Upload 19 files

.gitattributes

@@ -1,35 +1,37 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+data/thads2011.txt filter=lfs diff=lfs merge=lfs -text
+data/thads2013n.txt filter=lfs diff=lfs merge=lfs -text

.streamlit/config.toml

@@ -0,0 +1,5 @@
+[theme]
+backgroundColor="#525252"
+secondaryBackgroundColor="#5b5b5c"
+textColor="#f3f6ff"
+font="monospace"

README.md

@@ -1,12 +1,73 @@
----
-title: Xai Final Project
-emoji: 🚀
-colorFrom: pink
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.40.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: XAI Term Project
+emoji: 👁
+colorFrom: red
+colorTo: red
+sdk: streamlit
+sdk_version: 1.40.2
+app_file: app.py
+pinned: false
+---
+
+# Explainable AI for Housing Estimates 
+
+## Instructions to Run
+1. Clone the repo
+```bash 
+git clone https://huggingface.co/spaces/keesephillips/xai_term_project
+```
+2. Install all the package dependencies
+```bash
+pip install -r requirements.txt
+```
+3. Run the application via streamlit
+```bash
+streamlit run app.py
+```
+4. Access via localhost (port 8501 on windows)
+
+## Background
+
+_This application is designed to demonstrate an understanding of how complex problems can be explained using Generalized Additive Models (GAMs) and LIME, and when used in conjunction of one another can sometimes explain the decision boundary no matter the complexity._
+
+**Generalized Additive Models**
+
+GAMs are an extension of linear regression models that allow for non-linear relationships between the features and target.
+
+GAMs use "smooth functions of our feature variables, which can take on a great many forms, with more detail on what that means in the following section" (Clarke). This is where GAMs differ from generalized linear models like linear regression. A GAM is "composed of a sum of smooth functions of features instead of or in addition to the standard linear feature contributions" (Clarke). These smooth functions or spline functions can create non-linear decision boundaries. Spline functions show the partial dependence of each feature on the target variable, enabling a high-level understanding of the model predictions.  
+
+**Local Interpretable Model-agnostic Explanations (LIME)**
+- Local - explanation should reflect the behavior of the classifier in the neighborhood of the instance being predicted
+- Interpretable - human is able to make sense of it
+- Model Agnostic - applied to any machine learning model
+- Explanation - that helps interpret the model  
+
+LIME is a powerful tool that explains some predictions created by a neural network. 
+However, LIME only explains a local area within the neural network model and does not fully explain the entire decision space of a given model. 
+This is an important consideration when using LIME, for example, you are only mapping a subset of the entire decision space of a black box model.
+    
+
+## Purpose
+
+This project aims to provide insights into Generalized Additive Models and how they can be used to create non-linear solutions.
+
+## Models
+
+- **Neural Network**: 3 linear layers using PyTorch
+- **GAM**: Linear GAM using PyGAM
+
+## Author
+
+Created by Keese Phillips
+
+## Contact
+
+For any questions or inquiries, please contact [keese.phillips@duke.edu](mailto:keese.phillips@duke.edu)
+
+## References
+
+Clark, Michael. "Generalized Additive Models." Generalized Additive Models, m-clark.github.io/generalized-additive-models/introduction.html. Accessed 2 Dec. 2024.
+
+## Attribution
+
+[Dr. Brinnae Bent](https://github.com/AIPI-590-XAI/Duke-AI-XAI)

app.py

@@ -0,0 +1,24 @@
+import streamlit as st
+from streamlit_option_menu import option_menu
+from pages import main, about
+
+if __name__ == '__main__':
+
+    st.set_page_config(page_title="Generalized Additive Models", page_icon="🚀")
+
+    page = option_menu(
+        menu_title=None,
+        options=["Home", "About"],
+        icons=["house", "book"],
+        menu_icon="cast",
+        default_index=0,
+        orientation="horizontal",
+    )
+
+    if page == "Home":
+        st.switch_page("pages/main.py")
+    elif page == "About":
+        st.switch_page("pages/about.py")
+        
+    st.info("This app is for explaining the problem domain using Generalized Additive Models")
+    

