m = len(sfs2d_folded[0])-1 for i in range(n+1): for j in range(m+1): sfs2d_folded[i,j] += sfs2d_folded[n-i, m-j] if i == n/2.0 and j == m/2.0: sfs2d_folded[i,j] /= 2 mask = sfs2d_folded._total_per_entry() > (n+m)/2 mask sfs2d_folded.mask = mask sfs2d_folded.fold = True dadi.Plotting.plot_single_2d_sfs(sfs2d_folded, vmin=1) # copy the unfolded 2D spectrum for folding import copy sfs2d_unfolded = copy.deepcopy(EryPar_unfolded_2dsfs) total_samples = pylab.sum(sfs2d_unfolded.sample_sizes) total_samples total_per_entry = dadi.Spectrum(sfs2d_unfolded._total_per_entry(), pop_ids=['ery', 'par']) #total_per_entry.pop_ids = ['ery', 'par'] dadi.Plotting.plot_single_2d_sfs(total_per_entry, vmin=1) total_per_entry = sfs2d_unfolded._total_per_entry() total_per_entry where_folded_out = total_per_entry > total_samples/2 where_folded_out original_mask = sfs2d_unfolded.mask original_mask pylab.logical_or([True, False, True], [False, False, True]) # get the number of elements along each axis sfs2d_unfolded.shape [slice(None, None, -1) for i in sfs2d_unfolded.shape] matrix = pylab.array([ [1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12] ]) reverse_slice = [slice(None, None, -1) for i in matrix.shape] reverse_slice matrix[reverse_slice] matrix[::-1,::-1] final_mask = pylab.logical_or(original_mask, dadi.Numerics.reverse_array(original_mask)) final_mask ?pylab.where pylab.where(matrix < 6, matrix, 0) # this takes the part of the spectrum that is non-sensical if the derived allele is not known # and sets the rest to 0 print pylab.where(where_folded_out, sfs2d_unfolded, 0) # let's plot the bit of the spectrum that we are going to fold onto the rest: dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(pylab.where(where_folded_out, sfs2d_unfolded, 0)), vmin=1) # now let's reverse this 2D array, i. e. last row first and last element of each row first: _reversed = dadi.Numerics.reverse_array(pylab.where(where_folded_out, sfs2d_unfolded, 0)) _reversed dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(_reversed), vmin=1) # This shall now be added to the original unfolded 2D spectrum. sfs2d_folded = pylab.ma.masked_array(sfs2d_unfolded.data + _reversed) dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(sfs2d_folded), vmin=1) sfs2d_folded.data sfs2d_folded.data[where_folded_out] = 0 sfs2d_folded.data dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(sfs2d_folded), vmin=1) sfs2d_folded.shape where_ambiguous = (total_per_entry == total_samples/2.0) where_ambiguous # this extracts the diagonal values from the UNfolded spectrum and sets the rest to 0 ambiguous = pylab.where(where_ambiguous, sfs2d_unfolded, 0) dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(ambiguous), vmin=1) reversed_ambiguous = dadi.Numerics.reverse_array(ambiguous) dadi.Plotting.plot_single_2d_sfs(dadi.Spectrum(reversed_ambiguous), vmin=1) a = -1.0*ambiguous + 0.5*ambiguous + 0.5*reversed_ambiguous b = -0.5*ambiguous + 0.5*reversed_ambiguous a == b sfs2d_folded += -0.5*ambiguous + 0.5*reversed_ambiguous final_mask = pylab.logical_or(final_mask, where_folded_out) final_mask sfs2d_folded = dadi.Spectrum(sfs2d_folded, mask=final_mask, data_folded=True, pop_ids=['ery', 'par']) pylab.rcParams['figure.figsize'] = [12.0, 8.0] dadi.Plotting.plot_single_2d_sfs(sfs2d_folded, vmin=1) <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 number of unique sites in Location file is around 2100. However, as you can see below,
<ASSISTANT_TASK:> Python Code: ozone_daily['site'][ozone_daily['site'].isin([2778, 2783])] len(ozone_daily['site'].unique()) #this was done once in the beginning to #save data set as ".csv" file. #ozone_daily.to_csv('daily_ozone_obs_1980_2014.csv', sep = ',') locations = pd.read_excel('Location.xlsx') def get_county_site(locations, county = 'Colusa'): county_of_interest = (locations.set_index(['County Name', 'Site']).loc[county]) county_of_interest = county_of_interest.reset_index() county_sites = county_of_interest['Site'] return county_sites colusa_sites = get_county_site(locations).dropna() colusa_daily_ozone = ozone_daily[ozone_daily['site'].isin(colusa_sites)] colusa_daily_ozone = (colusa_daily_ozone.reset_index(). drop('index', axis = 1)) #this also was done only once to save the output as csv file. colusa_daily_ozone.to_csv('colusa_daily_ozone_1980_2014.csv', sep = ',') colusa_daily_ozone.head() colusa_daily_ozone['site'].unique() <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: Get information about code base Step2: The cost is an arbitrary attribute to indicate if the information is retrieved from a wfs query (cost = 1), Step3: Try-out of use cases Step4: Select interpretations in a bbox with selected properties Step5: The property feature methodes listed above are available from the owslib module. These were not adapted for use in pydov. Step6: Select interpretations in a municipality Step7: Get interpretations using info from wfs fields, not available in the standard output dataframe Step8: Visualize results
<ASSISTANT_TASK:> Python Code: %matplotlib inline import os, sys import inspect import pydov from pydov.search.interpretaties import HydrogeologischeStratigrafieSearch ip_hydrogeo = HydrogeologischeStratigrafieSearch() # information about the HydrogeologischeStratigrafie type (In Dutch): print(ip_hydrogeo.get_description()) # information about the available fields for a HydrogeologischeStratigrafie object fields = ip_hydrogeo.get_fields() # print available fields for f in fields.values(): print(f['name']) # print information for a certain field fields['aquifer'] # if an attribute can have several values, these are listed under 'values', e.g. for 'Type_proef': fields['Type_proef'] from pydov.util.location import Within, Box # Get all borehole data in a bounding box (llx, lly, ulx, uly) # the pkey_boring link is not available below, but is in the df df = ip_hydrogeo.search(location=Within(Box(153145, 206930, 153150, 206935))) print(df.head()) # list available query methods methods = [i for i,j in inspect.getmembers(sys.modules['owslib.fes'], inspect.isclass) if 'Property' in i] print(methods) from owslib.fes import PropertyIsGreaterThanOrEqualTo # Get deep boreholes in a bounding box from owslib.fes import PropertyIsEqualTo # the propertyname can be any of the fields of the hydrogeological interpretations object that belong to the wfs source # the literal is always a string, no matter what its definition is in the boring object (string, float...) query = PropertyIsGreaterThanOrEqualTo( propertyname='betrouwbaarheid_interpretatie', literal='goed') df = ip_hydrogeo.search(location=Within(Box(153145, 206930, 153150, 206935)), query=query ) print(df.head()) query = PropertyIsEqualTo(propertyname='gemeente', literal='Aartselaar') df = ip_hydrogeo.search(query=query) print(df.head()) from owslib.fes import And from owslib.fes import PropertyIsEqualTo query = And([PropertyIsEqualTo(propertyname='gemeente', literal='Antwerpen'), PropertyIsEqualTo(propertyname='Type_proef', literal='Boring')] ) df = ip_hydrogeo.search(query=query, ) print(df.head()) # import the necessary modules (not included in the requirements of pydov!) import folium from folium.plugins import MarkerCluster from pyproj import Transformer # convert the coordinates to lat/lon for folium def convert_latlon(x1, y1): transformer = Transformer.from_crs("epsg:31370", "epsg:4326", always_xy=True) x2,y2 = transformer.transform(x1, y1) return x2, y2 df['lon'], df['lat'] = zip(*map(convert_latlon, df['x'], df['y'])) # convert to list loclist = df[['lat', 'lon']].values.tolist() # initialize the Folium map on the centre of the selected locations, play with the zoom until ok# initia fmap = folium.Map(location=[df['lat'].mean(), df['lon'].mean()], zoom_start=12) marker_cluster = MarkerCluster().add_to(fmap) for loc in range(0, len(loclist)): folium.Marker(loclist[loc], popup=df['aquifer'][loc]).add_to(marker_cluster) fmap <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 that we have created a toy example for playing around with the DataFrame, let's print it out in different ways.
<ASSISTANT_TASK:> Python Code: # Note: Do not change this code! import numpy as np import pandas import sys import modin pandas.__version__ modin.__version__ # Implement your answer here. You are also free to play with the size # and shape of the DataFrame, but beware of exceeding your memory! import pandas as pd frame_data = np.random.randint(0, 100, size=(2**10, 2**5)) df = pd.DataFrame(frame_data) # ***** Do not change the code below! It verifies that # ***** the exercise has been done correctly. ***** try: assert df is not None assert frame_data is not None assert isinstance(frame_data, np.ndarray) except: raise AssertionError("Don't change too much of the original code!") assert "modin.pandas" in sys.modules, "Not quite correct. Remember the single line of code change (See above)" import modin.pandas assert pd == modin.pandas, "Remember the single line of code change (See above)" assert hasattr(df, "_query_compiler"), "Make sure that `df` is a modin.pandas DataFrame." print("Success! You only need to change one line of code!") # Print the first 10 lines. df.head(10) # Print the DataFrame. df # Free cell for custom interaction (Play around here!) df.add_prefix("col") df.count() <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 input image is processed in the first convolutional layer using the filter-weights. This results in 16 new images, one for each filter in the convolutional layer. The images are also down-sampled so the image resolution is decreased from 28x28 to 14x14. Step2: The step-size for moving the filter across the input is called the stride. There is a stride for moving the filter horizontally (x-axis) and another stride for moving vertically (y-axis). Step3: This was developed using Python 3.5.2 (Anaconda) and TensorFlow version Step4: Configuration of Neural Network Step5: Load Data Step6: The MNIST data-set has now been loaded and consists of 70,000 images and associated labels (i.e. classifications of the images). The data-set is split into 3 mutually exclusive sub-sets. We will only use the training and test-sets in this tutorial. Step7: The class-labels are One-Hot encoded, which means that each label is a vector with 10 elements, all of which are zero except for one element. The index of this one element is the class-number, that is, the digit shown in the associated image. We also need the class-numbers as integers for the test-set, so we calculate it now. Step8: Data Dimensions Step9: Helper-function for plotting images Step10: Plot a few images to see if data is correct Step11: TensorFlow Graph Step12: Helper-function for creating a new Convolutional Layer Step13: Helper-function for flattening a layer Step14: Helper-function for creating a new Fully-Connected Layer Step15: Placeholder variables Step16: The convolutional layers expect x to be encoded as a 4-dim tensor so we have to reshape it so its shape is instead [num_images, img_height, img_width, num_channels]. Note that img_height == img_width == img_size and num_images can be inferred automatically by using -1 for the size of the first dimension. So the reshape operation is Step17: Next we have the placeholder variable for the true labels associated with the images that were input in the placeholder variable x. The shape of this placeholder variable is [None, num_classes] which means it may hold an arbitrary number of labels and each label is a vector of length num_classes which is 10 in this case. Step18: We could also have a placeholder variable for the class-number, but we will instead calculate it using argmax. Note that this is a TensorFlow operator so nothing is calculated at this point. Step19: Create placeholder var for dropout Step20: Convolutional Layer 1 Step21: Check the shape of the tensor that will be output by the convolutional layer. It is (?, 14, 14, 16) which means that there is an arbitrary number of images (this is the ?), each image is 14 pixels wide and 14 pixels high, and there are 16 different channels, one channel for each of the filters. Step22: Convolutional Layer 2 Step23: Check the shape of the tensor that will be output from this convolutional layer. The shape is (?, 7, 7, 36) where the ? again means that there is an arbitrary number of images, with each image having width and height of 7 pixels, and there are 36 channels, one for each filter. Step24: Flatten Layer Step25: Check that the tensors now have shape (?, 1764) which means there's an arbitrary number of images which have been flattened to vectors of length 1764 each. Note that 1764 = 7 x 7 x 36. Step26: Fully-Connected Layer 1 Step27: Check that the output of the fully-connected layer is a tensor with shape (?, 128) where the ? means there is an arbitrary number of images and fc_size == 128. Step28: Fully-Connected Layer 2 Step29: Predicted Class Step30: The class-number is the index of the largest element. Step31: Cost-function to be optimized Step32: We have now calculated the cross-entropy for each of the image classifications so we have a measure of how well the model performs on each image individually. But in order to use the cross-entropy to guide the optimization of the model's variables we need a single scalar value, so we simply take the average of the cross-entropy for all the image classifications. Step33: Optimization Method Step34: Performance Measures Step35: This calculates the classification accuracy by first type-casting the vector of booleans to floats, so that False becomes 0 and True becomes 1, and then calculating the average of these numbers. Step36: TensorFlow Run Step37: Initialize variables Step38: Helper-function to perform optimization iterations Step39: Function for performing a number of optimization iterations so as to gradually improve the variables of the network layers. In each iteration, a new batch of data is selected from the training-set and then TensorFlow executes the optimizer using those training samples. The progress is printed every 100 iterations. Step40: Helper-function to plot example errors Step41: Helper-function to plot confusion matrix Step42: Helper-function for showing the performance Step43: Performance before any optimization Step44: Performance after 1 optimization iteration Step45: Performance after 100 optimization iterations Step46: Performance after 1000 optimization iterations Step47: Performance after 10,000 optimization iterations Step48: Visualization of Weights and Layers Step49: Helper-function for plotting the output of a convolutional layer Step50: Input Images Step51: Plot an image from the test-set which will be used as an example below. Step52: Plot another example image from the test-set. Step53: Convolution Layer 1 Step54: Applying each of these convolutional filters to the first input image gives the following output images, which are then used as input to the second convolutional layer. Note that these images are down-sampled to 14 x 14 pixels which is half the resolution of the original input image. Step55: The following images are the results of applying the convolutional filters to the second image. Step56: It is difficult to see from these images what the purpose of the convolutional filters might be. It appears that they have merely created several variations of the input image, as if light was shining from different angles and casting shadows in the image. Step57: There are 16 input channels to the second convolutional layer, so we can make another 15 plots of filter-weights like this. We just make one more with the filter-weights for the second channel. Step58: It can be difficult to understand and keep track of how these filters are applied because of the high dimensionality. Step59: And these are the results of applying the filter-weights to the second image. Step60: From these images, it looks like the second convolutional layer might detect lines and patterns in the input images, which are less sensitive to local variations in the original input images.
<ASSISTANT_TASK:> Python Code: from IPython.display import Image Image('images/02_network_flowchart.png') Image('images/02_convolution.png') %matplotlib inline import matplotlib.pyplot as plt import tensorflow as tf import numpy as np from sklearn.metrics import confusion_matrix import time from datetime import timedelta import math tf.__version__ # Convolutional Layer 1. filter_size1 = 5 # Convolution filters are 5 x 5 pixels. num_filters1 = 9 # There are 16 of these filters. # Convolutional Layer 2. filter_size2 = 5 # Convolution filters are 5 x 5 pixels. num_filters2 = 9 # There are 36 of these filters. # Convolutional Layer 2. #filter_size3 = 5 # Convolution filters are 5 x 5 pixels. #num_filters3 = 25 # There are 25 of these filters. # Fully-connected layer. fc_size = 32 # Number of neurons in fully-connected layer. from tensorflow.examples.tutorials.mnist import input_data data = input_data.read_data_sets('data/MNIST/', one_hot=True) print("Size of:") print("- Training-set:\t\t{}".format(len(data.train.labels))) print("- Test-set:\t\t{}".format(len(data.test.labels))) print("- Validation-set:\t{}".format(len(data.validation.labels))) data.test.cls = np.argmax(data.test.labels, axis=1) # We know that MNIST images are 28 pixels in each dimension. img_size = 28 # Images are stored in one-dimensional arrays of this length. img_size_flat = img_size * img_size # Tuple with height and width of images used to reshape arrays. img_shape = (img_size, img_size) # Number of colour channels for the images: 1 channel for gray-scale. num_channels = 1 # Number of classes, one class for each of 10 digits. num_classes = 10 def plot_images(images, cls_true, cls_pred=None): assert len(images) == len(cls_true) == 9 # Create figure with 3x3 sub-plots. fig, axes = plt.subplots(3, 3) fig.subplots_adjust(hspace=0.3, wspace=0.3) for i, ax in enumerate(axes.flat): # Plot image. ax.imshow(images[i].reshape(img_shape), cmap='binary') # Show true and predicted classes. if cls_pred is None: xlabel = "True: {0}".format(cls_true[i]) else: xlabel = "True: {0}, Pred: {1}".format(cls_true[i], cls_pred[i]) # Show the classes as the label on the x-axis. ax.set_xlabel(xlabel) # Remove ticks from the plot. ax.set_xticks([]) ax.set_yticks([]) # Ensure the plot is shown correctly with multiple plots # in a single Notebook cell. plt.show() # Get the first images from the test-set. images = data.test.images[0:9] # Get the true classes for those images. cls_true = data.test.cls[0:9] # Plot the images and labels using our helper-function above. plot_images(images=images, cls_true=cls_true) def new_weights(shape): return tf.Variable(tf.truncated_normal(shape, stddev=0.05)) def new_biases(length): return tf.Variable(tf.constant(0.05, shape=[length])) def new_conv_layer(input, # The previous layer. num_input_channels, # Num. channels in prev. layer. filter_size, # Width and height of each filter. num_filters, # Number of filters. use_pooling=True): # Use 2x2 max-pooling. # Shape of the filter-weights for the convolution. # This format is determined by the TensorFlow API. shape = [filter_size, filter_size, num_input_channels, num_filters] # Create new weights aka. filters with the given shape. weights = new_weights(shape=shape) # Create new biases, one for each filter. biases = new_biases(length=num_filters) # Create the TensorFlow operation for convolution. # Note the strides are set to 1 in all dimensions. # The first and last stride must always be 1, # because the first is for the image-number and # the last is for the input-channel. # But e.g. strides=[1, 2, 2, 1] would mean that the filter # is moved 2 pixels across the x- and y-axis of the image. # The padding is set to 'SAME' which means the input image # is padded with zeroes so the size of the output is the same. layer = tf.nn.conv2d(input=input, filter=weights, strides=[1, 1, 1, 1], padding='SAME') # Add the biases to the results of the convolution. # A bias-value is added to each filter-channel. layer += biases # Use pooling to down-sample the image resolution? if use_pooling: # This is 2x2 max-pooling, which means that we # consider 2x2 windows and select the largest value # in each window. Then we move 2 pixels to the next window. layer = tf.nn.max_pool(value=layer, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # Rectified Linear Unit (ReLU). # It calculates max(x, 0) for each input pixel x. # This adds some non-linearity to the formula and allows us # to learn more complicated functions. layer = tf.nn.relu(layer) # Note that ReLU is normally executed before the pooling, # but since relu(max_pool(x)) == max_pool(relu(x)) we can # save 75% of the relu-operations by max-pooling first. # We return both the resulting layer and the filter-weights # because we will plot the weights later. return layer, weights def flatten_layer(layer): # Get the shape of the input layer. layer_shape = layer.get_shape() # The shape of the input layer is assumed to be: # layer_shape == [num_images, img_height, img_width, num_channels] # The number of features is: img_height * img_width * num_channels # We can use a function from TensorFlow to calculate this. num_features = layer_shape[1:4].num_elements() # Reshape the layer to [num_images, num_features]. # Note that we just set the size of the second dimension # to num_features and the size of the first dimension to -1 # which means the size in that dimension is calculated # so the total size of the tensor is unchanged from the reshaping. layer_flat = tf.reshape(layer, [-1, num_features]) # The shape of the flattened layer is now: # [num_images, img_height * img_width * num_channels] # Return both the flattened layer and the number of features. return layer_flat, num_features def new_fc_layer(input, # The previous layer. num_inputs, # Num. inputs from prev. layer. num_outputs, # Num. outputs. use_relu=True): # Use Rectified Linear Unit (ReLU)? # Create new weights and biases. weights = new_weights(shape=[num_inputs, num_outputs]) biases = new_biases(length=num_outputs) # Calculate the layer as the matrix multiplication of # the input and weights, and then add the bias-values. layer = tf.matmul(input, weights) + biases # Use ReLU? if use_relu: layer = tf.nn.relu(layer) return layer x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x') x_image = tf.reshape(x, [-1, img_size, img_size, num_channels]) y_true = tf.placeholder(tf.float32, shape=[None, 10], name='y_true') y_true_cls = tf.argmax(y_true, dimension=1) keep_prob = tf.placeholder(tf.float32) layer_conv1, weights_conv1 = \ new_conv_layer(input=x_image, num_input_channels=num_channels, filter_size=filter_size1, num_filters=num_filters1, use_pooling=True) layer_conv1 layer_conv2, weights_conv2 = \ new_conv_layer(input=layer_conv1, num_input_channels=num_filters1, filter_size=filter_size2, num_filters=num_filters2, use_pooling=True) layer_conv2 #layer_conv3, weights_conv3 = \ # new_conv_layer(input=layer_conv2, # num_input_channels=num_filters2, # filter_size=filter_size3, # num_filters=num_filters3, # use_pooling=True) #layer_conv3 layer_flat, num_features = flatten_layer(layer_conv2) layer_flat num_features layer_fc1 = new_fc_layer(input=layer_flat, num_inputs=num_features, num_outputs=fc_size, use_relu=True) layer_fc1 layer_dropout1 = tf.nn.dropout(layer_fc1, keep_prob) #layer_fc2 = new_fc_layer(input=layer_dropout1, # num_inputs=fc_size, # num_outputs=fc_size, # use_relu=True) #layer_dropout2 = tf.nn.dropout(layer_fc2, keep_prob) layer_fc3 = new_fc_layer(input=layer_dropout1, num_inputs=fc_size, num_outputs=num_classes, use_relu=False) layer_fc3 y_pred = tf.nn.softmax(layer_fc3) y_pred_cls = tf.argmax(y_pred, dimension=1) cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc3, labels=y_true) cost = tf.reduce_mean(cross_entropy) optimizer = tf.train.AdamOptimizer(learning_rate=1e-3).minimize(cost) correct_prediction = tf.equal(y_pred_cls, y_true_cls) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) session = tf.Session() session.run(tf.initialize_all_variables()) train_batch_size = 64 print(data.train) # Counter for total number of iterations performed so far. total_iterations = 0 def optimize(num_iterations): # Ensure we update the global variable rather than a local copy. global total_iterations # Start-time used for printing time-usage below. start_time = time.time() for i in range(total_iterations, total_iterations + num_iterations): # Get a batch of training examples. # x_batch now holds a batch of images and # y_true_batch are the true labels for those images. x_batch, y_true_batch = data.train.next_batch(train_batch_size) # Put the batch into a dict with the proper names # for placeholder variables in the TensorFlow graph. feed_dict_train = {x: x_batch, y_true: y_true_batch, keep_prob: 0.5} # Run the optimizer using this batch of training data. # TensorFlow assigns the variables in feed_dict_train # to the placeholder variables and then runs the optimizer. session.run(optimizer, feed_dict=feed_dict_train) # Print status every 100 iterations. if i % 100 == 0: # Calculate the accuracy on the training-set. acc = session.run(accuracy, feed_dict=feed_dict_train) # Message for printing. msg = "Optimization Iteration: {0:>6}, Training Accuracy: {1:>6.1%}" # Print it. print(msg.format(i + 1, acc)) # Update the total number of iterations performed. total_iterations += num_iterations # Ending time. end_time = time.time() # Difference between start and end-times. time_dif = end_time - start_time # Print the time-usage. print("Time usage: " + str(timedelta(seconds=int(round(time_dif))))) def plot_example_errors(cls_pred, correct): # This function is called from print_test_accuracy() below. # cls_pred is an array of the predicted class-number for # all images in the test-set. # correct is a boolean array whether the predicted class # is equal to the true class for each image in the test-set. # Negate the boolean array. incorrect = (correct == False) # Get the images from the test-set that have been # incorrectly classified. images = data.test.images[incorrect] # Get the predicted classes for those images. cls_pred = cls_pred[incorrect] # Get the true classes for those images. cls_true = data.test.cls[incorrect] # Plot the first 9 images. plot_images(images=images[0:9], cls_true=cls_true[0:9], cls_pred=cls_pred[0:9]) def plot_confusion_matrix(cls_pred): # This is called from print_test_accuracy() below. # cls_pred is an array of the predicted class-number for # all images in the test-set. # Get the true classifications for the test-set. cls_true = data.test.cls # Get the confusion matrix using sklearn. cm = confusion_matrix(y_true=cls_true, y_pred=cls_pred) # Print the confusion matrix as text. print(cm) # Plot the confusion matrix as an image. plt.matshow(cm) # Make various adjustments to the plot. plt.colorbar() tick_marks = np.arange(num_classes) plt.xticks(tick_marks, range(num_classes)) plt.yticks(tick_marks, range(num_classes)) plt.xlabel('Predicted') plt.ylabel('True') # Ensure the plot is shown correctly with multiple plots # in a single Notebook cell. plt.show() # Split the test-set into smaller batches of this size. test_batch_size = 256 def print_test_accuracy(show_example_errors=False, show_confusion_matrix=False): # Number of images in the test-set. num_test = len(data.test.images) # Allocate an array for the predicted classes which # will be calculated in batches and filled into this array. cls_pred = np.zeros(shape=num_test, dtype=np.int) # Now calculate the predicted classes for the batches. # We will just iterate through all the batches. # There might be a more clever and Pythonic way of doing this. # The starting index for the next batch is denoted i. i = 0 while i < num_test: # The ending index for the next batch is denoted j. j = min(i + test_batch_size, num_test) # Get the images from the test-set between index i and j. images = data.test.images[i:j, :] # Get the associated labels. labels = data.test.labels[i:j, :] # Create a feed-dict with these images and labels. feed_dict = {x: images, y_true: labels, keep_prob:1} # Calculate the predicted class using TensorFlow. cls_pred[i:j] = session.run(y_pred_cls, feed_dict=feed_dict) # Set the start-index for the next batch to the # end-index of the current batch. i = j # Convenience variable for the true class-numbers of the test-set. cls_true = data.test.cls # Create a boolean array whether each image is correctly classified. correct = (cls_true == cls_pred) # Calculate the number of correctly classified images. # When summing a boolean array, False means 0 and True means 1. correct_sum = correct.sum() # Classification accuracy is the number of correctly classified # images divided by the total number of images in the test-set. acc = float(correct_sum) / num_test # Print the accuracy. msg = "Accuracy on Test-Set: {0:.1%} ({1} / {2})" print(msg.format(acc, correct_sum, num_test)) # Plot some examples of mis-classifications, if desired. if show_example_errors: print("Example errors:") plot_example_errors(cls_pred=cls_pred, correct=correct) # Plot the confusion matrix, if desired. if show_confusion_matrix: print("Confusion Matrix:") plot_confusion_matrix(cls_pred=cls_pred) print_test_accuracy() optimize(num_iterations=1) print_test_accuracy() optimize(num_iterations=99) # We already performed 1 iteration above. print_test_accuracy(show_example_errors=True) optimize(num_iterations=900) # We performed 100 iterations above. print_test_accuracy(show_example_errors=True) optimize(num_iterations=9000) # We performed 1000 iterations above. print_test_accuracy(show_example_errors=True, show_confusion_matrix=True) def plot_conv_weights(weights, input_channel=0): # Assume weights are TensorFlow ops for 4-dim variables # e.g. weights_conv1 or weights_conv2. # Retrieve the values of the weight-variables from TensorFlow. # A feed-dict is not necessary because nothing is calculated. w = session.run(weights) # Get the lowest and highest values for the weights. # This is used to correct the colour intensity across # the images so they can be compared with each other. w_min = np.min(w) w_max = np.max(w) # Number of filters used in the conv. layer. num_filters = w.shape[3] # Number of grids to plot. # Rounded-up, square-root of the number of filters. num_grids = math.ceil(math.sqrt(num_filters)) # Create figure with a grid of sub-plots. fig, axes = plt.subplots(num_grids, num_grids) # Plot all the filter-weights. for i, ax in enumerate(axes.flat): # Only plot the valid filter-weights. if i<num_filters: # Get the weights for the i'th filter of the input channel. # See new_conv_layer() for details on the format # of this 4-dim tensor. img = w[:, :, input_channel, i] # Plot image. ax.imshow(img, vmin=w_min, vmax=w_max, interpolation='nearest', cmap='seismic') # Remove ticks from the plot. ax.set_xticks([]) ax.set_yticks([]) # Ensure the plot is shown correctly with multiple plots # in a single Notebook cell. plt.show() def plot_conv_layer(layer, image): # Assume layer is a TensorFlow op that outputs a 4-dim tensor # which is the output of a convolutional layer, # e.g. layer_conv1 or layer_conv2. # Create a feed-dict containing just one image. # Note that we don't need to feed y_true because it is # not used in this calculation. feed_dict = {x: [image], keep_prob: 1} # Calculate and retrieve the output values of the layer # when inputting that image. values = session.run(layer, feed_dict=feed_dict) # Number of filters used in the conv. layer. num_filters = values.shape[3] # Number of grids to plot. # Rounded-up, square-root of the number of filters. num_grids = math.ceil(math.sqrt(num_filters)) # Create figure with a grid of sub-plots. fig, axes = plt.subplots(num_grids, num_grids) # Plot the output images of all the filters. for i, ax in enumerate(axes.flat): # Only plot the images for valid filters. if i<num_filters: # Get the output image of using the i'th filter. # See new_conv_layer() for details on the format # of this 4-dim tensor. img = values[0, :, :, i] # Plot image. ax.imshow(img, interpolation='nearest', cmap='binary') # Remove ticks from the plot. ax.set_xticks([]) ax.set_yticks([]) # Ensure the plot is shown correctly with multiple plots # in a single Notebook cell. plt.show() def plot_image(image): plt.imshow(image.reshape(img_shape), interpolation='nearest', cmap='binary') plt.show() image1 = data.test.images[0] plot_image(image1) image2 = data.test.images[13] plot_image(image2) plot_conv_weights(weights=weights_conv1) plot_conv_layer(layer=layer_conv1, image=image1) plot_conv_layer(layer=layer_conv1, image=image2) plot_conv_weights(weights=weights_conv2, input_channel=0) plot_conv_weights(weights=weights_conv2, input_channel=1) plot_conv_layer(layer=layer_conv2, image=image1) plot_conv_layer(layer=layer_conv2, image=image2) #plot_conv_layer(layer=layer_conv3, image=image1) #plot_conv_layer(layer=layer_conv3, image=image2) # This has been commented out in case you want to modify and experiment # with the Notebook without having to restart it. # session.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: Let's also load the plotting and numerical libraries so we have them ready for visualization later on. Step2: Now, we load the MPI libraries into the engine namespaces, and do a simple printing of their MPI rank information to verify that all nodes are operational and they match our cluster's real capacity. Step4: We write a utility that reorders a list according to the mpi ranks of the engines, since all gather operations will return data in engine id order, not in MPI rank order. We'll need this later on when we want to reassemble in IPython data structures coming from all the engines Step5: We now define a local (to this notebook) plotting function that fetches data from the engines' global namespace. Once it has retrieved the current state of the relevant variables, it produces and returns a figure
<ASSISTANT_TASK:> Python Code: from ipyparallel import Client, error cluster = Client() view = cluster[:] %matplotlib inline import numpy as np import matplotlib.pyplot as plt %%px # MPI initialization, library imports and sanity checks on all engines from mpi4py import MPI # Load data publication API so engines can send data to notebook client from ipykernel.datapub import publish_data import numpy as np import time mpi = MPI.COMM_WORLD bcast = mpi.bcast barrier = mpi.barrier rank = mpi.rank size = mpi.size print("MPI rank: %i/%i" % (mpi.rank,mpi.size)) ranks = view['rank'] engine_mpi = np.argsort(ranks) def mpi_order(seq): Return elements of a sequence ordered by MPI rank. The input sequence is assumed to be ordered by engine ID. return [seq[x] for x in engine_mpi] mpi_order(view.apply_sync(lambda : mpi.rank)) %%px --noblock import numpy as np from ipykernel.datapub import publish_data N = 1000 stride = N // size x = np.linspace(0, 10, N)[stride * rank:stride*(rank+1)] publish_data({'x': x}) for i in range(10): y = np.sin(x * i) publish_data({'y': y, 'i': i}) time.sleep(1) ar = _ def stitch_data(ar, key): data = mpi_order(ar.data) parts = [ d[key] for d in data ] return np.concatenate(parts) ar.wait(1) while not ar.ready(): clear_output(wait=True) x = stitch_data(ar, 'x') y = stitch_data(ar, 'y') plt.plot(x, y) plt.show() ar.wait(1) ar.get() <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 source is by default a Ricker wavelet with a central frequency of seis.csts['f0'], so 20 Hz here. We then generate a synthetic shot, which will serve as the observed data $\pmb{d}^0$. Step2: We can then change the frequency of the source to 15 Hz and recompute the data with the bad source signature. Step3: If we look at the observed data and the modeled data, they indeed have a different source signature. Step4: We can then call the source inversion routine of SeisCL, which needs the source to be updated src2, the observed data data and the modelled data data2. If we provide a srcid, it will overwrite the source function in seis.src_all for this srcid with the new wavelet. Step5: The source function contained in seis.src_all is now the corrected wavelet, which is the same as the initial, that is a Ricker wavelet of 20 Hz.
<ASSISTANT_TASK:> Python Code: %matplotlib inline from SeisCL import SeisCL import matplotlib.pyplot as plt import numpy as np seis = SeisCL() # Constants for the modeling N = 200 seis.N = np.array([N, N]) seis.ND = 2 seis.dt = 0.25e-03 seis.NT = 1000 seis.dh = dh= 2 seis.f0 = 20 seis.freesurf = 0 # Source and receiver positions sx = N//2 * dh sy = 0 sz = N//2 * dh gx = np.arange(N//4 * dh, (N - N//4)*dh, dh) gy = gx * 0 gz = gx * 0 + N//4*dh gsid = gz * 0 gid = np.arange(0, len(gz)) seis.src_pos_all = np.stack([[sx], [sy], [sz], [0], [0]], axis=0) seis.rec_pos_all = np.stack([gx, gy, gz, gsid, gid, gx * 0, gx * 0, gx * 0], axis=0) # We start with a simple model vp_a = np.zeros(seis.N) + 3500 vs_a = np.zeros(seis.N) + 2000 rho_a = np.zeros(seis.N) + 2000 seis.set_forward(seis.src_pos_all[3, :], {"vp": vp_a, "rho": rho_a, "vs": vs_a}, withgrad=False) seis.execute() data = seis.read_data() src1 = seis.src_all * 1.0 seis.f0 = 15 seis.src_all = None seis.set_forward(seis.src_pos_all[3, :], {"vp": vp_a, "rho": rho_a, "vs": vs_a}, withgrad=False) seis.execute() data2 = seis.read_data() src2 = seis.src_all * 1.0 fig, ax = plt.subplots(1, 2) ax[0].imshow(data2[0], aspect='auto', cmap=plt.get_cmap('Greys')) ax[0].set_title("Observed data") ax[1].imshow(data[0], aspect='auto', cmap=plt.get_cmap('Greys')) ax[1].set_title("Data with wrong wavelet") plt.show() src3 = seis.invert_source(src2, data[0], data2[0], srcid=0) plt.plot(src1, label="true wavelet") plt.plot(src2, label="initial wavelet") plt.plot(seis.src_all[:,0], label="inverted wavelet") plt.legend() 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: Problem 1b Step2: Problem 1c Step3: Problem 1d Step4: An important, but necessary, aside โ€“โ€“ Step5: The common Fourier pairs are especially useful in light of the convolution theorem. Fourier transforms convert convolutions into point-wise products. We define a convolution as Step6: Sampling a signal directly at the Nyquist frequency results in a lack of any variability. But does this just mean that $f_\mathrm{Ny}$ is special? What happens at $f > f_\mathrm{Ny}$? Step7: From the plot the signal is clearly variable (unlike when $f = f_\mathrm{Ny}$). However, there are fewer than 2 observations per cycle. Step8: The observations are identical! Here is what you need to remember about the Nyquist frequency Step9: Problem 3b Step10: Problem 3c Step11: Problem 3d Step12: Problem 3e Step13: Problem 3f Step14: Congratulations Step15: Problem 4) Other Considerations and Faster Implementations Step16: Unlike ls_periodogram, LombScargle effectively takes no time to run on the simulated data. Step17: There are many choices regarding the calculation of the periodogram, so read the docs. Step18: We can see that the best fit model doesn't match the signal in the case where we do not allow a floating mean. Step19: Window Functions Step20: Problem 4e Step21: Interestingly, there are very strong peaks in the data at $P \approx 3\,\mathrm{d} \;\&\; 365\,\mathrm{d}$. Step22: Uncertainty on the best-fit period Step23: Problem 5b Step24: Problem 5c Step25: Herein lies a fundamental issue regarding the LS periodogram Step26: One way to combat this very specific issue is to include more Fourier terms at the harmonic of the best fit period. This is easy to implement in LombScargle with the nterms keyword. [Though always be weary of adding degrees of freedom to a model, especially at the large pipeline level of analysis.] Step27: Interestingly, for the $n=2, 3, 4$ harmonics, it appears as though we get the period that we have visually confirmed. However, by $n=5$ harmonics we no longer get a reasonable answer. Again - be very careful about adding harmonics, especially in large analysis pipelines. Step28: This example also shows why it is somewhat strange to provide an uncertainty with a LS best-fit period. Errors tend to be catastrophic, and not some small fractional percentage, with the LS periodogram.