data/cal_cities_lat_long.csv

@@ -0,0 +1,460 @@
+Name,Latitude,Longitude
+Adelanto,34.582769,-117.409214
+Agoura Hills,34.153339,-118.761675
+Alameda,37.765206,-122.241636
+Albany,37.886869,-122.297747
+Alhambra,34.095286,-118.127014
+Aliso Viejo,33.575,-117.725556
+Alturas,41.487114,-120.542456
+Amador City,38.419356,-120.824103
+American Canyon,38.174917,-122.260803
+Anaheim,33.835292,-117.914503
+Anderson,40.448208,-122.297783
+Angels,38.067783,-120.538531
+Antioch,38.004922,-121.805789
+Arcadia,34.139728,-118.035344
+Arcata,40.866517,-124.082839
+Arroyo Grande,35.118586,-120.590725
+Artesia,33.865847,-118.083122
+Arvin,35.2018,-118.833106
+Atascadero,35.489417,-120.670725
+Atwater,37.347717,-120.609083
+Auburn,38.896564,-121.076889
+Avalon,33.342819,-118.328228
+Avenal,36.004122,-120.129028
+Azusa,34.133619,-117.907564
+Bakersfield,35.373292,-119.018711
+Baldwin Park,34.085286,-117.960897
+Banning,33.925572,-116.876411
+Barstow,34.895797,-117.017283
+Beaumont,33.929461,-116.977247
+Bell,33.977514,-118.187017
+Bell Gardens,33.965292,-118.151458
+Bellflower,33.881683,-118.117011
+Belmont,37.520214,-122.275800
+Belvedere,37.872703,-122.464417
+Berkeley,37.871592,-122.272747
+Beverly Hills,34.073619,-118.400356
+Big Bear Lake,34.243897,-116.911422
+Biggs,39.412389,-121.712750
+Bishop,37.363539,-118.395111
+Blue Lake,40.882908,-123.983950
+Blythe,33.617233,-114.589175
+Bradbury,34.14695,-117.970897
+Brawley,32.978658,-115.530267
+Brea,33.916681,-117.900061
+Brentwood,34.057361,-118.480511
+Brisbane,37.680767,-122.399972
+Buellton,34.613597,-120.192650
+Buena Park,33.867514,-117.998117
+Burbank,34.180839,-118.308967
+Burlingame,37.584103,-122.366083
+Calabasas,34.138333,-118.660833
+Calexico,32.678947,-115.498883
+California City,35.1258,-117.985903
+Calimesa,34.003903,-117.061975
+Calipatria,33.125597,-115.514153
+Calistoga,38.578797,-122.579706
+Camarillo,34.216394,-119.037603
+Campbell,37.287164,-121.949958
+Canyon Lake,33.685022,-117.273092
+Capitola,36.975228,-121.953292
+Carlsbad,33.158092,-117.350594
+Carmel-By-the-Sea,36.555239,-121.923289
+Carpinteria,34.398883,-119.518456
+Carson,33.831406,-118.282017
+Cathedral City,33.779742,-116.465292
+Ceres,37.594933,-120.957711
+Cerritos,33.858347,-118.064786
+Chico,39.728494,-121.837478
+Chino,34.012236,-117.688944
+Chino Hills,33.989819,-117.732586
+Chowchilla,37.123,-120.260175
+Chula Vista,32.640053,-117.084197
+Citrus Heights,38.707125,-121.281061
+Claremont,34.096675,-117.719778
+Clayton,37.941033,-121.935792
+Clearlake,38.958231,-122.626372
+Cloverdale,38.805461,-123.017222
+Clovis,36.825228,-119.702919
+Coachella,33.6803,-116.173894
+Coalinga,36.139678,-120.360150
+Colfax,39.100731,-120.953275
+Colton,34.073903,-117.313656
+Colusa,39.214333,-122.009417
+Commerce,34.000569,-118.159792
+Compton,33.89585,-118.220072
+Concord,37.977978,-122.031072
+Corcoran,37.977978,-122.031072
+Corning,39.927658,-122.179156
+Corona,33.875294,-117.566439
+Coronado,32.685886,-117.183089
+Costa Mesa,33.641133,-117.918669
+Cotati,38.327778,-122.709167
+Covina,34.090008,-117.890339
+Crescent City,41.755947,-124.201747
+Cudahy,33.960569,-118.185350
+Culver City,34.021122,-118.396467
+Cupertino,37.322997,-122.032183
+Cypress,37.320531,-121.962242
+Daly City,37.687925,-122.470208
+Dana Point,33.466972,-117.698108
+Davis,38.544906,-121.740517
+Del Mar,32.959489,-117.265314
+Del Rey Oaks,36.593292,-121.834953
+Delano,35.768842,-119.247053
+Desert Hot Springs,33.961125,-116.501678
+Diamond Bar,34.028622,-117.810336
+Dinuba,36.543283,-119.387067
+Dixon,38.445464,-121.823297
+Dorris,41.967369,-121.918061
+Dos Palos,36.986058,-120.626572
+Downey,33.940014,-118.132569
+Duarte,34.13945,-117.977286
+Dublin,37.702153,-121.935792
+Dunsmuir,41.208208,-122.271953
+East Palo Alto,37.468828,-122.141075
+Eastvale,33.963056,-117.563889
+El Cajon,32.794772,-116.962528
+El Centro,32.792,-115.563050
+El Cerrito,37.916133,-122.310764
+El Monte,34.068622,-118.027567
+El Segundo,33.919181,-118.416464
+Elk Grove,38.4088,-121.371617
+Emeryville,37.831317,-122.285247
+Encinitas,33.036986,-117.291983
+Escalon,37.797428,-120.996603
+Escondido,33.119208,-117.086422
+Etna,41.456806,-122.894756
+Eureka,40.802072,-124.163672
+Exeter,36.296061,-119.142053
+Fairfield,38.249358,-122.039967
+Farmersville,36.297728,-119.206778
+Ferndale,40.576242,-124.263944
+Fillmore,34.399164,-118.918153
+Firebaugh,36.858839,-120.456008
+Folsom,38.677958,-121.176058
+Fontana,34.092233,-117.435047
+Fort Bragg,39.445722,-123.805292
+Fort Jones,41.663864,-124.252892
+Fortuna,40.598186,-124.157275
+Foster City,37.558547,-122.271078
+Fountain Valley,33.709186,-117.953669
+Fowler,36.630506,-119.678469
+Fremont,37.548269,-121.988572
+Fresno,36.746842,-119.772586
+Fullerton,33.870292,-117.925339
+Galt,38.254636,-121.299947
+Garden Grove,33.773906,-117.941447
+Gardena,33.88835,-118.308961
+Gilroy,37.005783,-121.568275
+Glendale,34.142508,-118.255075
+Glendora,34.136119,-117.865339
+Goleta,34.435828,-119.827639
+Gonzales,36.506628,-121.444381
+Grand Terrace,34.033903,-117.313653
+Grass Valley,39.219061,-121.061061
+Greenfield,36.3208,-121.243814
+Gridley,39.363778,-121.693583
+Grover Beach,35.121642,-120.621283
+Guadalupe,34.971644,-120.571836
+Gustine,37.257717,-120.998814
+Half Moon Bay,37.463553,-122.428586
+Hanford,36.32745,-119.645683
+Hawaiian Gardens,33.831403,-118.072842
+Hawthorne,33.916403,-118.352575
+Hayward,37.668819,-122.080797
+Healdsburg,38.610467,-122.869161
+Hemet,33.747519,-116.971967
+Hercules,38.017144,-122.288581
+Hermosa Beach,33.862236,-118.399519
+Hesperia,34.426389,-117.300878
+Hidden Hills,34.160283,-118.652311
+Highland,34.128344,-117.208650
+Hollister,36.852453,-121.401603
+Holtville,32.811161,-115.380264
+Hughson,37.602725,-120.866481
+Huntington Beach,33.660297,-117.999225
+Huntington Park,33.981681,-118.225072
+Huron,36.202731,-120.102917
+Imperial,32.847553,-115.569439
+Imperial Beach,32.583944,-117.113086
+Indian Wells,33.717631,-116.340756
+Indio,33.720578,-116.215561
+Industry,34.019733,-117.958675
+Inglewood,33.961681,-118.353131
+Ione,38.352692,-120.932717
+Irvine,33.683947,-117.794694
+Irwindale,34.106953,-117.935342
+Isleton,38.161861,-121.611622
+Jackson,38.348803,-120.774103
+Jurupa Valley,33.999522,-117.475397
+Kerman,36.723558,-120.059878
+King City,36.212744,-121.126028
+Kingsburg,36.513839,-119.554017
+La Cañada Flintridge,34.206817,-118.200028
+La Habra,33.931958,-117.946172
+La Habra Heights,33.960847,-117.950619
+La Mesa,32.767828,-117.023083
+La Mirada,33.917236,-118.012008
+La Palma,33.846403,-118.046731
+La Puente,34.020011,-117.949508
+La Quinta,33.646692,-116.310008
+La Verne,34.100842,-117.767836
+Lafayette,37.885758,-122.118019
+Laguna Beach,33.542247,-117.783111
+Laguna Hills,33.599722,-117.699444
+Laguna Niguel,33.522525,-117.707553
+Laguna Woods,33.6103,-117.725331
+Lake Elsinore,33.668078,-117.327261
+Lake Forest,33.646967,-117.689217
+Lakeport,39.04295,-122.915828
+Lakewood,33.853628,-118.133956
+Lancaster,34.686786,-118.154164
+Larkspur,37.934092,-122.535253
+Lathrop,37.822706,-121.276611
+Lawndale,33.887236,-118.352575
+Lemon Grove,32.742553,-117.031417
+Lemoore,36.300783,-119.782911
+Lincoln,38.891564,-121.293008
+Lindsay,36.203006,-119.088161
+Live Oak,36.983561,-121.980517
+Livermore,37.681875,-121.768008
+Livingston,37.386883,-120.723533
+Lodi,38.134147,-121.272219
+Loma Linda,34.048347,-117.261153
+Lomita,33.792239,-118.315072
+Lompoc,34.63915,-120.457942
+Long Beach,33.768322,-118.195617
+Los Alamitos,33.803072,-118.072564
+Los Altos,33.796331,-118.118119
+Los Angeles,34.052233,-118.243686
+Los Banos,37.058278,-120.849914
+Loyalton,39.676294,-120.241039
+Lynwood,33.930292,-118.211461
+Madera,36.961336,-120.060717
+Malibu,34.005008,-118.810172
+Manhattan Beach,33.884736,-118.410908
+Manteca,37.797428,-121.216053
+Maricopa,35.058858,-119.400950
+Marina,36.684403,-121.802172
+Martinez,38.019367,-122.134133
+Marysville,39.145725,-121.591356
+Maywood,33.986681,-118.185350
+McFarland,35.678011,-119.229275
+Mendota,36.753561,-120.381558
+Menifee,33.678333,-117.166944
+Menlo Park,37.453828,-122.182186
+Merced,37.302164,-120.482967
+Mill Valley,37.906036,-122.544975
+Millbrae,37.598547,-122.387194
+Milpitas,37.428272,-121.906625
+Mission Viejo,33.600022,-117.671994
+Modesto,37.639097,-120.996878
+Monrovia,34.144428,-118.001947
+Montague,41.728197,-122.527800
+Montclair,34.077511,-117.689778
+Monte Sereno,37.236333,-121.992458
+Montebello,34.016506,-118.113753
+Monterey,36.600239,-121.894675
+Monterey Park,34.062511,-118.122847
+Moorpark,34.144897,-118.268742
+Moreno Valley,33.942467,-117.229672
+Morgan Hill,37.1305,-121.654389
+Morro Bay,35.365808,-120.849900
+Mount Shasta,41.410806,-122.194575
+Mountain View,37.386053,-122.083850
+Murrieta,33.553914,-117.213922
+Napa,38.297539,-122.286864
+National City,32.678108,-117.099197
+Needles,34.848061,-114.614133
+Nevada City,39.261561,-121.016058
+Newark,37.529658,-122.040239
+Newman,37.313828,-121.020761
+Newport Beach,33.618911,-117.928947
+Norco,33.931125,-117.548661
+Norwalk,33.902236,-118.081733
+Novato,38.107419,-122.569703
+Oakdale,37.766594,-120.847153
+Oakland,37.804364,-122.271114
+Oakley,37.997422,-121.712453
+Oceanside,33.195869,-117.379483
+Ojai,34.44805,-119.242889
+Ontario,34.063344,-117.650889
+Orange,33.787794,-117.853111
+Orange Cove,36.624394,-119.313731
+Orinda,37.877147,-122.179689
+Orland,39.747381,-122.196375
+Oroville,39.513775,-121.556358
+Oxnard,34.197506,-119.177053
+Pacific Grove,36.617736,-121.916622
+Pacifica,37.613825,-122.486919
+Palm Desert,33.722244,-116.374456
+Palm Springs,33.830297,-116.545292
+Palmdale,34.579433,-118.116461
+Palo Alto,37.441883,-122.143019
+Palos Verdes Estates,33.800572,-118.390075
+Paramount,33.889461,-118.159792
+Parlier,36.611617,-119.527072
+Pasadena,34.147786,-118.144517
+Paso Robles,35.632278,-120.664186
+Patterson,37.4716,-121.129656
+Perris,33.782519,-117.228647
+Petaluma,38.232417,-122.636653
+Pico Rivera,33.983069,-118.096736
+Piedmont,37.824372,-122.231636
+Pinole,38.004367,-122.298858
+Pismo Beach,35.142753,-120.641283
+Pittsburg,38.027975,-121.884681
+Placentia,33.872236,-117.870336
+Placerville,38.729625,-120.798547
+Pleasant Hill,37.947978,-122.060797
+Pleasanton,37.662431,-121.874678
+Plymouth,38.481853,-120.844658
+Point Arena,38.908797,-123.693072
+Pomona,34.055228,-117.752306
+Port Hueneme,34.180728,-119.208158
+Porterville,36.065231,-119.016767
+Portola,39.810458,-120.469103
+Poway,32.962822,-117.035864
+Rancho Cordova,38.589072,-121.302728
+Rancho Cucamonga,34.1064,-117.593108
+Rancho Mirage,33.739744,-116.412789
+Rancho Palos Verdes,33.744461,-118.387017
+Rancho Santa Margarita,33.640856,-117.603103
+Red Bluff,40.178489,-122.235831
+Redding,40.586539,-122.391675
+Redlands,34.055569,-117.182539
+Redondo Beach,33.849183,-118.388408
+Redwood City,37.485214,-122.236356
+Reedley,36.596339,-119.450403
+Rialto,34.1064,-117.370325
+Richmond,37.935758,-122.347750
+Ridgecrest,35.622456,-117.670897
+Rio Dell,40.4993,-124.106436
+Rio Vista,38.15575,-121.691344
+Ripon,37.739453,-121.135414
+Riverbank,37.736039,-120.935489
+Riverside,33.95335,-117.396156
+Rocklin,38.790733,-121.235783
+Rohnert Park,38.339636,-122.701097
+Rolling Hills,33.756961,-118.353961
+Rolling Hills Estates,33.787794,-118.358128
+Rosemead,34.080564,-118.072847
+Roseville,38.752122,-121.288006
+Sacramento,38.581572,-121.494400
+Salinas,36.677736,-121.655500
+San Bernardino,34.108344,-117.289764
+San Bruno,37.630489,-122.411083
+San Carlos,37.507158,-122.260522
+San Clemente,33.426972,-117.611992
+San Diego,32.715328,-117.157256
+San Dimas,34.106675,-117.806725
+San Fernando,34.281947,-118.438972
+San Francisco,37.774931,-122.419417
+San Gabriel,34.096111,-118.105833
+San Jacinto,33.783908,-116.958636
+San Joaquin,36.606617,-120.189044
+San Jose,37.339386,-121.894956
+San Juan Bautista,36.845511,-121.537997
+San Juan Capistrano,33.501692,-117.662550
+San Leandro,37.724931,-122.156078
+San Luis Obispo,35.282753,-120.659617
+San Marcos,33.143372,-117.166144
+San Marino,34.121397,-118.106458
+San Mateo,37.562992,-122.325525
+San Pablo,37.962147,-122.345525
+San Rafael,37.973536,-122.531086
+San Ramon,37.779928,-121.978014
+Sand City,36.617183,-121.848286
+Sanger,36.708006,-119.555964
+Santa Ana,33.745572,-117.867833
+Santa Barbara,34.420831,-119.698189
+Santa Clara,37.354108,-121.955236
+Santa Clarita,34.391664,-118.542586
+Santa Cruz,36.974117,-122.030797
+Santa Fe Springs,33.947236,-118.085344
+Santa Maria,34.953033,-120.435719
+Santa Monica,34.019453,-118.491192
+Santa Paula,34.354167,-119.059269
+Santa Rosa,38.440467,-122.714431
+Santee,32.838383,-116.973917
+Saratoga,37.263833,-122.023014
+Sausalito,37.859094,-122.485250
+Scotts Valley,37.051061,-122.014683
+Seal Beach,33.741406,-118.104786
+Seaside,33.819361,-118.366647
+Sebastopol,38.402136,-122.823881
+Selma,36.570783,-119.612075
+Shafter,35.500514,-119.271775
+Shasta Lake,40.680428,-122.370842
+Sierra Madre,34.161672,-118.052847
+Signal Hill,33.804461,-118.167847
+Simi Valley,34.269447,-118.781483
+Solana Beach,32.991156,-117.271147
+Soledad,32.991156,-117.271147
+Solvang,34.595819,-120.137647
+Sonoma,38.291858,-122.458036
+Sonora,37.984092,-120.382139
+South El Monte,34.051956,-118.046733
+South Gate,33.954736,-118.212017
+South Lake Tahoe,38.939925,-119.977186
+South Pasadena,34.116119,-118.150350
+South San Francisco,37.654656,-122.407750
+St. Helena,38.505242,-122.470386
+Stanton,33.802517,-117.993117
+Stockton,37.957703,-121.290781
+Suisun City,38.238247,-122.040244
+Sunnyvale,37.368831,-122.036350
+Susanville,40.416283,-120.653006
+Sutter Creek,38.392967,-120.802436
+Taft,35.142467,-119.456508
+Tehachapi,35.132189,-118.448975
+Tehama,40.027103,-122.123322
+Temecula,33.493639,-117.148364
+Temple City,34.107231,-118.057847
+Thousand Oaks,34.107231,-118.057847
+Torrance,33.83585,-118.340628
+Tracy,37.73965,-121.425222
+Trinidad,41.059292,-124.143125
+Tulare,36.207728,-119.347339
+Tulelake,41.955989,-121.477492
+Turlock,37.494658,-120.846594
+Tustin,33.74585,-117.826167
+Twentynine Palms,34.135558,-116.054169
+Ukiah,39.150172,-123.207783
+Union City,37.593392,-122.043831
+Upland,34.097511,-117.648389
+Vacaville,38.356578,-121.987744
+Vallejo,38.104086,-122.256636
+Ventura,34.274639,-119.229006
+Vernon,34.003903,-118.230072
+Victorville,34.536108,-117.291158
+Villa Park,33.814461,-117.813111
+Visalia,36.330228,-119.292058
+Vista,33.200036,-117.242536
+Walnut,34.020289,-117.865339
+Walnut Creek,37.910078,-122.065183
+Wasco,35.594125,-119.340947
+Waterford,37.641319,-120.760483
+Watsonville,36.910231,-121.756894
+Weed,41.42265,-122.386128
+West Covina,34.068622,-117.938953
+West Hollywood,34.090008,-118.361744
+West Sacramento,38.580461,-121.530233
+Westlake Village,34.145839,-118.805647
+Westminster,33.751342,-117.993992
+Westmorland,33.037267,-115.621383
+Wheatland,39.009894,-121.423014
+Whittier,33.979178,-118.032844
+Wildomar,33.598914,-117.280036
+Williams,39.154614,-122.149419
+Willits,39.409608,-123.355567
+Willows,39.524325,-122.193592
+Winters,38.524906,-121.970803
+Woodlake,36.413561,-119.098717
+Woodland,38.678517,-121.773297
+Yorba Linda,33.888625,-117.813111
+Yreka,41.735419,-122.634472
+Yuba City,39.140447,-121.616911
+Yucaipa,34.033625,-117.043086

data/cal_populations_city.csv

@@ -0,0 +1,457 @@
+County,City,Incorportation_date,pop_april_1980,pop_april_1990,pop_april_2000,pop_april_2010
+San Bernardino,Adelanto,1970,2164,8517,18130,31765
+Los Angeles,Agoura Hills,1982,,20390,20537,20330
+Alameda,Alameda,1854,63852,76459,72259,73812
+Alameda,Albany,1908,15130,16327,16444,18539
+Los Angeles,Alhambra,1903,64767,82106,85804,83089
+Modoc,Alturas,1901,3025,3231,2892,2827
+Amador,Amador City,1915,136,196,196,185
+Orange,Anaheim,1876,219494,266406,328014,336265
+Shasta,Anderson,1956,7381,8299,9022,9932
+Calaveras,Angels,1912,2302,2409,3004,3836
+Contra Costa,Antioch,1872,42683,62195,90532,102372
+San Bernardino,Apple Valley,1988,,46079,54239,69135
+Los Angeles,Arcadia,1903,45993,48290,53054,56364
+Humboldt,Arcata,1858,12850,15197,16651,17231
+San Luis Obispo,Arroyo Grande,1911,11290,14378,15851,17252
+Los Angeles,Artesia,1959,14301,15464,16380,16522
+Kern,Arvin,1960,6863,9286,12956,19304
+San Luis Obispo,Atascadero,1979,16232,23138,26411,28310
+San Mateo,Atherton,1923,7797,7163,7194,6914
+Merced,Atwater,1922,17530,22282,23113,28168
+Placer,Auburn,1888,7540,10592,12462,13330
+Los Angeles,Avalon,1913,2022,2918,3127,3728
+Kings,Avenal,1979,4137,9770,14674,15505
+Los Angeles,Azusa,1898,29380,41333,44712,46361
+Kern,Bakersfield,1873,105611,174820,246889,347483
+Los Angeles,Baldwin Park,1956,50554,69330,75837,75390
+Riverside,Banning,1913,14020,20570,23562,29603
+San Bernardino,Barstow,1947,17690,21472,21119,22639
+Riverside,Beaumont,1912,6818,9685,11384,36877
+Los Angeles,Bell,1927,25450,34365,36664,35477
+Los Angeles,Bell Gardens,1961,34117,42355,44054,42072
+Los Angeles,Bellflower,1957,53441,61815,72878,76616
+San Mateo,Belmont,1926,24505,24127,25123,25835
+Marin,Belvedere,1896,2401,2147,2125,2068
+Solano,Benicia,1850,15376,24437,26865,26997
+Alameda,Berkeley,1878,103328,102724,102743,112580
+Los Angeles,Beverly Hills,1914,32646,31971,33784,34109
+San Bernardino,Big Bear Lake,1980,,5351,5438,5019
+Butte,Biggs,1903,1413,1581,1793,1707
+Inyo,Bishop,1903,3333,3475,3575,3879
+Humboldt,Blue Lake,1910,1201,1235,1135,1253
+Riverside,Blythe,1916,6805,8428,20463,20817
+Los Angeles,Bradbury,1957,846,829,855,1048
+Imperial,Brawley,1908,14946,18923,22052,24953
+Orange,Brea,1917,27913,32873,35410,39282
+Contra Costa,Brentwood,1948,4434,7563,23302,51481
+San Mateo,Brisbane,1961,2969,2952,3597,4282
+Orange,Buena Park,1953,64165,68784,78282,80530
+Los Angeles,Burbank,1911,84625,93643,100316,103340
+San Mateo,Burlingame,1908,26173,26801,28158,28806
+Imperial,Calexico,1908,14412,18633,27109,38572
+Kern,California City,1965,2743,5955,8385,14120
+Imperial,Calipatria,1919,2636,2690,7289,7705
+Napa,Calistoga,1886,3879,4468,5190,5155
+Ventura,Camarillo,1964,37797,52303,57077,65201
+Santa Clara,Campbell,1952,26910,36048,38138,39349
+Santa Cruz,Capitola,1949,9095,10171,10033,9918
+San Diego,Carlsbad,1952,35490,63126,78247,105328
+Monterey,Carmel-By-The-Sea,1916,4707,4239,4081,3722
+Santa Barbara,Carpinteria,1965,10835,13747,14194,13040
+Los Angeles,Carson,1968,81221,83995,89730,91714
+Riverside,Cathedral City,1981,,30085,42647,51200
+Stanislaus,Ceres,1918,13281,26314,34609,45417
+Los Angeles,Cerritos,1956,53020,53240,51488,49041
+Butte,Chico,1872,26716,40079,60516,86187
+San Bernardino,Chino,1910,40165,59682,67168,77983
+Madera,Chowchilla,1923,5122,5930,14416,18720
+San Diego,Chula Vista,1911,35490,63126,173556,243916
+Los Angeles,Claremont,1907,31028,32503,33998,34926
+Contra Costa,Clayton,1964,4325,7317,10762,10897
+Sonoma,Cloverdale,1872,3989,4924,6831,8618
+Fresno,Clovis,1912,33021,50323,68468,95631
+Riverside,Coachella,1946,9129,16896,22724,40704
+Fresno,Coalinga,1906,6593,8212,16213,13380
+Placer,Colfax,1910,981,1306,1496,1963
+San Mateo,Colma,1924,395,1103,1187,1792
+San Bernardino,Colton,1887,21310,40213,47662,52154
+Colusa,Colusa,1868,4075,4934,5402,5971
+Los Angeles,Commerce,1960,10509,12135,12568,12823
+Los Angeles,Compton,1888,81347,90454,93493,96455
+Contra Costa,Concord,1905,103763,111348,121780,122067
+Kings,Corcoran,1914,6454,13364,20835,24813
+Tehama,Corning,1907,4745,5870,6741,7663
+Riverside,Corona,1896,37791,76095,124966,152374
+San Diego,Coronado,1890,18790,26540,24100,18912
+Marin,Corte Madera,1916,8074,8272,9100,9253
+Orange,Costa Mesa,1953,82562,96357,108724,109960
+Sonoma,Cotati,1963,3346,5714,6471,7265
+Los Angeles,Covina,1901,32746,43207,46837,47796
+Del Norte,Crescent City,1854,3075,4380,7347,7643
+Los Angeles,Cudahy,1960,18275,22817,24208,23805
+Los Angeles,Culver City,1917,38139,38793,38816,38883
+Santa Clara,Cupertino,1955,34297,40263,50546,58302
+Orange,Cypress,1956,40738,42655,46229,47802
+San Mateo,Daly City,1911,78427,92311,103625,101123
+Orange,Dana Point,1989,,31896,35110,33351
+Contra Costa,Danville,1982,26446,31306,41715,42039
+Yolo,Davis,1917,36640,46209,60308,65622
+San Diego,Del Mar,1959,5017,4860,4389,4161
+Monterey,Del Rey Oaks,1953,1557,1661,1650,1624
+Kern,Delano,1915,16491,22762,39489,53041
+Riverside,Desert Hot Springs,1963,5941,11668,16582,25938
+Los Angeles,Diamond Bar,1989,,53672,56287,55544
+Tulare,Dinuba,1906,9907,12743,16844,21453
+Solano,Dixon,1878,7541,10401,16103,18351
+Siskiyou,Dorris,1908,836,892,886,939
+Merced,Dos Palos,1935,3121,4196,4581,4950
+Los Angeles,Downey,1956,82602,91444,107323,111772
+Los Angeles,Duarte,1957,16766,20688,21486,21321
+Alameda,Dublin,1982,13496,23229,29973,46036
+Siskiyou,Dunsmuir,1909,2253,2129,1923,1650
+San Mateo,East Palo Alto,1983,,23451,29506,28155
+San Diego,El Cajon,1912,73892,88693,94869,99478
+Imperial,El Centro,1908,23996,31384,37835,42598
+Contra Costa,El Cerrito,1917,22731,22869,23171,23549
+Los Angeles,El Monte,1912,79494,106209,115965,113475
+Los Angeles,El Segundo,1917,13752,15223,16033,16654
+Alameda,Emeryville,1896,3714,5740,6882,10080
+San Diego,Encinitas,1986,,55386,58014,59518
+San Joaquin,Escalon,1957,3127,4437,5963,7132
+San Diego,Escondido,1888,64355,108635,133559,143911
+Siskiyou,Etna,1878,754,835,781,737
+Humboldt,Eureka,1856,24153,27025,26128,27191
+Tulare,Exeter,1911,5606,7276,9168,10334
+Marin,Fairfax,1931,7391,6931,7319,7441
+Solano,Fairfield,1903,58099,77211,96178,105321
+Tulare,Farmersville,1960,5544,6235,8737,10588
+Humboldt,Ferndale,1893,1367,1331,1382,1371
+Ventura,Fillmore,1914,9602,11992,13643,15002
+Fresno,Firebaugh,1914,3740,4429,5743,7549
+Sacramento,Folsom,1946,11003,29802,51884,72203
+San Bernardino,Fontana,1952,36991,87535,128929,196069
+Mendocino,Fort Bragg,1889,5019,6078,6814,7273
+Siskiyou,Fort Jones,1872,544,639,660,839
+Humboldt,Fortuna,1906,7591,8788,10497,11926
+San Mateo,Foster City,1971,23287,28176,28803,30567
+Orange,Fountain Valley,1957,55080,53691,54978,55313
+Fresno,Fowler,1908,2496,3208,3979,5570
+Alameda,Fremont,1956,131945,173339,203413,214089
+Fresno,Fresno,1885,217129,354202,427652,494665
+Orange,Fullerton,1904,102246,114144,126003,135161
+Sacramento,Galt,1946,5514,8889,19472,23647
+Orange,Garden Grove,1956,123307,143050,165196,170883
+Los Angeles,Gardena,1930,45165,49847,57746,58829
+Santa Clara,Gilroy,1870,25769,26303,41464,48821
+Los Angeles,Glendale,1906,139060,180038,194973,191719
+Los Angeles,Glendora,1911,38500,47828,49415,50073
+Monterey,Gonzales,1947,2891,4660,7564,8187
+San Bernardino,Grand Terrace,1978,8498,10946,11626,12040
+Nevada,Grass Valley,1893,6697,9048,10922,12860
+Monterey,Greenfield,1947,4181,7464,12648,16330
+Butte,Gridley,1905,3982,4631,5382,6584
+San Luis Obispo,Grover Beach,1959,8827,11656,13067,13156
+Santa Barbara,Guadalupe,1946,3629,5479,5659,7080
+Merced,Gustine,1915,3142,3931,4698,5520
+San Mateo,Half Moon Bay,1959,7282,8886,11842,11324
+Kings,Hanford,1891,20958,30897,41686,53967
+Los Angeles,Hawaiian Gardens,1964,10548,13639,14779,14254
+Los Angeles,Hawthorne,1922,56437,71349,84112,84293
+Alameda,Hayward,1876,94342,111498,140030,144186
+Sonoma,Healdsburg,1867,7217,9469,10722,11254
+Riverside,Hemet,1910,22454,36094,58812,78657
+Contra Costa,Hercules,1900,5963,16829,19488,24060
+Los Angeles,Hermosa Beach,1907,18070,18219,18566,19506
+San Bernardino,Hesperia,1988,,50418,62582,90173
+Los Angeles,Hidden Hills,1961,1760,1729,1875,1856
+San Bernardino,Highland,1987,,34439,44605,53104
+San Mateo,Hillsborough,1910,10372,10667,10825,10825
+San Benito,Hollister,1872,11488,19212,34413,34928
+Imperial,Holtville,1908,4399,4820,5612,5939
+Stanislaus,Hughson,1972,2943,3259,3980,6640
+Orange,Huntington Beach,1909,170505,181519,189594,189992
+Los Angeles,Huntington Park,1906,45932,56065,61348,58114
+Fresno,Huron,1951,2768,4766,6306,6754
+Imperial,Imperial,1904,3451,4113,7560,14758
+San Diego,Imperial Beach,1956,22689,26512,26992,26324
+Riverside,Indian Wells,1967,1394,2647,3816,4958
+Riverside,Indio,1930,21611,36793,49116,76036
+Los Angeles,Industry,1957,412,631,777,219
+Los Angeles,Inglewood,1908,94162,109602,112580,109673
+Amador,Ione,1953,2207,6516,7129,7918
+Orange,Irvine,1971,62134,110330,143072,212375
+Los Angeles,Irwindale,1957,1030,1050,1446,1422
+Sacramento,Isleton,1923,914,833,828,804
+Amador,Jackson,1905,2331,3545,3989,4651
+Fresno,Kerman,1946,4002,5448,8551,13544
+Monterey,King City,1911,5495,7634,11204,12874
+Fresno,Kingsburg,1908,5115,7205,9199,11382
+Los Angeles,La Cañada Flintridge,1976,20153,19378,20318,20246
+Orange,La Habra,1925,45232,51266,58974,60239
+Los Angeles,La Habra Heights,1978,4786,6226,5712,5325
+San Diego,La Mesa,1912,50308,52931,54749,57065
+Los Angeles,La Mirada,1960,40986,40452,46783,48527
+Orange,La Palma,1955,15399,15392,15408,15568
+Los Angeles,La Puente,1956,30882,36955,41063,39816
+Riverside,La Quinta,1982,,11215,23694,37467
+Los Angeles,La Verne,1906,23508,30897,31638,31063
+Contra Costa,Lafayette,1968,20837,23501,23908,23893
+Orange,Laguna Beach,1927,17858,23170,23727,22723
+Orange,Laguna Niguel,1989,,44400,61891,62979
+Riverside,Lake Elsinore,1888,5982,18285,28928,51821
+Lake,Lakeport,1888,3675,4390,4820,4753
+Los Angeles,Lakewood,1954,74654,73557,79345,80048
+Los Angeles,Lancaster,1977,48027,97291,118718,156633
+Marin,Larkspur,1908,11064,11070,12014,11926
+San Joaquin,Lathrop,1989,,6841,10445,18023
+Los Angeles,Lawndale,1959,23460,27331,31711,32769
+San Diego,Lemon Grove,1977,20780,23984,24918,25320
+Kings,Lemoore,1900,8832,13622,19712,24531
+Placer,Lincoln,1890,4132,7248,11205,42819
+Tulare,Lindsay,1910,6936,8338,10297,11768
+Sutter,Live Oak,1947,3103,4320,6229,8392
+Alameda,Livermore,1876,48349,56741,73345,80968
+Merced,Livingston,1922,5326,7317,10473,13058
+San Joaquin,Lodi,1906,35221,51874,56999,62134
+San Bernardino,Loma Linda,1970,10694,17400,18681,23261
+Los Angeles,Lomita,1964,18807,19382,20046,20256
+Santa Barbara,Lompoc,1888,26267,37649,41103,42434
+Los Angeles,Long Beach,"i. 1888/ d.1896/ 
+ri. 1897",361355,429433,461522,462257
+Placer,Loomis,1984,,5705,6260,6430
+Orange,Los Alamitos,1960,11529,11676,11536,11449
+Santa Clara,Los Altos,1952,25769,26303,27693,28976
+Santa Clara,Los Altos Hills,1956,7421,7514,7902,7922
+Los Angeles,Los Angeles,1850,2968579,3485398,3694742,3792621
+Merced,Los Banos,1907,10341,14519,25869,35972
+Santa Clara,Los Gatos,1887,26906,27357,28592,29413
+Sierra,Loyalton,1901,1030,931,862,769
+Los Angeles,Lynwood,1921,48409,61945,69845,69772