<ASSISTANT_TASK:> Python Code: def gen_periodic_data(x, period=1, amplitude=1, phase=0, noise=0): '''Generate periodic data given the function inputs y = A*cos(x/p - phase) + noise Parameters ---------- x : array-like input values to evaluate the array period : float (default=1) period of the periodic signal amplitude : float (default=1) amplitude of the periodic signal phase : float (default=0) phase offset of the periodic signal noise : float (default=0) variance of the noise term added to the periodic signal Returns ------- y : array-like Periodic signal evaluated at all points x ''' y = amplitude*np.sin(2*np.pi*x/(period) - phase) + np.random.normal(0, np.sqrt(noise), size=len(x)) return y x = # complete y = gen_periodic_data( # complete fig, ax = plt.subplots() ax.scatter( # complete # complete # complete fig.tight_layout() def phase_plot(x, y, period, y_unc = 0.0): '''Create phase-folded plot of input data x, y Parameters ---------- x : array-like data values along abscissa y : array-like data values along ordinate period : float period to fold the data y_unc : array-like uncertainty of the ''' phases = (x/period) % 1 if type(y_unc) == float: y_unc = np.zeros_like(x) plot_order = np.argsort(phases) fig, ax = plt.subplots() ax.errorbar(phases[plot_order], y[plot_order], y_unc[plot_order], fmt='o', mec="0.2", mew=0.1) ax.set_xlabel("phase") ax.set_ylabel("signal") fig.tight_layout() phase_plot( # complete fourier_pairs_plot() x = # complete y = # complete x_signal = # complete y_signal = # complete fig, ax = plt.subplots() ax.scatter( # complete ax.plot( # complete fig.tight_layout() x = # complete y = # complete x_signal = # complete y_signal = # complete fig, ax = plt.subplots() ax.scatter( # complete ax.plot( # complete fig.tight_layout() x = # complete y = # complete x_signal = # complete y_signal = # complete # complete # complete # complete # complete def chi2( # complete # complete # complete # complete from scipy.optimize import minimize def min_chi2( # complete # complete # complete def ls_periodogram( # complete psd = np.empty_like(f_grid) chi2_0 = # complete for f_num, f in enumerate(f_grid): psd[f_num] = # complete return psd np.random.seed(23) # calculate the periodogram x = # complete y = # complete y_unc = # complete f_grid = # complete psd_ls = # complete # plot the periodogram fig, ax = plt.subplots() ax.plot( # complete # complete # complete fig.tight_layout() # calculate the periodogram f_grid = # complete psd_ls = # complete # plot the periodogram fig,ax = plt.subplots() ax.plot(# complete # complete # complete fig.tight_layout() print("The best fit period is: {:.4f}".format( # complete phase_plot( # complete f_min = # complete f_max = # complete delta_f = # complete f_grid = np.arange( # complete print("{:d} grid points are needed to sample the periodogram".format( # complete from astropy.stats import LombScargle frequency, power = LombScargle(x, y, y_unc).autopower() fig, ax = plt.subplots() ax.plot( # complete # complete # complete # complete fig.tight_layout() # complete freq_no_mean, power_no_mean = LombScargle( # complete freq_fit_mean, power_fit_mean = LombScargle( # complete fig, (ax1, ax2) = plt.subplots(2, 1, sharex=True) ax1.plot( # complete ax2.plot( # complete ax1.set_xlim(0,15) fig.tight_layout() fit_mean_model = LombScargle(x[bright], y[bright], y_unc[bright], fit_mean=True).model(np.linspace(0,10,1000), freq_fit_mean[np.argmax(power_fit_mean)]) no_mean_model = LombScargle(x[bright], y[bright], y_unc[bright], fit_mean=False).model(np.linspace(0,10,1000), freq_no_mean[np.argmax(power_no_mean)]) fig, ax = plt.subplots() ax.errorbar(x[bright], y[bright], y_unc[bright], fmt='o', label='data') ax.plot(np.linspace(0,10,1000), fit_mean_model, label='fit mean') ax.plot(np.linspace(0,10,1000), no_mean_model, label='no mean') ax.set_xlabel('x') ax.set_ylabel('y') ax.legend() fig.tight_layout() # set up simulated observations t_obs = np.arange(0, 10*365, 3) # 3d cadence # complete # complete # complete y = gen_periodic_data( # complete # complete fig, ax = plt.subplots() ax.errorbar( # complete ax.set_xlabel("Time (d)") ax.set_ylabel("Flux (arbitrary units)") ls = LombScargle( # complete freq_window, power_window = # complete fig, ax = plt.subplots() ax.plot( # complete ax.set_ylabel("Power") ax.set_xlabel("Period (d)") ax.set_xlim(0,500) axins = plt.axes([.2, .65, .5, .2]) axins.plot( # complete axins.set_xlim(0,5) ls = LombScargle( # complete frequency, power = # complete fig, (ax,ax2) = plt.subplots(2,1, sharex=True) ax.plot( # complete ax.set_ylabel("Power") ax.set_ylim(0,1) ax2.plot( # complete ax2.set_ylabel("Power") ax2.set_xlabel("Period (d)") ax2.set_xlim(0,10) fig.tight_layout() data = # complete fig, ax = plt.subplots() ax.errorbar( # complete ax.set_xlabel('HJD (d)') ax.set_ylabel('V (mag)') ax.set_ylim(ax.get_ylim()[::-1]) fig.tight_layout() frequency, power = # complete # complete fig,ax = plt.subplots() ax.plot(# complete ax.set_ylabel("Power") ax.set_xlabel("Period (d)") ax.set_xlim(0, 800) axins = plt.axes([.25, .55, .6, .3]) axins.plot( # complete axins.set_xlim(0,5) fig.tight_layout() # plot the phase folded light curve phase_plot( # complete phase_plot( # complete fig, ax = plt.subplots() ax.errorbar(data['hjd']/ls_period % 1, data['mag'], data['mag_unc'], fmt='o', zorder=-1) ax.plot(np.linspace(0,1,1000), LombScargle(data['hjd'],data['mag'], data['mag_unc']).model(np.linspace(0,1,1000)*ls_period, 1/ls_period) ) ax.set_xlabel('Phase') ax.set_ylabel('V (mag)') ax.set_ylim(ax.get_ylim()[::-1]) fig.tight_layout() for i in np.arange(1,6): frequency, power = # complete # complete print('For {:d} harmonics, P_LS = {:.8f}'.format( # complete best_period = 0.73508568 fig, ax = plt.subplots() ax.errorbar((data['hjd'])/best_period % 1, data['mag'], data['mag_unc'], fmt='o',zorder=-1) ax.plot(np.linspace(0,1,1000), LombScargle(data['hjd'],data['mag'], data['mag_unc'], nterms=4).model(np.linspace(0,1,1000)*best_period, 1/best_period) ) ax.set_xlabel('Phase') ax.set_ylabel('V (mag)') ax.set_ylim(ax.get_ylim()[::-1]) fig.tight_layout() def fourier_pairs_plot(): fig, ax = plt.subplots(4, 2, figsize=(10, 6)) fig.subplots_adjust(left=0.04, right=0.98, bottom=0.02, top=0.95, hspace=0.3, wspace=0.2) x = np.linspace(-5, 5, 1000) for axi in ax.flat: axi.xaxis.set_major_formatter(plt.NullFormatter()) axi.yaxis.set_major_formatter(plt.NullFormatter()) # draw center line axi.axvline(0, linestyle='dotted', color='gray') axi.axhline(0, linestyle='dotted', color='gray') style_re = dict(linestyle='solid', color='k', linewidth=2) style_im = dict(linestyle='solid', color='gray', linewidth=2) text_style = dict(size=14, color='gray') # sine -> delta ax[0, 0].plot(x, np.cos(x),**style_re) ax[0, 0].set(xlim=(-5, 5), ylim=(-1.2, 1.2)) ax[0, 0].annotate('', (-np.pi, 0), (np.pi, 0), arrowprops=dict(arrowstyle='|-|', color='gray')) ax[0, 0].text(0, 0, '$1/f_0$', ha='center', va='bottom', **text_style) ax[0, 0].set_title('Sinusoid') ax[0, 1].plot([-5, 2, 2, 2, 5], [0, 0, 1, 0, 0], **style_re) ax[0, 1].plot([-5, -2, -2, -2, 5], [0, 0, 1, 0, 0], **style_re) ax[0, 1].set(xlim=(-5, 5), ylim=(-0.2, 1.2)) ax[0, 1].annotate('', (0, 0.4), (2, 0.4), arrowprops=dict(arrowstyle='<-', color='gray')) ax[0, 1].annotate('', (0, 0.4), (-2, 0.4), arrowprops=dict(arrowstyle='<-', color='gray')) ax[0, 1].text(1, 0.45, '$+f_0$', ha='center', va='bottom', **text_style) ax[0, 1].text(-1, 0.45, '$-f_0$', ha='center', va='bottom', **text_style) ax[0, 1].set_title('Delta Functions') # gaussian -> gaussian ax[1, 0].plot(x, np.exp(-(2 * x) ** 2), **style_re) ax[1, 0].set(xlim=(-5, 5), ylim=(-0.2, 1.2)) ax[1, 0].annotate('', (0, 0.35), (0.6, 0.35), arrowprops=dict(arrowstyle='<-', color='gray')) ax[1, 0].text(0, 0.4, '$\sigma$', ha='center', va='bottom', **text_style) ax[1, 0].set_title('Gaussian') ax[1, 1].plot(x, np.exp(-(x / 2) ** 2), **style_re) ax[1, 1].set(xlim=(-5, 5), ylim=(-0.2, 1.2)) ax[1, 1].annotate('', (0, 0.35), (2, 0.35), arrowprops=dict(arrowstyle='<-', color='gray')) ax[1, 1].text(0, 0.4, '$(2\pi\sigma)^{-1}$', ha='center', va='bottom', **text_style) ax[1, 1].set_title('Gaussian') # top hat -> sinc ax[2, 0].plot([-2, -1, -1, 1, 1, 2], [0, 0, 1, 1, 0, 0], **style_re) ax[2, 0].set(xlim=(-2, 2), ylim=(-0.3, 1.2)) ax[2, 0].annotate('', (-1, 0.5), (1, 0.5), arrowprops=dict(arrowstyle='<->', color='gray')) ax[2, 0].text(0.0, 0.5, '$T$', ha='center', va='bottom', **text_style) ax[2, 0].set_title('Top Hat') ax[2, 1].plot(x, np.sinc(x), **style_re) ax[2, 1].set(xlim=(-5, 5), ylim=(-0.3, 1.2)) ax[2, 1].annotate('', (-1, 0), (1, 0), arrowprops=dict(arrowstyle='<->', color='gray')) ax[2, 1].text(0.0, 0.0, '$2/T$', ha='center', va='bottom', **text_style) ax[2, 1].set_title('Sinc') # comb -> comb ax[3, 0].plot([-5.5] + sum((3 * [i] for i in range(-5, 6)), []) + [5.5], [0] + 11 * [0, 1, 0] + [0], **style_re) ax[3, 0].set(xlim=(-5.5, 5.5), ylim=(-0.2, 1.2)) ax[3, 0].annotate('', (0, 0.5), (1, 0.5), arrowprops=dict(arrowstyle='<->', color='gray')) ax[3, 0].text(0.5, 0.6, '$T$', ha='center', va='bottom', **text_style) ax[3, 0].set_title('Dirac Comb') ax[3, 1].plot([-5.5] + sum((3 * [i] for i in range(-5, 6)), []) + [5.5], [0] + 11 * [0, 1, 0] + [0], **style_re) ax[3, 1].set(xlim=(-2.5, 2.5), ylim=(-0.2, 1.2)); ax[3, 1].annotate('', (0, 0.5), (1, 0.5), arrowprops=dict(arrowstyle='<->', color='gray')) ax[3, 1].text(0.5, 0.6, '$1/T$', ha='center', va='bottom', **text_style) ax[3, 1].set_title('Dirac Comb') for i, letter in enumerate('abcd'): ax[i, 0].set_ylabel('({0})'.format(letter), rotation=0) # Draw arrows between pairs of axes for i in range(4): left = ax[i, 0].bbox.inverse_transformed(fig.transFigure).bounds right = ax[i, 1].bbox.inverse_transformed(fig.transFigure).bounds x = 0.5 * (left[0] + left[2] + right[0]) y = left[1] + 0.5 * left[3] fig.text(x, y, r'$\Longleftrightarrow$', ha='center', va='center', size=30) <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: PageCount API Step2: Summing up accross mobile-app and mobile-site for PageViews into a single access type called 'mobile'. Also, grouping by year, month and accessTypes to get the results Step3: Generating the final CSV Data frame used for visualization!! Step4: Plotting the time series Visualization
<ASSISTANT_TASK:> Python Code: import requests import pandas endpoint = 'https://wikimedia.org/api/rest_v1/metrics/pageviews/aggregate/{project}/{access}/{agent}/{granularity}/{start}/{end}' headers={'User-Agent' : 'https://github.com/r1rajiv92', 'From' : 'rajiv92@uw.edu'} yearMonthCombinations = { '2015' : [ 7, 8, 9, 10, 11, 12], '2016' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2017' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9] } for accessType in [ 'desktop', 'mobile-web', 'mobile-app' ]: for year in range(2015, 2018): for month in yearMonthCombinations[str(year)]: if int(month / 10) == 0: startMonth = ''.join( [ '0', str(month) ] ) startParam = ''.join([ str(year), startMonth, '0100' ]) if int((month+1) / 10) == 0: endParam = ''.join([ str(year), '0', str(month+1), '0100' ]) else: endParam = ''.join([ str(year), str(month+1), '0100' ]) else: startMonth = str(month) startParam = ''.join([ str(year), startMonth, '0100' ]) endParam = ''.join([ str(year), str(month+1), '0100' ]) if month + 1 == 13: endParam = ''.join( [str(year+1), '01', '0100']) params = {'project' : 'en.wikipedia.org', 'access' : accessType, 'agent' : 'user', 'granularity' : 'monthly', 'start' : startParam, 'end' : endParam } api_call = requests.get(endpoint.format(**params)) response = api_call.json() for result in response['items']: result['year'] = str(year) result['month'] = startMonth if 'PageViewDataFrame' in locals(): PageViewDataFrame = pandas.concat([ PageViewDataFrame, pandas.DataFrame.from_dict(response['items']) ]) else: PageViewDataFrame = pandas.DataFrame.from_dict(response['items']) endpoint = 'https://wikimedia.org/api/rest_v1/metrics/legacy/pagecounts/aggregate/{project}/{access-site}/{granularity}/{start}/{end}' headers={'User-Agent' : 'https://github.com/r1rajiv92', 'From' : 'rajiv92@uw.edu'} yearMonthCombinations = { '2008' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2009' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2010' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2011' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2012' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2013' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2014' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2015' : [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], '2016' : [ 1, 2, 3, 4, 5, 6, 7] } for accessType in [ 'desktop-site', 'mobile-site' ]: for year in range(2008, 2017): for month in yearMonthCombinations[str(year)]: if int(month / 10) == 0: startMonth = ''.join( [ '0', str(month) ] ) startParam = ''.join([ str(year), startMonth, '0100' ]) if int((month+1) / 10) == 0: endParam = ''.join([ str(year), '0', str(month+1), '0100' ]) else: endParam = ''.join([ str(year), str(month+1), '0100' ]) else: startMonth = str(month) startParam = ''.join([ str(year), startMonth, '0100' ]) endParam = ''.join([ str(year), str(month+1), '0100' ]) if month + 1 == 13: endParam = ''.join( [str(year+1), '01', '0100']) params = {'project' : 'en.wikipedia.org', 'access-site' : accessType, 'granularity' : 'monthly', 'start' : startParam, 'end' : endParam } api_call = requests.get(endpoint.format(**params)) response = api_call.json() if 'items' in response.keys(): for result in response['items']: result['year'] = str(year) result['month'] = startMonth else: print('Page Count Data Missing for', accessType, 'on', month, year ) continue if 'PageCountDataFrame' in locals(): PageCountDataFrame = pandas.concat([ PageCountDataFrame, pandas.DataFrame.from_dict(response['items']) ]) else: PageCountDataFrame = pandas.DataFrame.from_dict(response['items']) PageViewDataFrame.loc[PageViewDataFrame.access != 'desktop', 'access'] = 'mobile' PageCountDataFrame['access'] = "desktop" PageCountDataFrame.loc[PageCountDataFrame['access-site'] != 'desktop-site', 'access'] = 'mobile' pageCounts = pandas.DataFrame( PageCountDataFrame.groupby(['year', 'month', 'access'])['count'].sum().reset_index() ) pageViews = pandas.DataFrame( PageViewDataFrame.groupby(['year', 'month', 'access'])['views'].sum().reset_index() ) finalCSVDataFrame = pandas.DataFrame( columns = ['year', 'month', 'pagecount_all_views', 'pagecount_desktop_views', 'pagecount_mobile_views', 'pageview_all_views', 'pageview_desktop_views', 'pageview_mobile_views' ] ) for year in range( 2008, 2018): for month in range(1,13): if year == 2017 and month > 9: continue else: if month < 9: monthString = ''.join(['0', str(month)]) pagecount_desktop_views = pageCounts[(pageCounts['year'] == str(year)) & (pageCounts['month'] == monthString) & (pageCounts['access'] == 'desktop' )] if len(pagecount_desktop_views) != 0: pagecount_desktop_views = int(pagecount_desktop_views['count']) else: pagecount_desktop_views = 0 pagecount_mobile_views = pageCounts[(pageCounts['year'] == str(year)) & (pageCounts['month'] == monthString) & (pageCounts['access'] == 'mobile' )] if len(pagecount_mobile_views) != 0: pagecount_mobile_views = int(pagecount_mobile_views['count']) else: pagecount_mobile_views = 0 pagecount_all_views = pagecount_desktop_views + pagecount_mobile_views pageview_desktop_views = pageViews[(pageViews['year'] == str(year)) & (pageViews['month'] == monthString) & (pageViews['access'] == 'desktop' )] if len(pageview_desktop_views) != 0: pageview_desktop_views = int(pageview_desktop_views['views']) else: pageview_desktop_views = 0 pageview_mobile_views = pageViews[(pageViews['year'] == str(year)) & (pageViews['month'] == monthString) & (pageViews['access'] == 'mobile' )] if len(pageview_mobile_views) != 0: pageview_mobile_views = int(pageview_mobile_views['views']) else: pageview_mobile_views = 0 pageview_all_views = pageview_desktop_views + pageview_mobile_views finalCSVDataFrame = finalCSVDataFrame.append( {'year': int(year), 'month': int(month), 'pagecount_all_views': int(pagecount_all_views), 'pagecount_desktop_views': int(pagecount_desktop_views), 'pagecount_mobile_views': int(pagecount_mobile_views), 'pageview_all_views': int(pageview_all_views), 'pageview_desktop_views': int(pageview_desktop_views), 'pageview_mobile_views': int(pageview_mobile_views) }, ignore_index=True ) finalCSVDataFrame finalCSVDataFrame.to_csv('finalCSV.csv') import matplotlib.pyplot as plt dates = pandas.date_range('2008-01', '2017-10',freq='M') plt.plot(dates, finalCSVDataFrame["pagecount_all_views"]/1000000, label = " All PageCounts", color = "black", linewidth = 0.5) plt.plot(dates, finalCSVDataFrame["pagecount_desktop_views"]/1000000, label = "Desktop PageCounts", color = "blue", linewidth = 0.5) plt.plot(dates, finalCSVDataFrame["pagecount_mobile_views"]/1000000, label = "Mobile PageCounts", color = "brown", linewidth = 0.5) plt.plot(dates, finalCSVDataFrame["pageview_all_views"]/1000000, label = " All PageViews", color = "black", linewidth = 2) plt.plot(dates, finalCSVDataFrame["pageview_desktop_views"]/1000000, label = "Desktop PageViews", color = "blue", linewidth = 2) plt.plot(dates, finalCSVDataFrame["pageview_mobile_views"]/1000000, label = "Mobile PageViews", color = "brown", linewidth = 2) fig_size = plt.rcParams["figure.figsize"] fig_size[0] = 15 fig_size[1] = 10 plt.xlabel("Dates") plt.ylabel("PageViews - millions") plt.title("Pageviews on English Wikipedia from July 2015 to Sept 2017") plt.legend(loc=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: <p style="text-align Step2: <p style="text-align Step3: <p style="text-align Step4: <span style="text-align Step5: <p style="text-align Step6: <p style="text-align Step7: <div style="text-align
<ASSISTANT_TASK:> Python Code: shoes_in_my_drawer = int(input("How many shoes do you have in your drawer? ")) if shoes_in_my_drawer % 2 == 1: print("You have an odd number of shoes. Something is wrong!") shoes_in_my_drawer = int(input("How many shoes do you have in your drawer? ")) if shoes_in_my_drawer % 2 == 1: print("You have an odd number of shoes. Something is wrong!") if shoes_in_my_drawer % 2 != 1: print("You have an even number of shoes. Congratulations!") shoes_in_my_drawer = int(input("How many shoes do you have in your drawer? ")) if shoes_in_my_drawer % 2 == 1: print("You have an odd number of shoes. Something is wrong!") else: print("You have an even number of shoes. Congratulations!") is_boiler_on = input("Is your boiler turned on? [yes/no] ") hour = int(input("Enter the hour (00-23): ")) minute = int(input("Enter the minute (00-59): ")) if is_boiler_on == 'yes': is_boiler_on = True else: is_boiler_on = False if not is_boiler_on and hour == 7 and minute > 0: is_boiler_on = True else: if is_boiler_on: is_boiler_on = False if is_boiler_on: boiler_status = "on" else: boiler_status = "off" print("Boiler is " + boiler_status + " right now.") copies_sold = int(input("How many copies were sold? ")) # ืื ื—ื ื• ืžืฉืชืžืฉื™ื ื‘ืื•ืชื™ื•ืช ื’ื“ื•ืœื•ืช ืขื‘ื•ืจ ืฉืžื•ืช ื”ืžืฉืชื ื™ื ื”ืืœื•. # ื–ื• ืžื•ืกื›ืžื” ื‘ื™ืŸ ืžืชื›ื ืชื™ื ืฉืžื‘ืงืฉืช ืœื”ื“ื’ื™ืฉ ืฉืขืจื›ื™ ื”ืžืฉืชื ื™ื ื”ื ืงื‘ื•ืขื™ื, ื•ืœื ื”ื•ืœื›ื™ื ืœื”ืฉืชื ื•ืช ื‘ืžื”ืœืš ื”ืชื•ื›ื ื™ืช. SILVER_ALBUM = 100000 GOLD_ALBUM = 500000 PLATINUM_ALBUM = 1000000 DIAMOND_ALBUM = 10000000 if copies_sold >= DIAMOND_ALBUM: print("Diamond album") else: if copies_sold >= PLATINUM_ALBUM: print("Platinum album") else: if copies_sold >= GOLD_ALBUM: print("Gold album") else: if copies_sold >= SILVER_ALBUM: print("Silver album") else: print("Your album is not a best-seller") copies_sold = int(input("How many copies were sold? ")) SILVER_ALBUM = 100000 GOLD_ALBUM = 500000 PLATINUM_ALBUM = 1000000 DIAMOND_ALBUM = 10000000 if copies_sold >= DIAMOND_ALBUM: print("Diamond album") if copies_sold >= PLATINUM_ALBUM and copies_sold < DIAMOND_ALBUM: print("Platinum album") if copies_sold >= GOLD_ALBUM and copies_sold < PLATINUM_ALBUM: print("Gold album") if copies_sold >= SILVER_ALBUM and copies_sold < GOLD_ALBUM: print("Silver album") if copies_sold < SILVER_ALBUM: print("Your album is not a best-seller") copies_sold = int(input("How many copies were sold? ")) SILVER_ALBUM = 100000 GOLD_ALBUM = 500000 PLATINUM_ALBUM = 1000000 DIAMOND_ALBUM = 10000000 if copies_sold >= DIAMOND_ALBUM: print("Diamond album") elif copies_sold >= PLATINUM_ALBUM: print("Platinum album") elif copies_sold >= GOLD_ALBUM: print("Gold album") elif copies_sold >= SILVER_ALBUM: print("Silver album") else: print("Your album is not a best-seller") age = int(input("Please enter your age: "))) if age < 0: print("Your age is invalid." if age < 18: print("Younger than 18.") else print("You are so old!") <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: In the above example we can see that we can replace the letter "c" with a "b" using the replace 'method'. What happens if I have the number 711 and want to change the 7 to a 9 to make 911? Step6: When we try to use replace with integers we get an error; "'int' object has no attribute 'replace'". Basically this is Python's way of telling us that 'replace' is not a method belonging to the integer class. Step12: The above code doesn't work, but it should give you a feel for what a "ball UI" could look like in Python. Now lets do something similar for a football player. Step13: Let's suppose you are a developer on this project and a colleague of yours has implemented these methods already. The really cool thing is this UI adds a layer of abstraction that allows you to meaningfully interact with the ball/player without needing to actually understand exactly how this stuff works. Step16: So what does the above code do? Well, even though we haven't covered indentation and if/else statements (yet) my well-chosen variables names and comments were probably sufficient for you to figure out what is going on. Step17: Okay, so what does this code to? Well, it creates an object which I call โ€˜Timeโ€™. A Time object takes two integers as input (hours and minutes). Letโ€™s create a Time object and see what happens when I print it. Step18: When we print time objects they are represented as a string that looks just like an alarm clock; Time(12, 30) returns "12 Step19: As a minor implementation detail my code adds Time to other Time objects, if we try to add an integer (e.g 4) to the time 10
<ASSISTANT_TASK:> Python Code: x = "I love cats." # <= x is a string... print(x.upper()) # converts string to upper case print(x.replace("c", "b")) # cats? I'm a bat kinda guy myself! print(x.__add__(x)) # x.__add__(x) is EXACTLY the same as x + x. print(x.__mul__(3)) # Equivalent to x * 3 z = 711 print(z.replace(7, 1)) # With this said, integers do have some of the "same" methods as well. # Please note however these methods are the "same" in name only, behind the scenes they work very differently from each other. i = 5 print(i.__add__(i)) # i + i => 5 + 5 print(i.__mul__(i)) # i * i => 5 * 5 # Note the following code doesn't work, it is for demonstration purposes only! class Ball(): def get_speed(): The get_speed method returns the current speed of the ball. # magic goes here... return speed def get_direction(): The get_direction method returns the direction the ball is currently traveling in (in 3 dimensions). # magic goes here... return direction def get_position(): The get_position method returns the current position of the ball. # magic goes here... return position def bounce_off_of_object(other_object): This method calculates a new speed and position of the ball after colliding with another object. # magic goes here... return # something wilson = Ball() # creates a ball called Wilson. # Note the following code doesn't work, it is for demonstration purposes only! class Football_Player(): def name(name): This method gives the footballer a name. # magic goes here... return name def get_position(): The get_position method returns the current position of the player. # magic goes here... return position def get_speed(): The get_speed method returns the current speed of the player. # magic goes here... return speed def move(direction, speed): The move method makes the player run in X direction at Y speed. # magic goes here... return # new_speed of self def kick_ball(ball, power, direction): This method kicks ball Z with X power in Y direction. # magic goes here... return # new_speed of ball, direction of ball. # Note the following code doesn't work, it is for demonstration purposes only! Messi = Football_Player().name("Messi") # This line creates a footballer called 'Messi' football = Ball() # create a ball object. if ball.get_position == Messi.get_position: # This line asks if Messi and the football are at the same position in space. Messi.kick_ball(football, "100mph", direction="NorthWest") # Messi kicks the balls 100mph to the northwest. else: # If Messi is NOT near the ball then... target_position = football.get_position() # Messi wants to know where the football is. Messi.move(target_position, "12mph") # Messi is now running at 12mph towards the ball. class Time(object): # Do you remember in the variable names lecture I said that # you shouldn't name a variable '__something' unless you know what you are doing? # Well, thats because double underscore is usually reserved for "hidden" class properties/functions. # In this particular case, __init__, __repr__, __add__, all have very special meanings in Python. def __init__(self, hours, mins=0): assert isinstance(hours, int) and 0<= hours <=24 # Hours should be between 0 and 24 for a 24-hour clock. assert isinstance(mins, int) and 0<= mins <=60 self.hours = hours self.mins = mins def __repr__(self): return format_time(self.hours, self.mins) def __add__(self, other): This function takes itself and another Time object and adds them together. a = self.mins b = other.mins x = self.hours y = other.hours c = str( (a + b) % 60 ).zfill(2) # Integer division and Modulo Arithmetic. You have seen this before! z = str((((a+b) // 60) + x + y) % 25).zfill(2) return format_time(z, c) def format_time(h, m): This function takes hours (int) and mins(int) and returns them in a pretty format. 2, 59 => 02:59 return "{}:{}".format(str(h).zfill(2), str(m).zfill(2)) a = Time(4,50) b = Time(0, 1) c = Time(24, 59) print(a, b, c, sep="\n") print( Time(10,40) + Time(0,20) ) # 10:40 + 00:20 => 11:00 print( Time(0,0) + Time(7,30) ) # 00:00 + 07:30 => 7:30 print( Time(20,20) + 10 ) # Error, can't add integer to a Time object # Notice that, just like my "Time" object, integers, strings, floats, etc are all implemented in Python as classes. print(type(Time(10,0)),type("hello"),type(10), type(5.67), sep="\n") <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: Energy Surfaces of Al-Ni (N. Dupin et al., 2001) Step2: Al-Zn (S. Mey et al., 1993) Step4: Prototyping New Models (Advanced)
<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt from pycalphad import Database, binplot db_alfe = Database('alfe_sei.TDB') my_phases_alfe = ['LIQUID', 'B2_BCC', 'FCC_A1', 'HCP_A3', 'AL5FE2', 'AL2FE', 'AL13FE4', 'AL5FE4'] fig = plt.figure(figsize=(9,6)) pdens = [{'B2_BCC': 20000}, 2000] %time binplot(db_alfe, ['AL', 'FE', 'VA'] , my_phases_alfe, 'X(AL)', 300, 2000, steps=100, \ pdens=pdens, ax=fig.gca(), mode='numexpr') plt.show() %matplotlib inline from pycalphad import energy_surf, Database from pycalphad.plot.utils import phase_legend import numpy as np import matplotlib.pyplot as plt db_alni = Database('NI_AL_DUPIN_2001.TDB') my_phases_alni = ['LIQUID', 'FCC_L12', 'BCC_B2', 'AL3NI5', 'AL3NI2', 'AL3NI1'] fig = plt.figure(figsize=(9,6)) ax = fig.gca() %time nrg_df = energy_surf(db_alni, ['AL', 'NI', 'VA'], my_phases_alni, T=1000.0) legend_handles, colorlist = phase_legend(my_phases_alni) group_df = nrg_df.groupby('Phase') for phase, phase_df in group_df: ax = phase_df.plot(kind='scatter', x='X(AL)', y='GM', ax=ax, color=colorlist[phase.upper()], s=1, xlim=(0,1), ylim=(-11e4, -3e4)) ax = ax.legend(handles=legend_handles, loc='center left', bbox_to_anchor=(1, 0.6)) plt.title('Al-Ni Gibbs Energy at 1000 K', fontsize=20) plt.show() nrg_df nrg_df.to_excel('alni_energies.xlsx') from pycalphad import Model, Database, binplot db_alzn = Database('alzn_noparams.tdb') assessed_parameters = { 'LIQALZN0H': 10465.3, 'LIQALZN0S': 3.39259, 'FCCALZN0H': 7297.5, 'FCCALZN0S': -0.47512, 'FCCALZN1H': 6612.9, 'FCCALZN1S': 4.5911, 'FCCALZN2H': -3097.2, 'FCCALZN2S': -3.306635, 'HCPALZN0H': 18821.0, 'HCPALZN0S': 8.95255, 'HCPALZN3H': -702.8, 'HCPALZN3S': 0.0 } # Initialize phase models assessed_models = { 'LIQUID': Model(db_alzn, ['AL', 'ZN'], 'LIQUID', parameters=assessed_parameters), 'FCC_A1': Model(db_alzn, ['AL', 'ZN', 'VA'], 'FCC_A1', parameters=assessed_parameters), 'HCP_A3': Model(db_alzn, ['AL', 'ZN', 'VA'], 'HCP_A3', parameters=assessed_parameters) } fig = plt.figure(figsize=(9,6)) ax = binplot(db_alzn, ['AL', 'ZN', 'VA'] , ['LIQUID', 'FCC_A1', 'HCP_A3'], \ 'X(ZN)', 300, 1000, ax=plt.gca(), model=assessed_models) ax = ax.set_title('Al-Zn', fontsize=20) blank_parameters = { 'LIQALZN0H': 0.0, 'LIQALZN0S': 0.0, 'FCCALZN0H': 0.0, 'FCCALZN0S': 0.0, 'FCCALZN1H': 0.0, 'FCCALZN1S': 0.0, 'FCCALZN2H': 0.0, 'FCCALZN2S': 0.0, 'HCPALZN0H': 0.0, 'HCPALZN0S': 0.0, 'HCPALZN3H': 0.0, 'HCPALZN3S': 0.0 } models = { 'LIQUID': Model(db_alzn, ['AL', 'ZN'], 'LIQUID', parameters=blank_parameters), 'FCC_A1': Model(db_alzn, ['AL', 'ZN', 'VA'], 'FCC_A1', parameters=blank_parameters), 'HCP_A3': Model(db_alzn, ['AL', 'ZN', 'VA'], 'HCP_A3', parameters=blank_parameters) } fig = plt.figure(figsize=(9,6)) ax = binplot(db_alzn, ['AL', 'ZN', 'VA'] , ['LIQUID', 'FCC_A1', 'HCP_A3'], \ 'X(ZN)', 300, 1000, ax=plt.gca(), model=models) ax = ax.set_title('Al-Zn with endmembers only', fontsize=20) from sympy import Piecewise, log from tinydb import where import pycalphad.variables as v class MyMagneticModel(Model): def __init__(self, db, comps, phase, **kwargs): super().__init__(db, comps, phase, **kwargs) self.models['mag'] = self.my_magnetic_energy(db.phases[phase], db.search) def my_magnetic_energy(self, phase, param_search): Return the energy from magnetic ordering in symbolic form. The implemented model is the Inden-Hillert-Jarl formulation. The approach follows from the background section of W. Xiong, 2011. Note that this is a demonstration model; use pycalphad's builtin implementation as a reference. site_ratio_normalization = self._site_ratio_normalization(phase) # define basic variables afm_factor = phase.model_hints['ihj_magnetic_afm_factor'] bm_param_query = ( (where('phase_name') == phase.name) & \ (where('parameter_type') == 'BMAGN') & \ (where('constituent_array').test(self._array_validity)) ) tc_param_query = ( (where('phase_name') == phase.name) & \ (where('parameter_type') == 'TC') & \ (where('constituent_array').test(self._array_validity)) ) mean_magnetic_moment = \ self.redlich_kister_sum(phase, param_search, bm_param_query) beta = Piecewise( (mean_magnetic_moment, mean_magnetic_moment > 0), (mean_magnetic_moment/afm_factor, mean_magnetic_moment <= 0) ) curie_temp = \ self.redlich_kister_sum(phase, param_search, tc_param_query) tc = Piecewise( (curie_temp, curie_temp > 0), (curie_temp/afm_factor, curie_temp <= 0) ) tau = Piecewise( (v.T / tc, tc > 0), (10000., tc == 0) # tau is 'infinity' ) # define model parameters p = phase.model_hints['ihj_magnetic_structure_factor'] A = 518/1125 + (11692/15975)*(1/p - 1) # factor when tau < 1 sub_tau = 1 - (1/A) * ((79/(140*p))*(tau**(-1)) + (474/497)*(1/p - 1) \ * ((tau**3)/6 + (tau**9)/135 + (tau**15)/600) ) # factor when tau >= 1 super_tau = -(1/A) * ((tau**-5)/10 + (tau**-15)/315 + (tau**-25)/1500) expr_cond_pairs = [(sub_tau, tau < 1), (super_tau, tau >= 1) ] g_term = Piecewise(*expr_cond_pairs) return 1e6 * v.R * v.T * log(beta+1) * \ g_term / site_ratio_normalization %matplotlib inline import matplotlib.pyplot as plt from pycalphad import Database, binplot db_alfe = Database('alfe_sei.TDB') my_phases_alfe = ['LIQUID', 'B2_BCC', 'FCC_A1', 'HCP_A3', 'AL5FE2', 'AL2FE', 'AL13FE4', 'AL5FE4'] models = [{'FCC_A1': MyMagneticModel}, Model] fig = plt.figure(figsize=(9,6)) pdens = [{'B2_BCC': 20000}, 2000] %time binplot(db_alfe, ['AL', 'FE', 'VA'] , my_phases_alfe, 'X(AL)', 300, 2000, steps=100, \ pdens=pdens, ax=fig.gca(), model=models, mode='numexpr') plt.title('Al-Fe with toy magnetic model', fontsize=20) 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: But, why? Step2: Our fledgeling Python script kiddie then enters the following code Step3: resulting in this workflow Step4: How does it work? Step5: Mocking a 'real' Python object Step6: Merging workflows into a function call Step7: eeeehm, What can we do (sort of)? Step8: Step9: embedded workflows Step10: Step11: Using objects Step12: Step13:
<ASSISTANT_TASK:> Python Code: from noodles import schedule, run, run_parallel, gather @schedule def add(a, b): return a+b @schedule def sub(a, b): return a-b @schedule def mul(a, b): return a*b u = add(5, 4) v = sub(u, 3) w = sub(u, 2) x = mul(v, w) draw_workflow('callgraph1.png', x._workflow) run_parallel(x, n_threads = 2) def schedule(f): @wraps(f) def wrapped(*args, **kwargs): bound_args = signature(f).bind(*args, **kwargs) bound_args.apply_defaults() return PromisedObject(merge_workflow(f, bound_args)) return wrapped class PromisedObject: def __init__(self, workflow): self._workflow = workflow def __call__(self, *args, **kwargs): return _do_call(self._workflow, *args, **kwargs) def __getattr__(self, attr): if attr[0] == '_': return self.__dict__[attr] return _getattr(self._workflow, attr) def __setattr__(self, attr, value): if attr[0] == '_': self.__dict__[attr] = value return self._workflow = get_workflow(_setattr(self._workflow, attr, value)) def merge_workflow(f, bound_args): variadic = next((x.name for x in bound_args.signature.parameters.values() if x.kind == Parameter.VAR_POSITIONAL), None) if variadic: bound_args.arguments[variadic] = list(bound_args.arguments[variadic]) node = FunctionNode(f, bound_args) idx = id(node) nodes = {idx: node} links = {idx: set()} for address in serialize_arguments(bound_args): workflow = get_workflow( ref_argument(bound_args, address)) if not workflow: continue set_argument(bound_args, address, Parameter.empty) for n in workflow.nodes: if n not in nodes: nodes[n] = workflow.nodes[n] links[n] = set() links[n].update(workflow.links[n]) links[workflow.top].add((idx, address)) return Workflow(id(node), nodes, links) from noodles import schedule, run, run_parallel, gather @schedule def sum(a, buildin_sum = sum): return buildin_sum(a) r1 = add(1, 1) r2 = sub(3, r1) def foo(a, b, c): return mul(add(a, b), c) multiples = [foo(i, r2, r1) for i in range(6)] r5 = sum(gather(*multiples)) draw_workflow('callgraph2.png', r5._workflow) run_parallel(r5, n_threads = 4) @schedule def sqr(a): return a*a @schedule def map(f, lst): return gather(*[f(x) for x in lst]) @schedule def num_range(a, b): return range(a, b) wf = sum(map(sqr, num_range(0, 1000))) draw_workflow('callgraph3.png', wf._workflow) run_parallel(wf, n_threads=4) @schedule class A: def __init__(self, value): self.value = value def multiply(self, factor): self.value *= factor a = A(5) a.multiply(10) a.second = 7 draw_workflow("callgraph4.png", a._workflow) @schedule class A: def __init__(self, value): self.value = value def multiply(self, factor): self.value *= factor return self a = A(5) a = a.multiply(10) a.second = 7 draw_workflow("callgraph5.png", a._workflow) result = run_parallel(a, n_threads=4) print(result.value, result.second) <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: Source Step2: Kharrufa method. Kharrufa (1985) derived an equation through correlation of ET/p and T in the form of
<ASSISTANT_TASK:> Python Code: import pandas as pd import numpy as np import matplotlib.pyplot as plt %matplotlib inline data = pd.read_csv('../data/hbv_s_data.csv', index_col=0, parse_dates=True) evap_true = np.array([0.6,1.9,2.4,1.8,1.4,1.3,1.0,0.8,0.6,0.4,0.2,0.3])*1.2 #evapo for jan-dec def romanenko(data): Ta = np.array([data.ix[data.index.month == x, 'Temp'].mean() for x in range(1, 13)]) Td = 2 def et(T): return 33.8679*( ((0.00738*T + 0.8072)**8) - 0.000019*(np.abs(1.8*T + 48)) + 0.001316) Rh = et(Td)*100/et(Ta) # best results with manual evap setup # Rh = np.array([60, 0, 0, 45, 70, 80, 85, 90, 90, 90, 90, 76]) return (0.0018*((25+Ta)**2))*(100-Rh)/30 Ta = np.array([data.ix[data.index.month == x, 'Temp'].mean() for x in range(1, 13)]) Td = np.array([0, 0, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10]) et(Td)*100/et(Ta) Ta plt.plot(range(1,13), romanenko(data), 'b', range(1,13), evap_true, 'r') def kharufa(data): Ta = np.array([data.ix[data.index.month == x, 'Temp'].mean() for x in range(1, 13)]) p = 0.85 return 0.34*p*(Ta**1.3) plt.plot(range(1,13), kharufa(data), 'b', range(1,13), romanenko(data), 'g', range(1,13), evap_true, 'r') print(kharufa(data)) import numpy as np import pandas as pd import matplotlib.pyplot as plt %matplotlib inline import sys sys.path.append('../models/') import hbv_s swe_riv = pd.read_csv('../data/hbv_s_data.csv', index_col=0, parse_dates=True) Qobs = swe_riv.Qobs Qsim = hbv_s.simulation(swe_riv) pd.DataFrame({'obs':Qobs, 'sim':Qsim}, index=swe_riv.index).plot() swe_riv2 = swe_riv.drop('Evap', 1) swe_riv2['Evap'] = swe_riv2.index.map(lambda x: romanenko(swe_riv2)[x.month-1]) Qsim = hbv_s.simulation(swe_riv2) pd.DataFrame({'obs':Qobs, 'sim':Qsim}, index=swe_riv2.index).plot() swe_riv2['Evap'].plot(); swe_riv['Evap'].plot() evap_true a = np.array([0.6,1.9,2.4,1.8,1.4,1.3,1.0,0.8,0.6,0.4,0.2,0.3]) np.savetxt('../data/Evap_monthly_constants.txt', a) np.loadtxt('../data/Evap_monthly_constants.txt') swe_riv2['Evap2'] = swe_riv2.index.map(lambda x: np.loadtxt('../data/Evap_monthly_constants.txt')[x.month-1]) swe_riv2[['Evap', 'Evap2']].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: This is an example of applying learning rate decay in TensorFlow, using Gradient Descent to solve a simple Linear Regression. Step2: Now we're ready to set up the TensorFlow solution Step3: First we define placeholders and a weights vector that we'll learn from the data. Step4: Then we use calculate the MSE between the prediction $w^TX$ and the actual y and use a GradientDescentOptimizer to minimize the loss using a staircased learning rate.
<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt plt.style.use('ggplot') import numpy as np import pandas as pd X_df = pd.DataFrame(np.random.rand(100, 3)) w_actual = pd.Series(data=[2, 3, 5]) y_true = X_df.dot(w_actual) # add a small noise to y y_true += np.random.normal(scale=1E-6, size=100) import tensorflow as tf tf.reset_default_graph() X = tf.placeholder(shape=X_df.shape, dtype=tf.float32, name='X') y = tf.placeholder(shape=[len(y_true), 1], dtype=tf.float32, name='y') w = tf.get_variable( 'coeff', initializer=tf.truncated_normal_initializer(dtype=tf.float32), shape=[3, 1] ) y_pred = tf.matmul(X, w) loss = tf.losses.mean_squared_error(y_pred, y) starter_learning_rate = 0.08 learning_rate = tf.train.exponential_decay( learning_rate=starter_learning_rate, global_step=tf.train.get_or_create_global_step(), decay_steps=10, decay_rate=0.8, staircase=True, name='learning_rate') train_op = tf.train.GradientDescentOptimizer( learning_rate=learning_rate).minimize(loss, global_step=tf.train.get_global_step()) losses = [] learning_rates = [] input_data = { X: X_df.values, y: y_true.values.reshape([100, 1]) } with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for i in range(1, 500): _, loss_val, lr = sess.run([train_op, loss, learning_rate], feed_dict=input_data) losses.append(loss_val) learning_rates.append(lr) w_estimated = sess.run(w).squeeze() _, ax = plt.subplots(1, 3, figsize=(12, 3)) losses = pd.Series(losses) _ = losses.rolling(10).mean().plot(title='Loss over Training Steps', ax=ax[0]) w_df = pd.DataFrame.from_records( [w_actual.values, w_estimated], index=['actual', 'estimated']).T _ = w_df.plot(kind='bar', rot=0, ax=ax[1], title='Actual vs. Estimated Weights') learning_rates = pd.Series(learning_rates) _ = learning_rates.plot(ax=ax[2], title='Learning Rate over Training Steps') <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 open the file for reading. We use the with statement that takes care of closing the file Step2: In the code above, we have imported the module csv, which allows us to parse character-delimited files. In this case, we do not need to specify any special option, as we're reading a plain-vanilla csv file, delimited by commas. Step3: Now all the cities are stored in the set cities, with all the duplicates automatically removed (as we're using a set) Step4: Write a program that creates a dictionary where the keys are the cities, and the values are the number of records (rows) for that city in the data. Step5: The code above shows that when the key is not already, present, the key will be added, and its value will be initially 1. If on the other hand the key is present, we will simply increment its associated value Step6: With this at hand, we can write our program Step7: That's it. Let's print the counts for a few cities Step8: Write a program that calculates the mean population for each city, obtained by averaging the value of pop. Step9: Excellent. Now each key in the dictionary indexes a list whose first element is the sum of all the population values, and the second element is the number of records that contributed to the sum. To obtain the average population, we divide the first by the second Step10: Let's see some of the averages to make sure they make sense Step11: If we want print only a few decimals, we can use round Step12: Write a program that calculates the mean population for each city and year. Step13: Let's look at the results for Chicago
<ASSISTANT_TASK:> Python Code: cities = set([]) # initialize an empty set import csv # we this module to handle csv files with open('../data/Dalziel2016_data.csv', 'r') as f: # 'r' stands for reading my_csv = csv.DictReader(f) # set up the csv reader for line in my_csv: # loop over all lines print(line) break # break the loop after printing the first line to inspect results import csv # we use the csv module, as we want to read a csv file with open('../data/Dalziel2016_data.csv', 'r') as f: # 'r' stands for reading my_csv = csv.DictReader(f) for line in my_csv: cities.add(line['loc']) cities a = {} # an empty dictionary a['my_new_key'] = a.get('my_new_key', 0) + 1 a a['my_new_key'] = a.get('my_new_key', 0) + 1 a citycount = {} # initiate an empty dictionary import csv # we use the csv module, as we want to read a csv file with open('../data/Dalziel2016_data.csv', 'r') as f: # 'r' stands for reading my_csv = csv.DictReader(f) for line in my_csv: # this is the city to update mycity = line['loc'] # if it's present, increment the value # if it's not present, initialize to 1 citycount[mycity] = citycount.get(mycity, 0) citycount[mycity] = citycount[mycity] + 1 for city in ['CHICAGO', 'LOS ANGELES', 'NEW YORK']: print(city, citycount[city]) citypop = {} import csv # we use the csv module, as we want to read a csv file with open('../data/Dalziel2016_data.csv', 'r') as f: # 'r' stands for reading my_csv = csv.DictReader(f) for line in my_csv: # this is the city to update mycity = line['loc'] # current pop pop = float(line['pop']) # transform to float # if it's present, increment the value # if it's not present, initialize a list with both population and count as zero citypop[mycity] = citypop.get(mycity, [0,0]) # update population (stored as first value of list) citypop[mycity][0] = citypop[mycity][0] + pop # update number of records (stored as second value of list) citypop[mycity][1] = citypop[mycity][1] + 1 citypop for city in citypop.keys(): citypop[city][0] = citypop[city][0] / citypop[city][1] for city in ['CHICAGO', 'LOS ANGELES', 'NEW YORK']: print(city, citypop[city][0]) for city in ['CHICAGO', 'LOS ANGELES', 'NEW YORK']: print(city, round(citypop[city][0],1)) cityyear = {} cityyear = {} import csv # we use the csv module, as we want to read a csv file with open('../data/Dalziel2016_data.csv', 'r') as f: # 'r' stands for reading my_csv = csv.DictReader(f) for line in my_csv: # this is the city to update mycity = line['loc'] # this is the year to update year = line['year'] # current pop pop = float(line['pop']) # transform to float # make sure the city is in the dictionary, or initialize cityyear[mycity] = cityyear.get(mycity, {}) # make sure the year is in the sub-dictionary, or initialize cityyear[mycity][year] = cityyear[mycity].get(year, [0,0]) # now proceed as for exercise 3 but access the inner dictionary # update population cityyear[mycity][year][0] = cityyear[mycity][year][0] + pop # update number of records cityyear[mycity][year][1] = cityyear[mycity][year][1] + 1 # now compute averages for city in cityyear.keys(): for year in cityyear[city].keys(): cityyear[city][year][0] = cityyear[city][year][0] / cityyear[city][year][1] # a dictionary has no natural order but here we want to order by year # store the years in a list years = list(cityyear['CHICAGO'].keys()) # sort the years years.sort() # this is done in place! # now print population for each year for year in years: print(year, round(cityyear['CHICAGO'][year][0])) <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: try now for bouillon
<ASSISTANT_TASK:> Python Code: act = Database("ecoinvent 3.2 cutoff").search("pineapple") act act = Database("ecoinvent 3.2 cutoff").search("pineapple")[1] act lca = LCA( {act.key: 1}, method=('IPCC 2013', 'climate change', 'GWP 100a'), ) lca.lci() lca.lcia() lca.score bou = Database("bouillon").search("Paste") bou lca = LCA( demand={bouillon.random(): 1}, method=('IPCC 2013', 'climate change', 'GWP 100a'), ) lca.lci() lca.lcia() lca.score lca = LCA( demand={bouillonZ.random(): 1}, method=('IPCC 2013', 'climate change', 'GWP 100a'), ) lca.lci() lca.lcia() lca.score <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: Petite histoire Step2: Six mois plus tard, vous crรฉez une fonction f5 qui appelle une fonction f4 et la fonction f2. Step3: Ah au fait, ce faisant, vous modifiez la fonction f2 et vous avez un peu oubliรฉ ce que faisait la fonction f3... Bref, vous ne savez pas si la fonction f3 sera impactรฉe par la modification introduite dans la fonction f2 ? C'est ce type de problรจme qu'on rencontre tous les jours quand on รฉcrit un logiciel ร  plusieurs et sur une longue durรฉe. Ce notebook prรฉsente les briques classiques pour s'assurer de la robustesse d'un logiciel. Step4: Ecrire un test unitaire Step5: Il y a des badges un peu pour tout.