+Madera,Madera,1907,21732,29281,43207,61416
+Mono,Mammoth Lakes,1984,3929,4785,7093,8234
+Los Angeles,Manhattan Beach,1912,31542,32063,33852,35135
+San Joaquin,Manteca,1918,24925,40773,49258,67096
+Kern,Maricopa,1911,946,1193,1111,1154
+Monterey,Marina,1975,20647,26436,18925,19718
+Contra Costa,Martinez,1876,22582,31808,35866,35824
+Yuba,Marysville,1851,9898,12324,12268,12072
+Los Angeles,Maywood,1924,21810,27850,28083,27395
+Kern,McFarland,1957,5151,7005,9837,12707
+Fresno,Mendota,1942,5038,6821,7890,11014
+San Mateo,Menlo Park,1927,26438,28040,30785,32026
+Merced,Merced,1889,36499,56216,63893,78958
+Marin,Mill Valley,1900,12967,13038,13600,13903
+San Mateo,Millbrae,1948,20058,20412,20718,21532
+Santa Clara,Milpitas,1954,37820,50686,62698,66790
+Orange,Mission Viejo,1988,,72820,93102,93305
+Stanislaus,Modesto,1884,106963,164730,188856,201165
+Los Angeles,Monrovia,1887,30531,35761,36929,36590
+Siskiyou,Montague,1909,1285,1415,1456,1443
+San Bernardino,Montclair,1956,22628,28434,33049,36664
+Santa Clara,Monte Sereno,1957,3434,3287,3483,3341
+Los Angeles,Montebello,1920,52929,59564,62150,62500
+Monterey,Monterey,1890,27558,31954,29696,27810
+Los Angeles,Monterey Park,1916,54338,60738,60051,60269
+Ventura,Moorpark,1983,,25494,31415,34421
+Contra Costa,Moraga,1974,15014,15852,16290,16016
+Riverside,Moreno Valley,1984,,118779,142381,193365
+Santa Clara,Morgan Hill,1906,17060,23928,33556,37882
+San Luis Obispo,Morro Bay,1964,9064,9664,10350,10234
+Siskiyou,Mount Shasta,1905,2837,3460,3621,3394
+Santa Clara,Mountain View,1902,58655,67460,70708,74066
+Napa,Napa,1872,50879,61842,72585,76915
+San Diego,National City,1887,48772,54249,54260,58582
+San Bernardino,Needles,1913,4120,5191,4830,4844
+Nevada,Nevada City,1856,2431,2855,3001,3068
+Alameda,Newark,1955,32126,37861,42471,42573
+Stanislaus,Newman,1908,2785,4151,7093,10224
+Orange,Newport Beach,1906,62556,66643,70032,85186
+Riverside,Norco,1964,19732,23302,24157,27063
+Los Angeles,Norwalk,1957,84901,94279,104323,105549
+Marin,Novato,1960,43916,47585,47630,51904
+Stanislaus,Oakdale,1906,8474,11961,15503,20675
+Alameda,Oakland,1852,339337,372242,399484,390724
+San Diego,Oceanside,1888,76698,128398,161029,167086
+Ventura,Ojai,1921,6816,7613,7862,7461
+San Bernardino,Ontario,1891,88820,133179,158007,163924
+Orange,Orange,1888,91450,110658,128868,136416
+Fresno,Orange Cove,1948,4026,5604,7722,9078
+Contra Costa,Orinda,1985,,16642,17599,17643
+Glenn,Orland,1909,4031,5052,6281,7291
+Butte,Oroville,1906,8693,11960,13004,15546
+Ventura,Oxnard,1903,108195,142216,170358,197899
+Monterey,Pacific Grove,1889,15755,16117,15522,15041
+San Mateo,Pacifica,1957,36866,37670,38390,37234
+Riverside,Palm Desert,1973,11801,23252,41155,48445
+Riverside,Palm Springs,1938,32359,40181,42807,44552
+Los Angeles,Palmdale,1962,12277,68842,116670,152750
+Santa Clara,Palo Alto,1894,55225,55900,58598,64403
+Los Angeles,Palos Verdes Estates,1939,14376,13512,13340,13438
+Butte,Paradise,1979,22571,25408,26408,26218
+Los Angeles,Paramount,1957,36407,47669,55266,54098
+Fresno,Parlier,1921,2902,7938,11145,14494
+Los Angeles,Pasadena,1886,118072,131591,133936,137122
+San Luis Obispo,Paso Robles,1889,9163,18583,24297,29793
+Stanislaus,Patterson,1919,3908,8626,11606,20413
+Riverside,Perris,1911,6827,21460,36189,68386
+Sonoma,Petaluma,1858,33834,43184,54548,57941
+Los Angeles,Pico Rivera,1958,53387,59177,63428,62942
+Alameda,Piedmont,1907,10498,10602,10952,10667
+Contra Costa,Pinole,1903,14253,17460,19039,18390
+San Luis Obispo,Pismo Beach,1939,5364,7669,8551,7655
+Contra Costa,Pittsburg,1903,33465,47564,56769,63264
+Orange,Placentia,1926,35041,41259,46488,50533
+El Dorado,Placerville,1854,6739,8355,9610,10389
+Contra Costa,Pleasant Hill,1961,25547,31585,32837,33152
+Alameda,Pleasanton,1894,35160,50553,63654,70285
+Amador,Plymouth,1917,699,811,980,1005
+Mendocino,Point Arena,1908,425,407,474,449
+Los Angeles,Pomona,1888,92742,131723,149473,149058
+Ventura,Port Hueneme,1948,17803,20319,21845,21723
+Tulare,Porterville,1902,19707,29563,39615,54165
+Plumas,Portola,1946,1885,2193,2227,2104
+San Mateo,Portola Valley,1964,3939,4194,4462,4353
+San Diego,Poway,1980,,43516,48044,47811
+San Bernardino,Rancho Cucamonga,1977,55250,101409,127743,165269
+Riverside,Rancho Mirage,1973,6281,9778,13249,17218
+Los Angeles,Rancho Palos Verdes,1973,36577,41659,41145,41643
+Tehama,Red Bluff,1876,9490,12363,13147,14076
+Shasta,Redding,1887,41995,66462,80865,89861
+San Bernardino,Redlands,1888,43619,60394,63591,68747
+Los Angeles,Redondo Beach,1892,57102,60167,63261,66748
+San Mateo,Redwood City,1867,54951,66072,75402,76815
+Fresno,Reedley,1913,11071,15791,20756,24194
+San Bernardino,Rialto,1911,37862,72388,91873,99171
+Contra Costa,Richmond,1905,74676,87425,99216,103701
+Kern,Ridgecrest,1963,15929,27725,24927,27616
+Humboldt,Rio Dell,1965,2687,3012,3174,3368
+Solano,Rio Vista,1894,3142,3316,4571,7360
+San Joaquin,Ripon,1945,3509,7455,10146,14297
+Stanislaus,Riverbank,1922,5695,8547,15826,22678
+Riverside,Riverside,1883,170591,226505,255166,303871
+Placer,Rocklin,1893,7344,19033,36330,56974
+Sonoma,Rohnert Park,1962,22965,36326,42236,40971
+Los Angeles,Rolling Hills,1957,2049,1871,1871,1860
+Los Angeles,Rolling Hills Estates,1957,7701,7789,7676,8067
+Los Angeles,Rosemead,1959,42604,51638,53505,53764
+Placer,Roseville,1909,24347,44685,79921,118788
+Marin,Ross,1908,2801,2123,2329,2415
+Sacramento,Sacramento,1850,275741,369365,407018,466488
+Monterey,Salinas,1874,80479,108777,142685,150441
+Marin,San Anselmo,1907,12067,11743,12378,12336
+San Bernardino,San Bernardino,1869,118794,164164,185401,209924
+San Mateo,San Bruno,1914,35417,38961,40165,41114
+San Mateo,San Carlos,1925,24710,26167,27718,28406
+Orange,San Clemente,1928,27325,41100,49936,63522
+San Diego,San Diego,1850,875538,1110549,1223400,1307402
+Los Angeles,San Dimas,1960,24014,32397,34980,33371
+Los Angeles,San Fernando,1911,17731,22580,23564,23645
+San Francisco,San Francisco,1850,678974,723959,776733,805235
+Los Angeles,San Gabriel,1913,30072,37120,39804,39718
+Riverside,San Jacinto,1888,7098,16210,23779,44199
+Fresno,San Joaquin,1920,1930,2311,3270,4001
+Santa Clara,San Jose,1850,629531,782248,894943,945942
+San Benito,San Juan Bautista,1869,1276,1570,1549,1862
+Orange,San Juan Capistrano,1961,18959,26183,33826,34593
+Alameda,San Leandro,1872,63952,68223,79452,84950
+San Luis Obispo,San Luis Obispo,1856,34252,41958,44174,45119
+San Diego,San Marcos,1963,17479,38974,54977,83781
+Los Angeles,San Marino,1913,13307,12959,12945,13147
+San Mateo,San Mateo,1894,77640,85486,92482,97207
+Contra Costa,San Pablo,1948,19750,25158,30215,29139
+Marin,San Rafael,1874,44700,48404,56063,57713
+Contra Costa,San Ramon,1983,,35303,44722,72148
+Monterey,Sand City,1960,182,192,261,334
+Fresno,Sanger,1911,12542,16839,18931,24270
+Orange,Santa Ana,1886,204023,293742,337977,324528
+Santa Barbara,Santa Barbara,1850,74414,85571,89600,88410
+Santa Clara,Santa Clara,1852,87700,93613,102361,116468
+Los Angeles,Santa Clarita,1987,,110642,151088,176320
+Santa Cruz,Santa Cruz,1866,41483,49040,54593,59946
+Los Angeles,Santa Fe Springs,1957,14520,15520,16413,16223
+Santa Barbara,Santa Maria,1905,39685,61284,77423,99553
+Los Angeles,Santa Monica,1886,88314,86905,84084,89736
+Ventura,Santa Paula,1902,20658,25062,28598,29321
+Sonoma,Santa Rosa,1868,82658,113313,147595,167815
+San Diego,Santee,1980,,52902,52975,53413
+Santa Clara,Saratoga,1956,29261,28061,29843,29926
+Marin,Sausalito,1893,7338,7152,7330,7061
+Santa Cruz,Scotts Valley,1966,6891,8615,11385,11580
+Orange,Seal Beach,1915,25975,25098,24157,24168
+Monterey,Seaside,1954,36567,38901,33097,33025
+Sonoma,Sebastopol,1902,5595,7004,7774,7379
+Fresno,Selma,1893,10942,14757,19444,23219
+Kern,Shafter,1938,7010,8409,12736,16988
+Los Angeles,Sierra Madre,1907,10837,10762,10578,10917
+Los Angeles,Signal Hill,1924,5734,8371,9333,11016
+Ventura,Simi Valley,1969,77500,100217,111351,124237
+San Diego,Solana Beach,1986,,12962,12979,12867
+Monterey,Soledad,1921,3091,7146,23015,25738
+Santa Barbara,Solvang,1985,,4741,5332,5245
+Sonoma,Sonoma,1883,6054,8121,9128,10648
+Tuolumne,Sonora,1851,3247,4153,4423,4903
+Los Angeles,South El Monte,1958,16623,20850,21144,20116
+Los Angeles,South Gate,1923,66784,86284,96375,94396
+El Dorado,South Lake Tahoe,1965,20681,21586,23609,21403
+Los Angeles,South Pasadena,1888,22681,23936,24292,25619
+San Mateo,South San Francisco,1908,49393,54312,60552,63632
+Napa,St. Helena,1876,4898,4990,5950,5814
+Orange,Stanton,1911,23723,30491,37403,38186
+San Joaquin,Stockton,1850,148283,210943,243771,291707
+Solano,Suisun City,1868,11087,22686,26118,28111
+Santa Clara,Sunnyvale,1912,106618,117229,131760,140081
+Lassen,Susanville,1900,6520,7279,17428,17947
+Amador,Sutter Creek,1913,1705,1835,2303,2501
+Kern,Taft,1910,5316,5902,8811,9327
+Kern,Tehachapi,1909,4126,5791,11125,14414
+Tehama,Tehama,1906,365,401,432,418
+Riverside,Temecula,1989,,27099,57716,100097
+Los Angeles,Temple City,1960,28972,31100,33377,35558
+Ventura,Thousand Oaks,1964,77072,104352,117005,126683
+Marin,Tiburon,1964,6685,7532,8666,8962
+Los Angeles,Torrance,1921,129881,133107,137946,145438
+San Joaquin,Tracy,1910,18428,33558,56929,82922
+Humboldt,Trinidad,1870,379,362,311,367
+Tulare,Tulare,1888,22530,33249,43994,59278
+Siskiyou,Tulelake,1937,783,1010,1020,1010
+Stanislaus,Turlock,1908,26287,42198,55810,68549
+Orange,Tustin,1927,32256,50689,67504,75540
+San Bernardino,Twentynine Palms,1987,,11821,14764,25048
+Mendocino,Ukiah,1876,12035,14599,15497,16075
+Alameda,Union City,1959,39406,53762,66869,69516
+San Bernardino,Upland,1906,47647,63374,68393,73732
+Solano,Vacaville,1892,43367,71479,88625,92428
+Solano,Vallejo,1868,80303,109199,116760,115942
+Ventura,Ventura,1866,73774,92575,100916,106433
+Los Angeles,Vernon,1905,90,152,91,112
+San Bernardino,Victorville,1962,14220,40674,64029,115903
+Orange,Villa Park,1962,7137,6299,5952,5812
+Tulare,Visalia,1874,49729,75636,91877,124442
+San Diego,Vista,1963,35834,71872,89857,93834
+Los Angeles,Walnut,1959,12478,29105,30004,29172
+Contra Costa,Walnut Creek,1914,53490,60569,64296,64173
+Kern,Wasco,1945,9613,12412,21263,25545
+Stanislaus,Waterford,1969,2683,4771,6924,8456
+Santa Cruz,Watsonville,1868,23662,31099,44265,51199
+Siskiyou,Weed,1961,2879,3062,2978,2967
+Los Angeles,West Covina,1923,81292,96086,105080,106098
+Los Angeles,West Hollywood,1984,,36118,35794,34399
+Yolo,West Sacramento,1987,,28898,31615,48744
+Los Angeles,Westlake Village,1981,,7455,8368,8270
+Orange,Westminster,1957,71133,78118,88207,89701
+Imperial,Westmorland,1934,1590,1380,2131,2225
+Yuba,Wheatland,1874,1474,1631,2275,3456
+Los Angeles,Whittier,1898,68558,77671,83680,85331
+Colusa,Williams,1920,1658,2297,3670,5123
+Mendocino,Willits,1888,4008,5027,5073,4888
+Glenn,Willows,1886,4777,5988,6220,6166
+Yolo,Winters,1898,2652,4639,6125,6624
+Tulare,Woodlake,1941,4343,5678,6651,7279
+Yolo,Woodland,1871,30235,39802,49151,55468
+San Mateo,Woodside,1956,5291,5035,5352,5287
+Orange,Yorba Linda,1967,28254,52422,58918,64234
+Napa,Yountville,1965,2893,3259,3297,2933
+Siskiyou,Yreka,1857,5916,6948,7290,7765
+Sutter,Yuba City,1908,18736,27437,36758,64925
+San Bernardino,Yucaipa,1989,,32824,41207,51367