<ASSISTANT_TASK:> Python Code: from jyquickhelper import add_notebook_menu add_notebook_menu() from pyensae.graphhelper import draw_diagram draw_diagram("blockdiag { f0 -> f1 -> f3; f2 -> f3;}") draw_diagram('blockdiag { f0 -> f1 -> f3; f2 -> f3; f2 -> f5 [color="red"]; f4 -> f5 [color="red"]; }') def solve_polynom(a, b, c): # .... return None from IPython.display import SVG SVG("https://travis-ci.com/sdpython/ensae_teaching_cs.svg?branch=master") SVG("https://codecov.io/github/sdpython/ensae_teaching_cs/coverage.svg?branch=master") SVG("https://badge.fury.io/py/ensae_teaching_cs.svg") <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: Structure of this module Step2: Convinient functiones Step3: textwrap.fill(text, width=70, **kwargs) Step4: textwrap.dedent(text) Step5: you probaly notice that the result of textwrap.fill have some unwanted space. in this case we can work around this by dedent it first then fill. Step6: textwrap.indent(text, prefix, predicate=None) Step7: To control which lines receive the new prefix, pass a callable as the predicate argument to indent(). The callable will be invoked for each line of text in turn and the prefix will be added for lines where the return value is true. Step8: This example adds the prefix EVEN to lines that contain an even number of characters. Step9: textwrap.TextWrapper(**kwargs)
<ASSISTANT_TASK:> Python Code: import textwrap sample_text = ''' The textwrap module can be used to format text for output in situations where pretty-printing is desired. It offers programmatic functionality similar to the paragraph wrapping or filling features found in many text editors. ''' wrap_result = textwrap.wrap(sample_text,width=30) wrap_result fill_result = textwrap.fill(sample_text,width=30) fill_result # before dedent sample_text dedent_result = textwrap.dedent(sample_text) # after dedent dedent_result dedent_result_wrap = textwrap.fill(dedent_result,width=30) dedent_result_wrap indent_result = textwrap.indent(sample_text,prefix="=A=") indent_result print(indent_result) def should_indent(line): print('Indent {!r}?'.format(line)) return len(line.strip()) % 2 == 0 dedented_text = textwrap.dedent(sample_text) wrapped = textwrap.fill(dedented_text, width=50) final = textwrap.indent(wrapped, 'EVEN ', predicate=should_indent) print('\nQuoted block:\n') print(final) shorten_result = textwrap.shorten(sample_text,width=90) shorten_result # use different placeholder shorten_result_1 = textwrap.shorten(sample_text,width=90,placeholder='....') shorten_result_1 dedented_text = textwrap.dedent(sample_text).strip() print(textwrap.fill(dedented_text, initial_indent='', subsequent_indent=' ' * 4, width=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: Step1: ์ •๊ทœํ™” Step2: ๋ฐ์ดํ„ฐ์„ธํŠธ ์ค€๋น„ํ•˜๊ธฐ Step3: ๊ทธ๋ฃน ์ •๊ทœํ™” ํŠœํ† ๋ฆฌ์–ผ Step4: ์ธ์Šคํ„ด์Šค ์ •๊ทœํ™” ํŠœํ† ๋ฆฌ์–ผ Step5: ๋ ˆ์ด์–ด ์ •๊ทœํ™” ํŠœํ† ๋ฆฌ์–ผ
<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. !pip install -U tensorflow-addons import tensorflow as tf import tensorflow_addons as tfa mnist = tf.keras.datasets.mnist (x_train, y_train),(x_test, y_test) = mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0 model = tf.keras.models.Sequential([ # Reshape into "channels last" setup. tf.keras.layers.Reshape((28,28,1), input_shape=(28,28)), tf.keras.layers.Conv2D(filters=10, kernel_size=(3,3),data_format="channels_last"), # Groupnorm Layer tfa.layers.GroupNormalization(groups=5, axis=3), tf.keras.layers.Flatten(), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(x_test, y_test) model = tf.keras.models.Sequential([ # Reshape into "channels last" setup. tf.keras.layers.Reshape((28,28,1), input_shape=(28,28)), tf.keras.layers.Conv2D(filters=10, kernel_size=(3,3),data_format="channels_last"), # LayerNorm Layer tfa.layers.InstanceNormalization(axis=3, center=True, scale=True, beta_initializer="random_uniform", gamma_initializer="random_uniform"), tf.keras.layers.Flatten(), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(x_test, y_test) model = tf.keras.models.Sequential([ # Reshape into "channels last" setup. tf.keras.layers.Reshape((28,28,1), input_shape=(28,28)), tf.keras.layers.Conv2D(filters=10, kernel_size=(3,3),data_format="channels_last"), # LayerNorm Layer tf.keras.layers.LayerNormalization(axis=3 , center=True , scale=True), tf.keras.layers.Flatten(), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(x_test, y_test) <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 ... Step2: Heat equation Step3: Wave equation
<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib.pyplot as plt import matplotlib.animation as animation from matplotlib import rcParams %matplotlib notebook rcParams['mathtext.fontset'] = 'cm' rcParams['font.size'] = 14 red = "#e41a1c" blue = "#377eb8" gray = "#eeeeee" def heat_update(n): ax0.cla() for cont in range(ntime): u_heat[1:N-1] = dt/(factor*dx**2)*(u_heat[2:N] + u_heat[0:N-2] - 2*u_heat[1:N-1]) + u_heat[1:N-1] ax0.plot(x, u_heat) ax0.set_ylim(-1.2, 1.2) ax0.set_title("$t = {:.2f}$".format(n*ntime*dt)) N = 2001 x = np.linspace(-1, 1, N) dx = x[1] - x[0] diff = 1 factor = 10 dt = dx**2/(factor*diff) ntime = 10 u_heat = 1 - abs(4*x) u_heat[x < -0.25] = 0 u_heat[x > 0.25] = 0 fig0 = plt.figure(figsize=(5, 5)) ax0 = fig0.add_subplot(111) ani0 = animation.FuncAnimation(fig0, heat_update, range(100), blit=False, repeat=False) plt.show() def wave_update(n): ax1.cla() for cont in range(ntime): u_aux = u.copy() u_aux2 = u_old.copy() u_old[:] = u[:] u_w[1:N-1] = alpha**2*(u_aux[2:N] + u_aux[0:N-2] - 2*u_aux[1:N-1]) \ + 2*u_aux[1:N-1] - u_aux2[1:N-1] ax1.plot(x, u_w) ax1.set_ylim(-1.2, 1.2) ax1.set_title("$t = {:.2f}$".format(n*ntime*dt)) N = 2001 x = np.linspace(-1, 1, N) dx = x[1] - x[0] vel = 1 factor = 10 dt = dx/(factor*vel) alpha = vel*dt/dx ntime = 1000 u_old = 1 - abs(4*x) u_old[x < -0.25] = 0 u_old[x > 0.25] = 0 u_w = u_old.copy() fig1 = plt.figure(figsize=(5, 5)) ax1 = fig1.add_subplot(111) ani1 = animation.FuncAnimation(fig1, wave_update, range(100), blit=False, repeat=False) from IPython.core.display import HTML def css_styling(): styles = open('./styles/custom_barba.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: Read in the letters saved by the lettersketch app after converting into grayscale and resizing Step2: Reshape the image arrays Step3: Convert white into black background Step4: Load the test data, Convert white into black background, Reshape the data, and Plot a sample Step5: Create a label dictionary for the letters in the training set Step6: Assign labels to the images in the training set Step7: Vectorize the labels Step8: Join data and data labels Step12: <font color='green'>Utilities for working with a standard neural net</font> Step13: <font color='green'>Fit the neural net to the input data</font> Step14: Save the weights and biases in JSON Step15: <font color='green'>Test how well the model is performing</font>
<ASSISTANT_TASK:> Python Code: dirName = "../lettersketch/assets/train_images/UpperCase/StraightLines/" fileNames = [] fileLetters = [] for fileName in os.listdir(dirName): if fileName.endswith(".png") and (not "__" in fileName): fileNames.append(dirName+fileName) letter = fileName.split("_")[1] fileLetters.append(letter) #print fileNames #def rgb2gray(rgb): # return np.dot(rgb[...,:3], [0.299, 0.587, 0.144]) # #data = np.array([rgb2gray(mpimg.imread(fileName)) for fileName in fileNames], dtype = np.float64) #data.shape data = np.array([np.asarray(Image.open(fileName).convert('L').resize((28, 28), Image.NEAREST)) for fileName in fileNames], dtype = np.float64) print data.shape data = data.reshape(data.shape[0], data.shape[1]*data.shape[2]) print data.shape for dt in np.nditer(data, op_flags=['readwrite']): dt[...] = dt/255.0 if (dt == 1.0): dt[...] = 0.0 testDirName = "../lettersketch/assets/test_images/" testNames = [] for fileName in os.listdir(testDirName): if fileName.endswith(".png") and ("__" in fileName): testNames.append(testDirName+fileName) testData = np.array([np.asarray(Image.open(fileName).convert('L').resize((28, 28), Image.NEAREST)) for fileName in testNames], dtype = np.float64) print testData.shape testData = testData.reshape(testData.shape[0], testData.shape[1]*testData.shape[2]) print testData.shape for dt in np.nditer(testData, op_flags=['readwrite']): dt[...] = dt/255.0 if (dt == 1.0): dt[...] = 0.0 imgplot = plt.imshow(data[9].reshape(28,28), cmap="gray") testplot = plt.imshow(testData[1].reshape(28,28), cmap ="gray") labelDict = {'E':0, 'F':1, 'H':2, 'I':3, 'L':4, 'T':5} print fileLetters fileLabels = [labelDict[letter] for letter in fileLetters] print fileLabels def vectorizeLabels(label): vector = np.zeros((6)) vector[label] = 1.0 return vector dataLabels = np.array([vectorizeLabels(label) for label in fileLabels]) print dataLabels[0] print data.shape print dataLabels.shape training_data = zip(data, dataLabels) #print training_data[0] %load nnutils.py #--------------------------------------------------- # A neural net class #--------------------------------------------------- class NeuralNet(object): Constructor # layers: vector of length numLayers containing the # the number of neurons in each layer # e.g., layers = (4, 3, 2) -> 4 input values, 3 neurons in hidden layer, 2 output values # biases: initialized with random numbers except for first layer # e.g., biases = [ [b11, b21, b31]^T, # [b12, b22]^T ] # weights: initialized with random numbers # e.g., [ [[w111, w121, w131, w141], # [w211, w221, w231, w241], # [w311, w321, w331, w341]], # [[w112, w122, w132], # [w212, w222, w232]] ] def __init__(self, layers): self.numLayers = len(layers) self.numNeurons = layers self.biases = [random.randn(layer, 1) for layer in layers[1:]] self.weights = [random.randn(layer2, layer1) for layer1, layer2 in zip(layers[:-1], layers[1:])] Batch stochastic gradient descent to find minimum of objective function # training_data: [(x1,y1),(x2,y2),....] # where x1, x2, x3, ... are input data vectors # y1, y2, y3, ... are labels # max_iterations: number of iterations # batch_size: size of training batch # learning_rate: gradient descent parameter def batchStochasticGradientDescent(self, training_data, max_iterations, batch_size, learning_rate): # Get the number of training images nTrain = len(training_data) # Loop thru iterations for it in xrange(max_iterations): # Shuffle the training data random.shuffle(training_data) # Choose subsets of the training data batches = [ training_data[start:start+batch_size] for start in xrange(0, nTrain, batch_size) ] # Loop thru subsets for batch in batches: self.updateBatch(batch, learning_rate) #print "Iteration {0} complete".format(it) #print "weights = ", self.weights #print "biases = ", self.biases Partial update of weights and biases using gradient descent # with back propagation def updateBatch(self, batch, learning_rate): # Initialize gradC_w and gradC_b gradC_w = [np.zeros(w.shape) for w in self.weights] gradC_b = [np.zeros(b.shape) for b in self.biases] # Loop through samples in the batch for xx, yy in batch: # Compute correction to weights & biases using forward and backprop delta_gradC_w, delta_gradC_b = self.updateGradient(xx, yy) # Update the gradients gradC_w = [grad + delta_grad for grad, delta_grad in zip(gradC_w, delta_gradC_w)] gradC_b = [grad + delta_grad for grad, delta_grad in zip(gradC_b, delta_gradC_b)] # Update the weight and biases self.weights = [ weight - (learning_rate/len(batch))*grad for weight, grad in zip(self.weights, gradC_w) ] self.biases = [ bias - (learning_rate/len(batch))*grad for bias, grad in zip(self.biases, gradC_b) ] # Forward and then backpropagation to compute the gradient of the objective function def updateGradient(self, xx, yy): # Reshape into column vectors xx = np.reshape(xx, (len(xx), 1)) yy = np.reshape(yy, (len(yy), 1)) # Initialize gradC_w and gradC_b gradC_w = [np.zeros(w.shape) for w in self.weights] gradC_b = [np.zeros(b.shape) for b in self.biases] # Compute forward pass through net # Initial activation value = input value activationValue = xx activationValues = [xx] layerOutputValues = [] # Loop through layers for weight, bias in zip(self.weights, self.biases): #print weight.shape #print activationValue.shape layerOutputValue = np.dot(weight, activationValue) + bias layerOutputValues.append(layerOutputValue) activationValue = self.activationFunction(layerOutputValue) activationValues.append(activationValue) # Compute backpropagation corrections # Initial deltas delta = self.derivOfCostFunction(activationValues[-1], yy) * self.derivActivationFunction(layerOutputValues[-1]) gradC_b[-1] = delta gradC_w[-1] = np.dot(delta, activationValues[-2].transpose()) # Loop backward thru layers for layer in xrange(2, self.numLayers): layerOutputValue = layerOutputValues[-layer] derivActivation = self.derivActivationFunction(layerOutputValue) delta = np.dot(self.weights[-layer + 1].transpose(), delta)*derivActivation gradC_b[-layer] = delta gradC_w[-layer] = np.dot(delta, activationValues[-layer-1].transpose()) # Return updated gradients return(gradC_w, gradC_b) # The activation function def activationFunction(self, xx): return 1.0/(1.0 + np.exp(-xx)) # Derivative of activation function def derivActivationFunction(self, xx): return self.activationFunction(xx)*(1.0 - self.activationFunction(xx)) # Derivative of the cost function with respect to output values def derivOfCostFunction(self, xx, yy): return (xx - yy) # The feedforward output computation for the network # inputVector: (n, 1) array # n = number of inputs to network # outputVector: ???? def forwardCompute(self, inputVector): for bias, weight in zip(self.biases, self.weights): xx = np.dot(weight, inputVector) + bias inputVector = self.activationFunction(xx) return inputVector net = NeuralNet([4, 3, 2]) net.weights net.biases testNN = NeuralNet([28*28, 49, 16, 6]) max_iterations = 100 batch_size = 1 learning_rate = 0.01 testNN.batchStochasticGradientDescent(training_data, max_iterations, batch_size, learning_rate) weightsList = testNN.weights for weights in weightsList: print weights.shape biasesList = testNN.biases for biases in biasesList: print biases.shape weightsFileName = "../lettersketch/assets/json/UpperCase_StraightLines_weights.json" biasesFileName = "../lettersketch/assets/json/UpperCase_StraightLines_biases.json" for weights in weightsList: json.dump(weights.tolist(), codecs.open(weightsFileName, 'a', encoding='utf-8'), separators=(',', ':'), sort_keys=True, indent=2) for biases in biasesList: json.dump(biases.tolist(), codecs.open(biasesFileName, 'a', encoding='utf-8'), separators=(',', ':'), sort_keys=True, indent=2) fig = plt.figure() num_image_rows = np.ceil(np.sqrt(testData.shape[0])) for i in range(0, testData.shape[0]): a = fig.add_subplot(num_image_rows/2, num_image_rows*2, i+1) a.set_title(i) testplot = plt.imshow(testData[i].reshape(28,28), cmap ="gray") plt.axis('off') result = testNN.forwardCompute(np.reshape(testData[60], (28*28,1))) letterIndex = np.argmax(result) print letterIndex print labelDict.keys()[labelDict.values().index(letterIndex)] <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: Podemos graficar estas raรญces, de la forma siguiente Step2: Note que estas raรญces no estรกn igualmente espaciadas, lo que se aprecia mejor al graficar la diferencia entre una raiz y la siguiente Step3: Vemos sin embargo que la diferencia $\alpha_{\nu,n+1}-\alpha_{\nu,n}$ tiende a $\pi$ para valores grandes de $n$. Step4: En este caso, el grรกfico de las diferencias es tambiรฉn similar al caso anterior
<ASSISTANT_TASK:> Python Code: for nu in range(5): print('nu = '+str(nu)+': '+str(jn_zeros(nu,5))) figure() nmax = 20 numax = 10 for nu in range(numax): scatter(nu*ones(nmax),jn_zeros(nu,nmax)) ylim(0,50) xlim(-1,numax) xlabel('$\\nu$', fontsize=15) ylabel(r'$\alpha_{\nu,n}$', fontsize=15) xticks(range(numax)) grid() savefig('../figs/fig-Bessel-ceros-01.pdf') figure() nmax = 20 numax = 10 for nu in range(numax): plot(range(nmax-1),diff(jn_zeros(nu,nmax)), marker='o', markersize=5, lw=1, label='$\\nu = %d$'%nu) xlim(-1,nmax-1) ylim(3,) xlabel('$n$', fontsize=15) ylabel('$\\alpha_{\\nu,n+1}-\\alpha_{\\nu,n}$', fontsize=15) xticks(range(nmax)) legend() grid() savefig('../figs/fig-Bessel-ceros-02.pdf') for nu in range(5): print('nu = '+str(nu)+': '+str(jnp_zeros(nu,5))) figure() nmax = 20 numax = 10 for nu in range(numax): scatter(nu*ones(nmax),jnp_zeros(nu,nmax)) ylim(0,50) xlim(-1,numax) xlabel('$\\nu$', fontsize=15) ylabel('$\\beta_{\\nu,n}$', fontsize=15) xticks(range(numax)) grid() figure() nmax = 20 numax = 10 for nu in range(numax): plot(range(nmax-1),diff(jnp_zeros(nu,nmax)), marker='o', markersize=5, lw=1, label='$\\nu = %d$'%nu) xlim(-1,nmax-1) ylim(3,) xlabel('$n$', fontsize=15) ylabel('$\\beta_{\\nu,n+1}-\\beta_{\\nu,n}$', fontsize=15) xticks(range(nmax)) legend() grid() <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: Curve data Step2: You can also access curves by index (remembering that the first index is zero but the first curve is the depth). For example, the last twelve values Step3: All the curves are stored as a two-dimensional ndarray under the data attribute Step4: Header information Step5: In order from top to bottom as they usually are in LAS files, the section attributes are Step6: A simpler way of viewing this is to use the special _d attribute of each section's dictionary, but note that any changes to this dictionary do not have any effect Step7: To change metadata information you have to edit the Metadata object's particular field explicitly Step8: The other sections have slightly different classes for records Step9: For convenience there's a special attribute which is an ordinary dictionary that brings together all the metadata in the file. Again, changes to this dictionary have no effect. Step10: As per the standard, the ~Other section is free text. I know many companies put LAS-formatted metadata in here, but this isn't parsed yet. Step11: Finally there is some useful information in the provenance attribute that depends on how you opened the file in the first place Step12: Curves (more detail) Step13: Also, the index of the LAS file can be accessed directly by the .index attribute
<ASSISTANT_TASK:> Python Code: import las_reader l = las_reader.read("GT14574.LAS") print(type(l)) print(l._text) l.keys() l['NEUT'] print(l['GCPS'][-12:]) print(l[1][-12:]) print(l['NEUT'][-12:]) print(l[-1][-12:]) print(l.data.shape) print(l.data) m = las_reader.las.Metadata(mnemonic="SPEED", unit='something?', value=1.5, descr='The speed of light') m.value = 3 * 10 ** 8 m.unit = 'm/s' print(m) l.version l.version['VERS'].value l.well l.well._d l.well['SRVC'].value = "My logging company -- not anyone's" l.well._d l.params l.metadata print l.other l.provenance l.curves neutron_log = l.get_curve_name("NEUT") print(neutron_log) neutron_log.data print(l["DEPT"][:10]) print(l.index[:10]) import matplotlib.pyplot as plt import matplotlib.gridspec as gridspec %matplotlib inline l2 = las_reader.read("GT1457B.LAS") fig = plt.figure(figsize=(18, 5)) gs = gridspec.GridSpec(1, len(l2.curves)-1, wspace=0.2) for i, curve in enumerate(l2.curves[1:]): if i > 0: shareax = ax else: shareax = False ax = fig.add_subplot(gs[i], sharey=None) ax.plot(curve.data, l2.index) ax.set_title(curve.mnemonic) if i > 0: ax.set_yticklabels([]) ax.set_ylim(*ax.get_ylim()[::-1]) ax.set_xticklabels(["%.0f" % xi if xi in ax.get_xlim() else "" for xi in ax.get_xticks()], rotation=30) print(l2._text) <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: Marginalisation Step5: We now use pythons lambda functions to generate the specific prior and likelihoods Step6: We now have a choice about how to initialise the walkers. In the emcee docs the Step8: We can plot the progress of each walker during the MCMC exploration of Step9: We now can plot the marginal distributions in a so-called triangle plot. First "burning"
<ASSISTANT_TASK:> Python Code: # Model parameters A = 2.3 f = 1 X0 = 2.5 # Noise parameter sigma = 0.6 N = 300 t = np.sort(np.random.uniform(0, 10, N)) X = X0 + A * np.sin(2 * np.pi * f * t) + np.random.normal(0, sigma, N) plt.plot(t, X, "o") plt.xlabel("$t$") plt.ylabel(r"$X_{\mathrm{obs}}$") plt.show() def Generic_lnuniformprior(theta, theta_lims): Generic uniform priors on theta Parameters ---------- theta : array_like Value of the parameters theta_lims: array_like of shape (len(theta), 2) Array of pairs [min, max] for each theta paramater theta_lims = np.array(theta_lims) if all(theta - theta_lims[:, 0] > 0 ) and all(theta_lims[:, 1] - theta > 0): return np.prod(1.0/np.diff(theta_lims, axis=1)) return -np.inf def Generic_lnlike(theta, t, x, model): Generic likelihood function for signal in Gaussian noise Parameters ---------- theta : array_like Value of the parameters, the noise strength `sigma` should ALWAYS be the last element in the list t : array_like The independant variable x : array_like The observed dependent variable model : func Signal model, calling `model(theta[:-1], t)` should produced the corresponding value of the signal alone `x_val`, without noise. sigma2 = theta[-1]**2 return -0.5*(np.sum((x-model(theta[:-1], t))**2 / sigma2 + np.log(2*np.pi*sigma2))) # Prior theta_lims = [[2.0, 2.5], [0.99, 1.01], [1.0, 5.0], [0.3, 0.9] ] lnprior = lambda theta: Generic_lnuniformprior(theta, theta_lims) # Likelihood def model(theta, t): A, f, X0 = theta return X0 + A * np.sin(2 * np.pi * f * t) lnlike = lambda theta, x, y: Generic_lnlike(theta, x, y, model) # Tie the two together def lnprob(theta, x, y): Generic function ties together the lnprior and lnlike lp = lnprior(theta) if not np.isfinite(lp): return -np.inf return lp + lnlike(theta, x, y) ndim = 4 nwalkers = 100 # Initialise the walkers walker_pos = [[np.random.uniform(tl[0], tl[1]) for tl in theta_lims] for i in range(nwalkers)] # Run the sampler sampler = emcee.EnsembleSampler(nwalkers, ndim, lnprob, args=(t, X)) out = sampler.run_mcmc(walker_pos, 2000) def PlotWalkers(sampler, symbols=None, alpha=0.4, color="k"): Plot all the chains from a sampler nwalkers, nsteps, ndim = sampler.chain.shape fig, axes = plt.subplots(ndim, 1, sharex=True, figsize=(8, 9)) for i in range(ndim): axes[i].plot(sampler.chain[:, :, i].T, color="k", alpha=alpha) if symbols: axes[i].set_xlabel(symbols[i]) symbols = ["$A$", "$f$", "$X_{0}$", "$\sigma$"] PlotWalkers(sampler, symbols=symbols) plt.show() samples = sampler.chain[:, 1000:, :].reshape((-1, ndim)) fig = triangle.corner(samples, labels=symbols, truths=[A, f, X0, sigma] ) axes = fig.get_axes() ax = axes[0] def prior(x): return np.zeros(len(x)) + 7419.1 xlims = ax.get_xlim() x = np.linspace(xlims[0], xlims[1], 100) ax.plot(x, prior(x), "r", lw=10) print ax.get_ylim(), ax.get_xlim() 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: We want to compute the adjustment of the economy when this tax, goes back progressively from 10% to 0%, over 10 periods.
<ASSISTANT_TASK:> Python Code: model.calibration model.residuals() exo_g = linspace(0.1,0,10) # this is a vector of size 10 exo_g = atleast_2d(exo_g).T # the solver expects a 1x10 vector print(exo_g.shape) exo_g # Let's solve for the optimal adjustment by assuming that the # economy returns to steady-state after T=50 periods. from dolo.algos.perfect_foresight import deterministic_solve sim = deterministic_solve(model, shocks=exo_g, T=50) display(sim) # it returns a timeseries object model plt.plot(figsize=(10,10)) plt.subplot(221) plt.plot(sim['k'], label='capital') plt.plot(sim['y'], label='production') plt.legend() plt.subplot(222) plt.plot(sim['g'], label='gvt. spending') plt.plot(sim['c'], label='consumption') plt.legend() plt.subplot(223) plt.plot(sim['n'], label='work') plt.plot(sim['i'], label='investment') plt.legend() plt.subplot(224) plt.plot(sim['w'], label='wages') plt.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: Encoding syllables Step2: Once the syllabic segments have been marked as such in the phone inventory, the next step is to actually create the syllable Step3: The encode_syllables function uses a maximum onset algorithm based on all existing word-initial sequences of phones not Step4: Once pauses are encoded, the next step is to actually create the utterance annotations as follows Step5: In many cases, it is desirable Step6: Once enrichment is complete, we can then query information and extract information about these characteristics of speakers. Step7: Following this enrichment step, words will have a type property of stress_pattern and syllables will have a token property Step8: Next we will encode the number of syllables per word
<ASSISTANT_TASK:> Python Code: import os from polyglotdb import CorpusContext corpus_root = '/mnt/e/Data/pg_tutorial' syllabics = ["ER0", "IH2", "EH1", "AE0", "UH1", "AY2", "AW2", "UW1", "OY2", "OY1", "AO0", "AH2", "ER1", "AW1", "OW0", "IY1", "IY2", "UW0", "AA1", "EY0", "AE1", "AA0", "OW1", "AW0", "AO1", "AO2", "IH0", "ER2", "UW2", "IY0", "AE2", "AH0", "AH1", "UH2", "EH2", "UH0", "EY1", "AY0", "AY1", "EH0", "EY2", "AA2", "OW2", "IH1"] with CorpusContext('pg_tutorial') as c: c.encode_type_subset('phone', syllabics, 'syllabic') with CorpusContext('pg_tutorial') as c: c.encode_syllables(syllabic_label='syllabic') pause_labels = ['<SIL>'] with CorpusContext('pg_tutorial') as c: c.encode_pauses(pause_labels) with CorpusContext('pg_tutorial') as c: c.encode_utterances(min_pause_length=0.15) speaker_enrichment_path = os.path.join(corpus_root, 'enrichment_data', 'speaker_info.csv') with CorpusContext('pg_tutorial') as c: c.enrich_speakers_from_csv(speaker_enrichment_path) lexicon_enrichment_path = os.path.join(corpus_root, 'enrichment_data', 'iscan_lexicon.csv') with CorpusContext('pg_tutorial') as c: c.enrich_lexicon_from_csv(lexicon_enrichment_path) with CorpusContext('pg_tutorial') as c: c.encode_stress_from_word_property('stress_pattern') with CorpusContext('pg_tutorial') as c: c.encode_rate('utterance', 'syllable', 'speech_rate') with CorpusContext('pg_tutorial') as c: c.encode_count('word', 'syllable', 'num_syllables') <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: We'll also import our demand data Step2: As we have fixed costs and variable costs, we'll need to model both production and the status of the factory i.e. whether it is on or off. Step3: Factory status is modelled as a binary variable. It will have a value of 1 if the factory is on and a value of 0 when the factory is off. Step4: We instantiate our model and use LpMinimize as the aim is to minimise costs. Step5: In our objective function we include our 2 costs Step6: We build up our constraints Step7: An issue we run into here is that in linear programming we can't use conditional constraints. Step8: We then solve the model Step9: Let's take a look at the optimal production schedule output for each month from each factory. For ease of viewing we'll output the data to a pandas DataFrame. Step10: Notice above that the factory status is 0 when not producing and 1 when it is producing
<ASSISTANT_TASK:> Python Code: import pandas as pd import pulp factories = pd.DataFrame.from_csv('csv/factory_variables.csv', index_col=['Month', 'Factory']) factories factories.index demand = pd.DataFrame.from_csv('csv/monthly_demand.csv', index_col=['Month']) demand production = pulp.LpVariable.dicts("production", ((month, factory) for month, factory in factories.index), lowBound=0, cat='Integer') production factory_status = pulp.LpVariable.dicts("factory_status", ((month, factory) for month, factory in factories.index), cat='Binary') model = pulp.LpProblem("Cost minimising scheduling problem", pulp.LpMinimize) model += pulp.lpSum( [production[month, factory] * factories.loc[(month, factory), 'Variable_Costs'] for month, factory in factories.index] + [factory_status[month, factory] * factories.loc[(month, factory), 'Fixed_Costs'] for month, factory in factories.index] ) # Production in any month must be equal to demand months = demand.index for month in months: model += production[(month, 'A')] + production[(month, 'B')] == demand.loc[month, 'Demand'] # Production in any month must be between minimum and maximum capacity, or zero. for month, factory in factories.index: min_production = factories.loc[(month, factory), 'Min_Capacity'] max_production = factories.loc[(month, factory), 'Max_Capacity'] model += production[(month, factory)] >= min_production * factory_status[month, factory] model += production[(month, factory)] <= max_production * factory_status[month, factory] #model += production[(month, factory)] >= min_production #model += production[(month, factory)] <= max_production # Factory B is off in May model += factory_status[5, 'B'] == 0 model += production[5, 'B'] == 0 model.solve() pulp.LpStatus[model.status] x=production[1, 'A'] type(x) output = [] for month, factory in production: var_output = { 'Month': month, 'Factory': factory, 'Production': production[(month, factory)].varValue, 'Factory Status': factory_status[(month, factory)].varValue } output.append(var_output) output_df = pd.DataFrame.from_records(output).sort_values(['Month', 'Factory']) output_df.set_index(['Month', 'Factory'], inplace=True) output_df # Print our objective function value (Total Costs) print(pulp.value(model.objective)) <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: See UCI Data page Step2: 3. Data Preparation Step3: 4. Modeling
<ASSISTANT_TASK:> Python Code: ## import statements %matplotlib inline import numpy as np import pandas as pd import matplotlib as mpl import matplotlib.pyplot as plt import seaborn as sns import sklearn from sklearn import datasets from sklearn.cross_validation import cross_val_predict from sklearn import linear_model boston_cols = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV'] df = pd.read_csv("data/boston/housing.data", sep='\s+', names=boston_cols) df.head() sns.pairplot(df[["CRIM", "AGE", "RM", "MEDV"]]) df.describe() X = df boston = datasets.load_boston() y = boston.target from sklearn.linear_model import LinearRegression lm = LinearRegression() lm.fit(X, y) print('Estimated intercept coefficent:', lm.intercept_) print('Number of coefficients:', len(lm.coef_)) # def predict_house(crim, zn, indus, chas, nox, rm, age, dis, rad, tax, ptratio, b, lstat): # return lm.intercept_ + lm.coef_[0] * crim \ # + zn * lm.coef_[1] \ # + indus * lm.coef_[2] \ # + chas * lm.coef_[3] \ # + nox * lm.coef_[4] \ # + rm * lm.coef_[5] \ # + age * lm.coef_[6] \ # + dist * lm.coef_[7] \ # + rad * lm.coef_[8] \ # + tax * lm.coef_[9] \ # + ptratio * lm.coef_[10] \ # + b * lm.coef_[11] \ # + lstat * lm.coef_[12] #print(X.iloc[[41]].values) #print(y[41]) print("Predicted House price", lm.predict(X)[41] * 1000) print("Equation house price", (lm.intercept_ + np.dot(lm.coef_, X.iloc[[41]].values[0])) * 1000) print("Target price", y[41] * 1000) print("Residual price", (lm.predict(X)[41] - y[41]) * 1000) print("R^2 =", lm.score(X, y)) predicted = cross_val_predict(lm, boston.data, y, cv=10) fig, ax = plt.subplots() ax.scatter(y, predicted) ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4) ax.set_xlabel('Measured') ax.set_ylabel('Predicted') plt.show() errors = {} for feature in boston.feature_names: lm = LinearRegression() lm.fit(X[[feature]], y) mean_squared_error = np.mean((y - lm.predict(X[[feature]])) ** 2) errors[feature] = mean_squared_error errors = sorted(errors.items(), key=lambda x: x[1]) print("Features that Minimize Error") print(30 * "-") for e in errors: print(e[0], "\t", e[1]) <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: Harmonic Minimization Step2: Next we need to generate some random positions as well as particle sizes. Step3: Then we need to construct our FIRE minimization function. Like all simulations in JAX MD, the FIRE optimizer is two functions Step4: Now let's actually do minimization, keepting track of the energy and particle positions as we go. Step5: Let's plot the nearest distance for different species pairs. We see that particles on average have neighbors that are the right distance apart. Step6: Now let's plot the system. It's nice and minimized! Step7: If we want, we can visualize the entire minimization. Step8: Finally, let's plot the energy trajectory that we observer during FIRE minimization.
<ASSISTANT_TASK:> Python Code: #@title Imports & Utils !pip install jax-md import numpy as onp import jax.numpy as np from jax.config import config config.update('jax_enable_x64', True) from jax import random from jax import jit from jax_md import space, smap, energy, minimize, quantity, simulate from jax_md.colab_tools import renderer import matplotlib import matplotlib.pyplot as plt import seaborn as sns sns.set_style(style='white') def format_plot(x, y): plt.grid(True) plt.xlabel(x, fontsize=20) plt.ylabel(y, fontsize=20) def finalize_plot(shape=(1, 1)): plt.gcf().set_size_inches( shape[0] * 1.5 * plt.gcf().get_size_inches()[1], shape[1] * 1.5 * plt.gcf().get_size_inches()[1]) plt.tight_layout() N = 1000 dimension = 2 box_size = quantity.box_size_at_number_density(N, 0.8, dimension) displacement, shift = space.periodic(box_size) key = random.PRNGKey(0) R = box_size * random.uniform(key, (N, dimension), dtype=np.float32) # The system ought to be a 50:50 mixture of two types of particles, one # large and one small. sigma = np.array([[1.0, 1.2], [1.2, 1.4]]) N_2 = int(N / 2) species = np.where(np.arange(N) < N_2, 0, 1) energy_fn = energy.soft_sphere_pair(displacement, species=species, sigma=sigma) fire_init, fire_apply = minimize.fire_descent(energy_fn, shift) fire_apply = jit(fire_apply) fire_state = fire_init(R) E = [] trajectory = [] for i in range(200): fire_state = fire_apply(fire_state) E += [energy_fn(fire_state.position)] trajectory += [fire_state.position] R = fire_state.position trajectory = np.stack(trajectory) metric = lambda R: space.distance(space.map_product(displacement)(R, R)) dr = metric(R) plt.plot(np.min(dr[:N_2, :N_2] + 5 * np.eye(N_2, N_2), axis=0), 'o', label='$\\sigma_{AA}$') plt.plot(np.min(dr[:N_2, N_2:] + 5 * np.eye(N_2, N_2), axis=0), 'o', label='$\\sigma_{AB}$') plt.plot(np.min(dr[N_2:, N_2:] + 5 * np.eye(N_2, N_2), axis=0), 'o', label='$\\sigma_{BB}$') plt.legend() format_plot('', 'min neighbor distance') finalize_plot() ms = 45 R_plt = onp.array(fire_state.position) plt.plot(R_plt[:N_2, 0], R_plt[:N_2, 1], 'o', markersize=ms * 0.5) plt.plot(R_plt[N_2:, 0], R_plt[N_2:, 1], 'o', markersize=ms * 0.7) plt.xlim([0, np.max(R[:, 0])]) plt.ylim([0, np.max(R[:, 1])]) plt.axis('off') finalize_plot((2, 2)) diameter = np.where(species, 1.4, 1.0) color = np.where(species[:, None], np.array([[1.0, 0.5, 0.05]]), np.array([[0.15, 0.45, 0.8]])) renderer.render(box_size, { 'particles': renderer.Disk(trajectory, diameter, color)}, buffer_size=50) plt.plot(E, linewidth=3) format_plot('step', '$E$') finalize_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 Cifar Step2: Train Logistic Regression Model Step3: Deploy Logistic Regression Model Step4: Link your app to your model Step5: You can view which models your app is linked to by running the code below. Step7: Now that you've deployed and linked your model to your app, go ahead and check back on your running frontend application from part 1. You should see the accuracy rise from around 50% to the accuracy of your SKLearn model (68-74%), without having to stop or modify your application at all! Step8: Deploy TensorFlow Model Step9: Inspect Clipper Metrics Step10: Congratulations! You've now successfully completed the tutorial. You started Clipper, created an application and queried it from a frontend client, and deployed two models trained in two different machine learning frameworks (Scikit-Learn and TensorFlow) to the running system.
<ASSISTANT_TASK:> Python Code: import sys import os from clipper_admin import Clipper # Change the username if necessary user = "" # Set the path to the SSH key key = "" # Set the SSH host host = "" clipper = Clipper(host, user, key) cifar_loc = "" import cifar_utils train_x, train_y = cifar_utils.filter_data( *cifar_utils.load_cifar(cifar_loc, cifar_filename="cifar_train.data", norm=True)) test_x, test_y = cifar_utils.filter_data( *cifar_utils.load_cifar(cifar_loc, cifar_filename="cifar_test.data", norm=True)) from sklearn import linear_model as lm def train_sklearn_model(m, train_x, train_y): m.fit(train_x, train_y) return m lr_model = train_sklearn_model(lm.LogisticRegression(), train_x, train_y) print("Logistic Regression test score: %f" % lr_model.score(test_x, test_y)) model_name = "birds_vs_planes_classifier" model_added = clipper.deploy_model( model_name, 1, lr_model, "clipper/sklearn_cifar_container:latest", "doubles", num_containers=1 ) print("Model deploy successful? {success}".format(success=model_added)) clipper.link_model_to_app(app_name, model_name) clipper.get_linked_models(app_name) import os import tensorflow as tf import numpy as np tf_cifar_model_path = os.path.abspath("tf_cifar_model/cifar10_model_full") tf_session = tf.Session('', tf.Graph()) with tf_session.graph.as_default(): saver = tf.train.import_meta_graph("%s.meta" % tf_cifar_model_path) saver.restore(tf_session, tf_cifar_model_path) def tensorflow_score(session, test_x, test_y): NOTE: This predict method expects pre-whitened (normalized) images logits = session.run('softmax_logits:0', feed_dict={'x:0': test_x}) relevant_activations = logits[:, [cifar_utils.negative_class, cifar_utils.positive_class]] preds = np.argmax(relevant_activations, axis=1) return float(np.sum(preds == test_y)) / float(len(test_y)) print("TensorFlow CNN test score: %f" % tensorflow_score(tf_session, test_x, test_y)) model_added = clipper.deploy_model( model_name, 2, os.path.abspath("tf_cifar_model"), "clipper/tf_cifar_container:latest", "doubles", num_containers=1 ) print("Model deploy successful? {success}".format(success=model_added)) clipper.inspect_instance() clipper.stop_all() <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: Acquiring and seeing trends in multidimensional data Step2: FIGURE 3.1. For the Advertising data, the least squares fit for the regression of sales onto TV is shown. The fit is found by minimizing the sum of squared errors. Step3: Let $\hat{y}_i = \hat{\beta_0} + \hat{\beta_1}x_i$ be the prediction for $Y$ based on the $i$-th value of $X$. Step4: The residual is the difference between the model output and the observed output Step5: The residual is not very useful directly because balances over-estimates and under-estimates to produce the best overall estimate with the least error. We can understand the overall goodness of fit by the residual sum of squares - RSS. Step6: With this, we can build an independent model for each of the inputs and look at the associates RSS. Step7: We can look at how well each of these inputs predict the output by visualizing the residuals. Step8: Figure 3.2 - RSS and least squares regression Step9: 3.1.2 Assessing the accuracy of coefficient estimates Step10: "The property of unbiasedness holds for the least squares coefficient estimates given by (3.4) as well Step11: 3.1.3 Assessing the Acurracy of the Model Step12: The $R^2$ statistic provides an alternative measure of fit. It takes the form of a proportionโ€”the proportion of variance explainedโ€”and so it always takes on a value between 0 and 1, and is independent of the scale of Y.
<ASSISTANT_TASK:> Python Code: # HIDDEN # For Tables reference see http://data8.org/datascience/tables.html # This useful nonsense should just go at the top of your notebook. from datascience import * %matplotlib inline import matplotlib.pyplot as plots import numpy as np from sklearn import linear_model plots.style.use('fivethirtyeight') plots.rc('lines', linewidth=1, color='r') from ipywidgets import interact, interactive, fixed import ipywidgets as widgets # datascience version number of last run of this notebook version.__version__ import sys sys.path.append("..") from ml_table import ML_Table import locale locale.setlocale( locale.LC_ALL, 'en_US.UTF-8' ) # Getting the data advertising = ML_Table.read_table("./data/Advertising.csv") advertising.relabel(0, "id") ax = advertising.plot_fit_1d('Sales', 'TV', advertising.regression_1d('Sales', 'TV')) _ = ax.set_xlim(-20,300) lr = advertising.linear_regression('Sales', 'TV') advertising.plot_fit_1d('Sales', 'TV', lr.model) advertising.lm_summary_1d('Sales', 'TV') # Get the actual parameters that are captured within the model advertising.regression_1d_params('Sales', 'TV') # Regression yields a model. The computational representation of a model is a function # That can be applied to an input, 'TV' to get an estimate of an output, 'Sales' advertise_model_tv = advertising.regression_1d('Sales', 'TV') # Sales with no TV advertising advertise_model_tv(0) # Sales with 100 units TV advertising advertise_model_tv(100) # Here's the output of the model applied to the input data advertise_model_tv(advertising['TV']) residual = advertising['Sales'] - advertise_model_tv(advertising['TV']) residual # Residual Sum of Squares RSS = sum(residual*residual) RSS # This is common enough that we have it provided as a method advertising.RSS_model('Sales', advertising.regression_1d('Sales', 'TV'), 'TV') # And we should move toward a general regression framework advertising.RSS_model('Sales', advertising.linear_regression('Sales', 'TV').model, 'TV') advertising_models = Table().with_column('Input', ['TV', 'Radio', 'Newspaper']) advertising_models['Model'] = advertising_models.apply(lambda i: advertising.regression_1d('Sales', i), 'Input') advertising_models['RSS'] = advertising_models.apply(lambda i, m: advertising.RSS_model('Sales', m, i), ['Input', 'Model']) advertising_models advertising_models = Table().with_column('Input', ['TV', 'Radio', 'Newspaper']) advertising_models['Model'] = advertising_models.apply(lambda i: advertising.linear_regression('Sales', i).model, 'Input') advertising_models['RSS'] = advertising_models.apply(lambda i, m: advertising.RSS_model('Sales', m, i), ['Input', 'Model']) advertising_models for mode, mdl in zip(advertising_models['Input'], advertising_models['Model']) : advertising.plot_fit_1d('Sales', mode, mdl) # RSS at arbitrary point res = lambda b0, b1: advertising.RSS('Sales', b0 + b1*advertising['TV']) res(7.0325935491276965, 0.047536640433019729) ax = advertising.RSS_contour('Sales', 'TV', sensitivity=0.2) ax = advertising.RSS_wireframe('Sales', 'TV', sensitivity=0.2) # The minima point advertising.linear_regression('Sales', 'TV').params # Some other points along the trough points = [(0.042, 8.0), (0.044, 7.6), (0.050, 6.6), (0.054, 6.0)] ax = advertising.RSS_contour('Sales', 'TV', sensitivity=0.2) ax.plot([b0 for b1, b0 in points], [b1 for b1, b0 in points], 'ro') [advertising.RSS('Sales', b0 + b1*advertising['TV']) for b1,b0 in points] # Models as lines corresponding to points along the near-minimal vectors. ax = advertising.plot_fit_1d('Sales', 'TV', advertising.linear_regression('Sales', 'TV').model) for b1, b0 in points: fit = lambda x: b0 + b1*x ax.plot([0, 300], [fit(0), fit(300)]) _ = ax.set_xlim(-20,300) def model (x): return 3*x + 2 def population(n, noise_scale = 1): sample = ML_Table.runiform('x', n, -2, 2) noise = ML_Table.rnorm('e', n, sd=noise_scale) sample['Y'] = sample.apply(model, 'x') + noise['e'] return sample data = population(100, 2) data.scatter('x') ax = data.plot_fit('Y', data.linear_regression('Y').model) data.linear_regression('Y').params # A random sample of the population sample = data.sample(10) sample.plot_fit('Y', sample.linear_regression('Y').model) nsamples = 5 ax = data.plot_fit('Y', data.linear_regression('Y').model, linewidth=3) for s in range(nsamples): fit = data.sample(10).linear_regression('Y').model ax.plot([-2, 2], [fit(-2), fit(2)], linewidth=1) adv_sigma = advertising.RSE_model('Sales', advertising.linear_regression('Sales', 'TV').model, 'TV') adv_sigma b0, b1 = advertising.linear_regression('Sales', 'TV').params b0, b1 advertising.RSS_model('Sales', advertising.linear_regression('Sales', 'TV').model, 'TV') SE_b0, SE_b1 = advertising.SE_1d_params('Sales', 'TV') SE_b0, SE_b1 # b0 95% confidence interval (b0-2*SE_b0, b0+2*SE_b0) # b1 95% confidence interval (b1-2*SE_b1, b1+2*SE_b1) # t-statistic of the slope b0/SE_b0 # t-statistics of the intercept b1/SE_b1 # Similar to summary of a linear model in R advertising.lm_summary_1d('Sales', 'TV') # We can just barely reject the null hypothesis for Newspaper # advertising effecting sales advertising.lm_summary_1d('Sales', 'Newspaper') adver_model = advertising.regression_1d('Sales', 'TV') advertising.RSE_model('Sales', adver_model, 'TV') advertising.R2_model('Sales', adver_model, 'TV') # the other models of advertising suggest that there is more going on advertising.R2_model('Sales', adver_model, 'Radio') advertising.R2_model('Sales', adver_model, 'Newspaper') <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: Building an Animation Step2: You should see the box slide 1 meter to the right in the viewer. If you missed the animation, you can run it again from the viewer. Click "Open Controls", find the "Animations" section, and click "play". Step3: To animate the camera, we just have to do that same kind of settransform! to individual frames in an animation Step4: We can also animate object properties. For example, let's animate the camera's zoom property to smoothly zoom out and then back in. Note that to do this, we have to access a deeper path in the visualizer to get to the actual camera object. For more information, see Step5: Recording an Animation
<ASSISTANT_TASK:> Python Code: import meshcat from meshcat.geometry import Box vis = meshcat.Visualizer() ## To open the visualizer in a new browser tab, do: # vis.open() ## To open the visualizer inside this jupyter notebook, do: # vis.jupyter_cell() vis["box1"].set_object(Box([0.1, 0.2, 0.3])) from meshcat.animation import Animation import meshcat.transformations as tf anim = Animation() with anim.at_frame(vis, 0) as frame: # `frame` behaves like a Visualizer, in that we can # call `set_transform` and `set_property` on it, but # it just stores information inside the animation # rather than changing the current visualization frame["box1"].set_transform(tf.translation_matrix([0, 0, 0])) with anim.at_frame(vis, 30) as frame: frame["box1"].set_transform(tf.translation_matrix([0, 1, 0])) # `set_animation` actually sends the animation to the # viewer. By default, the viewer will play the animation # right away. To avoid that, you can also pass `play=false`. vis.set_animation(anim) vis["/Cameras/default"].set_transform(tf.translation_matrix([0, 0, 1])) anim = Animation() with anim.at_frame(vis, 0) as frame: frame["/Cameras/default"].set_transform(tf.translation_matrix([0, 0, 0])) with anim.at_frame(vis, 30) as frame: frame["/Cameras/default"].set_transform(tf.translation_matrix([0, 0, 1])) # we can repeat the animation playback with the # repetitions argument: vis.set_animation(anim, repetitions=2) anim = Animation() camera_path = "/Cameras/default/rotated/<object>" with anim.at_frame(vis, 0) as frame: frame[camera_path].set_property("zoom", "number", 1) with anim.at_frame(vis, 30) as frame: frame[camera_path].set_property("zoom", "number", 0.5) with anim.at_frame(vis, 60) as frame: frame[camera_path].set_property("zoom", "number", 1) # While we're animating the camera zoom, we can also animate any other # properties we want. Let's simultaneously translate the box during # the same animation: with anim.at_frame(vis, 0) as frame: frame["box1"].set_transform(tf.translation_matrix([0, -1, 0])) with anim.at_frame(vis, 60) as frame: frame["box1"].set_transform(tf.translation_matrix([0, 1, 0])) vis.set_animation(anim) from meshcat.animation import convert_frames_to_video convert_frames_to_video("/home/rdeits/Downloads/meshcat_1528401494656.tar", overwrite=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: Time and space discretization as a Taylor expansion. Step2: Solve forward in time Step3: Define the discrete model Step4: Create functions for the PDE Step5: A Forward propagation example Step6: Adjoint test Step7: Least square objective Gradient Step8: Adjoint test for the gradient Step9: Jacobian test Step10: Gradient test
<ASSISTANT_TASK:> Python Code: p=Function('p') b=Function('b') m,s,h,r = symbols('m s h r') m=M(x,y) q=Q(x,y,t) d=D(x,y,t) e=E(x,y) r=rho(x,y) dtt=as_finite_diff(p(x,y,t).diff(t,t), [t-s,t, t+s]) dt=as_finite_diff(p(x,y,t).diff(t), [t-s, t+s]) # Spacial finite differences can easily be extended to higher order by increasing the list of sampling point in the next expression. # Be sure to keep this stencil symmetric and everything else in the notebook will follow. dxx=as_finite_diff(p(x,y,t).diff(x,x), [x-h,x, x+h]) dyy=as_finite_diff(p(x,y,t).diff(y,y), [y-h,y, y+h]) dy=as_finite_diff(p(x,y,t).diff(y), [y-h, y+h]) dx=as_finite_diff(p(x,y,t).diff(x), [x-h, x+h]) dyr=as_finite_diff(b(x,y).diff(y), [y-h, y+h]) dxr=as_finite_diff(b(x,y).diff(x), [x-h, x+h]) dtt,dxx,dyy,dt,dx,dy # In practice, compute rho. grad(rho) upfront (this is a constant) and just compute the following expression, it avoids # the recomputation of the gradient at every time step. int the following X and Y are the component of rho.grad(rho) in X and Y respectively gradgrad=X*dx+Y*dy expand(gradgrad) lap=(dxx+dyy) expand(lap + gradgrad) # Forward wave equation wave_equation = m*dtt- (dxx+dyy)- r*(dxr*dx+dyr*dy) - q + e*dt stencil = solve(wave_equation,p(x,y,t+s))[0] ts=lambdify((p(x,y,t-s),p(x-h,y,t), p(x,y,t), p(x+h,y,t),p(x,y-h,t), p(x,y+h,t),b(x-h,y), b(x,y), b(x+h,y),b(x,y-h), b(x,y+h), q , m,r, s, h,e),stencil,"numpy") stencil # Adjoint wave equation wave_equationA = m*dtt- (dxx+dyy) - r*(dxr*dx+dyr*dy) - d - e*dt stencilA = solve(wave_equationA,p(x,y,t-s))[0] tsA=lambdify((p(x,y,t+s),p(x-h,y,t), p(x,y,t), p(x+h,y,t),p(x,y-h,t), p(x,y+h,t),b(x-h,y), b(x,y), b(x+h,y),b(x,y-h), b(x,y+h), d, m,r, s, h,e),stencilA,"numpy") stencilA import matplotlib.pyplot as plt from matplotlib import animation hstep=25 #space increment d = minv/(10*f0); tstep=2 #time increment dt < .5 * hstep /maxv; tmin=0.0 #initial time tmax=600 #simulate until xmin=-500.0 - 10*hstep #left bound xmax=500.0 + 10*hstep #right bound...assume packet never reaches boundary ymin=-500.0 - 10*hstep #left bound ymax=500.0 + 10*hstep #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 nt = int((tmax-tmin)/tstep) + 2 #number of points on t grid xsrc=-400 ysrc=0.0 xrec = nbpml+4 #set source as Ricker wavelet for f0 def source(x,y,t): r = (np.pi*f0*(t-t0)) val = (1-2.*r**2)*np.exp(-r**2) if abs(x-xsrc)<hstep/2 and abs(y-ysrc)<hstep/2: return val else: return 0.0 def dampx(x): dampcoeff=1.5*np.log(1.0/0.001)/(5.0*hstep); 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=1.5*np.log(1.0/0.001)/(5.0*hstep); 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 # Velocity and density models def smooth10(vel,nx,ny): out=np.ones((nx,ny)) out[:,:]=vel[:,:] for a in range(5,nx-6): out[a,:]=np.sum(vel[a-5:a+5,:], axis=0) /10 return out # True velocity vel=np.ones((nx,ny)) + 2.0 rho=np.ones((nx,ny)) vel[floor(nx/2):nx,:]=4.5 rho[floor(nx/2):nx,:]=2.0 rho=rho**-1 mt=vel**-2 # Smooth velocity v0=smooth10(vel,nx,ny) m0=v0**-2 dm=m0-mt def Forward(nt,nx,ny,m,rho): u=np.zeros((nt,nx,ny)) rec=np.zeros((nt,ny-2)) for ti in range(0,nt): for a in range(1,nx-1): for b in range(1,ny-1): src = source(xmin+a*hstep,ymin+b*hstep,tstep*ti) damp=dampx(a)+dampy(b) if ti==0: u[ti,a,b]=ts(0,0,0,0,0,0,rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], src,m[a,b],rho[a,b]**-1,tstep,hstep,damp) elif ti==1: u[ti,a,b]=ts(0,u[ti-1,a-1,b],u[ti-1,a,b],u[ti-1,a+1,b],u[ti-1,a,b-1],u[ti-1,a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], src,m[a,b],rho[a,b]**-1,tstep,hstep,damp) else: u[ti,a,b]=ts(u[ti-2,a,b],u[ti-1,a-1,b],u[ti-1,a,b],u[ti-1,a+1,b],u[ti-1,a,b-1],u[ti-1,a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], src,m[a,b],rho[a,b]**-1,tstep,hstep,damp) if a==xrec : rec[ti,b-1]=u[ti,a,b] return rec,u def Adjoint(nt,nx,ny,m,rho,rec): v=np.zeros((nt,nx,ny)) srca=np.zeros((nt)) for ti in range(nt-1, -1, -1): for a in range(1,nx-1): for b in range(1,ny-1): if a==xrec: resid=rec[ti,b-1] else: resid=0 damp=dampx(a)+dampy(b) if ti==nt-1: v[ti,a,b]=tsA(0,0,0,0,0,0,rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], resid,m[a,b],rho[a,b]**-1,tstep,hstep,damp) elif ti==nt-2: v[ti,a,b]=tsA(0,v[ti+1,a-1,b],v[ti+1,a,b],v[ti+1,a+1,b],v[ti+1,a,b-1],v[ti+1,a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], resid,m[a,b],rho[a,b]**-1,tstep,hstep,damp) else: v[ti,a,b]=tsA(v[ti+2,a,b],v[ti+1,a-1,b],v[ti+1,a,b],v[ti+1,a+1,b],v[ti+1,a,b-1],v[ti+1,a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], resid,m[a,b],rho[a,b]**-1,tstep,hstep,damp) if abs(xmin+a*hstep-xsrc)<hstep/2 and abs(ymin+b*hstep-ysrc)<hstep/2: srca[ti]=v[ti,a,b] return srca,v def Gradient(nt,nx,ny,m,rho,rec,u): v1=np.zeros((nx,ny)) v2=np.zeros((nx,ny)) v3=np.zeros((nx,ny)) grad=np.zeros((nx,ny)) for ti in range(nt-1,-1,-1): for a in range(1,nx-1): for b in range(1,ny-1): if a==xrec: resid=rec[ti,b-1] else: resid=0 damp=dampx(a)+dampy(b) v3[a,b]=tsA(v1[a,b],v2[a-1,b],v2[a,b],v2[a+1,b],v2[a,b-1],v2[a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], resid,m[a,b],rho[a,b]**-1,tstep,hstep,damp) grad[a,b]=grad[a,b]-(v3[a,b]-2*v2[a,b]+v1[a,b])*(u[ti,a,b]) v1,v2,v3=v2,v3,v1 # No update inside the pml, only in the physical domain # grad[0:nbpml-1,:]=0 # grad[nx-nbpml-1:nx-1,:]=0 # grad[:,0:nbpml-1]=0 # grad[:,ny-nbpml-1:ny-1]=0 return tstep**-2*grad def Born(nt,nx,ny,m,rho,dm): u1=np.zeros((nx,ny)) U1=np.zeros((nx,ny)) u2=np.zeros((nx,ny)) U2=np.zeros((nx,ny)) u3=np.zeros((nx,ny)) U3=np.zeros((nx,ny)) rec=np.zeros((nt,ny-2)) src2=0 for ti in range(0,nt): for a in range(1,nx-1): for b in range(1,ny-1): damp=dampx(a)+dampy(b) src = source(xmin+a*hstep,ymin+b*hstep,tstep*ti) u3[a,b]=ts(u1[a,b],u2[a-1,b],u2[a,b],u2[a+1,b],u2[a,b-1],u2[a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], src,m[a,b],rho[a,b]**-1,tstep,hstep,damp) src2 = -tstep**-2*(u3[a,b]-2*u2[a,b]+u1[a,b])*dm[a,b] U3[a,b]=ts(U1[a,b],U2[a-1,b],U2[a,b],U2[a+1,b],U2[a,b-1],U2[a,b+1],rho[a-1,b],rho[a,b],rho[a+1,b],rho[a,b-1],rho[a,b+1], src2,m[a,b],rho[a,b]**-1,tstep,hstep,damp) if a==xrec : rec[ti,b-1]=U3[a,b] u1,u2,u3=u2,u3,u1 U1,U2,U3=U2,U3,U1 return rec (rect,ut)=Forward(nt,nx,ny,mt,rho) fig = plt.figure() plts = [] # get ready to populate this list the Line artists to be plotted plt.hold("off") for i in range(nt): r = plt.imshow(ut[i,:,:]) # this is how you'd plot a single line... plts.append( [r] ) ani = animation.ArtistAnimation(fig, plts, interval=50, repeat = False) # run the animation #plt.show() fig2 = plt.figure() plt.hold("off") shotrec = plt.imshow(rect,vmin=-10,vmax=10) # this is how you'd plot a single line... #plt.show() (rec0,u0)=Forward(nt,nx,ny,m0,rho) (srca,v)=Adjoint(nt,nx,ny,m0,rho,rec0) plts = [] # get ready to populate this list the Line artists to be plotted plt.hold("off") for i in range(0,nt): r = plt.imshow(v[i,:,:]) # this is how you'd plot a single line... plts.append( [r] ) ani = animation.ArtistAnimation(fig, plts, interval=50, repeat = False) # run the animation #plt.show() shotrec = plt.plot(srca) # this is how you'd plot a single line... plt.show() # Actual adjoint test term1=0 for ti in range(0,nt): term1=term1+srca[ti]*source(xsrc,ysrc,(ti)*tstep) term2=LA.norm(rec0)**2 term1,term2,term1-term2,term1/term2 #if abs(term11/term21-1)<1e-9 # print('Adjoint test passed') # Misfit F0=.5*LA.norm(rec0-rect)**2 F0 Im1=Gradient(nt,nx,ny,m0,rho,rec0-rect,u0) shotrec = plt.imshow(rec0-rect,vmin=-100,vmax=100) # this is how you'd plot a single line... #plt.show() shotrec = plt.imshow(Im1,vmin=-100000,vmax=100000) # this is how you'd plot a single line... #plt.show() Im2=Gradient(nt,nx,ny,m0,rho,rec0-rect,u0) du1=Born(nt,nx,ny,m0,rho,dm) term11=np.dot((rec0-rect).reshape(-1),du1.reshape(-1)) term21=np.dot(Im2.reshape(-1),dm.reshape(-1)) term11,term21,term11-term21,term11/term21 #if abs(term11/term21-1)<1e-9 # print('Adjoint test passed') shotrec = plt.imshow(Im2,vmin=-10000,vmax=10000) # this is how you'd plot a single line... #plt.show() H=[1,0.1,0.01,.001,0.0001,0.00001,0.000001] (D1,u0)=Forward(nt,nx,ny,m0,rho) dub=Born(nt,nx,ny,m0,rho,dm) error1=np.zeros((7)) error2=np.zeros((7)) for i in range(0,7): mloc=m0+H[i]*dm (d,u)=Forward(nt,nx,ny,mloc,rho) error1[i] = LA.norm(d - D1,ord=1) error2[i] = LA.norm(d - D1 - H[i]*dub,ord=1) hh=np.zeros((7)) for i in range(0,7): hh[i]=H[i]*H[i] shotrec = plt.loglog(H,error1,H,H) # this is how you'd plot a single line... plt.show() shotrec = plt.loglog(H,error2,H,hh) # this is howyou'd plot a single line... plt.show() (DT,uT)=Forward(nt,nx,ny,mt,rho) (D1,u0)=Forward(nt,nx,ny,m0,rho) F0=.5*LA.norm(D1-DT)**2 g=Gradient(nt,nx,ny,m0,rho,D1-DT,u0) G=np.dot(g.reshape(-1),dm.reshape(-1)); error21=np.zeros((7)) error22=np.zeros((7)) for i in range(0,7): mloc=m0+H[i]*dm (D,u)=Forward(nt,nx,ny,mloc,rho) error21[i] = .5*LA.norm(D-DT)**2 -F0 error22[i] = .5*LA.norm(D-DT)**2 -F0 - H[i]*G shotrec = plt.loglog(H,error21,H,H) # this is how you'd plot a single line... plt.show() shotrec = plt.loglog(H,abs(error22),H,hh) # this is how you'd plot a single line... plt.show() error22 <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: Generating synthetic data Step3: Fit a line of best fit using least squares (not ODR) Step6: Line of best fit using ODR Step7: Let's do it! Step9: Our results are now stored in an odr object. We can extract the parameters by typing odr.beta[0] (first parameter, intercept) or odr.beta[1] for the slope.
<ASSISTANT_TASK:> Python Code: import numpy as np import scipy as scipy import scipy.odr as odr import matplotlib as mpl import matplotlib.pyplot as plt import seaborn as sns from matplotlib import rc # set to use tex, but make sure it is sans-serif fonts only rc('text', usetex=True) rc('text.latex', preamble=r'\usepackage{cmbright}') rc('font', **{'family': 'sans-serif', 'sans-serif': ['Helvetica']}) # Magic function to make matplotlib inline; # other style specs must come AFTER %matplotlib inline # This enables SVG graphics inline. # There is a bug, so uncomment if it works. %config InlineBackend.figure_formats = {'png', 'retina'} # JB's favorite Seaborn settings for notebooks rc = {'lines.linewidth': 2, 'axes.labelsize': 18, 'axes.titlesize': 18, 'axes.facecolor': 'DFDFE5'} sns.set_context('notebook', rc=rc) sns.set_style("dark") mpl.rcParams['xtick.labelsize'] = 16 mpl.rcParams['ytick.labelsize'] = 16 mpl.rcParams['legend.fontsize'] = 14 n = 15 x = np.linspace(0, 10, n) xerr = np.abs(np.random.normal(0, 2.5, n)) x = np.random.normal(x, xerr, n) y = np.linspace(0, 20, n) yerr = np.abs(np.random.normal(0, 2.5, n)) y = np.random.normal(y, yerr) def line(x, a): The line of best fit. # unpack the parameters: y = a*x return y popt, pcov = scipy.optimize.curve_fit(line, x, y) # unpack the parameters of the line of best fit: a = popt plt.errorbar(x, y, xerr, yerr, 'o') plt.plot(x, line(x, a), label='fit') plt.legend(title='Legend') def odr_line(p, x): The line of best fit. # unpack the parameters: y = p*x return y def perform_odr(x, y, xerr, yerr): Finds the ODR for data {x, y} and returns the result linear = odr.Model(odr_line) mydata = odr.Data(x, y, wd=1./xerr, we=1./yerr) myodr = odr.ODR(mydata, linear, beta0=[0]) output = myodr.run() return output regression = perform_odr(x, y, xerr, yerr) plt.errorbar(x, y, xerr, yerr, 'o', alpha=0.7) plt.plot(x, line(x, a), label='least squares', lw=3, color='blue') plt.plot(x, line(x, regression.beta[0]), label='ODR', lw=3, color='purple') # plot the true line: X = np.linspace(-10, 10, 10) plt.plot(X, 2*X, label='True', lw=3, ls='--') plt.legend(title='Legend', loc=(1, .5)) plt.xlim(np.min(x)-1, np.max(x)+1) plt.ylim(np.min(y)-1, np.max(y)+1) print( The true model is y = 2.00x Least squares returns y = {0:.2g}x ODR returns y = {1:.2g}x .format(a[0], regression.beta[0])) <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 --&gt; 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 --&gt; Mass Balance Step26: 7. Ice --&gt; Mass Balance --&gt; Basal Step27: 7.2. Ocean Step28: 8. Ice --&gt; Mass Balance --&gt; Frontal Step29: 8.2. Melting Step30: 9. Ice --&gt; 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', 'test-institute-3', 'sandbox-2', '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: Simulation Step2: Experiment 1 Step3: Experiment 2 Step4: Experiment 3 Step5: Networkx
<ASSISTANT_TASK:> Python Code: import networkx as netx import numpy as np import matplotlib.pyplot as plt import warnings import random import itertools def power_law_graph(G): histo = netx.degree_histogram(G) _ = plt.loglog(histo, 'b-', marker='o') _ = plt.ylabel("k(x)") _ = plt.xlabel("k") plt.show() def plot(T,skew=True): plt.axis('off') pos=netx.spring_layout(T) if skew: D = dict(netx.degree(T)) sizes = [v * 200 for k,v in D.items()] netx.draw_networkx(T, pos=pos, with_labels=True, nodelist=D.keys(), node_size=sizes) else: netx.draw_networkx(T, pos=pos, with_labels=True) plt.show() def hist(T,bins=25): degree_lookup = dict(netx.degree(T)) degrees = list(degree_lookup.values()) _ = plt.title("Degree Distribution") _ = plt.hist(degrees,bins=bins) plt.show() def generate(nodes): n = 0 while n < nodes: n = n + 1 yield n # number of attachments per round m = 1 # nodes at time t = 0 a = 1 t0 = m + a # build graph G = netx.Graph() paths = list(generate(t0)) G.add_path(paths) plot(G) ## builds a distribution node sequence def linear_distribute(G,disregard=[]): for node in G.nodes(data = False): if node in disregard: continue for edge in netx.edges(G,node): yield node # randomly gets attachments of the new node def get_linear_attachments(G,m=1): if m < 1: return [] nodes = [] i = 0 while i < m: distribution = list(linear_distribute(G,disregard=nodes)) nodes.append(random.choice(distribution)) i = i + 1 return nodes def simulate(G,node,m=1,rounds=100): while node <= rounds: attachments = get_linear_attachments(G,m=m) G.add_node(node) for attachment in attachments: G.add_edge(node,attachment) node = node + 1 T = G.copy() simulate(T,m+1,m,rounds=15) plot(T,skew=True) # ramp up... T1 = G.copy() simulate(T1,m+1,m,rounds=3000) hist(T1) power_law_graph(T1) def draw(G,disregard=[],alpha=1): nodes = { } lookup = dict(G.degree()) denominator = 0.0 for k,v in lookup.items(): if k in disregard: continue nodes[k] = (v ** alpha) denominator = denominator + nodes[k] #print(np.array(list(nodes.values()))/denominator) drawing = random.uniform(0,1) key = None bottom = 0.0 top = 0.0 for k,v in nodes.items(): key = k top = bottom + (v / denominator) if (drawing >= bottom) & (drawing < top): key = k break bottom = top # print(drawing, " ", bottom, "-", top, ":", key) return key # randomly gets attachments of the new node def get_attachments(G,alpha=1,m=1): if m < 1: return [] nodes = [] i = 0 while i < m: node = draw(G,disregard=nodes,alpha=alpha) nodes.append(node) i = i + 1 # print() return nodes def simulate2(G,node,alpha=1,m=1,rounds=100): while node <= rounds: attachments = get_attachments(G,alpha,m=m) G.add_node(node) for attachment in attachments: G.add_edge(node,attachment) node = node + 1 T2 = G.copy() simulate2(T2,m+1,.5,m,3000) hist(T2) power_law_graph(T2) T3 = G.copy() simulate2(T3,m+1,3.5,m,3000) hist(T3) nodes = sorted(list(dict(T3.degree()).values()),reverse=True) # print segment of list out ... nodes[0:5] power_law_graph(T3) T4 = netx.generators.random_graphs.barabasi_albert_graph(8,1) plot(T4) scores = netx.preferential_attachment(G=T4) for u,v,score in scores: print('(%d, %d) -> score = %d' % (u, v, score)) len(list(T4.neighbors(1))) * len(list(T4.neighbors(7))) <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 returned images NumPy array will have the shape $n \times m$, where $n$ is the number of samples, and $m$ is the number of features. The images in the MNIST dataset consist of $28 \times 28$ pixels, and each pixel is represented by a grayscale intensity value. Here, we unroll the $28 \times 28$ images into 1D row vectors, which represent the rows in our matrix; thus $m=784$. Step2: To check if the pixels were retrieved correctly, let us print a few images Step3: Lastly, we can save the NumPy arrays as CSV files for more convenient retrievel, however, I wouldn't recommend storing the 60,000 samples as CSV files due to the enormous file size.
<ASSISTANT_TASK:> Python Code: import os import struct import numpy as np def load_mnist(path, which='train'): if which == 'train': labels_path = os.path.join(path, 'train-labels-idx1-ubyte') images_path = os.path.join(path, 'train-images-idx3-ubyte') elif which == 'test': labels_path = os.path.join(path, 't10k-labels-idx1-ubyte') images_path = os.path.join(path, 't10k-images-idx3-ubyte') else: raise AttributeError('`which` must be "train" or "test"') with open(labels_path, 'rb') as lbpath: magic, n = struct.unpack('>II', lbpath.read(8)) labels = np.fromfile(lbpath, dtype=np.uint8) with open(images_path, 'rb') as imgpath: magic, n, rows, cols = struct.unpack('>IIII', imgpath.read(16)) images = np.fromfile(imgpath, dtype=np.uint8).reshape(len(labels), 784) return images, labels X, y = load_mnist('/Users/sebastian/Desktop/mnist', which='train') print('Labels: %d' % y.shape[0]) print('Rows: %d, columns: %d' % (X.shape[0], X.shape[1])) import matplotlib.pyplot as plt %matplotlib inline def plot_digit(X, y, idx): img = X[idx].reshape(28,28) plt.imshow(img, cmap='Greys', interpolation='nearest') plt.title('true label: %d' % y[idx]) plt.show() for i in range(4): plot_digit(X, y, i) np.savetxt('train_img.csv', X[:3000, :], delimiter=',') np.savetxt('train_labels.csv', y[:3000], delimiter=',') X = np.genfromtxt('train_img.csv', delimiter=',') y = np.genfromtxt('train_labels.csv', delimiter=',') <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 matplotlib.pyplot as plt fig, ax = plt.subplots(3, 3, sharex=True, sharey=True, figsize=(5,5)) for images, labels in ds.take(1): for i in range(3): for j in range(3): ax[i][j].imshow(images[i*3+j].numpy().astype("uint8")) ax[i][j].set_title(ds.class_names[labels[i*3+j]]) 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: MMW staging (test) API Rapid Watershed Delineation (RWD) "watershed" endpoint Step2: 2. Construct and issue the job request Step3: 3. Fetch the job result once it's confirmed as done Step4: 4. Examine the results Step5: The results (result) are made up of two dictionary items Step6: watershed Step7: Render the geospatial results on an interactive map
<ASSISTANT_TASK:> Python Code: import json import requests from requests.adapters import HTTPAdapter from requests.packages.urllib3.util.retry import Retry def requests_retry_session( retries=3, backoff_factor=0.3, status_forcelist=(500, 502, 504), session=None, ): session = session or requests.Session() retry = Retry( total=retries, read=retries, connect=retries, backoff_factor=backoff_factor, status_forcelist=status_forcelist, ) adapter = HTTPAdapter(max_retries=retry) session.mount('http://', adapter) session.mount('https://', adapter) return session s = requests.Session() APIToken = 'Token YOURTOKEN' # Replace YOURTOKEN with your actual token string/key s.headers.update({ 'Authorization': APIToken, 'Content-Type': 'application/json' }) post_url = 'https://modelmywatershed.org/api/watershed/' payload = { 'location': [40.746054, -111.847987], # [latitude, longitude] 'snappingOn': True, 'dataSource': 'nhd'} json_dat = json.dumps(payload) post_req = requests_retry_session(session=s).post(post_url, data=json_dat) json_out = json.loads(post_req.content) json_out get_url = 'https://modelmywatershed.org/api/jobs/{job}/'.format result = '' while not result: get_req = requests_retry_session(session=s).get(get_url(job=json_out['job'])) result = json.loads(get_req.content)['result'] type(result), result.keys() input_pt_geojson = result['input_pt'] input_pt_geojson watershed_geojson = result['watershed'] watershed_geojson.keys(), watershed_geojson['geometry'].keys() watershed_geojson['properties'] # watershed has just one feature -- a single polygon print("Number of polygon features: {} \nFeature type: {} \nNumber of vertices in polygon: {}".format( len(watershed_geojson['geometry']['coordinates']), watershed_geojson['geometry']['type'], len(watershed_geojson['geometry']['coordinates'][0]) )) %matplotlib inline import folium # Initialize Folium map m = folium.Map(location=[input_pt_geojson['properties']['Lat'], input_pt_geojson['properties']['Lon']], tiles='CartoDB positron', zoom_start=12) # Add RWD watershed and drainage point onto map folium.GeoJson(watershed_geojson).add_to(m); folium.GeoJson(input_pt_geojson).add_to(m); 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: Step2: Choosing the class assignment objective Step3: Balanced classes Step4: Looking at the prediction results, we see that both class assignment objectives lead to qualitatively similar results. Step5: For balanced classes both class assignment objectives achieve comparable accuracy of 90.5% and 90.9%. Step6: We see that results are qualitatively different. The model with the class assignment objective maximize_accuracy tends to predict most of the points as class 0 (blue). This misclassification is especially obvious for the individual data points outside of the "bulk" of the distribution. The model with the class assignment objective maximize_minimum_recall tends to predict those points correctly. However, it misclassified the class 0 points in the middle. Step7: For unbalanced data set, maximize_accuracy leads to a higher overall accuracy (96% vs. 90%). However, the recall for the class 1 is only 64%, since the model tends to classify most data points as class 0. For maximize_minimum_recall the recall of class 1 is 88%. The price that we pay is that now even some points from class 0 are classified as class 1 (class 1 precision of 51%).
<ASSISTANT_TASK:> Python Code: # Some general notebook setting host = 'http://localhost:9200' # IMPORTANT: create a file credentials.json with credentials for your Elasticsearch instance! with open('credentials.json') as f: data = json.load(f) username = data['username'] password = data['password'] es = Elasticsearch(host, http_auth=(username, password)) def run_job(analysis_job_id: str, source_index: str, dest_index:str, class_assignment_objective:str): Run a data frame analytics job to completion. Args: analysis_job_id (str): Base name of the analysis job source_index (str): Source index dest_index (str): Base name of the destination index class_assignment_objective (str): Class assignment objective. Can be 'maximize_accuracy' or 'maximize_minimum_recall' destination = "_".join([dest_index, class_assignment_objective]) job_id = "_".join([analysis_job_id, class_assignment_objective]) api = '/_ml/data_frame/analytics/{}'.format(job_id) config = { "description": "", "source": { "index": source_index, "query": { "match_all": {} } }, "dest": { "index": destination, "results_field": "ml" }, "analysis": { "classification": { "dependent_variable": "target", "training_percent": 85, "randomize_seed": 42, "class_assignment_objective": class_assignment_objective } }, "model_memory_limit": "1gb", "max_num_threads": 1 } requests.put(host+api, auth=HTTPBasicAuth(username, password), json=config).json() api = "/_ml/data_frame/analytics/{}/_start".format(job_id) requests.post(host+api, auth=HTTPBasicAuth(username, password)).json() api = "/_ml/data_frame/analytics/{}/_stats".format(job_id) while True: results = requests.get(host+api, auth=HTTPBasicAuth(username, password),).json() state = results['data_frame_analytics'][0]['state'] if state == 'stopped': break time.sleep(1) def evaluate(dest_index: str, class_assignment_objective: str): Evaluation prediction results form the data frame analytics job. Args: dest_index (str): Base name of the destination index class_assignment_objective (str): Class assignment objective. Can be 'maximize_accuracy' or 'maximize_minimum_recall' destination = "_".join([dest_index, class_assignment_objective]) evaluate_train_config = { "index": destination, "evaluation": { "classification": { "actual_field": "target", "predicted_field": "ml.target_prediction", "metrics": { "accuracy": {}, "precision": {}, "recall": {} } } } } api = "/_ml/data_frame/_evaluate" results = requests.post(host+api, auth=HTTPBasicAuth(username, password), json=evaluate_train_config).json() return results analysis_job_id = 'classification_balanced' dest_index = 'classification_balanced_result' source_index = 'classification_balanced' X_balanced,y_balanced = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2, class_sep=0.5,flip_y=0,weights=[0.5,0.5], random_state=42) balanced_pd_df = pd.DataFrame(X_balanced, columns=['x1','x2']) balanced_pd_df['target'] = y_balanced balanced_ed_df = ed.pandas_to_eland(pd_df=balanced_pd_df, es_client=es, es_dest_index=source_index, es_if_exists='replace', es_refresh=True) # train models with different class assignment objectives run_job(analysis_job_id=analysis_job_id, source_index=source_index, dest_index=dest_index, class_assignment_objective='maximize_accuracy') run_job(analysis_job_id=analysis_job_id, source_index=source_index, dest_index=dest_index, class_assignment_objective='maximize_minimum_recall') # plot results results_balanced_maxacc = ed.DataFrame(es_client=es, es_index_pattern="_".join([dest_index, 'maximize_accuracy']), columns=['x1','x2','target','ml.target_prediction', 'ml.is_training', 'ml.prediction_probability', 'ml.prediction_score', 'ml.top_classes']) results_balanced_maxminrecall = ed.DataFrame(es_client=es, es_index_pattern="_".join([dest_index, 'maximize_minimum_recall']), columns=['x1','x2','target','ml.target_prediction', 'ml.is_training', 'ml.prediction_probability', 'ml.prediction_score', 'ml.top_classes']) results_balanced_maxacc = ed.eland_to_pandas(results_balanced_maxacc) results_balanced_maxminrecall = ed.eland_to_pandas(results_balanced_maxminrecall) f, (ax1, ax2, ax3) = plt.subplots(nrows=1, ncols=3, figsize=(20,5)) sns.scatterplot(x=balanced_pd_df['x1'], y=balanced_pd_df['x2'], hue=balanced_pd_df['target'], ax=ax1) ax1.set_title('Original balanced data set') sns.scatterplot(x=results_balanced_maxacc['x1'], y=results_balanced_maxacc['x2'], hue=results_balanced_maxacc['ml.target_prediction'], ax=ax2) ax2.set_title('Maximum accuracy classification') sns.scatterplot(x=results_balanced_maxminrecall['x1'], y=results_balanced_maxminrecall['x2'], hue=results_balanced_maxminrecall['ml.target_prediction'], ax=ax3) ax3.set_title('Maximum minimum recall classification') plt.show() display(Markdown("**Evaluation results for maximize_accuracy**")) pprint.pprint(evaluate(dest_index=dest_index, class_assignment_objective='maximize_accuracy')) display(Markdown("**Evaluation results for maximize_minimum_recall**")) pprint.pprint(evaluate(dest_index=dest_index, class_assignment_objective='maximize_minimum_recall')) analysis_job_id = 'classification_unbalanced' dest_index = 'classification_unbalanced_result' source_index = 'classification_unbalanced' X_unbalanced,y_unbalanced = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2, class_sep=0.5,flip_y=0,weights=[0.9,0.1], random_state=42) unbalanced_pd_df = pd.DataFrame(X_unbalanced, columns=['x1','x2']) unbalanced_pd_df['target'] = y_unbalanced unbalanced_ed_df = ed.pandas_to_eland(pd_df=unbalanced_pd_df, es_client=es, es_dest_index=source_index, es_if_exists='replace', es_refresh=True) # train models with different class assignment objectives run_job(analysis_job_id=analysis_job_id, source_index=source_index, dest_index=dest_index, class_assignment_objective='maximize_accuracy') run_job(analysis_job_id=analysis_job_id, source_index=source_index, dest_index=dest_index, class_assignment_objective='maximize_minimum_recall') # plot results results_unbalanced_maxacc = ed.DataFrame(es_client=es, es_index_pattern="_".join([dest_index, 'maximize_accuracy']), columns=['x1','x2','target','ml.target_prediction', 'ml.is_training', 'ml.prediction_probability', 'ml.prediction_score', 'ml.top_classes']) results_unbalanced_maxminrecall = ed.DataFrame(es_client=es, es_index_pattern="_".join([dest_index, 'maximize_minimum_recall']), columns=['x1','x2','target','ml.target_prediction', 'ml.is_training', 'ml.prediction_probability', 'ml.prediction_score', 'ml.top_classes']) results_unbalanced_maxacc = ed.eland_to_pandas(results_unbalanced_maxacc) results_unbalanced_maxminrecall = ed.eland_to_pandas(results_unbalanced_maxminrecall) f, (ax1, ax2, ax3) = plt.subplots(nrows=1, ncols=3, figsize=(20,5)) sns.scatterplot(x=unbalanced_pd_df['x1'], y=unbalanced_pd_df['x2'], hue=unbalanced_pd_df['target'], ax=ax1) ax1.set_title('Original unbalanced data set') sns.scatterplot(x=results_unbalanced_maxacc['x1'], y=results_unbalanced_maxacc['x2'], hue=results_unbalanced_maxacc['ml.target_prediction'], ax=ax2) ax2.set_title('Maximum accuracy classification') sns.scatterplot(x=results_unbalanced_maxminrecall['x1'], y=results_unbalanced_maxminrecall['x2'], hue=results_unbalanced_maxminrecall['ml.target_prediction'], ax=ax3) ax3.set_title('Maximum minimum recall classification') plt.show() display(Markdown("**Evaluation results for maximize_accuracy**")) pprint.pprint(evaluate(dest_index=dest_index, class_assignment_objective='maximize_accuracy')) display(Markdown("**Evaluation results for maximize_accuracy**")) pprint.pprint(evaluate(dest_index=dest_index, class_assignment_objective='maximize_minimum_recall')) display(Markdown('**Maximize accuracy result:**')) pprint.pprint(results_unbalanced_maxacc.iloc[26]['ml.top_classes']) display(Markdown('**Maximize minimum recall result:**')) pprint.pprint(results_unbalanced_maxminrecall.iloc[26]['ml.top_classes']) <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: Computers by definition cannot generate truly random numbers. The Mersenne Twister is a widely-used algorithm for generating pseudo random numbers form a deterministic process. That is, while the numbers generated from the algorithm are not random in the literal sense, they exhibit distributional qualities that make them indistinguishable from truly random numbers. Step2: Example Step3: The white noise process Step4: Example Step5: Notice that if $-1< \rho < 1$, then $\mu$ is the expected value of the process. That is, when $-1< \rho < 1$, the process will fluctuate around $\mu$. But if $\rho>1$ or $\rho<-1$, the process will explode away from $\mu$. Step6: Example Step7: The random walk process
<ASSISTANT_TASK:> Python Code: # Create an array with 5 draws from the normal(0,1) distribution and print np.random.normal(size=5) # Create an array with 5 draws from the normal(0,1) distribution and print np.random.normal(size=5) # Set the seed for the random number generator np.random.seed(129) # Create an array with 5 draws from the normal(0,1) distribution and print np.random.normal(size=5) # Set the seed for the random number generator np.random.seed(129) # Create two arrays: # x: 500 draws from the normal(0,1) distribution # y: 500 draws from the normal(0,2) distribution x = np.random.normal(loc=0,scale=1,size=500) y = np.random.normal(loc=0,scale=2,size=500) # Plot plt.plot(x,lw=3,alpha = 0.6,label='$\sigma=1$') plt.plot(y,lw=3,alpha = 0.6,label='$\sigma=2$') plt.grid(linestyle=':') plt.legend(ncol=2,loc='lower right') # Simulate an AR(1) process for 51 periods. Set the RNG seed to 129 np.random.seed(129) T = 51 x0=0 mu=1 rho=0.5 sigma=1 x = np.zeros(T) x[0] = x0 # draw random numbers for white noise process eps= np.random.normal(loc=0,scale=sigma,size=T-1) for t in range(T-1): x[t+1] = mu*(1-rho) + rho*x[t] + eps[t] # Plot plt.plot(x,lw=3,alpha = 0.6,label='$\sigma=1$') plt.grid(linestyle=':') # Simulate an AR(1) process for 51 periods. Set the RNG seed to 129 np.random.seed(129) T = 51 x0=0 mu=1 rho=1.5 sigma=1 import time # Wait for 5 seconds x = np.zeros(T) x[:] = np.NAN x[0] = x0 # draw random numbers for white noise process eps= np.random.normal(loc=0,scale=sigma,size=T-1) for t in range(T-1): x[t+1] = mu*(1-rho) + rho*x[t] + eps[t] # Plot plt.plot(x,lw=3,alpha = 0.6,label='$\sigma=1$') plt.grid(linestyle=':') def ar1(mu=0,rho=0,sigma=1,x0=0,T=25): '''Funciton for simulating an AR(1) process for T periods Args: mu (float): mean of the AR(1) process rho (float): autoregressive parameter sigma (float): standard deviation of the white noise process x0 (float): initial value of the process T (int): number of periods to simulate Returns: numpy array ''' # initialize x array x = np.zeros(T) x[0] = x0 # draw random numbers for white noise process eps= np.random.normal(loc=0,scale=sigma,size=T-1) for t in range(T-1): x[t+1] = mu*(1-rho) + rho*x[t] + eps[t] return x fig = plt.figure(figsize=(12,8)) np.random.seed(129) y = ar1(mu=0,rho=0,sigma=1,x0=0,T=51) ax1 = fig.add_subplot(2,2,1) ax1.plot(y,lw=3,alpha=0.7) ax1.set_title('$X_t = \epsilon_t$') ax1.grid() np.random.seed(129) y = ar1(mu=0,rho=0,sigma=1,x0=0,T=51) ax2 = fig.add_subplot(2,2,2) ax2.plot(y,lw=3,alpha=0.7) ax2.set_title('$X_t = 0.5\cdot X_{t-1} + \epsilon_t$') ax2.grid() np.random.seed(129) y = ar1(mu=0,rho=0.9,sigma=1,x0=0,T=51) ax3 = fig.add_subplot(2,2,3) ax3.plot(y,lw=3,alpha=0.7) ax3.set_title('$X_t = 0.9\cdot X_{t-1} + \epsilon_t$') ax3.grid() np.random.seed(129) y = ar1(mu=0,rho=-0.5,sigma=1,x0=0,T=51) ax4 = fig.add_subplot(2,2,4) ax4.plot(y,lw=3,alpha=0.7) ax4.set_title('$X_t = -0.5\cdot X_{t-1} + \epsilon_t$') ax4.grid() np.random.seed(129) for i in range(7): plt.plot(ar1(rho=1,T=501)) plt.grid() plt.title('Five random walk processes') <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: LAB Step2: How about in descending order?