data/california_cities.csv

@@ -0,0 +1,436 @@
+,Latitude,Longitude,County,City,Incorportation_date,pop_april_1980,pop_april_1990,pop_april_2000,pop_april_2010
+0,34.582769,-117.40921399999999,San Bernardino,Adelanto,1970,2164.0,8517,18130,31765
+1,34.153339,-118.761675,Los Angeles,Agoura Hills,1982,20390,20390,20537,20330
+2,37.765206,-122.24163600000001,Alameda,Alameda,1854,63852.0,76459,72259,73812
+3,37.886869,-122.297747,Alameda,Albany,1908,15130.0,16327,16444,18539
+4,34.095286,-118.12701399999999,Los Angeles,Alhambra,1903,64767.0,82106,85804,83089
+5,41.487114,-120.542456,Modoc,Alturas,1901,3025.0,3231,2892,2827
+6,38.419356,-120.82410300000001,Amador,Amador City,1915,136.0,196,196,185
+7,33.835291999999995,-117.914503,Orange,Anaheim,1876,219494.0,266406,328014,336265
+8,40.448208,-122.29778300000001,Shasta,Anderson,1956,7381.0,8299,9022,9932
+9,38.067783,-120.538531,Calaveras,Angels,1912,2302.0,2409,3004,3836
+10,38.004922,-121.80578899999999,Contra Costa,Antioch,1872,42683.0,62195,90532,102372
+11,34.139728000000005,-118.035344,Los Angeles,Arcadia,1903,45993.0,48290,53054,56364
+12,40.866517,-124.08283899999999,Humboldt,Arcata,1858,12850.0,15197,16651,17231
+13,35.118586,-120.590725,San Luis Obispo,Arroyo Grande,1911,11290.0,14378,15851,17252
+14,33.865846999999995,-118.083122,Los Angeles,Artesia,1959,14301.0,15464,16380,16522
+15,35.2018,-118.833106,Kern,Arvin,1960,6863.0,9286,12956,19304
+16,35.489416999999996,-120.670725,San Luis Obispo,Atascadero,1979,16232.0,23138,26411,28310
+17,37.347716999999996,-120.60908300000001,Merced,Atwater,1922,17530.0,22282,23113,28168
+18,38.896564,-121.076889,Placer,Auburn,1888,7540.0,10592,12462,13330
+19,33.342819,-118.328228,Los Angeles,Avalon,1913,2022.0,2918,3127,3728
+20,36.004121999999995,-120.129028,Kings,Avenal,1979,4137.0,9770,14674,15505
+21,34.133619,-117.907564,Los Angeles,Azusa,1898,29380.0,41333,44712,46361
+22,35.373292,-119.01871100000001,Kern,Bakersfield,1873,105611.0,174820,246889,347483
+23,34.085285999999996,-117.960897,Los Angeles,Baldwin Park,1956,50554.0,69330,75837,75390
+24,33.925571999999995,-116.876411,Riverside,Banning,1913,14020.0,20570,23562,29603
+25,34.895796999999995,-117.017283,San Bernardino,Barstow,1947,17690.0,21472,21119,22639
+26,33.929460999999996,-116.97724699999999,Riverside,Beaumont,1912,6818.0,9685,11384,36877
+27,33.977514,-118.187017,Los Angeles,Bell,1927,25450.0,34365,36664,35477
+28,33.965292,-118.151458,Los Angeles,Bell Gardens,1961,34117.0,42355,44054,42072
+29,33.881683,-118.117011,Los Angeles,Bellflower,1957,53441.0,61815,72878,76616
+30,37.520214,-122.2758,San Mateo,Belmont,1926,24505.0,24127,25123,25835
+31,37.872703,-122.464417,Marin,Belvedere,1896,2401.0,2147,2125,2068
+32,37.871592,-122.272747,Alameda,Berkeley,1878,103328.0,102724,102743,112580
+33,34.073619,-118.400356,Los Angeles,Beverly Hills,1914,32646.0,31971,33784,34109
+34,34.243897,-116.911422,San Bernardino,Big Bear Lake,1980,5351,5351,5438,5019
+35,39.412389000000005,-121.71275,Butte,Biggs,1903,1413.0,1581,1793,1707
+36,37.363539,-118.39511100000001,Inyo,Bishop,1903,3333.0,3475,3575,3879
+37,40.882908,-123.98395,Humboldt,Blue Lake,1910,1201.0,1235,1135,1253
+38,33.617233,-114.589175,Riverside,Blythe,1916,6805.0,8428,20463,20817
+39,34.14695,-117.970897,Los Angeles,Bradbury,1957,846.0,829,855,1048
+40,32.978658,-115.530267,Imperial,Brawley,1908,14946.0,18923,22052,24953
+41,33.916681,-117.90006100000001,Orange,Brea,1917,27913.0,32873,35410,39282
+42,34.057361,-118.480511,Contra Costa,Brentwood,1948,4434.0,7563,23302,51481
+43,37.680766999999996,-122.39997199999999,San Mateo,Brisbane,1961,2969.0,2952,3597,4282
+44,33.867514,-117.998117,Orange,Buena Park,1953,64165.0,68784,78282,80530
+45,34.180839,-118.308967,Los Angeles,Burbank,1911,84625.0,93643,100316,103340
+46,37.584103000000006,-122.366083,San Mateo,Burlingame,1908,26173.0,26801,28158,28806
+47,32.678946999999994,-115.498883,Imperial,Calexico,1908,14412.0,18633,27109,38572
+48,35.1258,-117.98590300000001,Kern,California City,1965,2743.0,5955,8385,14120
+49,33.125597,-115.51415300000001,Imperial,Calipatria,1919,2636.0,2690,7289,7705
+50,38.578796999999994,-122.579706,Napa,Calistoga,1886,3879.0,4468,5190,5155
+51,34.216394,-119.037603,Ventura,Camarillo,1964,37797.0,52303,57077,65201
+52,37.287164000000004,-121.94995800000001,Santa Clara,Campbell,1952,26910.0,36048,38138,39349
+53,36.975228,-121.95329199999999,Santa Cruz,Capitola,1949,9095.0,10171,10033,9918
+54,33.158091999999996,-117.350594,San Diego,Carlsbad,1952,35490.0,63126,78247,105328
+55,34.398883000000005,-119.518456,Santa Barbara,Carpinteria,1965,10835.0,13747,14194,13040
+56,33.831406,-118.282017,Los Angeles,Carson,1968,81221.0,83995,89730,91714
+57,33.779742,-116.46529199999999,Riverside,Cathedral City,1981,30085,30085,42647,51200
+58,37.594933000000005,-120.957711,Stanislaus,Ceres,1918,13281.0,26314,34609,45417
+59,33.858346999999995,-118.06478600000001,Los Angeles,Cerritos,1956,53020.0,53240,51488,49041
+60,39.728494,-121.837478,Butte,Chico,1872,26716.0,40079,60516,86187
+61,34.012236,-117.68894399999999,San Bernardino,Chino,1910,40165.0,59682,67168,77983
+62,37.123000000000005,-120.260175,Madera,Chowchilla,1923,5122.0,5930,14416,18720
+63,32.640053,-117.084197,San Diego,Chula Vista,1911,35490.0,63126,173556,243916
+64,34.096675,-117.719778,Los Angeles,Claremont,1907,31028.0,32503,33998,34926
+65,37.941033000000004,-121.93579199999999,Contra Costa,Clayton,1964,4325.0,7317,10762,10897
+66,38.805461,-123.017222,Sonoma,Cloverdale,1872,3989.0,4924,6831,8618
+67,36.825228,-119.702919,Fresno,Clovis,1912,33021.0,50323,68468,95631
+68,33.6803,-116.17389399999999,Riverside,Coachella,1946,9129.0,16896,22724,40704
+69,36.139678,-120.36015,Fresno,Coalinga,1906,6593.0,8212,16213,13380
+70,39.100731,-120.953275,Placer,Colfax,1910,981.0,1306,1496,1963
+71,34.073903,-117.31365600000001,San Bernardino,Colton,1887,21310.0,40213,47662,52154
+72,39.214333,-122.009417,Colusa,Colusa,1868,4075.0,4934,5402,5971
+73,34.000569,-118.159792,Los Angeles,Commerce,1960,10509.0,12135,12568,12823
+74,33.89585,-118.220072,Los Angeles,Compton,1888,81347.0,90454,93493,96455
+75,37.977978,-122.031072,Contra Costa,Concord,1905,103763.0,111348,121780,122067
+76,37.977978,-122.031072,Kings,Corcoran,1914,6454.0,13364,20835,24813
+77,39.927658,-122.179156,Tehama,Corning,1907,4745.0,5870,6741,7663
+78,33.875294,-117.56643899999999,Riverside,Corona,1896,37791.0,76095,124966,152374
+79,32.685885999999996,-117.183089,San Diego,Coronado,1890,18790.0,26540,24100,18912
+80,33.641133,-117.918669,Orange,Costa Mesa,1953,82562.0,96357,108724,109960
+81,38.327778,-122.709167,Sonoma,Cotati,1963,3346.0,5714,6471,7265
+82,34.090008000000005,-117.89033899999998,Los Angeles,Covina,1901,32746.0,43207,46837,47796
+83,41.755947,-124.201747,Del Norte,Crescent City,1854,3075.0,4380,7347,7643
+84,33.960569,-118.18535,Los Angeles,Cudahy,1960,18275.0,22817,24208,23805
+85,34.021122,-118.39646699999999,Los Angeles,Culver City,1917,38139.0,38793,38816,38883
+86,37.322996999999994,-122.032183,Santa Clara,Cupertino,1955,34297.0,40263,50546,58302
+87,37.320531,-121.96224199999999,Orange,Cypress,1956,40738.0,42655,46229,47802
+88,37.687925,-122.47020800000001,San Mateo,Daly City,1911,78427.0,92311,103625,101123
+89,33.466972,-117.698108,Orange,Dana Point,1989,31896,31896,35110,33351
+90,38.544906,-121.740517,Yolo,Davis,1917,36640.0,46209,60308,65622
+91,32.959489000000005,-117.26531399999999,San Diego,Del Mar,1959,5017.0,4860,4389,4161
+92,36.593292,-121.834953,Monterey,Del Rey Oaks,1953,1557.0,1661,1650,1624
+93,35.768842,-119.24705300000001,Kern,Delano,1915,16491.0,22762,39489,53041
+94,33.961125,-116.501678,Riverside,Desert Hot Springs,1963,5941.0,11668,16582,25938
+95,34.028622,-117.810336,Los Angeles,Diamond Bar,1989,53672,53672,56287,55544
+96,36.543283,-119.38706699999999,Tulare,Dinuba,1906,9907.0,12743,16844,21453
+97,38.445464,-121.823297,Solano,Dixon,1878,7541.0,10401,16103,18351
+98,41.967369,-121.91806100000001,Siskiyou,Dorris,1908,836.0,892,886,939
+99,36.986058,-120.626572,Merced,Dos Palos,1935,3121.0,4196,4581,4950
+100,33.940014,-118.13256899999999,Los Angeles,Downey,1956,82602.0,91444,107323,111772
+101,34.13945,-117.977286,Los Angeles,Duarte,1957,16766.0,20688,21486,21321
+102,37.702153,-121.93579199999999,Alameda,Dublin,1982,13496.0,23229,29973,46036
+103,41.208208,-122.271953,Siskiyou,Dunsmuir,1909,2253.0,2129,1923,1650
+104,37.468828,-122.141075,San Mateo,East Palo Alto,1983,23451,23451,29506,28155
+105,32.794771999999995,-116.962528,San Diego,El Cajon,1912,73892.0,88693,94869,99478
+106,32.792,-115.56305,Imperial,El Centro,1908,23996.0,31384,37835,42598
+107,37.916133,-122.31076399999999,Contra Costa,El Cerrito,1917,22731.0,22869,23171,23549
+108,34.068622,-118.02756699999999,Los Angeles,El Monte,1912,79494.0,106209,115965,113475
+109,33.919181,-118.41646399999999,Los Angeles,El Segundo,1917,13752.0,15223,16033,16654
+110,37.831317,-122.285247,Alameda,Emeryville,1896,3714.0,5740,6882,10080
+111,33.036986,-117.291983,San Diego,Encinitas,1986,55386,55386,58014,59518
+112,37.797428000000004,-120.99660300000001,San Joaquin,Escalon,1957,3127.0,4437,5963,7132
+113,33.119208,-117.086422,San Diego,Escondido,1888,64355.0,108635,133559,143911
+114,41.456806,-122.894756,Siskiyou,Etna,1878,754.0,835,781,737
+115,40.802071999999995,-124.16367199999999,Humboldt,Eureka,1856,24153.0,27025,26128,27191
+116,36.296061,-119.142053,Tulare,Exeter,1911,5606.0,7276,9168,10334
+117,38.249358,-122.03996699999999,Solano,Fairfield,1903,58099.0,77211,96178,105321
+118,36.297728,-119.206778,Tulare,Farmersville,1960,5544.0,6235,8737,10588
+119,40.576242,-124.263944,Humboldt,Ferndale,1893,1367.0,1331,1382,1371
+120,34.399164,-118.918153,Ventura,Fillmore,1914,9602.0,11992,13643,15002
+121,36.858839,-120.45600800000001,Fresno,Firebaugh,1914,3740.0,4429,5743,7549
+122,38.677958000000004,-121.17605800000001,Sacramento,Folsom,1946,11003.0,29802,51884,72203
+123,34.092233,-117.435047,San Bernardino,Fontana,1952,36991.0,87535,128929,196069
+124,39.445721999999996,-123.805292,Mendocino,Fort Bragg,1889,5019.0,6078,6814,7273
+125,41.663864000000004,-124.25289199999999,Siskiyou,Fort Jones,1872,544.0,639,660,839
+126,40.598186,-124.157275,Humboldt,Fortuna,1906,7591.0,8788,10497,11926
+127,37.558547,-122.271078,San Mateo,Foster City,1971,23287.0,28176,28803,30567
+128,33.709185999999995,-117.95366899999999,Orange,Fountain Valley,1957,55080.0,53691,54978,55313
+129,36.630506,-119.67846899999999,Fresno,Fowler,1908,2496.0,3208,3979,5570
+130,37.548269,-121.98857199999999,Alameda,Fremont,1956,131945.0,173339,203413,214089
+131,36.746842,-119.772586,Fresno,Fresno,1885,217129.0,354202,427652,494665
+132,33.870292,-117.925339,Orange,Fullerton,1904,102246.0,114144,126003,135161
+133,38.254636,-121.299947,Sacramento,Galt,1946,5514.0,8889,19472,23647
+134,33.773906,-117.941447,Orange,Garden Grove,1956,123307.0,143050,165196,170883
+135,33.88835,-118.30896100000001,Los Angeles,Gardena,1930,45165.0,49847,57746,58829
+136,37.005783,-121.568275,Santa Clara,Gilroy,1870,25769.0,26303,41464,48821
+137,34.142508,-118.255075,Los Angeles,Glendale,1906,139060.0,180038,194973,191719
+138,34.136119,-117.86533899999999,Los Angeles,Glendora,1911,38500.0,47828,49415,50073
+139,36.506628000000006,-121.444381,Monterey,Gonzales,1947,2891.0,4660,7564,8187
+140,34.033903,-117.313653,San Bernardino,Grand Terrace,1978,8498.0,10946,11626,12040
+141,39.219060999999996,-121.06106100000001,Nevada,Grass Valley,1893,6697.0,9048,10922,12860
+142,36.3208,-121.24381399999999,Monterey,Greenfield,1947,4181.0,7464,12648,16330
+143,39.363778,-121.693583,Butte,Gridley,1905,3982.0,4631,5382,6584
+144,35.121642,-120.621283,San Luis Obispo,Grover Beach,1959,8827.0,11656,13067,13156
+145,34.971644,-120.571836,Santa Barbara,Guadalupe,1946,3629.0,5479,5659,7080
+146,37.257717,-120.998814,Merced,Gustine,1915,3142.0,3931,4698,5520
+147,37.463553000000005,-122.42858600000001,San Mateo,Half Moon Bay,1959,7282.0,8886,11842,11324
+148,36.32745,-119.645683,Kings,Hanford,1891,20958.0,30897,41686,53967
+149,33.831403,-118.072842,Los Angeles,Hawaiian Gardens,1964,10548.0,13639,14779,14254
+150,33.916403,-118.352575,Los Angeles,Hawthorne,1922,56437.0,71349,84112,84293
+151,37.668819,-122.080797,Alameda,Hayward,1876,94342.0,111498,140030,144186
+152,38.610467,-122.869161,Sonoma,Healdsburg,1867,7217.0,9469,10722,11254
+153,33.747519,-116.97196699999999,Riverside,Hemet,1910,22454.0,36094,58812,78657
+154,38.017144,-122.28858100000001,Contra Costa,Hercules,1900,5963.0,16829,19488,24060
+155,33.862235999999996,-118.399519,Los Angeles,Hermosa Beach,1907,18070.0,18219,18566,19506
+156,34.426389,-117.300878,San Bernardino,Hesperia,1988,50418,50418,62582,90173
+157,34.160283,-118.65231100000001,Los Angeles,Hidden Hills,1961,1760.0,1729,1875,1856
+158,34.128344,-117.20865,San Bernardino,Highland,1987,34439,34439,44605,53104
+159,36.852453000000004,-121.40160300000001,San Benito,Hollister,1872,11488.0,19212,34413,34928
+160,32.811161,-115.380264,Imperial,Holtville,1908,4399.0,4820,5612,5939
+161,37.602725,-120.86648100000001,Stanislaus,Hughson,1972,2943.0,3259,3980,6640
+162,33.660297,-117.999225,Orange,Huntington Beach,1909,170505.0,181519,189594,189992
+163,33.981681,-118.225072,Los Angeles,Huntington Park,1906,45932.0,56065,61348,58114
+164,36.202731,-120.10291699999999,Fresno,Huron,1951,2768.0,4766,6306,6754
+165,32.847553000000005,-115.56943899999999,Imperial,Imperial,1904,3451.0,4113,7560,14758
+166,32.583944,-117.11308600000001,San Diego,Imperial Beach,1956,22689.0,26512,26992,26324
+167,33.717631,-116.340756,Riverside,Indian Wells,1967,1394.0,2647,3816,4958
+168,33.720578,-116.21556100000001,Riverside,Indio,1930,21611.0,36793,49116,76036
+169,34.019733,-117.958675,Los Angeles,Industry,1957,412.0,631,777,219
+170,33.961681,-118.353131,Los Angeles,Inglewood,1908,94162.0,109602,112580,109673
+171,38.352692,-120.932717,Amador,Ione,1953,2207.0,6516,7129,7918
+172,33.683946999999996,-117.79469399999999,Orange,Irvine,1971,62134.0,110330,143072,212375
+173,34.106953000000004,-117.93534199999999,Los Angeles,Irwindale,1957,1030.0,1050,1446,1422
+174,38.161861,-121.611622,Sacramento,Isleton,1923,914.0,833,828,804
+175,38.348803000000004,-120.774103,Amador,Jackson,1905,2331.0,3545,3989,4651
+176,36.723558000000004,-120.059878,Fresno,Kerman,1946,4002.0,5448,8551,13544
+177,36.212744,-121.126028,Monterey,King City,1911,5495.0,7634,11204,12874
+178,36.513839000000004,-119.55401699999999,Fresno,Kingsburg,1908,5115.0,7205,9199,11382
+179,34.206817,-118.200028,Los Angeles,La Cañada Flintridge,1976,20153.0,19378,20318,20246
+180,33.931958,-117.946172,Orange,La Habra,1925,45232.0,51266,58974,60239
+181,33.960846999999994,-117.95061899999999,Los Angeles,La Habra Heights,1978,4786.0,6226,5712,5325
+182,32.767828,-117.02308300000001,San Diego,La Mesa,1912,50308.0,52931,54749,57065
+183,33.917235999999995,-118.01200800000001,Los Angeles,La Mirada,1960,40986.0,40452,46783,48527
+184,33.846403,-118.04673100000001,Orange,La Palma,1955,15399.0,15392,15408,15568
+185,34.020011,-117.94950800000001,Los Angeles,La Puente,1956,30882.0,36955,41063,39816
+186,33.646692,-116.31000800000001,Riverside,La Quinta,1982,11215,11215,23694,37467
+187,34.100842,-117.76783600000002,Los Angeles,La Verne,1906,23508.0,30897,31638,31063
+188,37.885758,-122.11801899999999,Contra Costa,Lafayette,1968,20837.0,23501,23908,23893
+189,33.542246999999996,-117.783111,Orange,Laguna Beach,1927,17858.0,23170,23727,22723
+190,33.522525,-117.707553,Orange,Laguna Niguel,1989,44400,44400,61891,62979
+191,33.668078,-117.32726100000001,Riverside,Lake Elsinore,1888,5982.0,18285,28928,51821
+192,39.04295,-122.915828,Lake,Lakeport,1888,3675.0,4390,4820,4753
+193,33.853628,-118.13395600000001,Los Angeles,Lakewood,1954,74654.0,73557,79345,80048
+194,34.686786,-118.154164,Los Angeles,Lancaster,1977,48027.0,97291,118718,156633
+195,37.934092,-122.535253,Marin,Larkspur,1908,11064.0,11070,12014,11926
+196,37.822706,-121.27661100000002,San Joaquin,Lathrop,1989,6841,6841,10445,18023
+197,33.887236,-118.352575,Los Angeles,Lawndale,1959,23460.0,27331,31711,32769
+198,32.742553,-117.03141699999999,San Diego,Lemon Grove,1977,20780.0,23984,24918,25320
+199,36.300783,-119.78291100000001,Kings,Lemoore,1900,8832.0,13622,19712,24531
+200,38.891564,-121.293008,Placer,Lincoln,1890,4132.0,7248,11205,42819
+201,36.203006,-119.08816100000001,Tulare,Lindsay,1910,6936.0,8338,10297,11768
+202,36.983561,-121.98051699999999,Sutter,Live Oak,1947,3103.0,4320,6229,8392
+203,37.681875,-121.76800800000001,Alameda,Livermore,1876,48349.0,56741,73345,80968
+204,37.386883000000005,-120.723533,Merced,Livingston,1922,5326.0,7317,10473,13058
+205,38.134147,-121.27221899999999,San Joaquin,Lodi,1906,35221.0,51874,56999,62134
+206,34.048347,-117.26115300000001,San Bernardino,Loma Linda,1970,10694.0,17400,18681,23261
+207,33.792239,-118.315072,Los Angeles,Lomita,1964,18807.0,19382,20046,20256
+208,34.63915,-120.45794199999999,Santa Barbara,Lompoc,1888,26267.0,37649,41103,42434
+209,33.768322,-118.195617,Los Angeles,Long Beach,"i. 1888/ d.1896/ 
+ri. 1897",361355.0,429433,461522,462257
+210,33.803072,-118.07256399999999,Orange,Los Alamitos,1960,11529.0,11676,11536,11449
+211,33.796331,-118.118119,Santa Clara,Los Altos,1952,25769.0,26303,27693,28976
+212,34.052233,-118.24368600000001,Los Angeles,Los Angeles,1850,2968579.0,3485398,3694742,3792621
+213,37.058278,-120.84991399999998,Merced,Los Banos,1907,10341.0,14519,25869,35972
+214,39.676294,-120.24103899999999,Sierra,Loyalton,1901,1030.0,931,862,769
+215,33.930292,-118.21146100000001,Los Angeles,Lynwood,1921,48409.0,61945,69845,69772
+216,36.961335999999996,-120.060717,Madera,Madera,1907,21732.0,29281,43207,61416
+217,33.884736,-118.410908,Los Angeles,Manhattan Beach,1912,31542.0,32063,33852,35135
+218,37.797428000000004,-121.216053,San Joaquin,Manteca,1918,24925.0,40773,49258,67096
+219,35.058858,-119.40095,Kern,Maricopa,1911,946.0,1193,1111,1154
+220,36.684403,-121.802172,Monterey,Marina,1975,20647.0,26436,18925,19718
+221,38.019366999999995,-122.134133,Contra Costa,Martinez,1876,22582.0,31808,35866,35824
+222,39.145725,-121.591356,Yuba,Marysville,1851,9898.0,12324,12268,12072
+223,33.986681,-118.18535,Los Angeles,Maywood,1924,21810.0,27850,28083,27395
+224,35.678011,-119.229275,Kern,McFarland,1957,5151.0,7005,9837,12707
+225,36.753561,-120.38155800000001,Fresno,Mendota,1942,5038.0,6821,7890,11014
+226,37.453828,-122.18218600000002,San Mateo,Menlo Park,1927,26438.0,28040,30785,32026
+227,37.302164000000005,-120.48296699999999,Merced,Merced,1889,36499.0,56216,63893,78958
+228,37.906036,-122.544975,Marin,Mill Valley,1900,12967.0,13038,13600,13903
+229,37.598546999999996,-122.387194,San Mateo,Millbrae,1948,20058.0,20412,20718,21532
+230,37.428272,-121.906625,Santa Clara,Milpitas,1954,37820.0,50686,62698,66790
+231,33.600021999999996,-117.671994,Orange,Mission Viejo,1988,72820,72820,93102,93305
+232,37.639097,-120.99687800000001,Stanislaus,Modesto,1884,106963.0,164730,188856,201165
+233,34.144428000000005,-118.001947,Los Angeles,Monrovia,1887,30531.0,35761,36929,36590
+234,41.728196999999994,-122.5278,Siskiyou,Montague,1909,1285.0,1415,1456,1443
+235,34.077511,-117.689778,San Bernardino,Montclair,1956,22628.0,28434,33049,36664
+236,37.236333,-121.99245800000001,Santa Clara,Monte Sereno,1957,3434.0,3287,3483,3341
+237,34.016506,-118.113753,Los Angeles,Montebello,1920,52929.0,59564,62150,62500
+238,36.600239,-121.894675,Monterey,Monterey,1890,27558.0,31954,29696,27810
+239,34.062511,-118.122847,Los Angeles,Monterey Park,1916,54338.0,60738,60051,60269
+240,34.144897,-118.26874199999999,Ventura,Moorpark,1983,25494,25494,31415,34421
+241,33.942467,-117.229672,Riverside,Moreno Valley,1984,118779,118779,142381,193365
+242,37.1305,-121.654389,Santa Clara,Morgan Hill,1906,17060.0,23928,33556,37882
+243,35.365808,-120.8499,San Luis Obispo,Morro Bay,1964,9064.0,9664,10350,10234
+244,41.410806,-122.194575,Siskiyou,Mount Shasta,1905,2837.0,3460,3621,3394
+245,37.386053000000004,-122.08385,Santa Clara,Mountain View,1902,58655.0,67460,70708,74066
+246,38.297539,-122.286864,Napa,Napa,1872,50879.0,61842,72585,76915
+247,32.678108,-117.099197,San Diego,National City,1887,48772.0,54249,54260,58582
+248,34.848061,-114.61413300000001,San Bernardino,Needles,1913,4120.0,5191,4830,4844
+249,39.261561,-121.016058,Nevada,Nevada City,1856,2431.0,2855,3001,3068
+250,37.529658000000005,-122.04023899999999,Alameda,Newark,1955,32126.0,37861,42471,42573
+251,37.313828,-121.02076100000001,Stanislaus,Newman,1908,2785.0,4151,7093,10224
+252,33.618911,-117.928947,Orange,Newport Beach,1906,62556.0,66643,70032,85186
+253,33.931125,-117.54866100000001,Riverside,Norco,1964,19732.0,23302,24157,27063
+254,33.902236,-118.08173300000001,Los Angeles,Norwalk,1957,84901.0,94279,104323,105549
+255,38.107419,-122.569703,Marin,Novato,1960,43916.0,47585,47630,51904
+256,37.766594,-120.847153,Stanislaus,Oakdale,1906,8474.0,11961,15503,20675
+257,37.804364,-122.27111399999998,Alameda,Oakland,1852,339337.0,372242,399484,390724
+258,33.195869,-117.37948300000001,San Diego,Oceanside,1888,76698.0,128398,161029,167086
+259,34.44805,-119.24288899999999,Ventura,Ojai,1921,6816.0,7613,7862,7461
+260,34.063344,-117.65088899999999,San Bernardino,Ontario,1891,88820.0,133179,158007,163924
+261,33.787794,-117.85311100000001,Orange,Orange,1888,91450.0,110658,128868,136416
+262,36.624394,-119.313731,Fresno,Orange Cove,1948,4026.0,5604,7722,9078
+263,37.877146999999994,-122.179689,Contra Costa,Orinda,1985,16642,16642,17599,17643
+264,39.747381,-122.196375,Glenn,Orland,1909,4031.0,5052,6281,7291
+265,39.513775,-121.556358,Butte,Oroville,1906,8693.0,11960,13004,15546
+266,34.197506,-119.177053,Ventura,Oxnard,1903,108195.0,142216,170358,197899
+267,36.617736,-121.916622,Monterey,Pacific Grove,1889,15755.0,16117,15522,15041
+268,37.613825,-122.486919,San Mateo,Pacifica,1957,36866.0,37670,38390,37234
+269,33.722244,-116.37445600000001,Riverside,Palm Desert,1973,11801.0,23252,41155,48445
+270,33.830296999999995,-116.54529199999999,Riverside,Palm Springs,1938,32359.0,40181,42807,44552
+271,34.579433,-118.11646100000002,Los Angeles,Palmdale,1962,12277.0,68842,116670,152750
+272,37.441883000000004,-122.143019,Santa Clara,Palo Alto,1894,55225.0,55900,58598,64403
+273,33.800571999999995,-118.390075,Los Angeles,Palos Verdes Estates,1939,14376.0,13512,13340,13438
+274,33.889461,-118.159792,Los Angeles,Paramount,1957,36407.0,47669,55266,54098
+275,36.611616999999995,-119.527072,Fresno,Parlier,1921,2902.0,7938,11145,14494
+276,34.147785999999996,-118.144517,Los Angeles,Pasadena,1886,118072.0,131591,133936,137122
+277,35.632278,-120.66418600000002,San Luis Obispo,Paso Robles,1889,9163.0,18583,24297,29793
+278,37.4716,-121.12965600000001,Stanislaus,Patterson,1919,3908.0,8626,11606,20413
+279,33.782519,-117.228647,Riverside,Perris,1911,6827.0,21460,36189,68386
+280,38.232417,-122.63665300000001,Sonoma,Petaluma,1858,33834.0,43184,54548,57941
+281,33.983069,-118.096736,Los Angeles,Pico Rivera,1958,53387.0,59177,63428,62942
+282,37.824372,-122.23163600000001,Alameda,Piedmont,1907,10498.0,10602,10952,10667
+283,38.004366999999995,-122.29885800000001,Contra Costa,Pinole,1903,14253.0,17460,19039,18390
+284,35.142753000000006,-120.641283,San Luis Obispo,Pismo Beach,1939,5364.0,7669,8551,7655
+285,38.027975,-121.884681,Contra Costa,Pittsburg,1903,33465.0,47564,56769,63264
+286,33.872236,-117.87033600000001,Orange,Placentia,1926,35041.0,41259,46488,50533
+287,38.729625,-120.798547,El Dorado,Placerville,1854,6739.0,8355,9610,10389
+288,37.947978000000006,-122.060797,Contra Costa,Pleasant Hill,1961,25547.0,31585,32837,33152
+289,37.662431,-121.874678,Alameda,Pleasanton,1894,35160.0,50553,63654,70285
+290,38.481853,-120.84465800000001,Amador,Plymouth,1917,699.0,811,980,1005