<ASSISTANT_TASK:> Python Code: dinos.assign(Decimal = dinos.sha256.apply(lambda x: int(x, base=16))) dinos.sort_values(by='sha256').head(10) dinos.sort_values(by='sha256', ascending=False).head(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: Import section specific modules Step2: 4.5.1 UV coverage Step3: Let's express the corresponding physical baseline in ENU coordinates. Step4: Let's place the interferometer at a latitude $L_a=+45^\circ00'00''$. Step5: Figure 4.5.1 Step6: 4.5.1.1.3 Computing of the projected baselines in ($u$,$v$,$w$) coordinates as a function of time Step7: As the $u$, $v$, $w$ coordinates explicitly depend on $H$, we must evaluate them for each observational time step. We will use the equations defined in $\S$ 4.2.2 &#10142; Step8: We now have everything that describes the $uvw$-track of the baseline (over an 8-hour observational period). It is hard to predict which locus the $uvw$ track traverses given only the three mathematical equations from above. Let's plot it in $uvw$ space and its projection in $uv$ space. Step9: Figure 4.5.2 Step10: Figure 4.5.3 Step11: Let's compute the $uv$ tracks of an observation of the NCP ($\delta=90^\circ$) Step12: Let's compute the uv tracks when observing a source at $\delta=30^\circ$ Step13: Figure 4.5.4 Step14: Figure 4.5.5 Step15: <span style="background-color Step16: We then convert the ($\alpha$,$\delta$) to $l,m$ Step17: The source and phase centre coordinates are now given in degrees. Step18: Figure 4.5.6 Step19: We create the dimensions of our visibility plane. Step20: We create our fully-filled visibility plane. With a "perfect" interferometer, we could sample the entire $uv$-plane. Since we only have a finite amount of antennas, this is never possible in practice. Recall that our sky brightness $I(l,m)$ is related to our visibilites $V(u,v)$ via the Fourier transform. For a bunch of point sources we can therefore write Step21: Below we sample our visibility plane on the $uv$-track derived in the first section, i.e. $V(u_t,v_t)$. Step22: Figure 4.5.7 Step23: Figure 4.5.8 Step24: Figure 4.5.9
<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib.pyplot as plt %matplotlib inline from IPython.display import HTML HTML('../style/course.css') #apply general CSS from mpl_toolkits.mplot3d import Axes3D import plotBL HTML('../style/code_toggle.html') ant1 = np.array([-500e3,500e3,0]) # in m ant2 = np.array([500e3,-500e3,+10]) # in m b_ENU = ant2-ant1 # baseline D = np.sqrt(np.sum((b_ENU)**2)) # |b| print str(D/1000)+" km" L = (np.pi/180)*(45+0./60+0./3600) # Latitude in radians A = np.arctan2(b_ENU[0],b_ENU[1]) print "Baseline Azimuth="+str(np.degrees(A))+"ยฐ" E = np.arcsin(b_ENU[2]/D) print "Baseline Elevation="+str(np.degrees(E))+"ยฐ" %matplotlib nbagg plotBL.sphere(ant1,ant2,A,E,D,L) # Observation parameters c = 3e8 # Speed of light f = 1420e9 # Frequency lam = c/f # Wavelength dec = (np.pi/180)*(-30-43.0/60-17.34/3600) # Declination time_steps = 600 # Time Steps h = np.linspace(-4,4,num=time_steps)*np.pi/12 # Hour angle window ant1 = np.array([25.095,-9.095,0.045]) ant2 = np.array([90.284,26.380,-0.226]) b_ENU = ant2-ant1 D = np.sqrt(np.sum((b_ENU)**2)) L = (np.pi/180)*(-30-43.0/60-17.34/3600) A=np.arctan2(b_ENU[0],b_ENU[1]) print "Azimuth=",A*(180/np.pi) E=np.arcsin(b_ENU[2]/D) print "Elevation=",E*(180/np.pi) X = D*(np.cos(L)*np.sin(E)-np.sin(L)*np.cos(E)*np.cos(A)) Y = D*np.cos(E)*np.sin(A) Z = D*(np.sin(L)*np.sin(E)+np.cos(L)*np.cos(E)*np.cos(A)) u = lam**(-1)*(np.sin(h)*X+np.cos(h)*Y)/1e3 v = lam**(-1)*(-np.sin(dec)*np.cos(h)*X+np.sin(dec)*np.sin(h)*Y+np.cos(dec)*Z)/1e3 w = lam**(-1)*(np.cos(dec)*np.cos(h)*X-np.cos(dec)*np.sin(h)*Y+np.sin(dec)*Z)/1e3 %matplotlib nbagg plotBL.UV(u,v,w) %matplotlib inline from matplotlib.patches import Ellipse # parameters of the UVtrack as an ellipse a=np.sqrt(X**2+Y**2)/lam/1e3 # major axis b=a*np.sin(dec) # minor axis v0=Z/lam*np.cos(dec)/1e3 # center of ellipse plotBL.UVellipse(u,v,w,a,b,v0) L=np.radians(90.) ant1 = np.array([25.095,-9.095,0.045]) ant2 = np.array([90.284,26.380,-0.226]) b_ENU = ant2-ant1 D = np.sqrt(np.sum((b_ENU)**2)) A=np.arctan2(b_ENU[0],b_ENU[1]) print "Azimuth=",A*(180/np.pi) E=np.arcsin(b_ENU[2]/D) print "Elevation=",E*(180/np.pi) X = D*(np.cos(L)*np.sin(E)-np.sin(L)*np.cos(E)*np.cos(A)) Y = D*np.cos(E)*np.sin(A) Z = D*(np.sin(L)*np.sin(E)+np.cos(L)*np.cos(E)*np.cos(A)) dec=np.radians(90.) uNCP = lam**(-1)*(np.sin(h)*X+np.cos(h)*Y)/1e3 vNCP = lam**(-1)*(-np.sin(dec)*np.cos(h)*X+np.sin(dec)*np.sin(h)*Y+np.cos(dec)*Z)/1e3 wNCP = lam**(-1)*(np.cos(dec)*np.cos(h)*X-np.cos(dec)*np.sin(h)*Y+np.sin(dec)*Z)/1e3 # parameters of the UVtrack as an ellipse aNCP=np.sqrt(X**2+Y**2)/lam/1e3 # major axis bNCP=aNCP*np.sin(dec) # minor axi v0NCP=Z/lam*np.cos(dec)/1e3 # center of ellipse dec=np.radians(30.) u30 = lam**(-1)*(np.sin(h)*X+np.cos(h)*Y)/1e3 v30 = lam**(-1)*(-np.sin(dec)*np.cos(h)*X+np.sin(dec)*np.sin(h)*Y+np.cos(dec)*Z)/1e3 w30 = lam**(-1)*(np.cos(dec)*np.cos(h)*X-np.cos(dec)*np.sin(h)*Y+np.sin(dec)*Z)/1e3 a30=np.sqrt(X**2+Y**2)/lam/1e3 # major axis b30=a*np.sin(dec) # minor axi v030=Z/lam*np.cos(dec)/1e3 # center of ellipse %matplotlib inline plotBL.UVellipse(u30,v30,w30,a30,b30,v030) plotBL.UVellipse(uNCP,vNCP,wNCP,aNCP,bNCP,v0NCP) L=np.radians(90.) X = D*(np.cos(L)*np.sin(E)-np.sin(L)*np.cos(E)*np.cos(A)) Y = D*np.cos(E)*np.sin(A) Z = D*(np.sin(L)*np.sin(E)+np.cos(L)*np.cos(E)*np.cos(A)) # At local zenith == Celestial Equator dec=np.radians(0.) uEQ = lam**(-1)*(np.sin(h)*X+np.cos(h)*Y)/1e3 vEQ = lam**(-1)*(-np.sin(dec)*np.cos(h)*X+np.sin(dec)*np.sin(h)*Y+np.cos(dec)*Z)/1e3 wEQ = lam**(-1)*(np.cos(dec)*np.cos(h)*X-np.cos(dec)*np.sin(h)*Y+np.sin(dec)*Z)/1e3 # parameters of the UVtrack as an ellipse aEQ=np.sqrt(X**2+Y**2)/lam/1e3 # major axis bEQ=aEQ*np.sin(dec) # minor axi v0EQ=Z/lam*np.cos(dec)/1e3 # center of ellipse # Close to Zenith dec=np.radians(10.) u10 = lam**(-1)*(np.sin(h)*X+np.cos(h)*Y)/1e3 v10 = lam**(-1)*(-np.sin(dec)*np.cos(h)*X+np.sin(dec)*np.sin(h)*Y+np.cos(dec)*Z)/1e3 w10 = lam**(-1)*(np.cos(dec)*np.cos(h)*X-np.cos(dec)*np.sin(h)*Y+np.sin(dec)*Z)/1e3 a10=np.sqrt(X**2+Y**2)/lam/1e3 # major axis b10=a*np.sin(dec) # minor axi v010=Z/lam*np.cos(dec)/1e3 # center of ellipse %matplotlib inline plotBL.UVellipse(u10,v10,w10,a10,b10,v010) plotBL.UVellipse(uEQ,vEQ,wEQ,aEQ,bEQ,v0EQ) H = np.linspace(-6,6,600)*(np.pi/12) #Hour angle in radians d = 100 #We assume that we have already divided by wavelength delta = 60*(np.pi/180) #Declination in degrees u_60 = d*np.cos(H) v_60 = d*np.sin(H)*np.sin(delta) RA_sources = np.array([5+30.0/60,5+32.0/60+0.4/3600,5+36.0/60+12.8/3600,5+40.0/60+45.5/3600]) DEC_sources = np.array([60,60+17.0/60+57.0/3600,61+12.0/60+6.9/3600,61+56.0/60+34.0/3600]) Flux_sources_labels = np.array(["","1 Jy","0.5 Jy","0.2 Jy"]) Flux_sources = np.array([1,0.5,0.1]) #in Jy step_size = 200 print "Phase center Source 1 Source 2 Source3" print repr("RA="+str(RA_sources)).ljust(2) print "DEC="+str(DEC_sources) RA_rad = np.array(RA_sources)*(np.pi/12) DEC_rad = np.array(DEC_sources)*(np.pi/180) RA_delta_rad = RA_rad-RA_rad[0] l = np.cos(DEC_rad)*np.sin(RA_delta_rad) m = (np.sin(DEC_rad)*np.cos(DEC_rad[0])-np.cos(DEC_rad)*np.sin(DEC_rad[0])*np.cos(RA_delta_rad)) print "l=",l*(180/np.pi) print "m=",m*(180/np.pi) point_sources = np.zeros((len(RA_sources)-1,3)) point_sources[:,0] = Flux_sources point_sources[:,1] = l[1:] point_sources[:,2] = m[1:] %matplotlib inline fig = plt.figure(figsize=(10,10)) ax = fig.add_subplot(111) plt.xlim([-4,4]) plt.ylim([-4,4]) plt.xlabel("$l$ [degrees]") plt.ylabel("$m$ [degrees]") plt.plot(l[0],m[0],"bx") plt.hold("on") plt.plot(l[1:]*(180/np.pi),m[1:]*(180/np.pi),"ro") counter = 1 for xy in zip(l[1:]*(180/np.pi)+0.25, m[1:]*(180/np.pi)+0.25): ax.annotate(Flux_sources_labels[counter], xy=xy, textcoords='offset points',horizontalalignment='right', verticalalignment='bottom') counter = counter + 1 plt.grid() u = np.linspace(-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10, num=step_size, endpoint=True) v = np.linspace(-1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10, num=step_size, endpoint=True) uu, vv = np.meshgrid(u, v) zz = np.zeros(uu.shape).astype(complex) s = point_sources.shape for counter in xrange(1, s[0]+1): A_i = point_sources[counter-1,0] l_i = point_sources[counter-1,1] m_i = point_sources[counter-1,2] zz += A_i*np.exp(-2*np.pi*1j*(uu*l_i+vv*m_i)) zz = zz[:,::-1] u_track = u_60 v_track = v_60 z = np.zeros(u_track.shape).astype(complex) s = point_sources.shape for counter in xrange(1, s[0]+1): A_i = point_sources[counter-1,0] l_i = point_sources[counter-1,1] m_i = point_sources[counter-1,2] z += A_i*np.exp(-1*2*np.pi*1j*(u_track*l_i+v_track*m_i)) plt.figure(figsize=(12,6)) plt.subplot(121) plt.imshow(zz.real,extent=[-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10,-1*(np.amax(abs(v_60)))-10, \ np.amax(abs(v_60))+10]) plt.plot(u_60,v_60,"k") plt.xlim([-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10]) plt.ylim(-1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10) plt.xlabel("u") plt.ylabel("v") plt.title("Real part of visibilities") plt.subplot(122) plt.imshow(zz.imag,extent=[-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10,-1*(np.amax(abs(v_60)))-10, \ np.amax(abs(v_60))+10]) plt.plot(u_60,v_60,"k") plt.xlim([-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10]) plt.ylim(-1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10) plt.xlabel("u") plt.ylabel("v") plt.title("Imaginary part of visibilities") plt.figure(figsize=(12,6)) plt.subplot(121) plt.plot(z.real) plt.xlabel("Timeslots") plt.ylabel("Jy") plt.title("Real: sampled visibilities") plt.subplot(122) plt.plot(z.imag) plt.xlabel("Timeslots") plt.ylabel("Jy") plt.title("Imag: sampled visibilities") plt.figure(figsize=(12,6)) plt.subplot(121) plt.imshow(abs(zz), extent=[-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10, -1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10]) plt.plot(u_60,v_60,"k") plt.xlim([-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10]) plt.ylim(-1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10) plt.xlabel("u") plt.ylabel("v") plt.title("Amplitude of visibilities") plt.subplot(122) plt.imshow(np.angle(zz), extent=[-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10, -1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10]) plt.plot(u_60,v_60,"k") plt.xlim([-1*(np.amax(np.abs(u_60)))-10, np.amax(np.abs(u_60))+10]) plt.ylim(-1*(np.amax(abs(v_60)))-10, np.amax(abs(v_60))+10) plt.xlabel("u") plt.ylabel("v") plt.title("Phase of visibilities") plt.figure(figsize=(12,6)) plt.subplot(121) plt.plot(abs(z)) plt.xlabel("Timeslots") plt.ylabel("Jy") plt.title("Abs: sampled visibilities") plt.subplot(122) plt.plot(np.angle(z)) plt.xlabel("Timeslots") plt.ylabel("Jy") plt.title("Phase: sampled visibilities") <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: Problรจme 1 Step2: Random Forest Step3: On s'inspire de l'exemple Feature importances with forests of trees. Step4: Modรจle linรฉaire Step5: TPOT Step6: Le module optimise les hyperparamรจtres, parfois un peu trop ร  en juger la mauvaise performance obtenue sur la base de test. Step7: Feature importance pour une observations Step8: Problรจme 2 Step9: Mรฉthode non linรฉaire Step10: Texte Step11: Des mots aux coordonnรฉes - tf-idf Step12: LDA Step13: On obtient dix vecteurs qui reprรฉsentent les dix vecteurs associรฉs aux dix clusters. Chaque dimension reliรฉ au fait que le mot appartient ou non au cluster. Step14: Clustering
<ASSISTANT_TASK:> Python Code: from jyquickhelper import add_notebook_menu add_notebook_menu() import pandas df = pandas.read_csv("data/housing.data", delim_whitespace=True, header=None) df.head() cols = "CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT MEDV".split() df.columns = cols df.head() X = df.drop("MEDV", axis=1) y = df["MEDV"] from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33) from sklearn.ensemble import RandomForestRegressor clr = RandomForestRegressor() clr.fit(X, y) importances = clr.feature_importances_ importances %matplotlib inline import matplotlib.pyplot as plt import numpy as np plt.figure(figsize=(12,4)) indices = np.argsort(importances)[::-1] std = np.std([tree.feature_importances_ for tree in clr.estimators_], axis=0) plt.title("Feature importances") plt.bar(range(X.shape[1]), importances[indices], color="r", yerr=std[indices], align="center") xlabels = list(df.columns[:-1]) xlabels = [xlabels[i] for i in indices] plt.xticks(range(X.shape[1]), xlabels) plt.xlim([-1, X.shape[1]]) plt.show() from sklearn.metrics import r2_score r2_score(y_train, clr.predict(X_train)) r2_score(y_test, clr.predict(X_test)) import statsmodels.api as sm model = sm.OLS(y_train, X_train) results = model.fit() results.params results.summary() model = sm.OLS(y,X.drop("LSTAT", axis=1)) results = model.fit() results.summary() try: from tpot import TPOTRegressor except ImportError: # for sklearn 0.22 import sklearn.preprocessing from sklearn.impute import SimpleImputer sklearn.preprocessing.Imputer = SimpleImputer from tpot import TPOTRegressor tpot = TPOTRegressor(generations=2, population_size=50, verbosity=2) tpot.fit(X_train, y_train) print(tpot.score(X_test, y_test)) tpot.export('tpot_boston_pipeline.py') r2_score(y_train, tpot.predict(X_train)) r2_score(y_test, tpot.predict(X_test)) clr = RandomForestRegressor() clr.fit(X, y) from treeinterpreter import treeinterpreter as ti prediction, bias, contributions = ti.predict(clr, X_test) for i in range(min(2, X_train.shape[0])): print("Instance", i) print("Bias (trainset mean)", bias[i]) print("Feature contributions:") for c, feature in sorted(zip(contributions[i], df.columns), key=lambda x: -abs(x[0])): print(feature, round(c, 2)) print( "-"*20) import pandas df = pandas.read_csv("data/multiTimeline.csv", skiprows=1) df.columns= ["Semaine", "compte"] df["SemaineDt"] = pandas.to_datetime(df.Semaine) df=df.set_index("SemaineDt") df["compte"] = df["compte"].astype(float) df.head() %matplotlib inline df.plot() from statsmodels.tsa.arima_model import ARIMA arma_mod = ARIMA(df["compte"].values, order=(6 ,1, 1)) res = arma_mod.fit() res.params res.summary() from statsmodels.tsa.tsatools import lagmat lag = 8 X = lagmat(df["compte"], lag) lagged = df.copy() for c in range(1,lag+1): lagged["lag%d" % c] = X[:, c-1] pandas.concat([lagged.head(), lagged.tail()]) xc = ["lag%d" % i for i in range(1,lag+1)] split = 0.66 isplit = int(len(lagged) * split) xt = lagged[10:][xc] yt = lagged[10:]["compte"] X_train, y_train, X_test, y_test = xt[:isplit], yt[:isplit], xt[isplit:], yt[isplit:] from sklearn.ensemble import RandomForestRegressor clr = RandomForestRegressor() clr.fit(X_train, y_train) from sklearn.metrics import r2_score r2 = r2_score(y_test.values, clr.predict(X_test)) r2 plt.scatter(y_test.values, clr.predict(X_test)); from ensae_teaching_cs.data import twitter_zip df = twitter_zip(as_df=True) df.head(n=2).T keep = df.text.dropna().index dfnonan = df.iloc[keep, :] dfnonan.shape from sklearn.feature_extraction.text import TfidfVectorizer tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, max_features=1000) tfidf = tfidf_vectorizer.fit_transform(dfnonan["text"]) tfidf[:2, :] tfidf[:2, :].todense() from sklearn.decomposition import LatentDirichletAllocation lda = LatentDirichletAllocation(n_components=10, max_iter=5, learning_method='online', learning_offset=50., random_state=0) lda.fit(tfidf) tf_feature_names = tfidf_vectorizer.get_feature_names() tf_feature_names[100:103] lda.components_.shape def print_top_words(model, feature_names, n_top_words): for topic_idx, topic in enumerate(model.components_): print("Topic #%d:" % topic_idx) print(" ".join([feature_names[i] for i in topic.argsort()[:-n_top_words - 1:-1]])) print() print_top_words(lda, tf_feature_names, 10) from sklearn.cluster import KMeans km = KMeans(n_clusters=10) km.fit(tfidf) km.cluster_centers_.shape def print_top_words(model, feature_names, n_top_words): for topic_idx, topic in enumerate(model.cluster_centers_): print("Topic #%d:" % topic_idx) print(" ".join([feature_names[i] for i in topic.argsort()[:-n_top_words - 1:-1]])) print() print_top_words(km, tf_feature_names, 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: Visualization Step3: Classical Machine Learning Step4: Logistic Regression Step5: ElasticNet Step6: Decision Tree Step7: Random Forest Step8: SVM Step9: Results and save the model
<ASSISTANT_TASK:> Python Code: import os import librosa import itertools import numpy as np import pandas as pd import matplotlib.pyplot as plt from scipy.stats import kurtosis from scipy.stats import skew import sklearn from sklearn.preprocessing import StandardScaler from sklearn.metrics import accuracy_score from sklearn.metrics import confusion_matrix from sklearn.pipeline import Pipeline from sklearn.feature_selection import SelectKBest from sklearn.model_selection import GridSearchCV from sklearn.model_selection import train_test_split from sklearn.decomposition import PCA from sklearn.manifold import TSNE from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA from sklearn.feature_selection import VarianceThreshold from sklearn.feature_selection import SelectFromModel import lightgbm as lgbm from sklearn.linear_model import LogisticRegression from sklearn.linear_model import SGDClassifier from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier from sklearn.svm import SVC # Set the seed np.random.seed(42) gtzan_dir = '../data/genres/' # Parameters song_samples = 22050*30 genres = {'metal': 0, 'disco': 1, 'classical': 2, 'hiphop': 3, 'jazz': 4, 'country': 5, 'pop': 6, 'blues': 7, 'reggae': 8, 'rock': 9} def get_features(y, sr, n_fft = 1024, hop_length = 512): # Features to concatenate in the final dictionary features = {'centroid': None, 'roloff': None, 'flux': None, 'rmse': None, 'zcr': None, 'contrast': None, 'bandwidth': None, 'flatness': None} # Count silence if 0 < len(y): y_sound, _ = librosa.effects.trim(y, frame_length=n_fft, hop_length=hop_length) features['sample_silence'] = len(y) - len(y_sound) # Using librosa to calculate the features features['centroid'] = librosa.feature.spectral_centroid(y, sr=sr, n_fft=n_fft, hop_length=hop_length).ravel() features['roloff'] = librosa.feature.spectral_rolloff(y, sr=sr, n_fft=n_fft, hop_length=hop_length).ravel() features['zcr'] = librosa.feature.zero_crossing_rate(y, frame_length=n_fft, hop_length=hop_length).ravel() features['rmse'] = librosa.feature.rms(y, frame_length=n_fft, hop_length=hop_length).ravel() features['flux'] = librosa.onset.onset_strength(y=y, sr=sr).ravel() features['contrast'] = librosa.feature.spectral_contrast(y, sr=sr).ravel() features['bandwidth'] = librosa.feature.spectral_bandwidth(y, sr=sr, n_fft=n_fft, hop_length=hop_length).ravel() features['flatness'] = librosa.feature.spectral_flatness(y, n_fft=n_fft, hop_length=hop_length).ravel() # MFCC treatment mfcc = librosa.feature.mfcc(y, n_fft = n_fft, hop_length = hop_length, n_mfcc=13) for idx, v_mfcc in enumerate(mfcc): features['mfcc_{}'.format(idx)] = v_mfcc.ravel() # Get statistics from the vectors def get_moments(descriptors): result = {} for k, v in descriptors.items(): result['{}_max'.format(k)] = np.max(v) result['{}_min'.format(k)] = np.min(v) result['{}_mean'.format(k)] = np.mean(v) result['{}_std'.format(k)] = np.std(v) result['{}_kurtosis'.format(k)] = kurtosis(v) result['{}_skew'.format(k)] = skew(v) return result dict_agg_features = get_moments(features) dict_agg_features['tempo'] = librosa.beat.tempo(y, sr=sr)[0] return dict_agg_features def read_process_songs(src_dir, debug = True): # Empty array of dicts with the processed features from all files arr_features = [] # Read files from the folders for x,_ in genres.items(): folder = src_dir + x for root, subdirs, files in os.walk(folder): for file in files: # Read the audio file file_name = folder + "/" + file signal, sr = librosa.load(file_name) # Debug process if debug: print("Reading file: {}".format(file_name)) # Append the result to the data structure features = get_features(signal, sr) features['genre'] = genres[x] arr_features.append(features) return arr_features %%time # Get list of dicts with features and convert to dataframe features = read_process_songs(gtzan_dir, debug=False) df_features = pd.DataFrame(features) df_features.shape df_features.head() df_features.to_csv('../data/gtzan_features.csv', index=False) X = df_features.drop(['genre'], axis=1).values y = df_features['genre'].values # Standartize the dataset scale = StandardScaler() x_scaled = scale.fit_transform(X) # Use PCA only for visualization pca = PCA(n_components=35, whiten=True) x_pca = pca.fit_transform(x_scaled) print("cumulative explained variance ratio = {:.4f}".format(np.sum(pca.explained_variance_ratio_))) # Use LDA only for visualization lda = LDA() x_lda = lda.fit_transform(x_scaled, y) # Using tsne tsne = TSNE(n_components=2, verbose=1, learning_rate=250) x_tsne = tsne.fit_transform(x_scaled) plt.figure(figsize=(18, 4)) plt.subplot(131) plt.scatter(x_pca[:,0], x_pca[:,1], c=y) plt.colorbar() plt.title("Embedded space with PCA") plt.subplot(132) plt.scatter(x_lda[:,0], x_lda[:,1], c=y) plt.colorbar() plt.title("Embedded space with LDA") plt.subplot(133) plt.scatter(x_tsne[:,0], x_tsne[:,1], c=y) plt.colorbar() plt.title("Embedded space with TSNE") plt.show() # Helper to plot confusion matrix -- from Scikit-learn website def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion matrix', cmap=plt.cm.Blues): This function prints and plots the confusion matrix. Normalization can be applied by setting `normalize=True`. if normalize: cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] plt.imshow(cm, interpolation='nearest', cmap=cmap) plt.title(title) plt.colorbar() tick_marks = np.arange(len(classes)) plt.xticks(tick_marks, classes, rotation=45) plt.yticks(tick_marks, classes) fmt = '.2f' if normalize else 'd' thresh = cm.max() / 2. for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): plt.text(j, i, format(cm[i, j], fmt), horizontalalignment="center", color="white" if cm[i, j] > thresh else "black") plt.ylabel('True label') plt.xlabel('Predicted label') plt.show() X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y) params = { "cls__penalty": ["l1", "l2"], "cls__C": [0.5, 1, 2, 5], "cls__max_iter": [500] } pipe_lr = Pipeline([ ('scale', StandardScaler()), ('var_tresh', VarianceThreshold(threshold=(.8 * (1 - .8)))), ('feature_selection', SelectFromModel(lgbm.LGBMClassifier())), ('cls', LogisticRegression()) ]) grid_lr = GridSearchCV(pipe_lr, params, scoring='accuracy', n_jobs=6, cv=5) grid_lr.fit(X_train, y_train) preds = grid_lr.predict(X_test) print("best score on validation set (accuracy) = {:.4f}".format(grid_lr.best_score_)) print("best score on test set (accuracy) = {:.4f}".format(accuracy_score(y_test, preds))) params = { "cls__loss": ['log'], "cls__penalty": ["elasticnet"], "cls__l1_ratio": [0.15, 0.25, 0.5, 0.75], } pipe_en = Pipeline([ ('scale', StandardScaler()), ('var_tresh', VarianceThreshold(threshold=(.8 * (1 - .8)))), ('feature_selection', SelectFromModel(lgbm.LGBMClassifier())), ('cls', SGDClassifier()) ]) grid_en = GridSearchCV(pipe_en, params, scoring='accuracy', n_jobs=6, cv=5) grid_en.fit(X_train, y_train) preds = grid_en.predict(X_test) print("best score on validation set (accuracy) = {:.4f}".format(grid_en.best_score_)) print("best score on test set (accuracy) = {:.4f}".format(accuracy_score(y_test, preds))) params = { "cls__criterion": ["gini", "entropy"], "cls__splitter": ["best", "random"], } pipe_cart = Pipeline([ ('var_tresh', VarianceThreshold(threshold=(.8 * (1 - .8)))), ('feature_selection', SelectFromModel(lgbm.LGBMClassifier())), ('cls', DecisionTreeClassifier()) ]) grid_cart = GridSearchCV(pipe_cart, params, scoring='accuracy', n_jobs=6, cv=5) grid_cart.fit(X_train, y_train) preds = grid_cart.predict(X_test) print("best score on validation set (accuracy) = {:.4f}".format(grid_cart.best_score_)) print("best score on test set (accuracy) = {:.4f}".format(accuracy_score(y_test, preds))) params = { "cls__n_estimators": [100, 250, 500, 1000], "cls__criterion": ["gini", "entropy"], "cls__max_depth": [5, 7, None] } pipe_rf = Pipeline([ ('var_tresh', VarianceThreshold(threshold=(.8 * (1 - .8)))), ('feature_selection', SelectFromModel(lgbm.LGBMClassifier())), ('cls', RandomForestClassifier()) ]) grid_rf = GridSearchCV(pipe_rf, params, scoring='accuracy', n_jobs=6, cv=5) grid_rf.fit(X_train, y_train) preds = grid_rf.predict(X_test) print("best score on validation set (accuracy) = {:.4f}".format(grid_rf.best_score_)) print("best score on test set (accuracy) = {:.4f}".format(accuracy_score(y_test, preds))) params = { "cls__C": [0.5, 1, 2, 5], "cls__kernel": ['rbf', 'linear', 'sigmoid'], } pipe_svm = Pipeline([ ('scale', StandardScaler()), ('var_tresh', VarianceThreshold(threshold=(.8 * (1 - .8)))), ('feature_selection', SelectFromModel(lgbm.LGBMClassifier())), ('cls', SVC()) ]) grid_svm = GridSearchCV(pipe_svm, params, scoring='accuracy', n_jobs=6, cv=5) grid_svm.fit(X_train, y_train) preds = grid_svm.predict(X_test) print("best score on validation set (accuracy) = {:.4f}".format(grid_svm.best_score_)) print("best score on test set (accuracy) = {:.4f}".format(accuracy_score(y_test, preds))) cm = confusion_matrix(y_test, preds) classes = ['metal', 'disco', 'classical', 'hiphop', 'jazz', 'country', 'pop', 'blues', 'reggae', 'rock'] plt.figure(figsize=(10,10)) plot_confusion_matrix(cm, classes, normalize=True) from sklearn.externals import joblib joblib.dump(grid_svm, "../models/pipe_svm.joblib") <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 preparation (keras.dataset) Step2: Training Step3: Plotting Network Performance Trend Step4: After 100 epochs, we get a 98.8% validation accuracy.
<ASSISTANT_TASK:> Python Code: from keras.models import Sequential from keras.layers.core import Dense, Dropout from keras.optimizers import SGD nb_classes = 10 # FC@512+relu -> DropOut(0.2) -> FC@512+relu -> DropOut(0.2) -> FC@nb_classes+softmax # ... your Code Here # Decomment and Execute this cell to get the solution # %load solutions/sol_221_1.py from keras.datasets import mnist from keras.utils import np_utils (X_train, y_train), (X_test, y_test) = mnist.load_data() X_train = X_train.reshape(60000, 784) X_test = X_test.reshape(10000, 784) X_train = X_train.astype("float32") X_test = X_test.astype("float32") X_train /= 255 X_test /= 255 # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, 10) Y_test = np_utils.to_categorical(y_test, 10) network_history = model.fit(X_train, Y_train, batch_size=128, epochs=100, verbose=1, validation_data=(X_test, Y_test)) import matplotlib.pyplot as plt %matplotlib inline plt.figure() plt.xlabel('Epochs') plt.ylabel('Loss') plt.plot(network_history.history['loss']) plt.plot(network_history.history['val_loss']) plt.legend(['Training', 'Validation']) plt.figure() plt.xlabel('Epochs') plt.ylabel('Accuracy') plt.plot(network_history.history['acc']) plt.plot(network_history.history['val_acc']) plt.legend(['Training', 'Validation'], loc='lower right') # %load solutions/sol_221_2.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: The problem with the squared error is that it makes small errors (< 1.0) even smaller and large large errors (>1.0) disproportionately larger. Step2: Datasets with large outliers show heavy tails in the residual distribution when trained using MSE as shown above. Step3: MAE does not over-prioritize outliers and it is easy to interpret Step4: Particularly interesting is that for $\delta=1.0$ Huber loss is asymptotically similar to MAE and behaves as MSE around 0. For other values of $\delta$, Huber loss still increases linearly for large errors and $\delta$ controls simply the slope of this growth. Step5: Conclusion Step6: The distribution of the values has a "bump" for smaller values and then a long tail with a small number of very large values. Step7: Note that the scale of the y-axis in the bottom has been changed to be able to see those small residuals!
<ASSISTANT_TASK:> Python Code: a = symbols('a') #actual value p = symbols('p') #predicted value mse = lambda a,p: (a-p)**2 mse_plot = plot(mse(0, p),(p, -3, 3), show=False, legend=True, line_color="red") mse_plot[0].label='MSE' mse_plot.show() # Let's see how to identify np.random.seed(1000) N = 10000 w = np.ones(5) X = np.random.randn(N, 5) y = X.dot(w) # The last 1000 target values get some serious noise y[-1000:] += np.random.normal(0,100.0, 1000) mse = lambda x: mean_squared_error(y, X.dot(x)) x0 = np.zeros(X.shape[1]) #initial guess result_w = minimize(mse, x0, tol=1e-5)['x'] #MSE result residuals_mse = y - X.dot(result_w) # Plot the distribution of the residuals kde = gaussian_kde(residuals_mse) dist_space = np.linspace(min(residuals_mse), max(residuals_mse), 100) _ = pl.plot(dist_space, kde(dist_space)) mae = lambda a,p: Abs(a-p) mae_plot = plot(mae(0, p),(p, -3, 3), show=False, line_color="blue") mae_plot[0].label = "MAE" mse_plot.extend(mae_plot) mse_plot.show() huber = lambda delta,a,p: Piecewise((0.5*(a-p)**2, Abs(a-p) <= delta), (delta*Abs(a-p)-0.5*delta**2, True)) huber1_plot = plot(huber(1.0, 0, p),(p, -3, 3), show=False, line_color="green") huber1_plot[0].label = "Huber $\delta=1.0$" huber2_plot = plot(huber(2.0, 0, p),(p, -3, 3), show=False, line_color="turquoise") huber2_plot[0].label = "Huber $\delta=2.0$" mse_plot.extend(huber1_plot) mse_plot.extend(huber2_plot) mse_plot.show() pseudo_huber = lambda delta,a,p: delta**2*(sqrt(1+((a-p)/delta)**2)-1) pseudo_huber1 = plot(pseudo_huber(1.0, 0,p),(p, -3, 3), show=False, legend=True, line_color='lightgreen') pseudo_huber1[0].label='Pseud-Huber $\delta=1.0$' huber1_plot.extend(pseudo_huber1) huber1_plot.legend = True huber1_plot.show() from sympy.stats import LogNormal, density z = symbols('z') log_norm_1 = LogNormal("x", 0, 1.0) log_norm_2 = LogNormal("x", 0, 0.5) log_norm_3 = LogNormal("x", 0, 0.25) pdf_plot1= plot(density(log_norm_1)(z), (z,0.01, 5), show=False, line_color="blue") pdf_plot2= plot(density(log_norm_2)(z), (z,0.01, 5), show=False, line_color="green") pdf_plot3= plot(density(log_norm_3)(z), (z,0.01, 5), show=False, line_color="red") pdf_plot1.extend(pdf_plot2) pdf_plot1.extend(pdf_plot3) pdf_plot1.show() # We generate random data and train a simple linear model to minimize # MSE and MSLE loss functions. np.random.seed(1000) N = 10000 w = np.ones(5) X = np.random.randn(N, 5) y = X.dot(w) yexp = np.exp(y) mse = lambda x: mean_squared_error(yexp, X.dot(x)) def msle(x, t=1): pred = X.dot(x)+t pred[pred<0] = 0 return mean_squared_log_error(yexp+t, pred) x0 = np.zeros(X.shape[1]) #initial guess res_mse = minimize(mse, x0, tol=1e-5) #MSE residuals results = {} #MSLE residuals for different offsets T = [1.0, 10.0, 100.0] for t in T: results[t] = minimize(lambda x: msle(x, t), x0, tol=1e-5) sorted_idx = np.argsort(yexp) label_sorted = yexp[sorted_idx] def get_sorted_residuals(results): residuals = yexp - X.dot(results['x']) return residuals[sorted_idx] f, (axTop, axMiddle, axBottom) = pl.subplots(3, 1, sharex=True, figsize=(10, 15)) # plot the density distribution of the target values on top kde = gaussian_kde(yexp) yrange = np.logspace(min(y), max(y), 100, base=np.exp(1)) axTop.plot(yrange, kde(yrange)) axTop.set_ylabel('density') # plot the magnitudes of residuals for MSE and MSLE with different offsets for t in T: # use a median filter to smooth residuals and see the trend. axMiddle.plot(label_sorted, median_filter(get_sorted_residuals(results[t]), size=50), label='t={}'.format(t)) axBottom.plot(label_sorted, median_filter(get_sorted_residuals(results[t]), size=50), label='t={}'.format(t)) axMiddle.plot(label_sorted, median_filter(get_sorted_residuals(res_mse), size=50), label='mse') axBottom.plot(label_sorted, median_filter(get_sorted_residuals(res_mse), size=50), label='mse') axBottom.set_xscale('log') axBottom.set_xlabel('target') axBottom.set_xticks(np.logspace(-3,3,7)) axMiddle.set_ylabel('residual') axBottom.set_ylabel('residual') axMiddle.set_ylim(800,1000) axBottom.set_ylim(-20,75) axMiddle.legend() pl.show() quantiles = np.linspace(0, 1.0, 11) qvalues = np.quantile(yexp, np.linspace(0, 1.0, 11)) for q, val in zip(quantiles, qvalues): print("Percentile {:.0f}\tvalue {:.2f}".format(q*100, val)) <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: Influence of temperature Step2: Mole fractions Step3: Surface Production Rates Step4: Comparison between temperatures Step5: Effect of catalyst loading
<ASSISTANT_TASK:> Python Code: import os import matplotlib as mpl mpl.rcParams['figure.dpi'] = 500 import numpy as np import pandas as pd import matplotlib.pyplot as plt %matplotlib inline %config InlineBackend.figure_format = 'retina' ls T-950K/ mole_df = pd.read_csv(os.path.join('T-950K','gas_mole_tr.csv')) msdot_df = pd.read_csv(os.path.join('T-950K','gas_msdot_tr.csv')) surf_cov_df = pd.read_csv(os.path.join('T-950K','surf_cov_tr.csv')) ax = plt.subplot(1, 1, 1) ax.plot('t(s)', 'H2', color='r', data=mole_df, marker='^', markersize=0.5, label="$H_2$") ax.plot('t(s)', 'N2', color='g', data=mole_df, marker='v', markersize=0.5, label="$N_2$") ax.plot('t(s)', 'NH3', color='b', data=mole_df, marker='*', markersize=0.5, label="$NH_3$") ax.set_xlabel('Time (s)') ax.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax.set_ylabel('Mole Fraction') #ax.set_xlim([0,50]) # Change time limit to 1 ax.set_xlim([0,0.04]) ax.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.show() #plt.savefig('Ammonia_gas_species_molefrac.png', dpi=500) ax3 = plt.subplot(1, 1, 1) ax3.plot('t(s)', 'H2', color='r', data=msdot_df, marker='^', markersize=0.5, label="$H_2$") ax3.plot('t(s)', 'N2', color='g', data=msdot_df, marker='v', markersize=0.5, label="$N_2$") ax3.plot('t(s)', 'NH3', color='b', data=msdot_df, marker='*', markersize=0.5, label="$NH_3$") ax3.set_xlabel('Time (s)') ax3.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax3.set_ylabel('Surface Production Rate') #ax3.set_xlim([0,50]) ax3.set_xlim([0,0.001]) ax3.set_ylim([-1e-6,1e-6]) ax3.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.show() #plt.savefig('Ammonia_gas_species_production_rate.png', dpi=500) print(surf_cov_df.columns) ax1 = plt.subplot(1, 1, 1) ax1.plot('t(s)', 'RU(S1)', color='r', data=surf_cov_df, marker='^', markersize=0.5, label="$Ru*$") ax1.plot('t(s)', 'H(S1)', color='g', data=surf_cov_df, marker='v', markersize=0.5, label="$H*$") ax1.plot('t(s)', 'N(S1)', color='b', data=surf_cov_df, marker='*', markersize=0.5, label="$N*$") ax1.set_xlabel('Time (s)') ax1.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax1.set_ylabel('Surface Coverages') ax1.set_xlim([0,5]) #ax1.set_xlim([0,0.04]) ax1.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.show() #plt.savefig('Ammonia_surf_cov.png', dpi=500) mole_df_950 = pd.read_csv(os.path.join('T-950K','gas_mole_tr.csv')) msdot_df_950 = pd.read_csv(os.path.join('T-950K','gas_msdot_tr.csv')) surf_cov_df_950 = pd.read_csv(os.path.join('T-950K','surf_cov_tr.csv')) mole_df_900 = pd.read_csv(os.path.join('T-900K','gas_mole_tr.csv')) msdot_df_900 = pd.read_csv(os.path.join('T-900K','gas_msdot_tr.csv')) surf_cov_df_900 = pd.read_csv(os.path.join('T-900K','surf_cov_tr.csv')) ax = plt.subplot(1, 1, 1) ax.plot('t(s)', 'H2', '-', color='r', data=mole_df_950, marker='^', markersize=0.5, label="$H_2$ 950K") ax.plot('t(s)', 'H2', '--', color='r', data=mole_df_900, marker='^', markersize=0.5, label="$H_2$ 900K") ax.plot('t(s)', 'N2', '-', color='g', data=mole_df_950, marker='v', markersize=0.5, label="$N_2$ 950K") ax.plot('t(s)', 'N2', '--', color='g', data=mole_df_900, marker='v', markersize=0.5, label="$N_2$ 900K") ax.plot('t(s)', 'NH3', '-', color='b', data=mole_df_950, marker='*', markersize=0.5, label="$NH_3$ 950K") ax.plot('t(s)', 'NH3', '--', color='b', data=mole_df_900, marker='*', markersize=0.5, label="$NH_3$ 900K") ax.set_xlabel('Time (s)') ax.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax.set_ylabel('Mole Fraction') #ax.set_xlim([0,50]) # Change time limit to 1 ax.set_xlim([0,5]) ax.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.savefig('Ammonia_molefrac_Tcomp.png', dpi=500) ax = plt.subplot(1, 1, 1) ax.plot('t(s)', 'RU(S1)', '-', color='r', data=surf_cov_df_950, marker='^', markersize=0.5, label="$Ru*$ 950K") ax.plot('t(s)', 'RU(S1)', '--', color='r', data=surf_cov_df_900, marker='^', markersize=0.5, label="$Ru*$ 900K") ax.plot('t(s)', 'H(S1)', '-', color='g', data=surf_cov_df_950, marker='v', markersize=0.5, label="$H*$ 950K") ax.plot('t(s)', 'H(S1)', '--', color='g', data=surf_cov_df_900, marker='v', markersize=0.5, label="$H*$ 900K") ax.plot('t(s)', 'N(S1)', '-', color='b', data=surf_cov_df_950, marker='*', markersize=0.5, label="$N*$ 950K") ax.plot('t(s)', 'N(S1)', '--', color='b', data=surf_cov_df_900, marker='*', markersize=0.5, label="$N*$ 900K") ax.set_xlabel('Time (s)') ax.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax.set_ylabel('Surface Coverages') #ax.set_xlim([0,0.5]) ax.set_xlim([0,0.04]) ax.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.savefig('Ammonia_surf_cov_Tcomp.png', dpi=500) mole_df_10 = pd.read_csv(os.path.join('AbyV-1000','gas_mole_tr.csv')) msdot_df_10 = pd.read_csv(os.path.join('AbyV-1000','gas_msdot_tr.csv')) surf_cov_df_10 = pd.read_csv(os.path.join('AbyV-1000','surf_cov_tr.csv')) mole_df_15 = pd.read_csv(os.path.join('AbyV-1500','gas_mole_tr.csv')) msdot_df_15 = pd.read_csv(os.path.join('AbyV-1500','gas_msdot_tr.csv')) surf_cov_df_15 = pd.read_csv(os.path.join('AbyV-1500','surf_cov_tr.csv')) ax = plt.subplot(1, 1, 1) ax.plot('t(s)', 'H2', '-', color='r', data=mole_df_15, marker='^', markersize=0.5, label="$H_2$ 1.5k") ax.plot('t(s)', 'H2', '--', color='r', data=mole_df_10, marker='^', markersize=0.5, label="$H_2$ 1.0K") ax.plot('t(s)', 'N2', '-', color='g', data=mole_df_15, marker='v', markersize=0.5, label="$N_2$ 1.5k") ax.plot('t(s)', 'N2', '--', color='g', data=mole_df_10, marker='v', markersize=0.5, label="$N_2$ 1.0k") ax.plot('t(s)', 'NH3', '-', color='b', data=mole_df_15, marker='*', markersize=0.5, label="$NH_3$ 1.5k") ax.plot('t(s)', 'NH3', '--', color='b', data=mole_df_10, marker='*', markersize=0.5, label="$NH_3$ 1.0k") ax.set_xlabel('Time (s)') ax.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax.set_ylabel('Mole Fraction') #ax.set_xlim([0,50]) # Change time limit to 1 ax.set_xlim([0,5]) ax.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.show() #plt.savefig('Ammonia_molefrac_catload_cmp.png', dpi=500) ax = plt.subplot(1, 1, 1) ax.plot('t(s)', 'RU(S1)', '-', color='r', data=surf_cov_df_15, marker='^', markersize=0.5, label="$Ru*$ 1.5k") ax.plot('t(s)', 'RU(S1)', '--', color='r', data=surf_cov_df_10, marker='^', markersize=0.5, label="$Ru*$ 1.0k") ax.plot('t(s)', 'H(S1)', '-', color='g', data=surf_cov_df_15, marker='v', markersize=0.5, label="$H*$ 1.5k") ax.plot('t(s)', 'H(S1)', '--', color='g', data=surf_cov_df_10, marker='v', markersize=0.5, label="$H*$ 1.0k") ax.plot('t(s)', 'N(S1)', '-', color='b', data=surf_cov_df_15, marker='*', markersize=0.5, label="$N*$ 1.5k") ax.plot('t(s)', 'N(S1)', '--', color='b', data=surf_cov_df_10, marker='*', markersize=0.5, label="$N*$ 1.0k") ax.set_xlabel('Time (s)') ax.ticklabel_format(axis='y', style='sci', scilimits=(0,0)) ax.set_ylabel('Surface Coverages') #ax.set_xlim([0,0.5]) ax.set_xlim([0,0.04]) ax.legend(loc="upper left", bbox_to_anchor=(1,1)) plt.tight_layout() plt.show() #plt.savefig('Ammonia_surf_cov_catload-comp.png', dpi=500) <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 database Step2: Explore contents of the database file Step3: The content of the raw IMU file Step4: Implemented analysis methods Step5: Try an analysis
<ASSISTANT_TASK:> Python Code: import numpy as np import matplotlib.pyplot as plt import nvg.ximu.ximudata as ximudata %matplotlib notebook reload(ximudata) dbfilename = "/home/kjartan/Dropbox/Public/nvg201209.hdf5" db = ximudata.NVGData(dbfilename); dbfile = db.hdfFile; print "Subjects: ", dbfile.keys() print "Trials: ", dbfile['S5'].keys() print "IMUs: ", dbfile['S5/B'].keys() print "Attributes of example trial", dbfile['S5/B'].attrs.keys() print "Shape of example IMU data entry", dbfile['S5/B/N'].shape db.plot_imu_data() print [s for s in dir(db) if s.startswith("get")] res = db.apply_to_all_trials(db.get_RoM_angle_to_vertical, {'imu':'N'}, subjlist=['S2', 'S3'], triallist=['B', 'N']) res <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 MNIST Step3: Conversions Step4: Sweet! Step5: Okay, cool. Step6: Alternate Conversion Method
<ASSISTANT_TASK:> Python Code: from pathlib import Path import numpy as np import os from urllib.request import urlretrieve import matplotlib.pyplot as plt %matplotlib inline def download_mnist(path=Path('data/mnist')): os.makedirs(path, exist_ok=True) urls = ['http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz', 'http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz', 'http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz', 'http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz',] for url in urls: fname = url.split('/')[-1] if not os.path.exists(path/fname): urlretrieve(url, path/fname) import struct import gzip import numpy as np def read_IDX(fname): see: https://gist.github.com/tylerneylon/ce60e8a06e7506ac45788443f7269e40 with gzip.open(fname) as f: zero, data_type, dims = struct.unpack('>HBB', f.read(4)) shape = tuple(struct.unpack('>I', f.read(4))[0] for d in range(dims)) return np.frombuffer(f.read(), dtype=np.uint8).reshape(shape) # See: https://docs.python.org/3/library/struct.html#byte-order-size-and-alignment # IDX format assumes MSB (big-endian) ordering used by non-Intel machines. # Therefore if you're using an Intel cpu specify '>' when unpacking to let # Python know to handle the header bytes correctly download_mnist() fname = Path('data/mnist/t10k-images-idx3-ubyte.gz') tmp = read_IDX(fname) tmp.shape plt.imshow(tmp[0]) tmp = None fname = Path('data/mnist/t10k-labels-idx1-ubyte.gz') tmp = read_IDX(fname) tmp.shape tmp set(tmp) def read_IDX(fname): with gzip.open(fname) as f: zero, data_type, dims = struct.unpack('>HBB', f.read(4)) import pdb; pdb.set_trace() shape = tuple(struct.unpack('>I', f.read(4))[0] for d in range(dims)) return np.frombuffer(f.read(), dtype=np.uint8).reshape(shape) # fname = Path('data/mnist/t10k-labels-idx1-ubyte.gz') fname = Path('data/mnist/t10k-images-idx3-ubyte.gz') tmp = read_IDX(fname) ## see: https://medium.com/@mannasiladittya/converting-mnist-data-in-idx-format-to-python-numpy-array-5cb9126f99f1 # 1. imports import struct import numpy as np # 2. open IDX file in readable binary mode fname = {'images': 'train-images-idx3-ubyte', 'labels':'train-labels-idx1-ubyte'} fimg = open('data/mnist/' + fname['images'], 'rb') # 3. read magic number fimg.seek(0) magic = struct.unpack('>4B', fimg.read(4)) # 4. read dims of image dataset nimg = struct.unpack('>I', fimg.read(4))[0] # num images nrow= struct.unpack('>I', fimg.read(4))[0] # num rows ncol= struct.unpack('>I', fimg.read(4))[0] # num cols # 5. create numpy array img_arr = np.zeros((nimg, nrow, ncol)) # 6. read img data n_bytes_total = nimg * nrow * ncol * 1 # since ea. pixel is 1 byte img_arr = 255 - np.asarray(struct.unpack('>' + 'B' * n_bytes_total, fimg.read(n_bytes_total)) ).reshape((nimg, nrow, ncol)) <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: Demo Step2: A SampleSource can be sampled to get a TSTData (two-sample test data) object. A TSTData object is just an encapsulation of two $n\times d$ numpy arrays, representing the two samples. The TSTData object will be fed to a testing algorithm to conduct the two-sample test. All two-sample test algorithms are implemented to take in a TSTData object as its input. Step3: Note that in practice, we have access to only two data matrices Step4: Now that we have tst_data, let us randomly split it into two disjoint halves of equal size Step5: Optimize the test locations (features) and the Gaussian width Step6: The optimization procedure returns back 3 things Step7: Here we see that the test rejects the null hypothesis with a very small p-value.
<ASSISTANT_TASK:> Python Code: %load_ext autoreload %autoreload 2 %matplotlib inline import numpy as np import matplotlib.pyplot as plt import freqopttest.util as util import freqopttest.data as data import freqopttest.kernel as kernel import freqopttest.tst as tst import freqopttest.glo as glo import theano # Full sample size n = 600 # Consider two dimensions here dim = 2 seed = 15 # mean shift my = 1.0 ss = data.SSGaussMeanDiff(dim, my=my) #ss = data.SSGaussVarDiff(dim) #ss = data.SSSameGauss(dim) #ss = data.SSBlobs() # draw n points from P, and n points from Q. # tst_data is an instance of TSTData tst_data = ss.sample(n, seed=seed) # Let's plot the data x, y = tst_data.xy() plt.plot(x[:, 0], x[:, 1], 'b.', markeredgecolor='b', label='$X\sim P$', alpha=0.5) plt.plot(y[:, 0], y[:, 1], 'r.', markeredgecolor='r', label='$Y\sim Q$', alpha=0.5) plt.axis('equal') plt.legend() tr, te = tst_data.split_tr_te(tr_proportion=0.5, seed=2) # J = number of test locations (features) J = 1 # significance level of the test alpha = 0.01 # These are options to the optimizer. Many have default values. # See the code for the full list of options. op = { 'n_test_locs': J, # number of test locations to optimize 'max_iter': 200, # maximum number of gradient ascent iterations 'locs_step_size': 1.0, # step size for the test locations (features) 'gwidth_step_size': 0.1, # step size for the Gaussian width 'tol_fun': 1e-4, # stop if the objective does not increase more than this. 'seed': seed+5, # random seed } # optimize on the training set test_locs, gwidth, info = tst.MeanEmbeddingTest.optimize_locs_width(tr, alpha, **op) # Construct a MeanEmbeddingTest object with the best optimized test features, # and optimized Gaussian width met_opt = tst.MeanEmbeddingTest(test_locs, gwidth, alpha) # Do the two-sample test on the test data te. # The returned test_result is a dictionary. test_result = met_opt.perform_test(te) test_result # Plot evolution of the test locations, Gaussian width # trajectories of the Gaussian width gwidths = info['gwidths'] fig, axs = plt.subplots(2, 2, figsize=(10, 9)) axs[0, 0].plot(gwidths) axs[0, 0].set_xlabel('iteration') axs[0, 0].set_ylabel('Gaussian width') axs[0, 0].set_title('Gaussian width evolution') # evolution of objective values objs = info['obj_values'] axs[0, 1].plot(objs) axs[0, 1].set_title('Objective $\lambda(T)$') # trajectories of the test locations # iters x J. X Coordinates of all test locations locs = info['test_locs'] for coord in [0, 1]: locs_d0 = locs[:, :, coord] J = locs_d0.shape[1] axs[1, coord].plot(locs_d0) axs[1, coord].set_xlabel('iteration') axs[1, coord].set_ylabel('index %d of test_locs'%(coord)) axs[1, coord].set_title('evolution of %d test locations'%J) print('optimized width: %.3f'%gwidth) <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: Prioritize Step2: Note Step3: Some special objects Step4: http Step5: The above object was put as SAT==2, but is at very close z to AnaK...? r~=17.6 in DECALS. Marla says this is because it's too far from the host, so not worth special-izing Step6: Risa suggests Step7: This is not actually quite on the center-of-light in DECALS... but it might be an HII region? Step12: That one seems good Step13: Make the master catalogs Step14: For the remainder, generate and visually inspect them one at a time. Edit the file to remove any that are not good sky positions Step15: Actually generate the master catalogs Step16: Observations Step18: This function parses a dump of all the image headers from 'fitsheader ccd_?/.fits' Step19: Night 1 Step21: Make observing log Step22: Night 2 Step24: Make observing log Step25: Nights 3+ Step26: NSA 145729 is being treated a bit oddly because there might be two back-to-back-ish observations. So we're making one config in advance for both the p0 and p1 configurations, and making fld's for config 2 assuming either of those. Step27: Logs for observations Step28: Utilities for during the night Step29: Inspect guider fields as needed Step30: Planning Step31: Find possible targets Step32: Airmass chart Step33: Notes Step34: Note Step35: Basically there after 2 observations of Narnia and OBrother. AnaK and Dune 1 or maybe 2, Gilg/Ody 1. Step36: Log from last run
<ASSISTANT_TASK:> Python Code: nmstoget = ('Dune', 'AnaK', 'Odyssey', 'Gilgamesh', 'OBrother', 'Narnia', 'Catch22') hosts_to_target = [h for h in hsd.values() if h.name in nmstoget] assert len(hosts_to_target)==len(nmstoget) new_targets = [hosts.NSAHost(145729), hosts.NSAHost(21709)] hosts_to_target.extend(new_targets) # now set to the latest base catalogs for h in hsd.values() + hosts_to_target: h.fnsdss = 'SAGADropbox/base_catalogs/base_sql_nsa{0}.fits.gz'.format(h.nsaid) h._cached_sdss = None # make sure the catalogs are loaded for h in hosts_to_target: h.get_sdss_catalog() hosts_to_target # these are the already-observed objects # we use "h" for this only as a convenience because the method adds some useful bits that aren't in the raw catalogs spectra = h.load_and_reprocess_sdss_catalog('SAGADropbox/data/saga_spectra_clean.fits.gz') for h in hosts_to_target: print('On host', h.name) cat = h.get_sdss_catalog() r0 = cat['r'] - cat['Ar'] cutbyrawmagcut = (r0<20.75)&(cat['r']>21) if np.sum(cutbyrawmagcut)>0: print('WARNING: ', np.sum(cutbyrawmagcut), 'objects have rmags in selection but are extincted too much for r>21') pris = np.ones(len(cat)) # remove list tokeep = cat['REMOVE']==-1 pris[~tokeep] = -cat['REMOVE'][~tokeep] # sets the REMOVE objects to -their remove value remmskval = np.min(pris)-1 # remove anything in the remove list online but not in the catalog as remove pris[~targeting.remove_targets_with_remlist(cat, h, maskonly=True, verbose='warning')&(pris>-1)] = remmskval if np.sum(pris==remmskval) > 0: print('Removed', np.sum(pris==remmskval), 'due to online remove list. Remmsk val:', remmskval) photgood = ((cat['r'] < 21.) & # this is to cut the numbers a bit - more stringent mag cuts below (cat['fibermag_r']<23) & (cat['phot_sg']=='GALAXY')) nearish = (cat['RHOST_KPC']<450) # again, to limit the numbers pris[~photgood|~nearish] = 0 # pris ~-100 are removed due to already-observed nospec = cat['ZQUALITY']<3 pris[~nospec] = -100-cat['ZQUALITY'][~nospec] brighter = r0 < 20 fainter = (r0 < 20.75)&~brighter goodcolors = targeting.colorcut_mask(cat, {'g-r': (None, 0.85, 2), 'r-i': (None, 0.55, 2)},deredden=True) okcolors = targeting.colorcut_mask(cat, {'g-r': (None, 1.2), 'r-i': (None, 0.7)}, deredden=False) inside = cat['RHOST_KPC']<300 pris[(pris>0)&~inside&fainter&goodcolors] = np.max(pris) + 1 pris[(pris>0)&~inside&brighter&goodcolors] = np.max(pris) + 1 pris[(pris>0)&inside&fainter&okcolors] = np.max(pris) + 1 pris[(pris>0)&inside&brighter&okcolors] = np.max(pris) + 1 pris[(pris>0)&inside&fainter&goodcolors] = np.max(pris) + 1 pris[(pris>0)&inside&brighter&goodcolors] = np.max(pris) + 1 #everything left is in pri 1 # this *shouldn't* be necessary, as ZQUALITY should be in the base catalog. # But as a sanity check we look to see if anything in the spectral catalog is still being included spec_this_host = spectra[spectra['HOST_NSAID']==h.nsaid] spec_this_host = spec_this_host[np.in1d(spec_this_host['OBJID'], cat['OBJID'])] zq = cat['ZQUALITY'].copy() for i, zqi in zip(spec_this_host['OBJID'], spec_this_host['ZQUALITY']): zq[cat['OBJID']==i] = zqi if np.any(pris[zq>2]>=0): print('POSSIBLE PROBLEM: Found some objects in spectrum list that are *not* claimed ' 'as having spectra in the base catalogs. Setting them to -11x:', dict(Counter(pris[pris<-110]))) pris[zq>2] = -110 - zq[zq>2] #de-duplicate if len(np.unique(cat['OBJID'])) != len(cat): _, idxs = np.unique(cat['OBJID'], return_index=True) msk = np.ones_like(cat, dtype=bool) msk[idxs] = 0 pris[msk] = -1000 print('WARNING: some duplicate objid found. Setting', np.sum(pris==-1000), 'dupes to pri=-1000') cat['aat_pris'] = pris if 'aat_pris_unjiggered' in cat.colnames: cat.remove_column('aat_pris_unjiggered') #informational counter = Counter(pris) print('Rank counts:') for k in reversed(sorted(counter)): print(int(k), ':', counter[k]) for h in new_targets: print(h.name) cat = h.get_sdss_catalog() if 'aat_pris_unjiggered' in cat.colnames: print('Already rejiggered', h, 'skipping (but still reporting stats)...') pris = cat['aat_pris'] print(dict(Counter(pris[pris>0]))) print(dict(Counter(pris[pris<=0]))) continue p = cat['PROBABILITY_CLASS1'] if np.all(p<0): print('WARNING: host', h, 'does not have probs, so not re-jiggering based on ML probs') continue pris = np.array(cat['aat_pris_unjiggered' if 'aat_pris_unjiggered' in cat.colnames else 'aat_pris']) goodcolorbright = pris == 7 goodcolorfaint = pris == 6 okcolor = (pris==5) | (pris==4) pris[okcolor] = -0.75 pris[goodcolorfaint] = 4 pris[goodcolorbright] = 5 pris[goodcolorfaint&(p>.001)] = 6 pris[goodcolorbright&(p>.001)] = 7 print(dict(Counter(pris[pris>0]))) print(dict(Counter(pris[pris<=0]))) cat['aat_pris_unjiggered'] = cat['aat_pris'] cat['aat_pris'] = pris special_objids = [] possible_anak_sat = SkyCoord(353.7229, 1.2064, unit=u.deg) spectrascs = SkyCoord(spectra['ra'], spectra['dec'], unit=u.deg) row = spectra[np.argsort(possible_anak_sat.separation(spectrascs))[0]] special_objids.append(row['OBJID']) row del special_objids[special_objids.index(row['OBJID'])] possible_anak_sat = SkyCoord(354.286, 0.211, unit=u.deg) anakcat = hsd['AnaK'].get_sdss_catalog() anakscs = SkyCoord(anakcat['ra'], anakcat['dec'], unit=u.deg) seps = possible_anak_sat.separation(anakscs) closest = np.argsort(seps)[0] print(seps[closest].arcsec) row = anakcat[closest] special_objids.append(row['OBJID']) row possible_anak_sat = SkyCoord(354.527, 0.533964, unit=u.deg) seps = possible_anak_sat.separation(anakscs) closest = np.argsort(seps)[0] print(seps[closest].arcsec) row = anakcat[closest] special_objids.append(row['OBJID']) row def find_risa_objs(stringfromrisa, h): risa_tab = Table.read(stringfromrisa, delimiter='\t', format='ascii', names=['unk', 'ra', 'dec', 'mag', 'cand']) risa_sc = SkyCoord(risa_tab['ra'], risa_tab['dec'], unit=u.deg) cat = h.get_sdss_catalog() catsc = SkyCoord(cat['ra'], cat['dec'], unit=u.deg) idx, d2d, _ = risa_sc.match_to_catalog_sky(catsc) assertmsg = '{} matched of {}: {}'.format(np.sum(d2d < .1*u.arcsec),len(d2d), d2d[d2d > .1*u.arcsec]) assert np.all(d2d < .1*u.arcsec), assertmsg return cat['OBJID'][idx] risa_145729= -1 224.56410 -1.0730193 19.7973 true -1 224.59164 -1.1261357 17.9597 true -1 224.58605 -1.1340797 19.9805 true -1 224.65696 -1.1021396 17.4972 true -1 224.54478 -1.1645862 19.4057 true -1 224.50349 -1.1783027 17.7666 true -1 224.61258 -1.2283750 20.1190 true -1 224.66071 -1.2407656 20.3448 true -1 224.58210 -1.2891033 20.1278 true -1 224.68795 -0.82928863 18.7276 true -1 224.46354 -0.85993860 20.6228 true -1 224.43907 -1.3290346 20.2419 true -1 224.27041 -1.0663297 19.6382 true -1 224.92796 -1.0868430 19.9441 true -1 224.95218 -1.2046019 20.2506 true -1 224.98659 -1.0996963 19.2848 true -1 224.95028 -1.2134533 19.1667 true -1 224.56810 -0.71035594 19.5400 true -1 224.56710 -0.71155324 18.3361 true -1 224.63475 -0.76637428 20.5220 true -1 224.79342 -0.82424335 19.5245 true -1 224.26293 -1.3190454 19.7427 true -1 224.34037 -1.3851494 19.5061 true -1 224.67776 -1.3717603 18.9769 true -1 224.30819 -0.89372642 19.5476 true -1 224.95888 -1.0081097 19.6524 true -1 225.01145 -1.2106150 19.6745 true -1 224.27946 -0.80572367 19.0886 true -1 224.44473 -0.64135326 18.2103 true -1 224.59702 -0.60626247 19.4427 true -1 224.98059 -1.2775413 20.7447 true -1 224.25056 -1.3830278 20.6792 true -1 224.03729 -1.0589027 20.7401 true -1 224.94320 -0.87332390 19.9586 true -1 224.12169 -1.2418469 18.6920 true -1 225.09967 -1.2117895 19.8792 true -1 224.28313 -0.67401930 20.1558 true -1 224.18769 -0.79627184 19.9399 true -1 224.23305 -0.67032897 20.2131 true -1 225.00922 -0.80628957 20.5866 true -1 224.32848 -1.5812675 18.2125 true -1 224.27623 -1.5292467 18.4006 true -1 224.70055 -1.6463751 18.5479 true -1 225.06682 -1.2727903 20.5982 true -1 224.89664 -1.5217602 19.0338 true -1 225.02588 -1.4044669 20.2629 true -1 224.98083 -1.4368200 20.4261 true -1 225.07035 -0.95870445 19.6174 true -1 224.14144 -0.71374995 20.3682 true -1 224.18156 -0.65458846 19.8804 true -1 224.03748 -0.86010033 20.2428 true -1 224.29784 -1.5985485 19.0072 true -1 224.30080 -1.5957333 20.6291 true -1 224.65269 -1.6814901 20.2405 true -1 224.18598 -1.4982058 19.6720 true -1 225.18215 -0.98714751 20.2422 true [1:-1] special_objids.extend(find_risa_objs(risa_145729, [h for h in hosts_to_target if h.nsaid==145729][0]) risa_obrother= 1 335.97281 -3.4295662 17.7332 true 1 335.91314 -3.5404510 19.7043 true -1 335.77781 -3.4459616 20.1615 true -1 335.81490 -3.6025596 20.5123 true 1 336.04145 -3.2204987 20.5081 true -1 336.09493 -3.4649021 19.7341 true 1 335.99401 -3.7007769 20.5931 true 1 336.12273 -3.5101925 20.4868 true 1 335.72556 -3.1674595 20.6372 true 1 335.84376 -3.0261104 20.7444 true -1 336.23396 -3.1875586 20.7117 true 1 335.55249 -3.6052065 20.0624 true 1 335.65592 -3.6558837 20.5213 true -1 335.57983 -3.6963397 19.3788 true -1 336.30042 -3.4636766 19.8654 true [1:-1] special_objids.extend(find_risa_objs(risa_obrother, hsd['OBrother'])) risa_catch22= -1 348.62149 4.5071708 17.7932 true -1 348.73347 4.5865011 19.4766 true -1 348.67493 4.6123235 20.3472 true -1 348.72361 4.4495699 20.6729 true -1 348.72881 4.4323062 19.4804 true -1 348.55899 4.5900220 20.2576 true -1 348.64485 4.4040044 17.6392 true -1 348.59640 4.3492465 20.6181 true -1 348.68132 4.3095517 20.6868 true -1 348.68817 4.3020869 20.7035 true -1 348.89822 4.4892740 18.9281 true -1 348.43132 4.7245873 19.3515 true -1 348.51966 4.7464873 19.3880 true -1 348.39920 4.5666321 18.2252 true -1 348.99115 4.5918658 20.7471 true -1 348.31622 4.3290159 19.6409 true -1 348.87290 4.8064919 18.9324 true -1 348.63961 4.2011104 20.5785 true -1 348.98746 4.3261837 18.3678 true -1 348.40085 4.8681252 17.4557 true -1 348.64976 4.8775596 18.4048 true -1 348.82739 4.9078081 19.3681 true -1 348.68761 4.9226928 17.8673 true -1 348.85846 4.8346772 19.6157 true [1:-1] special_objids.extend(find_risa_objs(risa_catch22, hsd['Catch22'])) risa_narnia= [1:-1] special_objids.extend(find_risa_objs(risa_narnia, hsd['Narnia'])) for soid in special_objids: for h in hosts_to_target: cat = h.get_sdss_catalog() if soid in cat['OBJID']: print('Found oid', soid, 'in', h.name, 'so setting to pri=9') pris = cat['aat_pris'] if np.any(pris[np.in1d(cat['OBJID'], soid)]<1): print('WARNING: ', np.sum(pris[np.in1d(cat['OBJID'], soid)]<1), 'special objects in', h.name, 'are pri<0... skipping') cat['aat_pris'][np.in1d(cat['OBJID'], soid)&(pris>0)] = 9 break else: print('Could not find oid', soid, 'anywhere') # commented because it should only be run once !ls aat_targets_jun2015/*_sky.dat #!cp aat_targets_jun2015/*_sky.dat aat_targets_jul2016/ #Identify sky regions for each host and write out to separate files - from os.path import exists for h in hosts_to_target: outfn = 'aat_targets_jul2016/' + h.name.replace(' ','_') + '_sky.dat' if exists(outfn): print(outfn, 'exists, not overwriting') else: try: h.get_usnob_catalog() usnocat = None except IOError: # this is currently hanging as the usno server is down... #print('Downloading USNO B1 catalog for', h.name) #h.usnob_environs_query(dl=True) #usnocat = None usnocat = False aat.select_sky_positions(h, nsky=100, outfn=outfn, rad=1*u.deg, usnocat=usnocat) aat.imagelist_fld_targets(outfn, ttype='sky', n=np.inf) !subl $outfn raw_input('Wrote ' + outfn + '. Press enter to continue onto the next one once ' 'you remove bad entries from this file.') for h in hosts_to_target: cat = h.get_sdss_catalog() pris = cat['aat_pris'] guides = aat.select_guide_stars_sdss(cat) calibs = aat.select_flux_stars(cat, onlyoutside=300*u.kpc) skyradec = 'aat_targets_jul2016/{0}_sky.dat'.format(h.name) aat.produce_master_fld(h, datetime.date(2016, 7, 28), cat[pris>0], pris=pris[pris>0].astype(int), guidestars=guides, fluxstars=calibs,skyradec=skyradec, outfn='aat_targets_jul2016/{}_master.fld'.format(h.name), randomizeorder=True, inclhost=False) def do_subsampling(h, finum, n_in_pri, **kwargs): assert h in hosts_to_target n_in_pri = dict(n_in_pri) #copy just in case for i in range(9): if i+1 not in n_in_pri: n_in_pri[i+1] = np.inf fnbase = 'aat_targets_jul2016/' + h.name fnmaster = fnbase + '_master.fld' fnconfig = kwargs.pop('fnconfig', fnbase + '_{0}.fld'.format(finum)) print('Writing', fnconfig, 'from master', fnmaster) kwargs.setdefault('nflux', 5) kwargs.setdefault('nguides', 30) kwargs.setdefault('fieldname', str(finum)) if 'listorem' not in kwargs: listorem = [] for i in range(1, finum): globpat = fnbase + '_' + str(i) + '*.lis' listorem.extend(glob(globpat)) assertmsg = 'Only got ' + str(len(listorem)) +' .lis file(s):'+str(listorem)+', expected ' + str(finum-1) assert len(listorem) == (finum-1), assertmsg kwargs['listorem'] = listorem aat.subsample_from_master_fld(fnmaster, fnconfig, n_in_pri, **kwargs) return fnconfig def make_logtab(logs, skip_res=[]): Generates a table with the AAT observing logs. ``logs`` can be a filename or list of lines from fitsheader logtab = Table() logtab['num'] = [1] logtab['ccd'] = [2] logtab['UTDATE'] = ['2015:06:19'] logtab['UTSTART'] = ['08:56:19'] logtab['OBJECT'] = ['a'*100] logtab['TOTALEXP'] = ['a'*20] logtab['RUNCMD'] = ['a'*20] logtab['GRATID'] = ['a'*20] logtab['SOURCE'] = ['plate 0 '] logtab['MEANRA'] = [1.1] logtab['MEANDEC'] = [1.1] logtab['CFG_FILE'] = ['Odyssey_1p0xxxxxxxxxx.sds'] logtab = logtab[1:] def add_logcol(accumulated_lines): l = accumulated_lines[0] hdunum = int(l.split()[2]) hdupath = l.split()[4][:-1] if hdunum != 0: return for rex in skip_res: if re.match(rex, hdupath): print('Skipping', hdupath, 'because it has', rex) return items = {'num': int(hdupath.split('/')[-1].split('.')[0][5:]), 'ccd': int(hdupath.split('/')[-2][4:])} for l in accumulated_lines[1:]: if '=' in l: nm, data = l.split('=') nm = nm.strip() data = data.split('/')[:2] if len(data)> 1: comment = data[1] data = data[0].replace("'", '').strip() if nm in logtab.colnames: items[nm] = data logtab.add_row(items) accumulated_lines = None if isinstance(logs, basestring): with open(logs) as f: loglines = list(f) else: loglines = logs for l in loglines: if l.startswith('# HDU'): if accumulated_lines is not None: add_logcol(accumulated_lines) accumulated_lines = [l] elif l.strip() == '': continue elif accumulated_lines is not None: accumulated_lines.append(l) return logtab sshtarget = 'visitor3@aatlxa' fnconfig = do_subsampling(hsd['Dune'], 1, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Odyssey'], 1, {1:200, 2:200, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['OBrother'], 1, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Catch22'], 1, {1:100, 2:50, 3:100}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['AnaK'], 1, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" # use this to get the log data from the remote machine rem_fitsheader_loc = '/home/visitor3/miniconda2/bin/fitsheader' datadir = '/data_lxy/aatobs/OptDet_data/160728' fitsheader_output = !ssh $sshtarget "$rem_fitsheader_loc $datadir/ccd_?/*.fits" # use this to use the local file to make the log fitsheader_output = !fitsheader aat_data/28jul2016/ccd_?/*.fits logtab = make_logtab(fitsheader_output, skip_res=['.*temp.*']) logtab[logtab['ccd']==1].show_in_notebook(display_length=20) comments_jul28 = * At start of night weather clear, but high humidity and possible fog * The Dune_1 observations have the blue side centered 20 angstroms further to the red than the remaining observations. The initial setup provides a bit more overlap but after inspecting a bit we concluded that it would be better to tryto make sure 3727 falls into the image at the blue side * start of Dune_1 : seeing ~1.5-2" * start of Odyssey_1 : seeing ~2-3" * start of OBrother_1: seeing ~4-5" * near end of OBrother_1: seeing ~2.5". Sudden improvement in weather, humidity fell/fog disappeared, * start of Catch22_1: seeing ~3" * start of AnaK_1: seeing ~1.9" [1:-1] display.Markdown(comments_jul28) logfn = 'aat_data/28jul2016/log_jul28' logtab.write(logfn,format='ascii') with open(logfn, 'a') as f: f.write('\nComments:\n') f.write(comments_jul28) fnconfig = do_subsampling(hsd['Dune'], 2, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Gilgamesh'], 1, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['OBrother'], 2, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Catch22'], 2, {1:50, 2:50, 3:200}) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Narnia'], 1, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" # use this to use the local file to make the log fitsheader_output = !fitsheader aat_data/29jul2016/ccd_?/*.fits logtab = make_logtab(fitsheader_output, skip_res=['.*temp.*']) logtab[logtab['ccd']==1].show_in_notebook(display_length=20) comments_jul29 = * start of Dune_2 : seeing ~1.3" * start of Gilgamesh_1 : seeing ~1.6" * start of Odyssey_1a : seeing ~1.4" * start of OBrother_2 : seeing ~1.7" * temperature rose dramatically near end of OBrother_2 - might lead to variable seeing * start of Catch22_2: seeing ~2.3" * start of Narnia_1: seeing ~1.5" [1:-1] display.Markdown(comments_jul29) logfn = 'aat_data/29jul2016/log_jul29' logtab.write(logfn,format='ascii') with open(logfn, 'a') as f: f.write('\nComments:\n') f.write(comments_jul29) hs = [h for h in hosts_to_target if h.nsaid==145729] assert len(hs) == 1 fnconfig = do_subsampling(hs[0], 1, {1:25, 2:25, 3:50, 4:100}) !scp $fnconfig "$sshtarget:configure/" hs = [h for h in hosts_to_target if h.nsaid==145729] assert len(hs) == 1 fnconfig = do_subsampling(hs[0], 2, {1:25, 2:25, 3:50, 4:100}, listorem=['aat_targets_jul2016/NSA145729_1_p0.lis'], fnconfig='aat_targets_jul2016/NSA145729_2_after1p0.fld') !scp $fnconfig "$sshtarget:configure/" hs = [h for h in hosts_to_target if h.nsaid==145729] assert len(hs) == 1 fnconfig = do_subsampling(hs[0], 2, {1:25, 2:25, 3:50, 4:100}, listorem=['aat_targets_jul2016/NSA145729_1_p1.lis'], fnconfig='aat_targets_jul2016/NSA145729_2_after1p1.fld') !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Catch22'], 3, {1:100, 2:100, 3:300) !scp $fnconfig "$sshtarget:configure/" fnconfig = do_subsampling(hsd['Narnia'], 2, {1:100, 2:100, 3:300}) !scp $fnconfig "$sshtarget:configure/" hs = [h for h in hosts_to_target if h.nsaid==21709] assert len(hs) == 1 fnconfig = do_subsampling(hs[0], 1, {1:25, 2:25, 3:50, 4:100}) !scp $fnconfig "$sshtarget:configure/" # fitsheader run on the output downloaded to another computer with open('/Users/erik/tmp/fitsheader_jul30') as f: fitsheader_output = list(f) logtab = make_logtab(fitsheader_output, skip_res=['.*temp.*']) logtab[logtab['ccd']==1].show_in_notebook(display_length=20) logfn = 'aat_data/30jul2016/log_jul30' logtab.write(logfn,format='ascii') !scp "$sshtarget:configure/*.sds" aat_targets_jul2016/ # *_* because otherwise the collision matrix list comes through too !scp "$sshtarget:configure/*_*.lis" aat_targets_jul2016/ listab, lisscs, lisheader = aat.load_lis_file('aat_targets_jul2016/Narnia_1_p1.lis') guidemsk = listab['codes']=='F' names = ['{0[ids]}_f#={0[fibnums]}'.format(row) for row in listab[guidemsk]] print(targeting.sampled_imagelist(lisscs[guidemsk], None, names=names)) import astroplan #if online ufo = urllib2.urlopen('https://docs.google.com/spreadsheet/ccc?key=1b3k2eyFjHFDtmHce1xi6JKuj3ATOWYduTBFftx5oPp8&output=csv') hosttab = QTable.read(ufo.read(), format='csv') ufo.close() #if offline #hosttab = Table.read('SAGADropbox/hosts/host_catalog_flag0.csv') hostscs = SkyCoord(u.Quantity(hosttab['RA'], u.deg), u.Quantity(hosttab['Dec'], u.deg), distance=u.Quantity(hosttab['distance'], u.Mpc)) allspec = Table.read('/Users/erik/Dropbox/SAGA/data/allspectaken_v5.fits.gz') sagaobsed = allspec[~((allspec['TELNAME']=='NSA')| (allspec['TELNAME']=='SDSS')| (allspec['TELNAME']=='GAMA'))] sagaobsed_nsaids = np.unique(sagaobsed['HOST_NSAID']) #UTC time from 8:35-19:35 is AAT 18 deg window nighttimes = Time('2016-7-28 8:45:00') + np.arange(12)*u.hour aao = EarthLocation(lon='149:3:57.9', lat='-31:16:37.3') aao_frame = AltAz(obstime=nighttimes, location=aao) sunaao = get_sun(nighttimes).transform_to(aao_frame) np.max(sunaao.alt.value) seczs = [] for sc in hostscs: az = sc.transform_to(aao_frame) seczs.append(az.secz) seczs = np.array(seczs) hrsvis = np.sum((1<=seczs)&(seczs<1.75),axis=1) visenough = hrsvis>2 aaoobs = astroplan.Observer(aao, 'Australia/NSW') midnight = aaoobs.midnight(Time('2016-7-28')) up_times = {} hoststoshow = hosttab[visenough] hosts_to_target_nsaids = [] for h in hosts_to_target: hosts_to_target_nsaids.append(h.nsaid) if h.nsaid not in hoststoshow['NSAID']: print('adding', h) hoststoshow.add_row(None) hoststoshow['NSAID'][-1] = h.nsaid hoststoshow['RA'][-1] = h.ra hoststoshow['Dec'][-1] = h.dec with open('aat_targets_jul2016/aattargs_iobserve.dat', 'w') as f: for host in hoststoshow: already_obs = host['NSAID'] in sagaobsed_nsaids name = 'NSA'+str(host['NSAID']) for nm, val in hsd.items(): if val.nsaid == host['NSAID']: name = nm if nm.startswith('NSA'): name = name+'_obsed' break f.write(name.replace(' ','_')) if already_obs: f.write('-observed') f.write(' ') f.write(str(host['RA']) + ' ') f.write(str(host['Dec']) + '\n') targ = astroplan.FixedTarget(SkyCoord(host['RA'], host['Dec'], unit=u.deg), name) tpl = (name, host['NSAID'], host['RA'], host['Dec']) transit = aaoobs.target_meridian_transit_time(midnight, targ) up_times[transit.jd] = tpl timestoplot = transit + np.linspace(-6, 6, 100)*u.hour taa = aaoobs.altaz(timestoplot, targ) msk = taa.secz >=1 color = 'g' if already_obs else 'k' color = 'r' if host['NSAID'] in hosts_to_target_nsaids else color plt.plot(timestoplot.plot_date[msk], taa.secz[msk], c=color) plt.text(transit.plot_date, aaoobs.altaz(transit, targ).secz, name, ha='center', color=color) t0 = aaoobs.sun_rise_time(midnight, 'previous') t1 = aaoobs.sun_set_time(midnight, 'previous') t2 = aaoobs.twilight_evening_civil(midnight, 'previous') t3 = aaoobs.twilight_evening_nautical(midnight, 'previous') t4 = aaoobs.twilight_evening_astronomical(midnight, 'previous') t5 = aaoobs.twilight_morning_astronomical(midnight, 'next') t6 = aaoobs.twilight_morning_nautical(midnight, 'next') t7 = aaoobs.twilight_morning_civil(midnight, 'next') t8 = aaoobs.sun_rise_time(midnight, 'next') t9 = aaoobs.sun_set_time(midnight, 'next') plt.fill_between([t0.plot_date,t1.plot_date],1,3, lw=0, facecolor='y', alpha=.9) plt.fill_between([t1.plot_date,t2.plot_date],1,3, lw=0, facecolor='y', alpha=.75) plt.fill_between([t2.plot_date,t3.plot_date],1,3, lw=0, facecolor='y', alpha=.5) plt.fill_between([t3.plot_date,t4.plot_date],1,3, lw=0, facecolor='y', alpha=.25) plt.fill_between([t5.plot_date,t6.plot_date],1,3, lw=0, facecolor='y', alpha=.25) plt.fill_between([t6.plot_date,t7.plot_date],1,3, lw=0, facecolor='y', alpha=.5) plt.fill_between([t7.plot_date,t8.plot_date],1,3, lw=0, facecolor='y', alpha=.75) plt.fill_between([t8.plot_date,t9.plot_date],1,3, lw=0, facecolor='y', alpha=.9) plt.axvline(midnight.plot_date, ls=':', c='k') plt.gca().xaxis_date(aaoobs.timezone) plt.xlim(t1.plot_date-.05, t8.plot_date+.05) plt.axhline(1/np.cos(65*u.deg), c='k', ls='--') #~AAT limit plt.ylim(2.5,1) plt.tight_layout() #NSA urls for jd in sorted(up_times): name, nsaid, ra, dec = up_times[jd] print(name, 'http://www.nsatlas.org/getAtlas.html?search=nsaid&nsaID={}&submit_form=Submit'.format(nsaid)) # DECALS URLs for jd in sorted(up_times): name, nsaid, ra, dec = up_times[jd] print(name, 'http://legacysurvey.org/viewer?ra={}&dec={}&zoom=8'.format(ra, dec)) sagaobsed[sagaobsed['HOST_NSAID']==150307].show_in_notebook() for h in hosts_to_target: fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 1 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) print('') for h in hosts_to_target: fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 2 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) print('') for h in hosts_to_target: fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 3 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) print('') h = hsd['Catch22'] fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 2 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) h = hsd['Catch22'] fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 3 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) h = hsd['Catch22'] fnbase = 'aat_targets_jul2016/test_runs/' + h.name finum = 4 fnmaster = fnbase.replace('test_runs/', '') + '_master.fld' fnconfig = fnbase + '_test_{0}.fld'.format(finum) print('Writing', fnconfig, 'from master', fnmaster) listorem = [fnbase + '_test_' + str(i) + '.lis' for i in range(1, finum)] aat.subsample_from_master_fld(fnmaster, fnconfig, {1:30, 2:30, 3:30, 4:np.inf, 5:np.inf, 6:np.inf, 7:np.inf, 8:np.inf, 9:np.inf}, #8 reserved for flux nflux=5, nguides=30, fieldname=str(finum), listorem=listorem) logtab2015 = make_logtab('aat_targets_jul2016/alljun_2015_aaomega_headers') logtab2015[(logtab2015['ccd']==1)].show_in_notebook(display_length=20) <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: Then instantiate a problem class, we'll name it "My LP problem" and we're looking for an optimal maximum so we use LpMaximize Step2: We then model our decision variables using the LpVariable class. In our example, x had a lower bound of 0 and y had a lower bound of 2. Step3: The objective function and constraints are added using the += operator to our model. Step4: We have now constructed our problem and can have a look at it. Step5: PuLP supports open source linear programming solvers such as CBC and GLPK, as well as commercial solvers such as Gurobi and IBM's CPLEX. Step6: We have also checked the status of the solver, there are 5 status codes
<ASSISTANT_TASK:> Python Code: import pulp my_lp_problem = pulp.LpProblem("My LP Problem", pulp.LpMaximize) x = pulp.LpVariable('x', lowBound=0, cat='Continuous') y = pulp.LpVariable('y', lowBound=2, cat='Continuous') # Objective function my_lp_problem += 4 * x + 3 * y, "Z" # Constraints my_lp_problem += 2 * y <= 25 - x my_lp_problem += 4 * y >= 2 * x - 8 my_lp_problem += y <= 2 * x - 5 my_lp_problem my_lp_problem.solve() pulp.LpStatus[my_lp_problem.status] for variable in my_lp_problem.variables(): print "{} = {}".format(variable.name, variable.varValue) print pulp.value(my_lp_problem.objective) <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: That's not very helpful to look at. One billionaire ended up squeezing everybody else into a single line in my histogram. Plus it skewed my mean income significantly Step2: It's important to dig into what is causing your outliers, and understand where they are coming from. You also need to think about whether removing them is a valid thing to do, given the spirit of what it is you're trying to analyze. If I know I want to understand more about the incomes of "typical Americans", filtering out billionaires seems like a legitimate thing to do. Step3: That looks better. And, our mean is more, well, meangingful now as well
<ASSISTANT_TASK:> Python Code: %matplotlib inline import numpy as np incomes = np.random.normal(27000, 15000, 10000) incomes = np.append(incomes, [1000000000]) import matplotlib.pyplot as plt plt.hist(incomes, 50) plt.show() incomes.mean() def reject_outliers(data): u = np.median(data) s = np.std(data) filtered = [e for e in data if (u - 2 * s < e < u + 2 * s)] return filtered filtered = reject_outliers(incomes) plt.hist(filtered, 50) plt.show() np.mean(filtered) <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: Exibimos sรฉrie histรณrica Step2: Regressรฃo entre taxa de inflaรงรฃo e taxa de crescimento do PIB Step3: Regressรฃo entre taxa de juros e inflaรงรฃo Step4: Note inflaรงรฃo correlaciona positivamente com taxa de juros, porรฉm isso se explica pelo fato de se subir os juros Step5: Regressรฃo entre taxa de juros e inflaรงรฃo no ano seguinte. Step6: Sanity check Step7: Note que a nรฃo hรก evidรชncia estatรญstica de que taxas de juros maiores provocaram reduรงรฃo da inflaรงรฃo no ano seguinte!
<ASSISTANT_TASK:> Python Code: df = pd.read_csv("../data/brazil_gdp_inflation_ir.csv", dtype={'Time':np.float64, 'GDP':np.float64, 'Inflation':np.float64, 'Interest':np.float64}, index_col="Time") df['RInterest'] = df.Interest - df.Inflation brazil = df.sort() brazil filter = brazil.Inflation < 11.0 sns.set(style="darkgrid") plt.title(u"PIB vs Inflaรงรฃo atรฉ faixa de 10%") ax = sns.regplot(brazil[filter].Inflation, brazil[filter].GDP, robust=True, n_boot=500) ax.set_xlabel(u"Inflaรงรฃo") ax.set_ylabel(u"PIB") sns.coefplot("GDP ~ Inflation", data=brazil[filter]) sns.residplot(brazil[brazil.Inflation < 11.0].Inflation, brazil[brazil.Inflation < 11.0].GDP, lowess=True) filter = brazil.Inflation < 11.0 color = sns.color_palette()[2] f, (ax1, ax2) = plt.subplots(1, 2, sharey=True) f.set_figwidth(12) sns.regplot(brazil[filter].Interest, brazil[filter].Inflation, robust=True, n_boot=500, ax=ax1) sns.regplot(brazil[filter].RInterest, brazil[filter].Inflation, robust=True, n_boot=500, ax=ax2).set_ylabel("") ax1.set_xlabel(u"Taxa de juros nominal") ax2.set_xlabel(u"Taxa de juros real") ax1.set_ylabel(u"Inflaรงรฃo") f.tight_layout() f = plt.figure() filter = brazil.index > 1998 l1, = plt.plot(brazil[filter].index, brazil[filter].Interest, figure=f, label=u"Tx juros nominal") l2, = plt.plot(brazil[filter].index, brazil[filter].Inflation, figure=f, label=u"Inflaรงรฃo") l3, = plt.plot(brazil[filter].index, brazil[filter].RInterest, figure=f, label=u"Tx juros real") f.legend(handles=[l1,l2,l3], labels=[u"Tx juros nominal",u"Inflaรงรฃo", u"Tx juros real"]) plt.title(u"Grรกfico da sรฉrie histรณrica analisada") #f.tight_layout() brazil[filter].describe() del filter brazil_ir_s1 = brazil.copy() brazil_ir_s1.Interest = brazil.Interest.shift(1) brazil_ir_s1.RInterest = brazil.RInterest.shift(1) brazil_ir_s1 color = sns.color_palette()[2] f, (ax1, ax2) = plt.subplots(1, 2, sharey=True) f.set_figwidth(12) sns.regplot(brazil_ir_s1.Interest, brazil_ir_s1.Inflation, robust=True, n_boot=500, ax=ax1) sns.regplot(brazil_ir_s1.RInterest, brazil_ir_s1.Inflation, robust=True, n_boot=500, ax=ax2).set_ylabel("") ax1.set_xlabel(u"Taxa de juros nominal do ano anterior") ax2.set_xlabel(u"Taxa de juros real do ano anterior") ax1.set_ylabel(u"Inflaรงรฃo") f.tight_layout() sns.coefplot("Inflation ~ RInterest", data=brazil_ir_s1, intercept=False) model = ols("Inflation ~ RInterest + 1", brazil_ir_s1).fit() model.summary() sns.residplot(brazil_ir_s1.RInterest, brazil_ir_s1.Inflation) model = rlm("Inflation ~ RInterest + 1", brazil_ir_s1).fit() model.summary2() brazil_ir_s1.describe() brazil_ir_s2 = brazil.copy() brazil_ir_s2.Interest = brazil.Interest.shift(2) brazil_ir_s2.RInterest = brazil.RInterest.shift(2) sns.set(style="darkgrid") color = sns.color_palette()[2] f, (ax1, ax2) = plt.subplots(1, 2, sharey=True) f.set_figwidth(12) sns.regplot(brazil_ir_s2.Interest, brazil_ir_s2.Inflation, robust=True, n_boot=500, ax=ax1) sns.regplot(brazil_ir_s2.RInterest, brazil_ir_s2.Inflation, robust=True, n_boot=500, ax=ax2).set_ylabel("") ax1.set_xlabel(u"Taxa de juros nominal de dois anos antes") ax2.set_xlabel(u"Taxa de juros real de dois anos antes") ax1.set_ylabel(u"Inflaรงรฃo") f.tight_layout() sns.coefplot("Inflation ~ RInterest", data=brazil_ir_s2) model = ols("Inflation ~ RInterest + 1", brazil_ir_s2).fit() model.summary() sns.residplot(brazil_ir_s2.RInterest, brazil_ir_s2.Inflation) model = rlm("Inflation ~ RInterest + 1", brazil_ir_s2).fit() model.summary() <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: ะขะธะฟะฐ ะปะธะฝะธั, ั‚ะธะฟะฐ ะฟั€ัะผะฐั Step3: Step4: <img src="http
<ASSISTANT_TASK:> Python Code: plt.plot(h1_phi - h2_phi[:3], h2_phi[:3]) plt.show() from sklearn.linear_model import LinearRegression LR = LinearRegression() LR.fit(h2_phi[:3].reshape(3, 1), (h1_phi - h2_phi[:3]).reshape(3, 1)) h1_phi_4_predicted_delta = LR.predict([[h2_phi[3]]]) h1_phi_4_predicted = h2_phi[3] + h1_phi_4_predicted_delta h1_phi_4_predicted # ะฟั€ะธะฑะปะธะทะธะปะธ ั€ะฐะทะฝะพัั‚ัŒ ะพะฟั‚ะธะผะฐะปัŒะฝะพะน ะบั€ะธะฒะพะน, ัะฟั€ะพะณะฝะพะทะธั€ะพะฒะฐะปะธ h1_phi_new = np.array(list(h1_phi) + [h1_phi_4_predicted]) h1_phi_new len(ne_phi), len(ne_lambda) len(hg_phi), len(hg_lambda) X = np.hstack([ne_phi, hg_phi]) y = np.hstack([ne_lambda, hg_lambda]) f = interp1d(X, y, kind='quadratic') plt.figure(figsize=(15, 15)) plt.plot(ne_phi, ne_lambda) plt.scatter(ne_phi, ne_lambda) plt.plot(hg_phi, hg_lambda) plt.scatter(hg_phi, hg_lambda) #plt.plot(h1_phi, h1_lambda) #plt.scatter(h1_phi, h1_lambda) grid = np.linspace(X.min(), X.max(), 1000) plt.plot(grid, f(grid), color="red") plt.grid() plt.show() plt.figure(figsize=(15, 15)) plt.scatter(ne_phi, ne_lambda, marker="+", s=200, label="ะะตะพะฝ", color="black") plt.scatter(hg_phi, hg_lambda, marker="x", s=200, label="ะ ั‚ัƒั‚ัŒ", color="black") plt.scatter(h1_phi_new, f(h1_phi_new), marker=4, s=150, label="ะ’ะพะดะพั€ะพะด", color="black") plt.scatter(h1_phi_new, f(h1_phi_new+2), marker=4, s=150, label="ะ’ะพะดะพั€ะพะด", color="black") plt.scatter(h1_phi_new, f(h1_phi_new-2), marker=4, s=150, label="ะ’ะพะดะพั€ะพะด", color="black") grid = np.linspace(X.min(), X.max(), 1000) plt.plot(grid, f(grid), color="red", label="ะ˜ะฝั‚ะตั€ะฟะพะปัั†ะธะพะฝะฝะฐั ะบั€ะธะฒะฐั", lw=2) plt.xlabel("ะฃะณะปั‹", fontsize=15) plt.ylabel("$\lambda$", fontsize=15) plt.legend() xticklocs = np.linspace(X.min(), X.max(), 20) yticklocs = np.linspace(y.min(), y.max(), 20) plt.xticks(xticklocs) plt.yticks(yticklocs) plt.grid(lw=2) plt.savefig(fname="2.2_Hydrogen_Spectre.pdf", dpi=900, format="pdf", papertype="a4") plt.savefig(fname="2.2_Hydrogen_Spectre.png", format="png") plt.show() h_lambda_predicted_lo = f(h1_phi_new - delta_phi) # ะธะฝั‚ะตั€ะฒะฐะป ะดะปั ะฟะพะณั€ะตัˆะฝะพัั‚ะตะน h_lambda_predicted_hi = f(h1_phi_new + delta_phi) h_lambda_predicted = (h_lambda_predicted_lo + h_lambda_predicted_hi) / 2 for i in range(4): error = (h_lambda_predicted_hi[i] - h_lambda_predicted_lo[i]) / 2 print("h_lambda_{} = ".format(i+3), labwork.sciRoundD(h_lambda_predicted[i], error, "ะะฝะณัั‚ั€ะตะผ" )) labwork.sciPrintD(h_lambda_predicted[i], error, "h_lambda_{} = ".format(i+3)) h_lambda_predicted, (h_lambda_predicted_hi - h_lambda_predicted_lo) / 2 n = 2 R = np.array([((n*m)**2) / (h_lambda_predicted[m-3] * (m*m - n*n))for m in range(3, 7)]) R # ั‚ะตะพั€ะธั: R = 109 677,6 ัะผ ^ (-1) R.mean() # ะดะปะธะฝั‹ ะฒะพะปะฝ ะฑั‹ะปะธ ะฒ ะฐะฝะณัั‚ั€ะตะผะฐั… -> ะฝัƒะถะฝะพ ัƒะผะฝะพะถะธั‚ัŒ ะฝะฐ 10^10 R.mean() * 10 ** 10 # ัั‚ะพ ะฒ ะผ ^ (-1) R_predicted = R.mean() * 10 ** 8 # ัั‚ะพ ะฒ cะผ ^ (-1) R_predicted R * 10 ** 8 # ั‚ะตะพั€ะธั: R = 109 677,6 ัะผ ^ (-1) labwork.sciPrintR(R_predicted , R.std(ddof=1) / (4)**0.5 / R.mean(), "R = ") # ั ะฟะพะณั€ะตัˆะฝะพัั‚ัŒัŽ print("R = ", labwork.sciRoundR(R_predicted , R.std(ddof=1) / (4)**0.5 / R.mean(), "ัะผ ^ (-1) ")) R_theory = 109677.6 (R_theory - R_predicted) / R_theory # ะพั‚ะปะธั‡ะธะต ะพั‚ ั‚ะตะพั€ะธะธ, ะดะพะปั <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: Start by parsing the .mat files from the matched controls Step2: Clean up - remove nan entries as these cause hddm to fail Step3: Merge patient and matched control data to single .csv file Step4: Build HDDM model
<ASSISTANT_TASK:> Python Code: %matplotlib inline %cd .. import warnings; warnings.filterwarnings('ignore') from utils import matparser, data_compiler import glob data_dir = 'data/controls/' matparser.parse_dir(data_dir) out_dir = "data/controls.csv" data_compiler.compile_dir(data_dir, out_dir) !cat data/controls.csv | grep -v nan > data/controls_clean.csv !cat data/patients_clean.csv | sed 1d | awk -v d="patient" -F"," 'BEGIN { OFS = "," } {$5=d; print}' | tr -d $'\r' > data/patients_tagged.csv !cat data/controls_clean.csv | sed 1d | awk -v d="control" -F"," 'BEGIN { OFS = "," } {$5=d; print}' | tr -d $'\r' > data/controls_tagged.csv !echo "response,rt,subj_idx,stim,subj_type" > data/combined_clean.csv !cat data/patients_tagged.csv >> data/combined_clean.csv; sed 1d data/controls_tagged.csv >> data/combined_clean.csv import hddm data = hddm.load_csv('data/combined_clean.csv') model = hddm.HDDM(data, depends_on={'v': ['stim', 'subj_type'], 'a': 'subj_type'}) model.find_starting_values() model.sample(6000, burn=20) <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 dataset Step2: Utilities function Step3: Extract data Step4: Modified imputation method using MLPRegressor Step5: Feature Augmentation method from Bestagini Step6: Neural Network Step7: Validation with Leave One Well Out on Training Dataset Step8: Applying to Test Dataset
<ASSISTANT_TASK:> Python Code: import numpy as np np.random.seed(1337) import warnings warnings.filterwarnings("ignore") import time as tm import pandas as pd from keras.models import Sequential, Model from keras.constraints import maxnorm from keras.layers import Dense, Dropout, Activation from keras.utils import np_utils from sklearn.metrics import f1_score, recall_score, accuracy_score, confusion_matrix from sklearn.model_selection import LeaveOneGroupOut from sklearn import preprocessing import matplotlib as mpl import matplotlib.pyplot as plt import matplotlib.colors as colors from mpl_toolkits.axes_grid1 import make_axes_locatable %matplotlib inline training_data = pd.read_csv('../data/facies_vectors.csv') def accuracy(conf): total_correct = 0. nb_classes = conf.shape[0] for i in np.arange(0,nb_classes): total_correct += conf[i][i] acc = total_correct/sum(sum(conf)) return acc adjacent_facies = np.array([[1], [0, 2], [1], [4], [3, 5], [4, 6, 7], [5, 7], [5, 6, 8], [6, 7]]) def accuracy_adjacent(conf, adjacent_facies): nb_classes = conf.shape[0] total_correct = 0. for i in np.arange(0,nb_classes): total_correct += conf[i][i] for j in adjacent_facies[i]: total_correct += conf[i][j] return total_correct / sum(sum(conf)) # 1=sandstone 2=c_siltstone 3=f_siltstone # 4=marine_silt_shale 5=mudstone 6=wackestone 7=dolomite # 8=packstone 9=bafflestone facies_colors = ['#F4D03F', '#F5B041','#DC7633','#6E2C00', '#1B4F72','#2E86C1', '#AED6F1', '#A569BD', '#196F3D'] facies_labels = ['SS', 'CSiS', 'FSiS', 'SiSh', 'MS', 'WS', 'D','PS', 'BS'] #facies_color_map is a dictionary that maps facies labels #to their respective colors facies_color_map = {} for ind, label in enumerate(facies_labels): facies_color_map[label] = facies_colors[ind] def label_facies(row, labels): return labels[ row['Facies'] -1] training_data.loc[:,'FaciesLabels'] = training_data.apply(lambda row: label_facies(row, facies_labels), axis=1) def make_facies_log_plot(logs, facies_colors): #make sure logs are sorted by depth logs = logs.sort_values(by='Depth') cmap_facies = colors.ListedColormap( facies_colors[0:len(facies_colors)], 'indexed') ztop=logs.Depth.min(); zbot=logs.Depth.max() cluster=np.repeat(np.expand_dims(logs['Facies'].values,1), 100, 1) f, ax = plt.subplots(nrows=1, ncols=6, figsize=(8, 12)) ax[0].plot(logs.GR, logs.Depth, '.g') ax[1].plot(logs.ILD_log10, logs.Depth, '.') ax[2].plot(logs.DeltaPHI, logs.Depth, '.', color='0.5') ax[3].plot(logs.PHIND, logs.Depth, '.', color='r') ax[4].plot(logs.PE, logs.Depth, '.', color='black') im=ax[5].imshow(cluster, interpolation='none', aspect='auto', cmap=cmap_facies,vmin=1,vmax=9) divider = make_axes_locatable(ax[5]) cax = divider.append_axes("right", size="20%", pad=0.05) cbar=plt.colorbar(im, cax=cax) cbar.set_label((17*' ').join([' SS ', 'CSiS', 'FSiS', 'SiSh', ' MS ', ' WS ', ' D ', ' PS ', ' BS '])) cbar.set_ticks(range(0,1)); cbar.set_ticklabels('') for i in range(len(ax)-1): ax[i].set_ylim(ztop,zbot) ax[i].invert_yaxis() ax[i].grid() ax[i].locator_params(axis='x', nbins=3) ax[0].set_xlabel("GR") ax[0].set_xlim(logs.GR.min(),logs.GR.max()) ax[1].set_xlabel("ILD_log10") ax[1].set_xlim(logs.ILD_log10.min(),logs.ILD_log10.max()) ax[2].set_xlabel("DeltaPHI") ax[2].set_xlim(logs.DeltaPHI.min(),logs.DeltaPHI.max()) ax[3].set_xlabel("PHIND") ax[3].set_xlim(logs.PHIND.min(),logs.PHIND.max()) ax[4].set_xlabel("PE") ax[4].set_xlim(logs.PE.min(),logs.PE.max()) ax[5].set_xlabel('Facies') ax[1].set_yticklabels([]); ax[2].set_yticklabels([]); ax[3].set_yticklabels([]) ax[4].set_yticklabels([]); ax[5].set_yticklabels([]) ax[5].set_xticklabels([]) f.suptitle('Well: %s'%logs.iloc[0]['Well Name'], fontsize=14,y=0.94) X = training_data.drop(['Formation', 'Well Name', 'Depth', 'Facies', 'FaciesLabels'], axis=1).values y = training_data['Facies'].values - 1 wells = training_data["Well Name"].values from sklearn.neural_network import MLPRegressor reg = MLPRegressor() DataImpAll = training_data.drop(['Formation', 'Well Name', 'Depth', 'FaciesLabels'], axis=1).copy() DataImp = DataImpAll.dropna(axis = 0, inplace=False) Ximp=DataImp.loc[:, DataImp.columns != 'PE'] Yimp=DataImp.loc[:, 'PE'] reg.fit(Ximp, Yimp) X[np.array(DataImpAll.PE.isnull()),4] = reg.predict(DataImpAll.loc[DataImpAll.PE.isnull(),:].drop('PE',axis=1,inplace=False)) # Feature windows concatenation function def augment_features_window(X, N_neig): # Parameters N_row = X.shape[0] N_feat = X.shape[1] # Zero padding X = np.vstack((np.zeros((N_neig, N_feat)), X, (np.zeros((N_neig, N_feat))))) # Loop over windows X_aug = np.zeros((N_row, N_feat*(2*N_neig+1))) for r in np.arange(N_row)+N_neig: this_row = [] for c in np.arange(-N_neig,N_neig+1): this_row = np.hstack((this_row, X[r+c])) X_aug[r-N_neig] = this_row return X_aug # Feature gradient computation function def augment_features_gradient(X, depth): # Compute features gradient d_diff = np.diff(depth).reshape((-1, 1)) d_diff[d_diff==0] = 0.001 X_diff = np.diff(X, axis=0) X_grad = X_diff / d_diff # Compensate for last missing value X_grad = np.concatenate((X_grad, np.zeros((1, X_grad.shape[1])))) return X_grad # Feature augmentation function def augment_features(X, well, depth, N_neig=1): # Augment features X_aug = np.zeros((X.shape[0], X.shape[1]*(N_neig*2+2))) for w in np.unique(well): w_idx = np.where(well == w)[0] X_aug_win = augment_features_window(X[w_idx, :], N_neig) X_aug_grad = augment_features_gradient(X[w_idx, :], depth[w_idx]) X_aug[w_idx, :] = np.concatenate((X_aug_win, X_aug_grad), axis=1) # Find padded rows padded_rows = np.unique(np.where(X_aug[:, 0:7] == np.zeros((1, 7)))[0]) return X_aug, padded_rows well = training_data['Well Name'].values depth = training_data['Depth'].values X, padded_rows = augment_features(X, well, depth, N_neig=1) def fDNN(in_dim, out_dim): # Model model = Sequential() model.add(Dense(152, input_dim=in_dim, activation='relu')) model.add(Dropout(0.2)) model.add(Dense(512, activation='relu')) model.add(Dropout(0.2)) model.add(Dense(out_dim, activation='softmax')) # Compilation model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) return model logo = LeaveOneGroupOut() nb_classes = 9 epoch = 10 bats = 20 t0 = tm.time() f1s_ls = [] acc_ls = [] adj_ls = [] from scipy.signal import medfilt for train, test in logo.split(X, y, groups=wells): well_name = wells[test[0]] # Scaling scaler = preprocessing.MinMaxScaler().fit(X) X_tr = scaler.transform(X[train]) X_te = scaler.transform(X[test]) Y_tr = np_utils.to_categorical(y[train], nb_classes) in_dim = len(X_tr[0]) # Method initialization mlp = fDNN(in_dim, nb_classes) # Training mlp.fit(X_tr, Y_tr, nb_epoch=epoch, batch_size=bats, verbose=0) # Predict y_hat = mlp.predict_classes(X_te, verbose=0) y_hat = medfilt(y_hat, kernel_size=5) try: f1s = f1_score(y[test], y_hat, average="weighted", labels=[0, 1, 2, 3, 4, 5, 6, 7, 8]) except: f1s = 0 try: conf = confusion_matrix(y[test], y_hat, labels=[0, 1, 2, 3, 4, 5, 6, 7, 8]) acc = f1_score(y[test], y_hat, average="micro", labels=[0, 1, 2, 3, 4, 5, 6, 7, 8]) except: acc = 0 try: acc_adj = accuracy_adjacent(conf, adjacent_facies) except: acc_adj = 0 f1s_ls += [f1s] acc_ls += [acc] adj_ls += [acc_adj] print("{:>20s} f1w:{:.3f} | f1m:{:.3f} | acc_adj:{:.3f}".format(well_name, f1s, acc, acc_adj)) t1 = tm.time() print("Avg F1w", np.average(f1s_ls)*100, "Avg F1m", np.average(acc_ls)*100, "Avg Adj", np.average(adj_ls)*100) print((t1-t0), "seconds") blind_data = pd.read_csv('../data/nofacies_data.csv') X_blind = blind_data.drop(['Formation', 'Well Name', 'Depth'], axis=1).values well_blind = blind_data['Well Name'].values depth_blind = blind_data['Depth'].values X_blind, padded_rows = augment_features(X_blind, well_blind, depth_blind, N_neig=1) # Scaling scl = preprocessing.MinMaxScaler().fit(X) X_train = scl.transform(X) X_blind = scl.transform(X_blind) Y_train = np_utils.to_categorical(y, nb_classes) # Method initialization model = fDNN(in_dim, nb_classes) # Training model.fit(X_train, Y_train, nb_epoch=epoch, batch_size=bats, verbose=0) # Predict y_blind = model.predict_classes(X_blind, verbose=0) y_blind = medfilt(y_blind, kernel_size=5) blind_data["Facies"] = y_blind + 1 # return the original value (1-9) blind_data.to_csv("PA_Team_Submission_2.csv") make_facies_log_plot( blind_data[blind_data['Well Name'] == 'STUART'], facies_colors) make_facies_log_plot( blind_data[blind_data['Well Name'] == 'CRAWFORD'], facies_colors) <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: Making an interpolation from TRIGDAT Step2: By default, GetGBMData will grad data from all detectors. However, one can set a subset to retrieve different data types Step3: Interpolating Step4: Single detector Step5: We can also go back into the GBMFrame Step6: Earth Centered Coordinates Step7: Working with the GBM class Step8: Plotting Step9: In Fermi GBM coodinates Step10: Capturing points on the sky Step11: Looking at Earth occulted points on the sky Step12: Source/Detector Separation Step13: Examining Legal Detector Pairs
<ASSISTANT_TASK:> Python Code: %pylab inline from astropy.coordinates import SkyCoord import astropy.coordinates as coord import astropy.units as u from gbmgeometry import * data = GetGBMData("080916009") data.set_destination("") # You can enter a folder here. If you want the CWD, you do not have to set data.get_trigdat() data.select_detectors('n1','n2','b0') data.get_rsp_cspec() interp = PositionInterpolator(trigdat="glg_trigdat_all_bn080916009_v02.fit") # In trigger times print "Quaternions" print interp.quaternion(0) print interp.quaternion(10) print print "SC XYZ" print interp.sc_pos(0) print interp.sc_pos(10) na = NaIA(interp.quaternion(0)) print na.get_center() print na.get_center().icrs #J2000 print na.get_center().galactic # Galactic print print "Changing in time" na.set_quaternion(interp.quaternion(100)) print na.get_center() print na.get_center().icrs #J2000 print na.get_center().galactic # Galactic center_j2000 = na.get_center().icrs center_j2000 center_j2000.transform_to(GBMFrame(quaternion=interp.quaternion(100.))) na = NaIA(interp.quaternion(0),interp.sc_pos(0)*u.km) na.get_center() myGBM = GBM(interp.quaternion(0),sc_pos=interp.sc_pos(0)*u.km) myGBM.get_centers() [x.icrs for x in myGBM.get_centers()] myGBM.detector_plot(radius=60) myGBM.detector_plot(radius=10,projection='ortho',lon_0=40) myGBM.detector_plot(radius=10,projection='ortho',lon_0=0,lat_0=40,fignum=2) myGBM.detector_plot(radius=60,fermi_frame=True) myGBM.detector_plot(radius=10,projection='ortho',lon_0=20,fermi_frame=True) myGBM.detector_plot(radius=10,projection='ortho',lon_0=200,fermi_frame=True,fignum=3) myGBM.detector_plot(radius=10,projection='ortho',lon_0=0,lat_0=40,fignum=2,fermi_frame=True) grb = SkyCoord(ra=130.,dec=-45 ,frame='icrs', unit='deg') myGBM.detector_plot(radius=60, projection='moll', good=True, # only plot NaIs that see the GRB point=grb, lon_0=110,lat_0=-0) myGBM.detector_plot(radius=60, projection='ortho', good=True, # only plot NaIs that see the GRB point=grb, lon_0=180,lat_0=-40,fignum=2) myGBM.detector_plot(radius=10,show_earth=True,lon_0=90) myGBM.detector_plot(radius=10,lon_0=100,show_earth=True,projection='ortho') myGBM.detector_plot(radius=10,show_earth=True,lon_0=120,lat_0=-30,fermi_frame=True,projection='ortho') seps = myGBM.get_separation(grb) seps.sort("Separation") seps get_legal_pairs() <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: Merge to 2 arrays into 1 array Step2: Extract the 2 arrays out Step3: Shuffle and see the output.