+291,38.908797,-123.693072,Mendocino,Point Arena,1908,425.0,407,474,449
+292,34.055228,-117.752306,Los Angeles,Pomona,1888,92742.0,131723,149473,149058
+293,34.180728,-119.20815800000001,Ventura,Port Hueneme,1948,17803.0,20319,21845,21723
+294,36.065231,-119.01676699999999,Tulare,Porterville,1902,19707.0,29563,39615,54165
+295,39.810458000000004,-120.469103,Plumas,Portola,1946,1885.0,2193,2227,2104
+296,32.962821999999996,-117.03586399999999,San Diego,Poway,1980,43516,43516,48044,47811
+297,34.1064,-117.593108,San Bernardino,Rancho Cucamonga,1977,55250.0,101409,127743,165269
+298,33.739744,-116.41278899999999,Riverside,Rancho Mirage,1973,6281.0,9778,13249,17218
+299,33.744461,-118.38701699999999,Los Angeles,Rancho Palos Verdes,1973,36577.0,41659,41145,41643
+300,40.178489,-122.235831,Tehama,Red Bluff,1876,9490.0,12363,13147,14076
+301,40.586539,-122.391675,Shasta,Redding,1887,41995.0,66462,80865,89861
+302,34.055569,-117.18253899999999,San Bernardino,Redlands,1888,43619.0,60394,63591,68747
+303,33.849183000000004,-118.38840800000001,Los Angeles,Redondo Beach,1892,57102.0,60167,63261,66748
+304,37.485214,-122.236356,San Mateo,Redwood City,1867,54951.0,66072,75402,76815
+305,36.596339,-119.45040300000001,Fresno,Reedley,1913,11071.0,15791,20756,24194
+306,34.1064,-117.370325,San Bernardino,Rialto,1911,37862.0,72388,91873,99171
+307,37.935758,-122.34775,Contra Costa,Richmond,1905,74676.0,87425,99216,103701
+308,35.622456,-117.670897,Kern,Ridgecrest,1963,15929.0,27725,24927,27616
+309,40.4993,-124.10643600000002,Humboldt,Rio Dell,1965,2687.0,3012,3174,3368
+310,38.15575,-121.691344,Solano,Rio Vista,1894,3142.0,3316,4571,7360
+311,37.739453000000005,-121.13541399999998,San Joaquin,Ripon,1945,3509.0,7455,10146,14297
+312,37.736039,-120.93548899999999,Stanislaus,Riverbank,1922,5695.0,8547,15826,22678
+313,33.95335,-117.396156,Riverside,Riverside,1883,170591.0,226505,255166,303871
+314,38.790733,-121.23578300000001,Placer,Rocklin,1893,7344.0,19033,36330,56974
+315,38.339636,-122.701097,Sonoma,Rohnert Park,1962,22965.0,36326,42236,40971
+316,33.756961,-118.35396100000001,Los Angeles,Rolling Hills,1957,2049.0,1871,1871,1860
+317,33.787794,-118.35812800000001,Los Angeles,Rolling Hills Estates,1957,7701.0,7789,7676,8067
+318,34.080564,-118.072847,Los Angeles,Rosemead,1959,42604.0,51638,53505,53764
+319,38.752122,-121.28800600000001,Placer,Roseville,1909,24347.0,44685,79921,118788
+320,38.581571999999994,-121.4944,Sacramento,Sacramento,1850,275741.0,369365,407018,466488
+321,36.677735999999996,-121.6555,Monterey,Salinas,1874,80479.0,108777,142685,150441
+322,34.108344,-117.28976399999999,San Bernardino,San Bernardino,1869,118794.0,164164,185401,209924
+323,37.630489000000004,-122.411083,San Mateo,San Bruno,1914,35417.0,38961,40165,41114
+324,37.507158000000004,-122.260522,San Mateo,San Carlos,1925,24710.0,26167,27718,28406
+325,33.426972,-117.61199199999999,Orange,San Clemente,1928,27325.0,41100,49936,63522
+326,32.715328,-117.157256,San Diego,San Diego,1850,875538.0,1110549,1223400,1307402
+327,34.106675,-117.806725,Los Angeles,San Dimas,1960,24014.0,32397,34980,33371
+328,34.281946999999995,-118.43897199999999,Los Angeles,San Fernando,1911,17731.0,22580,23564,23645
+329,37.774931,-122.419417,San Francisco,San Francisco,1850,678974.0,723959,776733,805235
+330,34.096111,-118.105833,Los Angeles,San Gabriel,1913,30072.0,37120,39804,39718
+331,33.783908000000004,-116.95863600000001,Riverside,San Jacinto,1888,7098.0,16210,23779,44199
+332,36.606617,-120.189044,Fresno,San Joaquin,1920,1930.0,2311,3270,4001
+333,37.339386,-121.89495600000001,Santa Clara,San Jose,1850,629531.0,782248,894943,945942
+334,36.845511,-121.537997,San Benito,San Juan Bautista,1869,1276.0,1570,1549,1862
+335,33.501692,-117.66255,Orange,San Juan Capistrano,1961,18959.0,26183,33826,34593
+336,37.724931,-122.15607800000001,Alameda,San Leandro,1872,63952.0,68223,79452,84950
+337,35.282753,-120.659617,San Luis Obispo,San Luis Obispo,1856,34252.0,41958,44174,45119
+338,33.143372,-117.16614399999999,San Diego,San Marcos,1963,17479.0,38974,54977,83781
+339,34.121396999999995,-118.106458,Los Angeles,San Marino,1913,13307.0,12959,12945,13147
+340,37.562992,-122.325525,San Mateo,San Mateo,1894,77640.0,85486,92482,97207
+341,37.962146999999995,-122.345525,Contra Costa,San Pablo,1948,19750.0,25158,30215,29139
+342,37.973535999999996,-122.53108600000002,Marin,San Rafael,1874,44700.0,48404,56063,57713
+343,37.779928000000005,-121.97801399999999,Contra Costa,San Ramon,1983,35303,35303,44722,72148
+344,36.617183000000004,-121.84828600000002,Monterey,Sand City,1960,182.0,192,261,334
+345,36.708006,-119.55596399999999,Fresno,Sanger,1911,12542.0,16839,18931,24270
+346,33.745571999999996,-117.867833,Orange,Santa Ana,1886,204023.0,293742,337977,324528
+347,34.420831,-119.69818899999999,Santa Barbara,Santa Barbara,1850,74414.0,85571,89600,88410
+348,37.354108000000004,-121.95523600000001,Santa Clara,Santa Clara,1852,87700.0,93613,102361,116468
+349,34.391664,-118.54258600000001,Los Angeles,Santa Clarita,1987,110642,110642,151088,176320
+350,36.974117,-122.03079699999999,Santa Cruz,Santa Cruz,1866,41483.0,49040,54593,59946
+351,33.947236,-118.08534399999999,Los Angeles,Santa Fe Springs,1957,14520.0,15520,16413,16223
+352,34.953033000000005,-120.43571899999999,Santa Barbara,Santa Maria,1905,39685.0,61284,77423,99553
+353,34.019453000000006,-118.491192,Los Angeles,Santa Monica,1886,88314.0,86905,84084,89736
+354,34.354167,-119.059269,Ventura,Santa Paula,1902,20658.0,25062,28598,29321
+355,38.440467,-122.714431,Sonoma,Santa Rosa,1868,82658.0,113313,147595,167815
+356,32.838383,-116.97391699999999,San Diego,Santee,1980,52902,52902,52975,53413
+357,37.263833,-122.02301399999999,Santa Clara,Saratoga,1956,29261.0,28061,29843,29926
+358,37.859094,-122.48525,Marin,Sausalito,1893,7338.0,7152,7330,7061
+359,37.051061,-122.014683,Santa Cruz,Scotts Valley,1966,6891.0,8615,11385,11580
+360,33.741406,-118.104786,Orange,Seal Beach,1915,25975.0,25098,24157,24168
+361,33.819361,-118.366647,Monterey,Seaside,1954,36567.0,38901,33097,33025
+362,38.402136,-122.823881,Sonoma,Sebastopol,1902,5595.0,7004,7774,7379
+363,36.570783,-119.612075,Fresno,Selma,1893,10942.0,14757,19444,23219
+364,35.500514,-119.271775,Kern,Shafter,1938,7010.0,8409,12736,16988
+365,34.161671999999996,-118.052847,Los Angeles,Sierra Madre,1907,10837.0,10762,10578,10917
+366,33.804460999999996,-118.167847,Los Angeles,Signal Hill,1924,5734.0,8371,9333,11016
+367,34.269447,-118.78148300000001,Ventura,Simi Valley,1969,77500.0,100217,111351,124237
+368,32.991156,-117.271147,San Diego,Solana Beach,1986,12962,12962,12979,12867
+369,32.991156,-117.271147,Monterey,Soledad,1921,3091.0,7146,23015,25738
+370,34.595819,-120.137647,Santa Barbara,Solvang,1985,4741,4741,5332,5245
+371,38.291858000000005,-122.458036,Sonoma,Sonoma,1883,6054.0,8121,9128,10648
+372,37.984092,-120.382139,Tuolumne,Sonora,1851,3247.0,4153,4423,4903
+373,34.051956,-118.046733,Los Angeles,South El Monte,1958,16623.0,20850,21144,20116
+374,33.954736,-118.21201699999999,Los Angeles,South Gate,1923,66784.0,86284,96375,94396
+375,38.939925,-119.977186,El Dorado,South Lake Tahoe,1965,20681.0,21586,23609,21403
+376,34.116119,-118.15035,Los Angeles,South Pasadena,1888,22681.0,23936,24292,25619
+377,37.654656,-122.40775,San Mateo,South San Francisco,1908,49393.0,54312,60552,63632
+378,38.505241999999996,-122.470386,Napa,St. Helena,1876,4898.0,4990,5950,5814
+379,33.802517,-117.993117,Orange,Stanton,1911,23723.0,30491,37403,38186
+380,37.957703,-121.29078100000001,San Joaquin,Stockton,1850,148283.0,210943,243771,291707
+381,38.238246999999994,-122.040244,Solano,Suisun City,1868,11087.0,22686,26118,28111
+382,37.368831,-122.03635,Santa Clara,Sunnyvale,1912,106618.0,117229,131760,140081
+383,40.416283,-120.653006,Lassen,Susanville,1900,6520.0,7279,17428,17947
+384,38.392967,-120.80243600000001,Amador,Sutter Creek,1913,1705.0,1835,2303,2501
+385,35.142466999999996,-119.45650800000001,Kern,Taft,1910,5316.0,5902,8811,9327
+386,35.132189000000004,-118.448975,Kern,Tehachapi,1909,4126.0,5791,11125,14414
+387,40.027103000000004,-122.123322,Tehama,Tehama,1906,365.0,401,432,418
+388,33.493639,-117.14836399999999,Riverside,Temecula,1989,27099,27099,57716,100097
+389,34.107231,-118.057847,Los Angeles,Temple City,1960,28972.0,31100,33377,35558
+390,34.107231,-118.057847,Ventura,Thousand Oaks,1964,77072.0,104352,117005,126683
+391,33.83585,-118.34062800000001,Los Angeles,Torrance,1921,129881.0,133107,137946,145438
+392,37.73965,-121.42522199999999,San Joaquin,Tracy,1910,18428.0,33558,56929,82922
+393,41.059292,-124.143125,Humboldt,Trinidad,1870,379.0,362,311,367
+394,36.207728,-119.34733899999999,Tulare,Tulare,1888,22530.0,33249,43994,59278
+395,41.955989,-121.477492,Siskiyou,Tulelake,1937,783.0,1010,1020,1010
+396,37.494658,-120.846594,Stanislaus,Turlock,1908,26287.0,42198,55810,68549
+397,33.74585,-117.826167,Orange,Tustin,1927,32256.0,50689,67504,75540
+398,34.135558,-116.05416899999999,San Bernardino,Twentynine Palms,1987,11821,11821,14764,25048
+399,39.150172,-123.207783,Mendocino,Ukiah,1876,12035.0,14599,15497,16075
+400,37.593392,-122.04383100000001,Alameda,Union City,1959,39406.0,53762,66869,69516
+401,34.097511,-117.648389,San Bernardino,Upland,1906,47647.0,63374,68393,73732
+402,38.356578000000006,-121.98774399999999,Solano,Vacaville,1892,43367.0,71479,88625,92428
+403,38.104085999999995,-122.25663600000001,Solano,Vallejo,1868,80303.0,109199,116760,115942
+404,34.274639,-119.22900600000001,Ventura,Ventura,1866,73774.0,92575,100916,106433
+405,34.003903,-118.23007199999999,Los Angeles,Vernon,1905,90.0,152,91,112
+406,34.536108,-117.29115800000001,San Bernardino,Victorville,1962,14220.0,40674,64029,115903
+407,33.814461,-117.813111,Orange,Villa Park,1962,7137.0,6299,5952,5812
+408,36.330228000000005,-119.29205800000001,Tulare,Visalia,1874,49729.0,75636,91877,124442
+409,33.200036,-117.24253600000002,San Diego,Vista,1963,35834.0,71872,89857,93834
+410,34.020289,-117.86533899999999,Los Angeles,Walnut,1959,12478.0,29105,30004,29172
+411,37.910078000000006,-122.065183,Contra Costa,Walnut Creek,1914,53490.0,60569,64296,64173
+412,35.594125,-119.340947,Kern,Wasco,1945,9613.0,12412,21263,25545
+413,37.641319,-120.76048300000001,Stanislaus,Waterford,1969,2683.0,4771,6924,8456
+414,36.910231,-121.75689399999999,Santa Cruz,Watsonville,1868,23662.0,31099,44265,51199
+415,41.42265,-122.386128,Siskiyou,Weed,1961,2879.0,3062,2978,2967
+416,34.068622,-117.938953,Los Angeles,West Covina,1923,81292.0,96086,105080,106098
+417,34.090008000000005,-118.36174399999999,Los Angeles,West Hollywood,1984,36118,36118,35794,34399
+418,38.580461,-121.53023300000001,Yolo,West Sacramento,1987,28898,28898,31615,48744
+419,34.145839,-118.805647,Los Angeles,Westlake Village,1981,7455,7455,8368,8270
+420,33.751342,-117.99399199999999,Orange,Westminster,1957,71133.0,78118,88207,89701
+421,33.037267,-115.62138300000001,Imperial,Westmorland,1934,1590.0,1380,2131,2225
+422,39.009894,-121.423014,Yuba,Wheatland,1874,1474.0,1631,2275,3456
+423,33.979178000000005,-118.032844,Los Angeles,Whittier,1898,68558.0,77671,83680,85331
+424,39.154614,-122.149419,Colusa,Williams,1920,1658.0,2297,3670,5123
+425,39.409608,-123.355567,Mendocino,Willits,1888,4008.0,5027,5073,4888
+426,39.524325,-122.193592,Glenn,Willows,1886,4777.0,5988,6220,6166
+427,38.524906,-121.970803,Yolo,Winters,1898,2652.0,4639,6125,6624
+428,36.413561,-119.098717,Tulare,Woodlake,1941,4343.0,5678,6651,7279
+429,38.678517,-121.773297,Yolo,Woodland,1871,30235.0,39802,49151,55468
+430,33.888625,-117.813111,Orange,Yorba Linda,1967,28254.0,52422,58918,64234
+431,41.735419,-122.634472,Siskiyou,Yreka,1857,5916.0,6948,7290,7765
+432,39.140446999999995,-121.61691100000002,Sutter,Yuba City,1908,18736.0,27437,36758,64925
+433,34.033625,-117.04308600000002,San Bernardino,Yucaipa,1989,32824,32824,41207,51367