<ASSISTANT_TASK:> Python Code: a = np.array([[[ 0., 1., 2.], [ 3., 4., 5.]], [[ 6., 7., 8.], [ 9., 10., 11.]], [[ 12., 13., 14.], [ 15., 16., 17.]]]) b = np.array([[ 0., 1.], [ 2., 3.], [ 4., 5.]]) print a.shape print b.shape c = np.c_[a.reshape(len(a), -1), b.reshape(len(b), -1)] print c a2 = c[:, :a.size//len(a)].reshape(a.shape) b2 = c[:, a.size//len(a):].reshape(b.shape) print a2 print b2 np.random.shuffle(c) print a2 print b2 <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: Constants Step2: Operations Step3: Placeholders Step4: Variables Step5: Classification using the MNIST dataset Step6: The MNIST dataset contain 55,000 images. The dimensions of each image is 28-by-28. Each vector has 784 elements because 28*28=784. Step7: Before we begin, we specify three parameters Step8: Network parameters Step9: def multi
<ASSISTANT_TASK:> Python Code: import tensorflow as tf import numpy as np import matplotlib.pyplot as plt %matplotlib inline tf.__version__ h = tf.constant('Hello World') h h.graph is tf.get_default_graph() x = tf.constant(100) x # Create Session object in which we can run operations. # A session object encapsulates the environment in which # operations are executed. Tensor objects are evaluated # by operations. session = tf.Session() session.run(h) session.run(x) type(session.run(x)) type(session.run(h)) a = tf.constant(2) b = tf.constant(3) with tf.Session() as session: print('Addition: {}'.format(session.run(a + b))) print('Subtraction: {}'.format(session.run(a - b))) print('Multiplication: {}'.format(session.run(a * b))) print('Division: {}'.format(session.run(a / b))) e = np.array([[5., 5.]]) f = np.array([[2.], [2.]]) e f # Convert numpy arrays to TensorFlow objects ec = tf.constant(e) fc = tf.constant(f) matrix_mult_op = tf.matmul(ec, fc) with tf.Session() as session: print('Matrix Multiplication: {}'.format(session.run(matrix_mult_op))) c = tf.placeholder(tf.int32) d = tf.placeholder(tf.int32) add_op = tf.add(c, d) sub_op = tf.subtract(c, d) mult_op = tf.multiply(c, d) div_op = tf.divide(c, d) with tf.Session() as session: input_dict = {c: 11, d: 10} print('Addition: {}'.format(session.run(add_op, feed_dict=input_dict))) print('Subtraction: {}'.format(session.run(sub_op, feed_dict=input_dict))) print('Multiplication: {}'.format(session.run(mult_op, feed_dict=input_dict))) print('Division: {}'.format(session.run(div_op, feed_dict={c:11, d:11}))) var2 = tf.get_variable('var2', [2]) var2 from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('data', one_hot=True) type(mnist) mnist.train.images mnist.train.images.shape # Convert the vector to a 28x28 matrix sample_img = mnist.train.images[0].reshape(28, 28) # Show the picture plt.imshow(sample_img, cmap='Greys') learning_rate = 0.001 training_epochs = 15 batch_size = 100 # Number of classes is 10 because we have 10 digits n_classes = 10 # Number of training examples n_samples = mnist.train.num_examples # The flatten array of the 28x28 image matrix contains 784 elements n_input = 784 # Number of neurons in the hidden layers. For image data, 256 neurons # is common because we have 256 intensity values (8-bit). # In this example, we only use 2 hidden layers. The more hidden # layers, we use the longer it takes for the model to run but # more layers has the possibility of being more accurate. n_hidden_1 = 256 n_hidden_2 = 256 def multilayer_perceptron(x, weights, biases): ''' x: Placeholder for the data input weights: Dictionary of weights biases: Dictionary of bias values ''' # First hidden layer with RELU activation layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1']) layer_1 = tf.nn.relu(layer_1) # Second hidden layer with RELU activation layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2']) layer_2 = tf.nn.relu(layer_2) # Output layer layer_out = tf.add(tf.matmul(layer_2, weights['out']), biases['out']) return layer_out weights = { 'h1': tf.Variable(tf.random_normal(shape=[n_input, n_hidden_1])), 'h2': tf.Variable(tf.random_normal(shape=[n_hidden_1, n_hidden_2])), 'out': tf.Variable(tf.random_normal(shape=[n_hidden_2, n_classes])) } tf.random_normal(shape=(n_input, n_hidden_1)) #tf.Session().run(weights['h1']) <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: As in previous examples, all data is contained in a 2-D feature matrix data.data, where the rows represent data samples, and the columns are the feature values Step2: With a look at the provided feature names, we recognize some that we mentioned above Step3: Since this is a binary classification task, we expect to find exactly two target names Step4: Let's split the dataset into training and test sets using a healthy 80-20 split Step5: Building the decision tree Step6: Since we did not specify any pre-pruning parameters, we would expect this decision tree to grow quite large and result in a perfect score on the training set Step7: However, to our surprise, the test error is not too shabby, either Step8: Now we want to do some model exploration. For example, we mentioned above that the depth of a tree influences its performance. If we wanted to study this dependency more systematically, we could repeat building the tree for different values of max_depth Step9: For each of these values, we want to run the full model cascade from start to finish. We also want to record the train and test scores. We do this in a for loop Step10: We can plot the scores as a function of the tree depth using Matplotlib Step11: Let's do one more. What about the minimum numbers of samples required to make a node a leaf node? Step12: This leads to a plot that looks quite different from the one before
<ASSISTANT_TASK:> Python Code: from sklearn import datasets data = datasets.load_breast_cancer() data.data.shape data.feature_names data.target_names import sklearn.model_selection as ms X_train, X_test, y_train, y_test = ms.train_test_split(data.data, data.target, test_size=0.2, random_state=42) X_train.shape, X_test.shape from sklearn import tree dtc = tree.DecisionTreeClassifier(random_state=42) dtc.fit(X_train, y_train) dtc.score(X_train, y_train) dtc.score(X_test, y_test) with open("tree.dot", 'w') as f: f = tree.export_graphviz(dtc, out_file=f, feature_names=data.feature_names, class_names=data.target_names) import numpy as np max_depths = np.array([1, 2, 3, 5, 7, 9, 11]) train_score = [] test_score = [] for d in max_depths: dtc = tree.DecisionTreeClassifier(max_depth=d, random_state=42) dtc.fit(X_train, y_train) train_score.append(dtc.score(X_train, y_train)) test_score.append(dtc.score(X_test, y_test)) import matplotlib.pyplot as plt %matplotlib inline plt.style.use('ggplot') plt.figure(figsize=(10, 6)) plt.plot(max_depths, train_score, 'o-', linewidth=3, label='train') plt.plot(max_depths, test_score, 's-', linewidth=3, label='test') plt.xlabel('max_depth') plt.ylabel('score') plt.ylim(0.85, 1.1) plt.legend() train_score = [] test_score = [] min_samples = np.array([2, 4, 8, 16, 32]) for s in min_samples: dtc = tree.DecisionTreeClassifier(min_samples_leaf=s, random_state=42) dtc.fit(X_train, y_train) train_score.append(dtc.score(X_train, y_train)) test_score.append(dtc.score(X_test, y_test)) plt.figure(figsize=(10, 6)) plt.plot(min_samples, train_score, 'o-', linewidth=3, label='train') plt.plot(min_samples, test_score, 's-', linewidth=3, label='test') plt.xlabel('min_samples_leaf') plt.ylabel('score') plt.ylim(0.9, 1) plt.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: Parsing job titles Step2: Check for duplicates in results Step3: Save invalid titles Step4: Rm dups due to invalid titles and replace NAs by empty strings (to avoid NAs destroying standard titles later) Step5: Standardize Job Titles Step6: The following helps to detect the confusing problem Step7: It shows that the problem is due to NA parts, e.g. sec-func, which add spaces (almost invisible to naked eyes) to the std-ized version. Thus we need a better join which combines only valid parts. That made me create joinValidParts(). Step8: From now on, title means standard title. Step9: Standardizing Job Titles of Posts Step10: Sanity check if the std-ation works Step11: Re-query job titles with at least 2 posts Step12: Domains in Job Titles Step13: Though the total no. of domains is large, we actually only interested in domains with at least $2$ job titles. The reason is the domains with only $1$ title give us no pairwise similarity score. Step14: Primary Functions in Job Titles Step15: Test parser web service (src by Koon Han)
<ASSISTANT_TASK:> Python Code: df = pd.read_csv(DATA_DIR + 'doc_index_filter.csv') titles = list(df['title'].unique()) n_title = len(titles) print('# unique titles: %d' % n_title) title_stats = pd.read_csv(DATA_DIR + 'stats_job_titles.csv') def parseBatch(b, start=None, end=None): ''' @brief: parse a batch of 100 titles @return: DF containing results of parsing the 100 titles in batch b ''' print('Parsing batch {}...'.format(b)) if (not start) and (not end): start = 100*b; end = start + 100 batch_titles = titles[start:end] frames = [parse(t) for t in batch_titles] res = pd.concat(frames) res.reset_index(inplace=True); del res['index'] time.sleep(3) # defensive save result of the batch fname = DATA_DIR + 'tmp/b{}.csv'.format(b) res.to_csv(fname, index=False) print('\t saved result to tmp file') return res n_batch = n_title/100; remainder = n_title % 100 frames = [parseBatch(b) for b in range(n_batch)] rem_titles = titles[-remainder:] last_frame = pd.concat([parse(t) for t in rem_titles]) frames.append(last_frame) res = pd.concat(frames) print res.shape print('# dups in parsing result: %d' %sum(res.duplicated('title'))) res[res.duplicated('title')] invalid_titles = res.title[res.duplicated('title')].unique() print('# invalid titles: %d' %len(invalid_titles)) pd.DataFrame({'title': invalid_titles}).to_csv(DATA_DIR + 'invalid_titles.csv', index=False) res = res.drop_duplicates('title') print res.shape res.domain.fillna('', inplace=True); res.position.fillna('', inplace=True) res.pri_func.fillna('', inplace=True); res.sec_func.fillna('', inplace=True) res.to_csv(DATA_DIR + 'parsed_titles.csv', index=False) def camelCase(s): return s.title() def joinValidParts(row): ''' @brief: Only join valid parts with data, parts which are empty str are removed ''' parts = [row.position, row.domain, row.sec_func, row.pri_func] valid_parts = [p for p in parts if p != ''] # print('# valid parts: %d' %len(valid_parts)) return ' '.join(valid_parts) # This naive join will cause confusing results res['std_title'] = res.position + ' ' + res.domain + ' ' + res.sec_func + ' ' + res.pri_func row = res.query('non_std_title != std_title').iloc[0] my_util.tagChanges(row.non_std_title, row.title) row = res.query('non_std_title == "Site Engineer"').iloc[0] print joinValidParts(row) ' '.join([row.position, row.domain, row.sec_func, row.pri_func]) res['std_title'] = res.apply(joinValidParts, axis=1) res.std_title = res.std_title.apply(camelCase) res.rename(columns={'std_title': 'title'}, inplace=True) res.to_csv(DATA_DIR + 'parsed_titles.csv', index=False) stdForm = dict(zip(res.non_std_title, res.title)) print('# non-std titles which can be standardized: %d' %len(stdForm.keys())) uniq_std_titles = np.unique((stdForm.values())) print('# unique standard titles: %d' % len(uniq_std_titles)) def toStd(t): if t not in stdForm.keys(): return t else: if stdForm[t] == '': # for titles which could not be parsed return t else: return stdForm[t] # return stdForm[t] if t in stdForm.keys() else t df = pd.read_csv(DATA_DIR + 'doc_index_filter.csv') df.columns uniq_non_std_titles = df['non_std_title'].unique() # sum([t not in stdForm.keys() for t in uniq_non_std_titles]) tmp = [t for t in uniq_non_std_titles if t not in stdForm.keys()] tmp[:5] del df['title'] print("# unique non-std titles in data: %d" % df.non_std_title.nunique()) df['title'] = map(toStd, df['non_std_title']) df.query('non_std_title != title')[['non_std_title', 'title']].head() any(df.title == '') df.to_csv(DATA_DIR + 'doc_index_filter.csv') by_title_agg = df.groupby('title').agg({'job_id': 'nunique'}) by_title_agg.rename(columns={'job_id': 'n_post'}, inplace=True) by_title_agg.reset_index(inplace=True) by_title_agg.head() titles2_ = by_title_agg.query('n_post >= 2') print('# titles with >= 2 posts: %d' %titles2_.shape[0]) title_df = pd.merge(titles2_, res) print(title_df.shape[0]) # res.columns title_df.columns title_df.to_csv(DATA_DIR + 'new_titles_2posts_up.csv', index=False) by_domain = res.groupby('domain') print('# domains: {}'.format(by_domain.ngroups)) by_domain_agg = by_domain.agg({'title': len}) by_domain_agg = by_domain_agg.add_prefix('n_').reset_index() by_domain_agg.sort_values('n_title', ascending=False, inplace=True) by_domain_agg.describe().round(1) domains_2 = by_domain_agg.query('n_title >= 2') print('# domains with at least 2 job titles: %d' %len(domains_2)) by_domain_agg.to_csv(DATA_DIR + 'stats_domains.csv', index=False) by_pri_func = res.groupby('pri_func') print('# primary functions: {}'.format(by_pri_func.ngroups)) by_pri_func_agg = by_pri_func.agg({'title': len}) by_pri_func_agg = by_pri_func_agg.add_prefix('n_').reset_index() by_pri_func_agg.sort_values('n_title', ascending=False, inplace=True) by_pri_func_agg.to_csv(DATA_DIR + 'stats_pri_funcs.csv', index=False) by_pri_func_agg.describe().round(1) by_pri_func_agg.head(10) # r0 = requests.post(parse_url, auth=(user, pwd), # json={"job_title":"accountant", "verbose": False}) # print r0.status_code # print r0.json()['output'] r1 = requests.post(parse_url, auth=(user, pwd), json={"job_title":"software developer", "verbose": False}) print r1.status_code print r1.json()['output'] # r2 = requests.post(parse_url, auth=(user, pwd), # json={"job_title":"pre-school teacher", "verbose": False}) # print r2.status_code # print r2.json()['output'] # r3 = requests.post(parse_url, auth=(user, pwd), # json={"job_title":"Assistant Civil and Structural Engineer", # "verbose": False}) r4 = requests.post(parse_url, auth=(user, pwd), json={"job_title": "Security Analyst, Information Technology", "verbose": False}) print r4.json()['output'] r5 = requests.post(parse_url, auth=(user, pwd), json={"job_title": "Data analyst and scientist", "verbose": False}) print r5.json()['output'] <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: Kvswap Step2: Examples
<ASSISTANT_TASK:> Python Code: #@title Licensed under the Apache License, Version 2.0 (the "License") # Licensed to the Apache Software Foundation (ASF) under one # or more contributor license agreements. See the NOTICE file # distributed with this work for additional information # regarding copyright ownership. The ASF licenses this file # to you 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 # # http://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. !pip install --quiet -U apache-beam import apache_beam as beam with beam.Pipeline() as pipeline: plants = ( pipeline | 'Garden plants' >> beam.Create([ ('๐Ÿ“', 'Strawberry'), ('๐Ÿฅ•', 'Carrot'), ('๐Ÿ†', 'Eggplant'), ('๐Ÿ…', 'Tomato'), ('๐Ÿฅ”', 'Potato'), ]) | 'Key-Value swap' >> beam.KvSwap() | beam.Map(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: Step2: Finding HIF-1 direct target candidates Step3: As a safety check, let's make a qPCR like plot to visualize our genes, and let's make sure they have the behavior we want Step4: vhl-1 dependent, hif-1-independent, genes Step5: Plot vhl-1-dependent, hif-1-independent genes
<ASSISTANT_TASK:> Python Code: # important stuff: import os import pandas as pd import numpy as np # morgan import tissue_enrichment_analysis as tea import epistasis as epi import genpy import gvars # Graphics import matplotlib as mpl import matplotlib.pyplot as plt import seaborn as sns from matplotlib import rc rc('text', usetex=True) rc('text.latex', preamble=r'\usepackage{cmbright}') rc('font', **{'family': 'sans-serif', 'sans-serif': ['Helvetica']}) # Magic function to make matplotlib inline; %matplotlib inline # This enables SVG graphics inline. %config InlineBackend.figure_formats = {'png', 'retina'} # JB's favorite Seaborn settings for notebooks rc = {'lines.linewidth': 2, 'axes.labelsize': 18, 'axes.titlesize': 18, 'axes.facecolor': 'DFDFE5'} sns.set_context('notebook', rc=rc) sns.set_style("dark") mpl.rcParams['xtick.labelsize'] = 16 mpl.rcParams['ytick.labelsize'] = 16 mpl.rcParams['legend.fontsize'] = 14 q = 0.1 genvar = gvars.genvars() tissue_df = tea.fetch_dictionary() phenotype_df = pd.read_csv('../input/phenotype_ontology.csv') go_df = pd.read_csv('../input/go_dictionary.csv') tidy_data = pd.read_csv('../output/temp_files/DE_genes.csv') tidy_data.sort_values('target_id', inplace=True) tidy_data.dropna(subset=['ens_gene'], inplace=True) tidy_data['fancy genotype'] = tidy_data.code.map(genvar.fancy_mapping) tidy_data = tidy_data[tidy_data.genotype != 'fog-2'] tidy_data.head() def collate(x): For a vector `x`, find what elements in x are contained in tidy_data.target_id. return tidy_data.target_id.isin(x) hif_genes = pd.read_csv('../output/temp_files/hypoxia_response.csv') n = len(hif_genes[hif_genes.b > 0].ens_gene.unique()) message = 'There are {0} unique genes that' +\ ' are candidates for HIF-1 direct binding' print(message.format(n)) ids = hif_genes[hif_genes.b > 0].target_id hypoxia_direct_targets = tidy_data[tidy_data.target_id.isin(ids)] names = hypoxia_direct_targets.sort_values('qval').target_id.unique()[0:10] name_sort = {} for i, name in enumerate(names): name_sort[name] = i+1 plot_df = tidy_data[tidy_data.target_id.isin(names)].copy() plot_df['order'] = plot_df.target_id.map(name_sort) plot_df.sort_values('order', inplace=True) plot_df.reset_index(inplace=True) genpy.qPCR_plot(plot_df, genvar.plot_order, genvar.plot_color, clustering='fancy genotype', plotting_group='target_id', rotation=90) res = tea.enrichment_analysis(hypoxia_direct_targets.ens_gene.unique(), tissue_df, show=False) res['logQ'] = -res['Q value'].apply(np.log10) tea.plot_enrichment_results(res, analysis='tissue', y='logQ') res = tea.enrichment_analysis(hypoxia_direct_targets.ens_gene.unique(), phenotype_df, show=False) res['logQ'] = -res['Q value'].apply(np.log10) tea.plot_enrichment_results(res, analysis='phenotype', y='logQ') res = tea.enrichment_analysis(hypoxia_direct_targets.ens_gene.unique(), go_df, show=False) res['logQ'] = -res['Q value'].apply(np.log10) tea.plot_enrichment_results(res, analysis='go', y='logQ') positive = tidy_data[(tidy_data.qval < q) & (tidy_data.b > 0)] negative = tidy_data[(tidy_data.qval < q) & (tidy_data.b < 0)] # find the genes that overlap between vhl1 and egl-9vhl-1 and change in # same directiom vhl_pos = epi.find_overlap(['d', 'a'], positive) vhl_neg = epi.find_overlap(['d', 'a'], negative) vhl = list(set(vhl_pos + vhl_neg)) # find genes that change in the same direction in vhl(-) and # vhl(+ datasets) same_vhl = [] for genotype in ['b', 'e', 'f', 'c']: same_vhl += epi.find_overlap(['d', 'a', genotype], positive) same_vhl += epi.find_overlap(['d', 'a', genotype], negative) # put it all together: ind = (collate(vhl)) & (~collate(same_vhl)) vhl_regulated = tidy_data[ind & (tidy_data.code == 'd')] n = len(vhl_regulated.ens_gene.unique()) message = 'There are {0} genes that appear to be ' + \ 'regulated in a hif-1-independent, vhl-1-dependent manner.' print(message.format(n)) # begin plotting names = vhl_regulated.sort_values('qval').target_id.unique()[0:10] name_sort = {} for i, name in enumerate(names): name_sort[name] = i+1 plot_df = tidy_data[tidy_data.target_id.isin(names)].copy() plot_df['order'] = plot_df.target_id.map(name_sort) plot_df.sort_values('order', inplace=True) plot_df.reset_index(inplace=True) genpy.qPCR_plot(plot_df, genvar.plot_order, genvar.plot_color, clustering='fancy genotype', plotting_group='target_id', rotation=90) # save to file cols = ['ext_gene', 'ens_gene', 'target_id', 'b', 'qval'] vhl_regulated[cols].to_csv('../output/temp_files/vhl_1_regulated_genes.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: Using the Apache Beam Orchestrator for TFX Step2: Import packages Step3: Check the versions Step4: Download example data Step5: Take a quick look at the CSV file Step6: Set up pipeline paths Step7: Define some constants and functions for both the Transform component and the Trainer component. Define them in a Python module, in this case saved to disk using the %%writefile magic command since you are working in a notebook. Step10: Now define a module containing the preprocessing_fn() function that we will pass to the Transform component. Step17: Create a Python module containing a trainer_fn function, which must return an estimator. If you prefer creating a Keras model, you can do so and then convert it to an estimator using keras.model_to_estimator(). Step19: Create the Pipeline Step20: Run the pipeline
<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. !pip install -q -U \ tensorflow==2.0.0 \ tfx==0.15.0rc0 import os import tempfile import urllib import tensorflow as tf import tfx from tfx.components.evaluator.component import Evaluator from tfx.components.example_gen.csv_example_gen.component import CsvExampleGen from tfx.components.example_validator.component import ExampleValidator from tfx.components.model_validator.component import ModelValidator from tfx.components.pusher.component import Pusher from tfx.components.schema_gen.component import SchemaGen from tfx.components.statistics_gen.component import StatisticsGen from tfx.components.trainer.component import Trainer from tfx.components.transform.component import Transform from tfx.proto import evaluator_pb2 from tfx.proto import pusher_pb2 from tfx.proto import trainer_pb2 from tfx.orchestration import metadata from tfx.orchestration import pipeline from tfx.orchestration.beam.beam_dag_runner import BeamDagRunner from tfx.utils.dsl_utils import external_input print('TensorFlow version: {}'.format(tf.__version__)) print('TFX version: {}'.format(tfx.__version__)) # Download the example data. DATA_PATH = 'https://raw.githubusercontent.com/ageron/open-datasets/master/' \ 'online_news_popularity_for_course/online_news_popularity_for_course.csv' _data_root = tempfile.mkdtemp(prefix='tfx-data') _data_filepath = os.path.join(_data_root, "data.csv") urllib.request.urlretrieve(DATA_PATH, _data_filepath) !head {_data_filepath} # Set up paths. _constants_module_file = 'online_news_constants.py' _transform_module_file = 'online_news_transform.py' _trainer_module_file = 'online_news_trainer.py' _serving_model_dir = os.path.join(tempfile.mkdtemp(), 'serving_model/online_news_simple') %%writefile {_constants_module_file} DENSE_FLOAT_FEATURE_KEYS = [ "timedelta", "n_tokens_title", "n_tokens_content", "n_unique_tokens", "n_non_stop_words", "n_non_stop_unique_tokens", "n_hrefs", "n_self_hrefs", "n_imgs", "n_videos", "average_token_length", "n_keywords", "kw_min_min", "kw_max_min", "kw_avg_min", "kw_min_max", "kw_max_max", "kw_avg_max", "kw_min_avg", "kw_max_avg", "kw_avg_avg", "self_reference_min_shares", "self_reference_max_shares", "self_reference_avg_shares", "is_weekend", "global_subjectivity", "global_sentiment_polarity", "global_rate_positive_words", "global_rate_negative_words", "rate_positive_words", "rate_negative_words", "avg_positive_polarity", "min_positive_polarity", "max_positive_polarity", "avg_negative_polarity", "min_negative_polarity", "max_negative_polarity", "title_subjectivity", "title_sentiment_polarity", "abs_title_subjectivity", "abs_title_sentiment_polarity"] VOCAB_FEATURE_KEYS = ["data_channel"] BUCKET_FEATURE_KEYS = ["LDA_00", "LDA_01", "LDA_02", "LDA_03", "LDA_04"] CATEGORICAL_FEATURE_KEYS = ["weekday"] # Categorical features are assumed to each have a maximum value in the dataset. MAX_CATEGORICAL_FEATURE_VALUES = [6] #UNUSED: date, slug LABEL_KEY = "n_shares_percentile" VOCAB_SIZE = 10 OOV_SIZE = 5 FEATURE_BUCKET_COUNT = 10 def transformed_name(key): return key + '_xf' %%writefile {_transform_module_file} import tensorflow as tf import tensorflow_transform as tft from online_news_constants import * def preprocessing_fn(inputs): tf.transform's callback function for preprocessing inputs. Args: inputs: map from feature keys to raw not-yet-transformed features. Returns: Map from string feature key to transformed feature operations. outputs = {} for key in DENSE_FLOAT_FEATURE_KEYS: # Preserve this feature as a dense float, setting nan's to the mean. outputs[transformed_name(key)] = tft.scale_to_z_score( _fill_in_missing(inputs[key])) for key in VOCAB_FEATURE_KEYS: # Build a vocabulary for this feature. outputs[transformed_name(key)] = tft.compute_and_apply_vocabulary( _fill_in_missing(inputs[key]), top_k=VOCAB_SIZE, num_oov_buckets=OOV_SIZE) for key in BUCKET_FEATURE_KEYS: outputs[transformed_name(key)] = tft.bucketize( _fill_in_missing(inputs[key]), FEATURE_BUCKET_COUNT, always_return_num_quantiles=False) for key in CATEGORICAL_FEATURE_KEYS: outputs[transformed_name(key)] = _fill_in_missing(inputs[key]) # How popular is this article? outputs[transformed_name(LABEL_KEY)] = _fill_in_missing(inputs[LABEL_KEY]) return outputs def _fill_in_missing(x): Replace missing values in a SparseTensor. Fills in missing values of `x` with '' or 0, and converts to a dense tensor. Args: x: A `SparseTensor` of rank 2. Its dense shape should have size at most 1 in the second dimension. Returns: A rank 1 tensor where missing values of `x` have been filled in. default_value = '' if x.dtype == tf.string else 0 return tf.squeeze( tf.sparse.to_dense( tf.SparseTensor(x.indices, x.values, [x.dense_shape[0], 1]), default_value), axis=1) %%writefile {_trainer_module_file} import tensorflow as tf import tensorflow_model_analysis as tfma import tensorflow_transform as tft from tensorflow_transform.tf_metadata import schema_utils from online_news_constants import * def transformed_names(keys): return [transformed_name(key) for key in keys] # Tf.Transform considers these features as "raw" def _get_raw_feature_spec(schema): return schema_utils.schema_as_feature_spec(schema).feature_spec def _gzip_reader_fn(filenames): Small utility returning a record reader that can read gzip'ed files. return tf.data.TFRecordDataset( filenames, compression_type='GZIP') def _build_estimator(config, hidden_units=None, warm_start_from=None): Build an estimator for predicting the popularity of online news articles Args: config: tf.estimator.RunConfig defining the runtime environment for the estimator (including model_dir). hidden_units: [int], the layer sizes of the DNN (input layer first) warm_start_from: Optional directory to warm start from. Returns: A dict of the following: - estimator: The estimator that will be used for training and eval. - train_spec: Spec for training. - eval_spec: Spec for eval. - eval_input_receiver_fn: Input function for eval. real_valued_columns = [ tf.feature_column.numeric_column(key, shape=()) for key in transformed_names(DENSE_FLOAT_FEATURE_KEYS) ] categorical_columns = [ tf.feature_column.categorical_column_with_identity( key, num_buckets=VOCAB_SIZE + OOV_SIZE, default_value=0) for key in transformed_names(VOCAB_FEATURE_KEYS) ] categorical_columns += [ tf.feature_column.categorical_column_with_identity( key, num_buckets=FEATURE_BUCKET_COUNT, default_value=0) for key in transformed_names(BUCKET_FEATURE_KEYS) ] categorical_columns += [ tf.feature_column.categorical_column_with_identity( key, num_buckets=num_buckets, default_value=0) for key, num_buckets in zip( transformed_names(CATEGORICAL_FEATURE_KEYS), MAX_CATEGORICAL_FEATURE_VALUES) ] return tf.estimator.DNNLinearCombinedRegressor( config=config, linear_feature_columns=categorical_columns, dnn_feature_columns=real_valued_columns, dnn_hidden_units=hidden_units or [100, 70, 50, 25], warm_start_from=warm_start_from) def _example_serving_receiver_fn(tf_transform_output, schema): Build the serving in inputs. Args: tf_transform_output: A TFTransformOutput. schema: the schema of the input data. Returns: Tensorflow graph which parses examples, applying tf-transform to them. raw_feature_spec = _get_raw_feature_spec(schema) raw_feature_spec.pop(LABEL_KEY) raw_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn( raw_feature_spec, default_batch_size=None) serving_input_receiver = raw_input_fn() transformed_features = tf_transform_output.transform_raw_features( serving_input_receiver.features) return tf.estimator.export.ServingInputReceiver( transformed_features, serving_input_receiver.receiver_tensors) def _eval_input_receiver_fn(tf_transform_output, schema): Build everything needed for the tf-model-analysis to run the model. Args: tf_transform_output: A TFTransformOutput. schema: the schema of the input data. Returns: EvalInputReceiver function, which contains: - Tensorflow graph which parses raw untransformed features, applies the tf-transform preprocessing operators. - Set of raw, untransformed features. - Label against which predictions will be compared. # Notice that the inputs are raw features, not transformed features here. raw_feature_spec = _get_raw_feature_spec(schema) raw_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn( raw_feature_spec, default_batch_size=None) serving_input_receiver = raw_input_fn() features = serving_input_receiver.features.copy() transformed_features = tf_transform_output.transform_raw_features(features) # NOTE: Model is driven by transformed features (since training works on the # materialized output of TFT, but slicing will happen on raw features. features.update(transformed_features) return tfma.export.EvalInputReceiver( features=features, receiver_tensors=serving_input_receiver.receiver_tensors, labels=transformed_features[transformed_name(LABEL_KEY)]) def _input_fn(filenames, tf_transform_output, batch_size=200): Generates features and labels for training or evaluation. Args: filenames: [str] list of CSV files to read data from. tf_transform_output: A TFTransformOutput. batch_size: int First dimension size of the Tensors returned by input_fn Returns: A (features, indices) tuple where features is a dictionary of Tensors, and indices is a single Tensor of label indices. transformed_feature_spec = ( tf_transform_output.transformed_feature_spec().copy()) dataset = tf.data.experimental.make_batched_features_dataset( filenames, batch_size, transformed_feature_spec, reader=_gzip_reader_fn) transformed_features = dataset.make_one_shot_iterator().get_next() # We pop the label because we do not want to use it as a feature while we're # training. return transformed_features, transformed_features.pop( transformed_name(LABEL_KEY)) # TFX will call this function def trainer_fn(hparams, schema): Build the estimator using the high level API. Args: hparams: Holds hyperparameters used to train the model as name/value pairs. schema: Holds the schema of the training examples. Returns: A dict of the following: - estimator: The estimator that will be used for training and eval. - train_spec: Spec for training. - eval_spec: Spec for eval. - eval_input_receiver_fn: Input function for eval. # Number of nodes in the first layer of the DNN first_dnn_layer_size = 100 num_dnn_layers = 4 dnn_decay_factor = 0.7 train_batch_size = 40 eval_batch_size = 40 tf_transform_output = tft.TFTransformOutput(hparams.transform_output) train_input_fn = lambda: _input_fn( hparams.train_files, tf_transform_output, batch_size=train_batch_size) eval_input_fn = lambda: _input_fn( hparams.eval_files, tf_transform_output, batch_size=eval_batch_size) train_spec = tf.estimator.TrainSpec( train_input_fn, max_steps=hparams.train_steps) serving_receiver_fn = lambda: _example_serving_receiver_fn( tf_transform_output, schema) exporter = tf.estimator.FinalExporter('online-news', serving_receiver_fn) eval_spec = tf.estimator.EvalSpec( eval_input_fn, steps=hparams.eval_steps, exporters=[exporter], name='online-news-eval') run_config = tf.estimator.RunConfig( save_checkpoints_steps=999, keep_checkpoint_max=1) run_config = run_config.replace(model_dir=hparams.serving_model_dir) estimator = _build_estimator( # Construct layers sizes with exponetial decay hidden_units=[ max(2, int(first_dnn_layer_size * dnn_decay_factor**i)) for i in range(num_dnn_layers) ], config=run_config, warm_start_from=hparams.warm_start_from) # Create an input receiver for TFMA processing receiver_fn = lambda: _eval_input_receiver_fn( tf_transform_output, schema) return { 'estimator': estimator, 'train_spec': train_spec, 'eval_spec': eval_spec, 'eval_input_receiver_fn': receiver_fn } _pipeline_name = 'online_news_beam' _pipeline_root = tempfile.mkdtemp(prefix='tfx-pipelines') _pipeline_root = os.path.join(_pipeline_root, 'pipelines', _pipeline_name) # Sqlite ML-metadata db path. _metadata_root = tempfile.mkdtemp(prefix='tfx-metadata') _metadata_path = os.path.join(_metadata_root, 'metadata.db') def _create_pipeline(pipeline_name, pipeline_root, data_root, transform_module_file, trainer_module_file, serving_model_dir, metadata_path): Implements the online news pipeline with TFX. input_data = external_input(data_root) # Brings data into the pipeline or otherwise joins/converts training data. example_gen = CsvExampleGen(input=input_data) # Computes statistics over data for visualization and example validation. statistics_gen = StatisticsGen(examples=example_gen.outputs['examples']) # Generates schema based on statistics files. infer_schema = SchemaGen( statistics=statistics_gen.outputs['statistics']) # Performs anomaly detection based on statistics and data schema. validate_stats = ExampleValidator( statistics=statistics_gen.outputs['statistics'], schema=infer_schema.outputs['schema']) # Performs transformations and feature engineering in training and serving. transform = Transform( examples=example_gen.outputs['examples'], schema=infer_schema.outputs['schema'], module_file=transform_module_file) # Uses user-provided Python function that implements a model using # TensorFlow's Estimators API. trainer = Trainer( module_file=trainer_module_file, transformed_examples=transform.outputs['transformed_examples'], schema=infer_schema.outputs['schema'], transform_graph=transform.outputs['transform_graph'], train_args=trainer_pb2.TrainArgs(num_steps=10000), eval_args=trainer_pb2.EvalArgs(num_steps=5000)) # Uses TFMA to compute a evaluation statistics over features of a model. model_analyzer = Evaluator( examples=example_gen.outputs['examples'], model=trainer.outputs['model'], feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[ evaluator_pb2.SingleSlicingSpec( column_for_slicing=['weekday']) ])) # Performs quality validation of a candidate model (compared to a baseline). model_validator = ModelValidator( examples=example_gen.outputs['examples'], model=trainer.outputs['model']) # Checks whether the model passed the validation steps and pushes the model # to a file destination if check passed. pusher = Pusher( model=trainer.outputs['model'], model_blessing=model_validator.outputs['blessing'], push_destination=pusher_pb2.PushDestination( filesystem=pusher_pb2.PushDestination.Filesystem( base_directory=serving_model_dir))) return pipeline.Pipeline( pipeline_name=pipeline_name, pipeline_root=pipeline_root, components=[ example_gen, statistics_gen, infer_schema, validate_stats, transform, trainer, model_analyzer, model_validator, pusher ], enable_cache=True, metadata_connection_config=metadata.sqlite_metadata_connection_config( metadata_path), additional_pipeline_args={}, ) online_news_pipeline = _create_pipeline( pipeline_name=_pipeline_name, pipeline_root=_pipeline_root, data_root=_data_root, transform_module_file=_transform_module_file, trainer_module_file=_trainer_module_file, serving_model_dir=_serving_model_dir, metadata_path=_metadata_path) BeamDagRunner().run(online_news_pipeline) <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: Hyperparameters Step2: An optimizer can be seen as a function that takes a gradient, obtained by backpropagation, and returns an update to be applied to the current parameters. Other optimizers can be found in Step3: Dataset Step4: The pre-processing consists in retrieving the list of symbols occuring in the text and to convert each of them into an unique index. This index will be used to create an one-hot representation of the symbol that will be the input of the model. Step6: The following auxiliary function creates a minibatch in a 3D tensor (batch_size, SEQ_LENGTH, vocab_size). Step8: Model definition Step9: Optimization Step11: The next function generates text given a phrase of length at least SEQ_LENGTH.
<ASSISTANT_TASK:> Python Code: import numpy as np import theano import theano.tensor as T import lasagne seed = 1 lasagne.random.set_rng(np.random.RandomState(seed)) # Sequence Length SEQ_LENGTH = 20 # Number of units in the hidden (LSTM) layers DEPTH = 2 N_HIDDEN = 512 NON_LINEARITY = lasagne.nonlinearities.rectify # All gradients above this will be clipped GRAD_CLIP = 100 # Number of epochs to train the net NUM_EPOCHS = 50 # Optimization learning rate LEARNING_RATE = 0.01 # Batch Size BATCH_SIZE = 128 # How often should we check the output? PRINT_FREQ = 500 my_optimizer = lambda loss, params: lasagne.updates.nesterov_momentum( loss, params, learning_rate=0.01, momentum=0.9) import urllib.request #For downloading the sample text file. You won't need this if you are providing your own file. try: in_text = urllib.request.urlopen('https://s3.amazonaws.com/text-datasets/nietzsche.txt').read() #in_text = open('your_file.txt', 'r').read() in_text = in_text.decode("utf-8") print(in_text[:250]) except Exception as e: print("Please verify the location of the input file/URL.") print("A sample txt file can be downloaded from https://s3.amazonaws.com/text-datasets/nietzsche.txt") raise IOError('Unable to Read Text') chars = list(set(in_text)) data_size, vocab_size = len(in_text), len(chars) char_to_ix = {ch:i for i,ch in enumerate(chars)} ix_to_char = {i:ch for i,ch in enumerate(chars)} print('Number of unique symbols: {}'.format(vocab_size)) print('Number of symbols in the dataset: {}'.format(data_size)) input_shape = (None, None, vocab_size) def iterate_minibatch( p, batch_size = BATCH_SIZE, data=in_text, return_target=True): Return a minibatch compatible with the input of the model and the associated targets :type p: int :param The index of the character to begin to read :type batch_size: int :param The number of datapoints in the current batch :type data: str :param The whole text :type return_target: bool :param Create the targets (next character) associated to the sequences x = np.zeros((batch_size,SEQ_LENGTH,vocab_size)) y = np.zeros(batch_size) for n in range(batch_size): ptr = n for i in range(SEQ_LENGTH): x[n,i,char_to_ix[data[p+ptr+i]]] = 1. if(return_target): y[n] = char_to_ix[data[p+ptr+SEQ_LENGTH]] return x, np.array(y,dtype='int32') def create_lstm( vocab_size, input_shape, input_var = None, nonlinearity = lasagne.nonlinearities.tanh, depth=2, n_hidden=800, grad_clip=100): A generic function for creating a LSTM neural network. :type vocab_size: int :param vocab_size: number of elements in the dictionary :type input_shape: tuple :param input_shape: a tuple containing the shape of the input :type input_var: theano.tensor.var.TensorVariable :param input_var: a theano symbolic variable, created automatically if None :type nonlinearity: lasagne.nonlinearities :param nonlinearity: a nonlinearity function that follows all dense layers :type depth: int :param depth: the depth of the LSTM :type n_hidden: int or list :param n_hidden: number of hidden units per LSTM cells (if int, the same for all layers) :type grad_clip: float :param grad_clip: threshold for the gradient in the LSTM # First, we build the network, starting with an input layer # Recurrent layers expect input of shape # (batch size, SEQ_LENGTH, num_features) network = lasagne.layers.InputLayer( shape=input_shape, input_var=input_var ) # We now build the LSTM layer # We clip the gradients at GRAD_CLIP to prevent the problem of exploding gradients. for _ in range(depth-1): network = lasagne.layers.LSTMLayer( network, num_units=n_hidden, grad_clipping=grad_clip, nonlinearity=nonlinearity) network = lasagne.layers.LSTMLayer( network, num_units=n_hidden, grad_clipping=grad_clip, nonlinearity=nonlinearity, only_return_final=True) # The output the previous module, with shape (batch_size, N_HIDDEN), # is then passed through the softmax nonlinearity to # create a probability distribution over the dictionary. # The output of this stage is (batch_size, vocab_size). network = lasagne.layers.DenseLayer(network, num_units=vocab_size, W = lasagne.init.Normal(), nonlinearity=lasagne.nonlinearities.softmax) return network # Theano tensor for the targets input_var = T.tensor3('inputs') target_values = T.ivector('target_output') network = create_lstm( vocab_size, input_shape, input_var, nonlinearity=NON_LINEARITY, depth=DEPTH, n_hidden=N_HIDDEN) # lasagne.layers.get_output produces a variable for the output of the net network_output = lasagne.layers.get_output(network) # The loss function is calculated as the mean of the (categorical) cross-entropy between the prediction and target. loss = lasagne.objectives.categorical_crossentropy(network_output, target_values).mean() # Retrieve all the parameters of the models and create the optimizer params = lasagne.layers.get_all_params(network,trainable=True) updates = my_optimizer(loss, params) # Theano functions for training and computing cost print("Compiling functions ...") train = theano.function([input_var, target_values], loss, updates=updates, allow_input_downcast=True) compute_loss = theano.function([input_var, target_values], loss, allow_input_downcast=True) # In order to generate text from the network, we need the probability distribution of the next character given # the state of the network and the input (a seed). # In order to produce the probability distribution of the prediction, we compile a function called probs. probs = theano.function([input_var],network_output,allow_input_downcast=True) generation_phrase = "The meaning of life is " #This phrase will be used as seed to generate text. def predict(N=200): Output a sequence of characters of lenght N according to the current model :type N: int :param N: the number of characters to generate assert(len(generation_phrase)>=SEQ_LENGTH) sample_ix = [] x,_ = iterate_minibatch(len(generation_phrase)-SEQ_LENGTH, 1, generation_phrase,0) for i in range(N): # Pick the character that got assigned the highest probability # ix = np.argmax(probs(x).ravel()) # Alternatively, to sample from the distribution instead: ix = np.random.choice(np.arange(vocab_size), p=probs(x).ravel()) sample_ix.append(ix) x[:,0:SEQ_LENGTH-1,:] = x[:,1:,:] x[:,SEQ_LENGTH-1,:] = 0 x[0,SEQ_LENGTH-1,sample_ix[-1]] = 1. random_snippet = generation_phrase + ''.join(ix_to_char[ix] for ix in sample_ix) print("----\n %s \n----" % random_snippet) print("Training ...") print("Seed used for text generation is: " + generation_phrase) p = 0 for it in range(int(data_size * NUM_EPOCHS / BATCH_SIZE)): predict() # Generate text using the p^th character as the start. avg_cost = 0; for i in range(PRINT_FREQ): x,y = iterate_minibatch(p) p += SEQ_LENGTH + BATCH_SIZE - 1 if(p+BATCH_SIZE+SEQ_LENGTH >= data_size): print('Carriage Return') p = 0; avg_cost += train(x, y) print("Epoch {} average loss = {}".format(it*1.0*PRINT_FREQ/data_size*BATCH_SIZE, avg_cost / PRINT_FREQ)) <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: Using interact for animation with data Step2: To create an animation of a soliton propagating in time, we are going to precompute the soliton data and store it in a 2d array. To set this up, we create the following variables and arrays Step3: Compute a 2d NumPy array called phi Step4: Write a plot_soliton_data(i) function that plots the soliton wave $\phi(x, t[i])$. Customize your plot to make it effective and beautiful. Step5: Use interact to animate the plot_soliton_data function versus time.
<ASSISTANT_TASK:> Python Code: %matplotlib inline from matplotlib import pyplot as plt import numpy as np from IPython.html.widgets import interact, interactive, fixed from IPython.display import display from math import sqrt def soliton(x, t, c, a): # make x and t arrays (if not already) if type(t) != np.ndarray: t = np.array([t]) if type(x) != np.ndarray: x = np.array([x]) #set "xct" to x-ct #because x and t are both arrays, use the sum of meshgid to "add" them without worrying about array size #this will givs us a 1D array if T or X is a single element array xct = sum(np.meshgrid(-1*c*t, x)) #set a to be the same array size as xct a = a*np.ones_like(xct) # z is the array that represents the bracketed expression z = (sqrt(c))/2*(xct-a) # sech = 2/e**z + e**-z use np.exp to input each element sech2z = (2/(np.exp(z) + np.exp(-z)))**2 answer = 1/2*c*sech2z return(answer) assert np.allclose(soliton(np.array([0]),0.0,1.0,0.0), np.array([0.5])) tmin = 0.0 tmax = 10.0 tpoints = 100 t = np.linspace(tmin, tmax, tpoints) xmin = 0.0 xmax = 10.0 xpoints = 200 x = np.linspace(xmin, xmax, xpoints) c = 1.0 a = 0.0 phi = soliton(x, t, c, a) phi.shape assert phi.shape==(xpoints, tpoints) assert phi.ndim==2 assert phi.dtype==np.dtype(float) assert phi[0,0]==soliton(x[0],t[0],c,a) def plot_soliton_data(i=0): #set the t to vary with [i] #note t is set at 0 (i=0) so this plot is a graph of Phi v X with t=0 plt.plot(x, soliton(x, t[i], c, a)) #Graph styling ax = plt.gca() ax.spines['right'].set_color('none') ax.spines['top'].set_color('none') plt.xlabel("X", fontsize = 14) plt.ylabel(r'$\phi$ (x, %s)' %(t[i]), fontsize = 16) plt.title("Korteweg de Vries Equation", fontsize = 16) plot_soliton_data(0) assert True # leave this for grading the plot_soliton_data function interact(plot_soliton_data, i=(0,99)); assert True # leave this for grading the interact with plot_soliton_data cell <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 configuration Step2: connecting, retrieving/sending messages Step3: 1and1 Step4: Gmail Step5: iTSCOM Step6: WIP
<ASSISTANT_TASK:> Python Code: import maildaemon cfg = maildaemon.load_config() connections = cfg['connections'] from maildaemon.imap_daemon import IMAPDaemon from maildaemon.smtp_connection import SMTPConnection from maildaemon.pop_daemon import POPDaemon one_and_one_imap = IMAPDaemon.from_dict(connections['1and1-imap']) one_and_one_imap.connect() one_and_one_imap.retrieve_folders_with_flags() one_and_one_imap.retrieve_messages([1, 2, 3]) one_and_one_imap.disconnect() one_and_one_smtp = SMTPConnection.from_dict(connections['1and1-smtp']) #one_and_one_pop = POPDaemon.from_dict(connections['1and1-pop']) one_and_one_smtp.connect() #one_and_one_pop.connect() one_and_one_smtp.disconnect() #one_and_one_pop.disconnect() gmail_imap = IMAPDaemon.from_dict(connections['gmail-imap']) gmail_imap.connect() gmail_imap.retrieve_folders_with_flags() gmail_imap.open_folder() gmail_imap.open_folder('[Gmail]/Sent Mail') gmail_imap.open_folder('[Gmail]/All Mail') gmail_imap.retrieve_message_ids() gmail_imap.retrieve_message_parts(1, ['UID', 'FLAGS']) gmail_imap.retrieve_messages_parts(range(1,100), ['ENVELOPE'], '[Gmail]/All Mail') gmail_imap.retrieve_messages_parts(range(1,100), ['ENVELOPE']) message_parts = gmail_imap.retrieve_message_parts(10, ['ENVELOPE']) message_parts gmail_imap.move_messages([10], '[Gmail]/Important') def enable(self): self._link.enable('MOVE') enable(gmail_imap) message = gmail_imap.retrieve_message(1) message gmail_imap.disconnect() gmail_smtp = SMTPConnection.from_dict(connections['gmail-smtp']) gmail_smtp.connect() gmail_smtp.disconnect() #itscom_smtp = SMTPConnection.from_dict(connections['itscom-smtp']) itscom_pop = POPDaemon.from_dict(connections['itscom-pop']) itscom_pop.connect() itscom_pop.retrieve_message_ids() itscom_pop.disconnect() import email envelope, body = message_parts email_message = email.message_from_bytes(body) # type: email.message.Message print(email_message.as_string()) email_message email_message.defects parser = email.parser.BytesParser() msg = parser.parsebytes(body, headersonly=False) print(msg.as_string()) msg.items() == email_message.items() <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 use Numpy arrays we need to import the module. Step2: Hm, we created the plot but where is it? Unlike matplotlib PyNGL can't display inline plots but IPython provides a solution for us. Step3: That's really sparse. Next, we want to add a title above the plot and add the axis titles, too. Step4: Display the grid lines of the coordinate system, too. Step5: Change the line settings Step6: To display two datasets in one xy-plot. Step7: Uh, that's not what we want! We want to have two lines with different colors, lets say red and blue. And while we're at it, they should have two different dash pattern types. Step8: NOTICE Step9: We can distinguish them now but don't know which line is y1, y2 or y3. It is always good to have legend and that's what we want to do next. Step10: That is the default. Doesn't look very nice, does it? So, we should fix it up a bit. Step11: The next example shows how to read a dataset from file. Step12: The variable time is x and and the variable tsurf is y. Step13: Hm, I would like to have the x-axis labels as dates and not as indices.
<ASSISTANT_TASK:> Python Code: import Ngl wks = Ngl.open_wks('png', 'plot_xy') import numpy as np x = np.arange(0,5) y = np.arange(0,10,2) plot = Ngl.xy(wks, x, y) from IPython.display import Image Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.tiXAxisString = 'x-axis title string' res.tiYAxisString = 'y-axis title string' plot = Ngl.xy(wks, x, y, res) Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.tiXAxisString = 'x-axis title string' res.tiYAxisString = 'y-axis title string' res.tmXMajorGrid = True res.tmYMajorGrid = True plot = Ngl.xy(wks, x, y, res) Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.tiXAxisString = 'x-axis title string' res.tiYAxisString = 'y-axis title string' res.tmXMajorGrid = True res.tmYMajorGrid = True res.xyLineColor = 'red' res.xyDashPattern = 3 # -- - -- - -- res.xyLineThicknessF = 5 plot = Ngl.xy(wks, x, y, res) Image(filename='plot_xy.png', retina=True) y1 = np.array([0,3,6,1,4]) y2 = np.array([2,5,3,2,7]) data = np.array([y1,y2]) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' plot = Ngl.xy(wks, x, data, res) Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.xyLineColors = ['red','blue'] res.xyDashPatterns = [3,16] res.xyLineThicknesses = [5,3] plot = Ngl.xy(wks, x, data, res) Image(filename='plot_xy.png', retina=True) y1 = np.array([0,3,6,1,4]) y2 = np.array([2,5,3,2,7]) y3 = np.array([1,1,2,3,5]) data = np.array([y1,y2,y3]) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.xyLineColors = ['red','blue','green'] res.xyDashPatterns = [3,16,0] res.xyLineThicknesses = [5,3,5] plot = Ngl.xy(wks, x, data, res) Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.xyLineColors = ['red','blue','green'] res.xyDashPatterns = [3,16,0] res.xyLineThicknesses = [5,3,5] res.pmLegendDisplayMode = "Always" #-- turn on the drawing plot = Ngl.xy(wks, x, data, res) Image(filename='plot_xy.png', retina=True) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy.png') res = Ngl.Resources() res.tiMainString = 'This is the title string' res.xyLineColors = ['red','blue','green'] res.xyDashPatterns = [3,16,0] res.xyLineThicknesses = [5,3,5] res.xyExplicitLegendLabels = ["y1","y2","y3"] res.pmLegendDisplayMode = "Always" #-- turn on the legend drawing res.pmLegendOrthogonalPosF = -1.0 #-- move the legend upward res.pmLegendParallelPosF = 0.17 #-- move the legend rightward res.pmLegendWidthF = 0.15 #-- increase width res.pmLegendHeightF = 0.10 #-- increase height res.lgPerimOn = False #-- turn off the perimeter plot = Ngl.xy(wks, x, data, res) Image(filename='plot_xy.png', retina=True) import xarray as xr ds = xr.open_dataset('./data/tsurf_fldmean.nc') tsurf = ds.tsurf time = np.arange(0,len(ds.time),1) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy_tsurf.png') res = Ngl.Resources() res.tiMainString = 'Variable tsurf' res.tiXAxisString = 'time' res.tiYAxisString = tsurf.long_name plot = Ngl.xy(wks, time, tsurf[:,0,0].values, res) Image(filename='plot_xy_tsurf.png', retina=True) import datetime ntime = len(ds.time) years = ds.time.dt.year.values months = ds.time.dt.month.values days = ds.time.dt.day.values date_labels = [datetime.date(years[i],months[i],days[i]) for i in range(0,ntime)] date_labels = list(np.array(date_labels,dtype='str')) Ngl.delete_wks(wks) wks = Ngl.open_wks('png', 'plot_xy_tsurf.png') res = Ngl.Resources() res.tiMainString = 'Variable tsurf' res.tiXAxisString = 'time' res.tiYAxisString = tsurf.long_name res.tmXBMode = 'Explicit' #-- use explicit values res.tmXBValues = time[::4] #-- use the new x-values array res.tmXBLabels = date_labels[::4] #-- use the new x-values array as labels res.tmXBLabelFontHeightF = 0.008 res.tmXBLabelAngleF = 45 res.tmXBMinorOn = False #-- turn off minor tickmark plot = Ngl.xy(wks, time, tsurf[:,0,0].values, res) Image(filename='plot_xy_tsurf.png', retina=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: sorted() ไธ้™ไบŽๅˆ—่กจ๏ผŒ่€Œไธ”ไผš็”Ÿๆˆๅนถ่ฟ”ๅ›žไธ€ไธชๆ–ฐ็š„ๆŽ’ๅบๅŽ็š„ๅˆ—่กจ๏ผŒๅŽŸๆœ‰ๅฏน่ฑกไธๅ—ๅฝฑๅ“๏ผš Step2: ่™ฝ็„ถไธๆ˜ฏๅŽŸๅœฐๆŽ’ๅบ๏ผŒไฝ†ๅฆ‚ๆžœๆ˜ฏไผ ๅ…ฅ็”Ÿๆˆๅ™จ๏ผŒ่ฟ˜ๆ˜ฏไผš่ขซๅพช็Žฏๆމ็š„๏ผš Step3: Key Step4: ๆˆ–่€…๏ผŒๅฝ“่ฟญไปฃๅฏน่ฑก็š„ๅ…ƒ็ด ่พƒไธบๅคๆ‚ๆ—ถ๏ผŒๅฏไปฅๅชๆŒ‰็…งๅ…ถไธญ็š„ๆŸไบ›ๅฑžๆ€ง่ฟ›่กŒๆŽ’ๅบ๏ผš Step5: Python ็š„ operator ๆ ‡ๅ‡†ๅบ“ๆไพ›ไบ†ไธ€ไบ›ๆ“ไฝœ็ฌฆ็›ธๅ…ณ็š„ๆ–นๆณ•๏ผŒๅฏไปฅๆ›ดๆ–นไพฟๅœฐ่Žทๅ–ๅ…ƒ็ด ็š„ๅฑžๆ€ง๏ผš Step6: ็ป่ฟ‡ key ๅค„็†ไน‹ๅŽไผš้€š่ฟ‡ &lt; ็ฌฆๅทๅฏนไธคไธชๅ…ƒ็ด ่ฟ›่กŒๆฏ”่พƒ๏ผŒๅœจ Python 2.7 ็š„็‰ˆๆœฌไธญ๏ผŒsorted() ่ฟ˜ๅฏไปฅๆŽฅๆ”ถๅฆๅค–ไธ€ไธชๅ‚ๆ•ฐ cmp๏ผŒ็”จๆฅๆŽฅ็ฎก &lt; ็š„ๆฏ”่พƒ่ฟ‡็จ‹ใ€‚ไฝ†ๆ˜ฏๅœจ Python 3.5 ไธญๅทฒ็ปๅ…จ้ขๆ‘’ๅผƒไบ†่ฟ™ไธ€ๅšๆณ•๏ผŒๅŒ…ๆ‹ฌ sorted() ไธญ็š„ cmp ๅ‚ๆ•ฐๅ’Œๅฏน่ฑกไธญ็š„ __cmp__ ๆฏ”่พƒๆ“ไฝœ๏ผŒๅชๆœ‰ๅœจ้œ€่ฆๅ‘ๅŽๅ…ผๅฎน็š„ๆ—ถๅ€™ๆ‰ๅฏ่ƒฝๅœจ Python 3.5 ็”จๅˆฐ่ฟ™ไธ€ๅŠŸ่ƒฝ๏ผŒๅ…ถๆ›ฟๆข็š„ๆ–นๆณ•ไธบ๏ผš
<ASSISTANT_TASK:> Python Code: from random import randrange lst = [randrange(1, 100) for _ in range(10)] print(lst) lst.sort() print(lst) lst = [randrange(1, 100) for _ in range(10)] tup = tuple(lst) print(sorted(tup)) # return List print(tup) tup = (randrange(1, 100) for _ in range(10)) print(sorted(tup)) for i in tup: print(i) lst = [randrange(-10, 10) for _ in range(10)] print(lst) print(sorted(lst, key=abs)) lst = list(zip("hello world hail python".split(), [randrange(1, 10) for _ in range(4)])) print(lst) print(sorted(lst, key=lambda item: item[1])) from operator import itemgetter, attrgetter print(lst) print(sorted(lst, key=itemgetter(1))) # ไธ€ๅˆ‡้ƒฝๅชๆ˜ฏๅ‡ฝๆ•ฐ fitemgetter = lambda ind: lambda item: item[ind] print(sorted(lst, key=fitemgetter(1))) class P(object): def __init__(self, w, n): self.w = w self.n = n def __repr__(self): return "{}=>{}".format(self.w, self.n) ps = [P(i[0], i[1]) for i in lst] print(sorted(ps, key=attrgetter('n'))) from functools import cmp_to_key as new_cmp_to_key # new_cmp_to_key works like this def cmp_to_key(mycmp): 'Convert a cmp= function into a key= function' class K: def __init__(self, obj, *args): self.obj = obj def __lt__(self, other): return mycmp(self.obj, other.obj) < 0 return K def reverse_cmp(x, y): return y[1] - x[1] sorted(lst, key=cmp_to_key(reverse_cmp)) <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: With Spaces Step2: Do the loop and calculate the scores Step3: Now without spaces Step4: Do the loop and calculate the scores
<ASSISTANT_TASK:> Python Code: import numpy as np from sklearn import svm, cross_validation import h5py import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline import sys sys.path.append("../") # Data to use Ndata = 10000 # First we load the file file_location = '../results_database/text_wall_street_columns.hdf5' # Now we need to get the letters and align them text_directory = '../data/wall_street_letters.npy' letters_sequence = np.load(text_directory) Nletters = len(letters_sequence) symbols = set(letters_sequence) targets = [] for index in range(Ndata): letter_index = index // 10 targets.append(letters_sequence[letter_index]) # Transform to array targets = np.array(targets) # Calculate the predictions Ntime_clusters_set = np.arange(3, 50, 3) scores_mixed = [] scores_indp = [] # Nexa parameters Nspatial_clusters = 3 Nembedding = 3 for Ntime_clusters in Ntime_clusters_set: print(Ntime_clusters) # Here calculate the scores for the mixes run_name = '/test' f = h5py.File(file_location, 'r') parameters_string = '/' + str(Nspatial_clusters) parameters_string += '-' + str(Ntime_clusters) parameters_string += '-' + str(Nembedding) nexa = f[run_name + parameters_string] cluster_to_index = nexa['cluster_to_index'] code_vectors_softmax = np.array(nexa['code-vectors-softmax']) # Now we need to classify X = code_vectors_softmax[:Ndata] y = targets X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.10) clf_linear = svm.SVC(C=1.0, kernel='linear') clf_linear.fit(X_train, y_train) score = clf_linear.score(X_test, y_test) * 100.0 scores_mixed.append(score) # Here calculate the scores for the independent run_name = '/indep' f = h5py.File(file_location, 'r') parameters_string = '/' + str(Nspatial_clusters) parameters_string += '-' + str(Ntime_clusters) parameters_string += '-' + str(Nembedding) nexa = f[run_name + parameters_string] cluster_to_index = nexa['cluster_to_index'] code_vectors_softmax = np.array(nexa['code-vectors-softmax']) # Now we need to classify X = code_vectors_softmax[:Ndata] y = targets X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.10) clf_linear = svm.SVC(C=1.0, kernel='linear') clf_linear.fit(X_train, y_train) score = clf_linear.score(X_test, y_test) * 100.0 scores_indp.append(score) fig = plt.figure(figsize=(16, 12)) ax = fig.add_subplot(111) ax.plot(Ntime_clusters_set, scores_indp, 'o-', label='independent', lw=2, markersize=10) ax.plot(Ntime_clusters_set, scores_mixed, 'o-', label='mixed', lw=2, markersize=10) ax.set_ylim(0, 105) ax.set_ylabel('Accuracy') ax.set_xlabel('Number of Data Clusters') ax.set_title('Accuracy vs Number of Data Clusters for different features') ax.legend() # Data to use Ndata = 10000 # First we load the file file_location = '../results_database/text_wall_street_columns_spaces.hdf5' # Now we need to get the letters and align them text_directory = '../data/wall_street_letters_spaces.npy' letters_sequence = np.load(text_directory) Nletters = len(letters_sequence) symbols = set(letters_sequence) targets = [] for index in range(Ndata): letter_index = index // 10 targets.append(letters_sequence[letter_index]) # Transform to array targets = np.array(targets) # Calculate the predictions Ntime_clusters_set = np.arange(3, 50, 3) scores_mixed_wspaces = [] scores_indp_wspaces = [] # Nexa parameters Nspatial_clusters = 3 Nembedding = 3 for Ntime_clusters in Ntime_clusters_set: print(Ntime_clusters) # Here calculate the scores for the mixes run_name = '/test' f = h5py.File(file_location, 'r') parameters_string = '/' + str(Nspatial_clusters) parameters_string += '-' + str(Ntime_clusters) parameters_string += '-' + str(Nembedding) nexa = f[run_name + parameters_string] cluster_to_index = nexa['cluster_to_index'] code_vectors_softmax = np.array(nexa['code-vectors-softmax']) # Now we need to classify X = code_vectors_softmax[:Ndata] y = targets X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.10) clf_linear = svm.SVC(C=1.0, kernel='linear') clf_linear.fit(X_train, y_train) score = clf_linear.score(X_test, y_test) * 100.0 scores_mixed_wspaces.append(score) # Here calculate the scores for the independent run_name = '/indep' f = h5py.File(file_location, 'r') parameters_string = '/' + str(Nspatial_clusters) parameters_string += '-' + str(Ntime_clusters) parameters_string += '-' + str(Nembedding) nexa = f[run_name + parameters_string] cluster_to_index = nexa['cluster_to_index'] code_vectors_softmax = np.array(nexa['code-vectors-softmax']) # Now we need to classify X = code_vectors_softmax[:Ndata] y = targets X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.10) clf_linear = svm.SVC(C=1.0, kernel='linear') clf_linear.fit(X_train, y_train) score = clf_linear.score(X_test, y_test) * 100.0 scores_indp_wspaces.append(score) fig = plt.figure(figsize=(16, 12)) ax = fig.add_subplot(111) ax.plot(Ntime_clusters_set, scores_indp, 'o-', label='independent', lw=2, markersize=10) ax.plot(Ntime_clusters_set, scores_mixed, 'o-', label='mixed', lw=2, markersize=10) ax.set_ylim(0, 105) ax.set_ylabel('Accuracy') ax.set_xlabel('Number of Data Clusters') ax.set_title('Accuracy vs Number of Data Clusters for different features (Without Sapces)') ax.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: TV Script Generation Step3: Explore the Data Step6: Implement Preprocessing Functions Step9: Tokenize Punctuation Step11: Preprocess all the data and save it Step13: Check Point Step15: Build the Neural Network Step18: Input Step21: Build RNN Cell and Initialize Step24: Word Embedding Step27: Build RNN Step30: Build the Neural Network Step33: Batches Step35: Neural Network Training Step37: Build the Graph Step39: Train Step41: Save Parameters Step43: Checkpoint Step46: Implement Generate Functions Step49: Choose Word Step51: Generate TV Script
<ASSISTANT_TASK:> Python Code: DON'T MODIFY ANYTHING IN THIS CELL import helper data_dir = './data/divina_commedia.txt' text = helper.load_data(data_dir) # Ignore notice, since we don't use it for analysing the data #text = text[81:] view_sentence_range = (0, 10) DON'T MODIFY ANYTHING IN THIS CELL import numpy as np print('Dataset Stats') print('Roughly the number of unique words: {}'.format(len({word: None for word in text.split()}))) scenes = text.split('\n\n') print('Number of scenes: {}'.format(len(scenes))) sentence_count_scene = [scene.count('\n') for scene in scenes] print('Average number of sentences in each scene: {}'.format(np.average(sentence_count_scene))) sentences = [sentence for scene in scenes for sentence in scene.split('\n')] print('Number of lines: {}'.format(len(sentences))) word_count_sentence = [len(sentence.split()) for sentence in sentences] print('Average number of words in each line: {}'.format(np.average(word_count_sentence))) print() print('The sentences {} to {}:'.format(*view_sentence_range)) print('\n'.join(text.split('\n')[view_sentence_range[0]:view_sentence_range[1]])) import numpy as np import problem_unittests as tests def create_lookup_tables(text): Create lookup tables for vocabulary :param text: The text of tv scripts split into words :return: A tuple of dicts (vocab_to_int, int_to_vocab) words_ordered = sorted(set(text)) # TODO: Implement Function vocab_to_int = {word: index for index, word in enumerate(words_ordered)} int_to_vocab = {index: word for index, word in enumerate(words_ordered)} return vocab_to_int, int_to_vocab DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_create_lookup_tables(create_lookup_tables) def token_lookup(): Generate a dict to turn punctuation into a token. :return: Tokenize dictionary where the key is the punctuation and the value is the token # TODO: Implement Function token_dict = dict() token_dict['.'] = "||Period||" token_dict[','] = "||Comma||" token_dict['"'] = "||Quotation_Mark||" token_dict[';'] = "||Semicolon||" token_dict['!'] = "||Exclamation_Mark||" token_dict['?'] = "||Question_Mark||" token_dict['('] = "||Left_Parentheses||" token_dict[')'] = "||Right_Parentheses||" token_dict['--'] = "||Dash||" token_dict['\n'] = "||Return||" return token_dict DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_tokenize(token_lookup) DON'T MODIFY ANYTHING IN THIS CELL # Preprocess Training, Validation, and Testing Data helper.preprocess_and_save_data(data_dir, token_lookup, create_lookup_tables) DON'T MODIFY ANYTHING IN THIS CELL import helper import numpy as np import problem_unittests as tests int_text, vocab_to_int, int_to_vocab, token_dict = helper.load_preprocess() DON'T MODIFY ANYTHING IN THIS CELL from distutils.version import LooseVersion import warnings import tensorflow as tf # Check TensorFlow Version assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer' print('TensorFlow Version: {}'.format(tf.__version__)) # Check for a GPU if not tf.test.gpu_device_name(): warnings.warn('No GPU found. Please use a GPU to train your neural network.') else: print('Default GPU Device: {}'.format(tf.test.gpu_device_name())) def get_inputs(): Create TF Placeholders for input, targets, and learning rate. :return: Tuple (input, targets, learning rate) # TODO: Implement Function inputs = tf.placeholder(tf.int32, shape=(None, None), name="input") targets = tf.placeholder(tf.int32, shape=(None,None), name="targets") learning_rate = tf.placeholder(tf.float32, name="learning_rate") return inputs, targets, learning_rate DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_get_inputs(get_inputs) def get_init_cell(batch_size, rnn_size): Create an RNN Cell and initialize it. :param batch_size: Size of batches :param rnn_size: Size of RNNs :return: Tuple (cell, initialize state) # TODO: Implement Function lstm_layers = 2 #Need to pass test?! (otherwise final_state shape will be wrong) lstm = tf.contrib.rnn.BasicLSTMCell(num_units=rnn_size) cell = tf.contrib.rnn.MultiRNNCell([lstm] * lstm_layers) initial_state = cell.zero_state(batch_size, tf.float32) # print(initial_state) initial_state = tf.identity(initial_state, name="initial_state") return cell, initial_state DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_get_init_cell(get_init_cell) def get_embed(input_data, vocab_size, embed_dim): Create embedding for <input_data>. :param input_data: TF placeholder for text input. :param vocab_size: Number of words in vocabulary. :param embed_dim: Number of embedding dimensions :return: Embedded input. # TODO: Implement Function embeddings = tf.Variable(tf.random_uniform((vocab_size, embed_dim), -1, 1)) embed = tf.nn.embedding_lookup(embeddings, ids=input_data) return embed DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_get_embed(get_embed) def build_rnn(cell, inputs): Create a RNN using a RNN Cell :param cell: RNN Cell :param inputs: Input text data :return: Tuple (Outputs, Final State) # TODO: Implement Function #print(cell) #print(inputs) outputs, final_state = tf.nn.dynamic_rnn(cell, inputs, dtype=tf.float32) final_state = tf.identity(final_state, name="final_state") # Shape is lstm_layers x 2 (inputs and targets) x None (batch_size) x lstm_units #print(final_state) return outputs, final_state DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_build_rnn(build_rnn) def build_nn(cell, rnn_size, input_data, vocab_size, embed_dim): Build part of the neural network :param cell: RNN cell :param rnn_size: Size of rnns :param input_data: Input data :param vocab_size: Vocabulary size :param embed_dim: Number of embedding dimensions :return: Tuple (Logits, FinalState) # TODO: Implement Function embed = get_embed(input_data, vocab_size, embed_dim=embed_dim) # outputs shape is batch_size x seq_len x lstm_units outputs, final_state = build_rnn(cell, inputs=embed) #print(outputs.shape) logits = tf.contrib.layers.fully_connected(outputs, vocab_size, activation_fn=None) # logits shape is batch_size x seq_len x vocab_size #print(logits.shape) return logits, final_state DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_build_nn(build_nn) def get_batches(int_text, batch_size, seq_length): Return batches of input and target :param int_text: Text with the words replaced by their ids :param batch_size: The size of batch :param seq_length: The length of sequence :return: Batches as a Numpy array #print("Batch_size: " + str(batch_size)) #print("Seq length: " + str(seq_length)) # Consider that targets is shifted by 1 num_batches = len(int_text)//(batch_size * seq_length + 1) #print("Num batches: " + str(num_batches)) #print("Text length: " + str(len(int_text))) batches = np.zeros(shape=(num_batches, 2, batch_size, seq_length), dtype=np.int32) #print(batches.shape) # TODO: Add a smarter check for batch_index in range(0, num_batches): for in_batch_index in range(0, batch_size): start_x = (batch_index * seq_length) + (seq_length * num_batches * in_batch_index) start_y = start_x + 1 x = int_text[start_x : start_x + seq_length] y = int_text[start_y : start_y + seq_length] #print("batch_index: " + str(batch_index)) #print("in_batch_index: " + str(in_batch_index)) #print("start_x: " + str(start_x)) #print(x) batches[batch_index][0][in_batch_index] = np.asarray(x) batches[batch_index][1][in_batch_index] = np.asarray(y) #print(batches) return batches DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_get_batches(get_batches) # FINAL LOSS: 0.213 - Seq length 20, LR 0.001, Epochs 250 # Number of Epochs num_epochs = 250 # Batch Size batch_size = 64 # RNN Size rnn_size = 256 # Embedding Dimension Size embed_dim = 300 # Sequence Length seq_length = 20 # Learning Rate learning_rate = 0.001 # Show stats for every n number of batches show_every_n_batches = 99 DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE save_dir = './save' DON'T MODIFY ANYTHING IN THIS CELL from tensorflow.contrib import seq2seq train_graph = tf.Graph() with train_graph.as_default(): vocab_size = len(int_to_vocab) input_text, targets, lr = get_inputs() input_data_shape = tf.shape(input_text) cell, initial_state = get_init_cell(input_data_shape[0], rnn_size) logits, final_state = build_nn(cell, rnn_size, input_text, vocab_size, embed_dim) # Probabilities for generating words # probs shape is batch_size x seq_len x vocab_size probs = tf.nn.softmax(logits, name='probs') #print(probs.shape) # Loss function cost = seq2seq.sequence_loss( logits, targets, tf.ones([input_data_shape[0], input_data_shape[1]])) # Optimizer optimizer = tf.train.AdamOptimizer(lr) # Gradient Clipping gradients = optimizer.compute_gradients(cost) capped_gradients = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gradients] train_op = optimizer.apply_gradients(capped_gradients) DON'T MODIFY ANYTHING IN THIS CELL batches = get_batches(int_text, batch_size, seq_length) with tf.Session(graph=train_graph) as sess: sess.run(tf.global_variables_initializer()) for epoch_i in range(num_epochs): state = sess.run(initial_state, {input_text: batches[0][0]}) for batch_i, (x, y) in enumerate(batches): # x and y shapes are batch_size x seq_len feed = { input_text: x, targets: y, initial_state: state, lr: learning_rate} train_loss, state, _ = sess.run([cost, final_state, train_op], feed) # Show every <show_every_n_batches> batches if (epoch_i * len(batches) + batch_i) % show_every_n_batches == 0: print('Epoch {:>3} Batch {:>4}/{} train_loss = {:.3f}'.format( epoch_i, batch_i, len(batches), train_loss)) # Save Model saver = tf.train.Saver() saver.save(sess, save_dir) print('Model Trained and Saved') DON'T MODIFY ANYTHING IN THIS CELL # Save parameters for checkpoint helper.save_params((seq_length, save_dir)) DON'T MODIFY ANYTHING IN THIS CELL import tensorflow as tf import numpy as np import helper import problem_unittests as tests _, vocab_to_int, int_to_vocab, token_dict = helper.load_preprocess() seq_length, load_dir = helper.load_params() def get_tensors(loaded_graph): Get input, initial state, final state, and probabilities tensor from <loaded_graph> :param loaded_graph: TensorFlow graph loaded from file :return: Tuple (InputTensor, InitialStateTensor, FinalStateTensor, ProbsTensor) # TODO: Implement Function return loaded_graph.get_tensor_by_name("input:0"), loaded_graph.get_tensor_by_name("initial_state:0"), \ loaded_graph.get_tensor_by_name("final_state:0"), loaded_graph.get_tensor_by_name("probs:0") DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_get_tensors(get_tensors) def pick_word(probabilities, int_to_vocab): Pick the next word in the generated text :param probabilities: Probabilites of the next word :param int_to_vocab: Dictionary of word ids as the keys and words as the values :return: String of the predicted word # TODO: Implement Function return int_to_vocab[np.argmax(probabilities)] DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE tests.test_pick_word(pick_word) #print(vocab_to_int) gen_length = 200 #prime_word = 'Inferno: Canto I' prime_word = 'vuolsi' prime_word = str.lower(prime_word) DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE loaded_graph = tf.Graph() with tf.Session(graph=loaded_graph) as sess: # Load saved model loader = tf.train.import_meta_graph(load_dir + '.meta') loader.restore(sess, load_dir) # Get Tensors from loaded model input_text, initial_state, final_state, probs = get_tensors(loaded_graph) # Sentences generation setup gen_sentences = prime_word.split() prev_state = sess.run(initial_state, {input_text: np.array([[1]])}) # Generate sentences for n in range(gen_length): # Dynamic Input dyn_input = [[vocab_to_int[word] for word in gen_sentences[-seq_length:]]] dyn_seq_length = len(dyn_input[0]) # Get Prediction probabilities, prev_state = sess.run( [probs, final_state], {input_text: dyn_input, initial_state: prev_state}) pred_word = pick_word(probabilities[dyn_seq_length-1], int_to_vocab) gen_sentences.append(pred_word) # Remove tokens tv_script = ' '.join(gen_sentences) for key, token in token_dict.items(): ending = ' ' if key in ['\n', '(', '"'] else '' tv_script = tv_script.replace(' ' + token.lower(), key) tv_script = tv_script.replace('\n ', '\n') tv_script = tv_script.replace('( ', '(') print(tv_script) <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: Hat potential Step2: Plot this function over the range $x\in\left[-3,3\right]$ with $b=1.0$ and $a=5.0$ Step3: Write code that finds the two local minima of this function for $b=1.0$ and $a=5.0$.
<ASSISTANT_TASK:> Python Code: %matplotlib inline import matplotlib.pyplot as plt import numpy as np import scipy.optimize as opt def hat(x,a,b): return -a*x**2+b*x**4 assert hat(0.0, 1.0, 1.0)==0.0 assert hat(0.0, 1.0, 1.0)==0.0 assert hat(1.0, 10.0, 1.0)==-9.0 a = 5.0 b = 1.0 x=np.linspace(-3,3,100) plt.figure(figsize=(9,6)) plt.xlabel('Range'), plt.ylabel('V(x)'), plt.title('Hat Potential') plt.plot(x, hat(x,a,b)) plt.box(False) plt.grid(True) plt.tick_params(axis='x', top='off', direction='out') plt.tick_params(axis='y', right='off', direction='out'); assert True # leave this to grade the plot res1 = opt.minimize_scalar(hat, bounds=(-3,0), args=(a,b), method='bounded') res2 = opt.minimize_scalar(hat, bounds=(0,3), args=(a,b), method='bounded') print('Local minima: %f, %f' % (res1.x, res2.x)) plt.figure(figsize=(9,6)) plt.xlabel('Range'), plt.ylabel('V(x)') plt.plot(x, hat(x,a,b), label="Potential") plt.scatter(res1.x, res1.fun, marker="o", color="r") plt.scatter(res2.x, res2.fun, marker="o", color="r") plt.title('Finding Local Minima of Hat Potential') plt.box(False), plt.grid(True), plt.xlim(-2.5,2.5), plt.ylim(-8,4) plt.tick_params(axis='x', top='off', direction='out') plt.tick_params(axis='y', right='off', direction='out') plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.); assert True # leave this for grading the 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: To create a transmission line of 100um Step2: More detailed examples illustrating how to create various kinds of Media Step3: For the purpose of microwave network analysis, the defining properties of a (single moded) transmission line are it's characteristic impedance and propagation constant. These properties return complex numpy.ndarray's, A port impedance is also needed when different networks are connected. Step4: The port impedance is given by z0 (lower z). Which we set to 1, just to illustrate how this works. The port impedance is used to compute impedance mismatched if circuits of different port impedance are connected. Step5: The propagation constant is given by gamma Step6: Lets take a look at some other Media's Step7: Simulate a 1cm slab of Si in half-space, Step8: Rectangular Waveguide Step9: The z0 argument in the Rectangular Waveguide constructor is used Step10: Because the wave quantities are dynamic they change when the attributes Step11: Network Synthesis Step12: Or to create a $90^{\circ}$ section of cpw line, Step13: Building Circuits Step14: When Networks with more than 2 ports need to be connected together, use Step15: Adding networks in shunt is pretty common, so there is a Media.shunt() function to do this, Step16: If a specific circuit is created frequently, it may make sense to Step17: A more useful example may be to create a function for a shunt-stub tuner, Step18: This approach lends itself to design optimization.
<ASSISTANT_TASK:> Python Code: %matplotlib inline import skrf as rf rf.stylely() from skrf import Frequency from skrf.media import CPW freq = Frequency(75,110,101,'ghz') cpw = CPW(freq, w=10e-6, s=5e-6, ep_r=10.6) cpw cpw.line(100*1e-6, name = '100um line') freq = Frequency(75,110,101,'ghz') cpw = CPW(freq, w=10e-6, s=5e-6, ep_r=10.6, z0 =1) cpw cpw.Z0[:3] cpw.z0[:3] cpw.gamma[:3] from skrf.media import Freespace freq = Frequency(10,20,101,'ghz') air = Freespace(freq) air air.z0[:2] # 377ohm baby! # plane wave in Si si = Freespace(freq, ep_r = 11.2) si.z0[:3] # ~110ohm slab = air.thru() ** si.line(1, 'cm') ** air.thru() slab.plot_s_db(n=0) from skrf.media import RectangularWaveguide freq = Frequency(75,110,101,'ghz') wg = RectangularWaveguide(freq, a=100*rf.mil, z0=50) # see note below about z0 wg air = Freespace(freq) from matplotlib import pyplot as plt air.plot(air.gamma.imag, label='Freespace') wg.plot(wg.gamma.imag, label='WR10') plt.ylabel('Propagation Constant (rad/m)') plt.legend() for ep_r in [9,10,11]: cpw.ep_r = ep_r cpw.frequency.plot(cpw.beta, label='er=%.1f'%ep_r) plt.xlabel('Frequency [GHz]') plt.ylabel('Propagation Constant [rad/m]') plt.legend() wg.short(name = 'short') cpw.line(d=90,unit='deg', name='line') delay_short = wg.line(d=90,unit='deg') ** wg.short() delay_short.name = 'delay short' delay_short tee = cpw.tee() delay_open = cpw.delay_open(40,'deg') shunt_open = rf.connect(tee,1,delay_open,0) cpw.shunt(delay_open) delay_short = lambda d: wg.line(d,'deg')**wg.short() delay_short(90) def shunt_stub(med, d0, d1): return med.line(d0,'deg')**med.shunt_delay_open(d1,'deg') shunt_stub(cpw,10,90) from scipy.optimize import fmin # the load we are trying to match load = cpw.load(.2+.2j) # single stub circuit generator function def shunt_stub(med, d0, d1): return med.line(d0,'deg')**med.shunt_delay_open(d1,'deg') # define the cost function we want to minimize (this uses sloppy namespace) def cost(d): # prevent negative length lines, returning high cost if d[0] <0 or d[1] <0: return 1e3 return (shunt_stub(cpw,d[0],d[1]) ** load)[100].s_mag.squeeze() # initial guess of optimal delay lengths in degrees d0 = 120,40 # initial guess #determine the optimal delays d_opt = fmin(cost,(120,40)) d_opt <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 Type Step7: 1.4. Elemental Stoichiometry Step8: 1.5. Elemental Stoichiometry Details Step9: 1.6. Prognostic Variables Step10: 1.7. Diagnostic Variables Step11: 1.8. Damping Step12: 2. Key Properties --&gt; Time Stepping Framework --&gt; Passive Tracers Transport Step13: 2.2. Timestep If Not From Ocean Step14: 3. Key Properties --&gt; Time Stepping Framework --&gt; Biology Sources Sinks Step15: 3.2. Timestep If Not From Ocean Step16: 4. Key Properties --&gt; Transport Scheme Step17: 4.2. Scheme Step18: 4.3. Use Different Scheme Step19: 5. Key Properties --&gt; Boundary Forcing Step20: 5.2. River Input Step21: 5.3. Sediments From Boundary Conditions Step22: 5.4. Sediments From Explicit Model Step23: 6. Key Properties --&gt; Gas Exchange Step24: 6.2. CO2 Exchange Type Step25: 6.3. O2 Exchange Present Step26: 6.4. O2 Exchange Type Step27: 6.5. DMS Exchange Present Step28: 6.6. DMS Exchange Type Step29: 6.7. N2 Exchange Present Step30: 6.8. N2 Exchange Type Step31: 6.9. N2O Exchange Present Step32: 6.10. N2O Exchange Type Step33: 6.11. CFC11 Exchange Present Step34: 6.12. CFC11 Exchange Type Step35: 6.13. CFC12 Exchange Present Step36: 6.14. CFC12 Exchange Type Step37: 6.15. SF6 Exchange Present Step38: 6.16. SF6 Exchange Type Step39: 6.17. 13CO2 Exchange Present Step40: 6.18. 13CO2 Exchange Type Step41: 6.19. 14CO2 Exchange Present Step42: 6.20. 14CO2 Exchange Type Step43: 6.21. Other Gases Step44: 7. Key Properties --&gt; Carbon Chemistry Step45: 7.2. PH Scale Step46: 7.3. Constants If Not OMIP Step47: 8. Tracers Step48: 8.2. Sulfur Cycle Present Step49: 8.3. Nutrients Present Step50: 8.4. Nitrous Species If N Step51: 8.5. Nitrous Processes If N Step52: 9. Tracers --&gt; Ecosystem Step53: 9.2. Upper Trophic Levels Treatment Step54: 10. Tracers --&gt; Ecosystem --&gt; Phytoplankton Step55: 10.2. Pft Step56: 10.3. Size Classes Step57: 11. Tracers --&gt; Ecosystem --&gt; Zooplankton Step58: 11.2. Size Classes Step59: 12. Tracers --&gt; Disolved Organic Matter Step60: 12.2. Lability Step61: 13. Tracers --&gt; Particules Step62: 13.2. Types If Prognostic Step63: 13.3. Size If Prognostic Step64: 13.4. Size If Discrete Step65: 13.5. Sinking Speed If Prognostic Step66: 14. Tracers --&gt; Dic Alkalinity Step67: 14.2. Abiotic Carbon Step68: 14.3. Alkalinity
<ASSISTANT_TASK:> Python Code: # DO NOT EDIT ! from pyesdoc.ipython.model_topic import NotebookOutput # DO NOT EDIT ! DOC = NotebookOutput('cmip6', 'bcc', 'sandbox-3', 'ocnbgchem') # 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.ocnbgchem.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.ocnbgchem.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.ocnbgchem.key_properties.model_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Geochemical" # "NPZD" # "PFT" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.elemental_stoichiometry') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Fixed" # "Variable" # "Mix of both" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.elemental_stoichiometry_details') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.prognostic_variables') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.diagnostic_variables') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.damping') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.time_stepping_framework.passive_tracers_transport.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "use ocean model transport time step" # "use specific time step" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.time_stepping_framework.passive_tracers_transport.timestep_if_not_from_ocean') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.time_stepping_framework.biology_sources_sinks.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "use ocean model transport time step" # "use specific time step" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.time_stepping_framework.biology_sources_sinks.timestep_if_not_from_ocean') # PROPERTY VALUE: # Set as follows: DOC.set_value(value) # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.transport_scheme.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Offline" # "Online" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.transport_scheme.scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Use that of ocean model" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.transport_scheme.use_different_scheme') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.boundary_forcing.atmospheric_deposition') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "from file (climatology)" # "from file (interannual variations)" # "from Atmospheric Chemistry model" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.boundary_forcing.river_input') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "from file (climatology)" # "from file (interannual variations)" # "from Land Surface model" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.boundary_forcing.sediments_from_boundary_conditions') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.boundary_forcing.sediments_from_explicit_model') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.CO2_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.CO2_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "OMIP protocol" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.O2_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.O2_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "OMIP protocol" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.DMS_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.DMS_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.N2_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.N2_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.N2O_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.N2O_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.CFC11_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.CFC11_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.CFC12_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.CFC12_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.SF6_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.SF6_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.13CO2_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.13CO2_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.14CO2_exchange_present') # 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.ocnbgchem.key_properties.gas_exchange.14CO2_exchange_type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.gas_exchange.other_gases') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.carbon_chemistry.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "OMIP protocol" # "Other protocol" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.carbon_chemistry.pH_scale') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Sea water" # "Free" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.key_properties.carbon_chemistry.constants_if_not_OMIP') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.overview') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.sulfur_cycle_present') # 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.ocnbgchem.tracers.nutrients_present') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Nitrogen (N)" # "Phosphorous (P)" # "Silicium (S)" # "Iron (Fe)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.nitrous_species_if_N') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Nitrates (NO3)" # "Amonium (NH4)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.nitrous_processes_if_N') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Dentrification" # "N fixation" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.upper_trophic_levels_definition') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.upper_trophic_levels_treatment') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.phytoplankton.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Generic" # "PFT including size based (specify both below)" # "Size based only (specify below)" # "PFT only (specify below)" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.phytoplankton.pft') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Diatoms" # "Nfixers" # "Calcifiers" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.phytoplankton.size_classes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Microphytoplankton" # "Nanophytoplankton" # "Picophytoplankton" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.zooplankton.type') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Generic" # "Size based (specify below)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.ecosystem.zooplankton.size_classes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "Microzooplankton" # "Mesozooplankton" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.disolved_organic_matter.bacteria_present') # 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.ocnbgchem.tracers.disolved_organic_matter.lability') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "None" # "Labile" # "Semi-labile" # "Refractory" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.particules.method') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Diagnostic" # "Diagnostic (Martin profile)" # "Diagnostic (Balast)" # "Prognostic" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.particules.types_if_prognostic') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "POC" # "PIC (calcite)" # "PIC (aragonite" # "BSi" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.particules.size_if_prognostic') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "No size spectrum used" # "Full size spectrum" # "Discrete size classes (specify which below)" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.particules.size_if_discrete') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.particules.sinking_speed_if_prognostic') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Constant" # "Function of particule size" # "Function of particule type (balast)" # "Other: [Please specify]" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.dic_alkalinity.carbon_isotopes') # PROPERTY VALUE(S): # Set as follows: DOC.set_value("value") # Valid Choices: # "C13" # "C14)" # TODO - please enter value(s) # PROPERTY ID - DO NOT EDIT ! DOC.set_id('cmip6.ocnbgchem.tracers.dic_alkalinity.abiotic_carbon') # 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.ocnbgchem.tracers.dic_alkalinity.alkalinity') # PROPERTY VALUE: # Set as follows: DOC.set_value("value") # Valid Choices: # "Prognostic" # "Diagnostic)" # TODO - please enter value(s) <END_TASK>