data/california_counties.csv

@@ -0,0 +1,55 @@
+,County,Latitude,Longitude,pop_april_1990
+0,Alameda,37.72108914285714,-122.10629442857139,1159300
+1,Amador,38.3991342,-120.8356034,12903
+2,Butte,39.504609,-121.70004225,58251
+3,Calaveras,38.067783,-120.538531,2409
+4,Colusa,39.1844735,-122.079418,7231
+5,Contra Costa,37.70406712500001,-121.891572375,605136
+6,Del Norte,41.755947,-124.201747,4380
+7,El Dorado,38.834775,-120.3878665,29941
+8,Fresno,36.60750253333333,-119.84778606666667,507854
+9,Glenn,39.635853,-122.1949835,11040
+10,Humboldt,40.754931000000006,-124.12874871428572,56950
+11,Imperial,32.895883285714284,-115.52534842857143,81943
+12,Inyo,37.363539,-118.395111,3475
+13,Kern,35.381668545454545,-118.90037272727272,281260
+14,Kings,36.65258325,-120.39717350000001,67653
+15,Lake,39.04295,-122.915828,4390
+16,Lassen,40.416283,-120.653006,7279
+17,Los Angeles,34.01223316279069,-118.16819196511624,7892444
+18,Madera,37.042168000000004,-120.16044600000001,35211
+19,Marin,37.942146666666666,-122.52178066666666,129396
+20,Mendocino,39.22857475,-123.5154285,26111
+21,Merced,37.22313616666667,-120.71514716666667,108461
+22,Modoc,41.487114,-120.542456,3231
+23,Monterey,35.967388909090914,-120.94583863636363,250942
+24,Napa,38.46052600000001,-122.445652,71300
+25,Nevada,39.240311000000005,-121.03855949999999,11903
+26,Orange,33.85135710344828,-118.01976731034482,2183131
+27,Placer,38.8863428,-121.16939219999999,82864
+28,Plumas,39.810458,-120.469103,2193
+29,Riverside,33.78326276190476,-116.72182676190475,785027
+30,Sacramento,38.41900675,-121.39550675,408889
+31,San Benito,36.848982,-121.46979999999999,20782
+32,San Bernardino,34.2241070952381,-117.15653514285717,1049825
+33,San Diego,32.90077138888889,-117.15095872222221,2027215
+34,San Francisco,37.774931,-122.419417,723959
+35,San Joaquin,37.85550214285714,-121.23041471428571,355881
+36,San Luis Obispo,35.30760528571428,-120.67110271428574,127046
+37,San Mateo,37.56470973333334,-122.33668913333334,563824
+38,Santa Barbara,34.66322666666667,-120.13663150000001,208471
+39,Santa Clara,37.027805692307695,-121.64295630769234,1351329
+40,Santa Cruz,36.97765925,-121.9389165,98925
+41,Shasta,40.517373500000005,-122.344729,74761
+42,Sierra,39.676294,-120.241039,931
+43,Siskiyou,41.61658977777777,-122.50645877777778,20390
+44,Solano,38.25824716666667,-121.97320533333334,294292
+45,Sonoma,38.4312775,-122.741206,228055
+46,Stanislaus,37.58453255555556,-120.92902288888887,274557
+47,Sutter,38.062004,-121.79871400000002,31757
+48,Tehama,40.04441666666666,-122.17943633333334,18634
+49,Tulare,36.29460325,-119.1973675,178718
+50,Tuolumne,37.984092,-120.382139,4153
+51,Ventura,34.2592223,-118.89802030000001,582143
+52,Yolo,38.5821975,-121.7537125,119548
+53,Yuba,39.0778095,-121.50718499999999,13955

data/thads2011.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72ed51a381d6b1a404a921f1979469fd321487b36fb064b700edbc52ff1f470
+size 119914024

data/thads2013n.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4286817ff2e3081332715d73c3e0dd258f4d8351a641d0af367b11098b9c25
+size 53281106

model.ipynb

@@ -0,0 +1,1383 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install pygam seaborn statsmodels --quiet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from sklearn.datasets import fetch_california_housing\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.preprocessing import StandardScaler,OrdinalEncoder\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression, LogisticRegression\n",
+    "from sklearn.metrics import classification_report, recall_score, precision_score, accuracy_score\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import zipfile\n",
+    "from statsmodels.genmod.generalized_linear_model import GLM\n",
+    "from statsmodels.genmod.families import Gamma\n",
+    "from statsmodels.genmod.families.links import Log\n",
+    "from statsmodels.tools import add_constant\n",
+    "from pygam import LinearGAM, GammaGAM, s, f"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>CONTROL</th>\n",
+       "      <th>AGE1</th>\n",
+       "      <th>METRO3</th>\n",
+       "      <th>REGION</th>\n",
+       "      <th>LMED</th>\n",
+       "      <th>FMR</th>\n",
+       "      <th>L30</th>\n",
+       "      <th>L50</th>\n",
+       "      <th>L80</th>\n",
+       "      <th>IPOV</th>\n",
+       "      <th>...</th>\n",
+       "      <th>FMTCOST06RELAMICAT</th>\n",
+       "      <th>FMTCOST08RELAMICAT</th>\n",
+       "      <th>FMTCOST12RELAMICAT</th>\n",
+       "      <th>FMTCOSTMEDRELAMICAT</th>\n",
+       "      <th>FMTINCRELAMICAT</th>\n",
+       "      <th>FMTASSISTED</th>\n",
+       "      <th>FMTBURDEN</th>\n",
+       "      <th>FMTREGION</th>\n",
+       "      <th>FMTSTATUS</th>\n",
+       "      <th>HOUSE_AGE</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>'036000001146'</td>\n",
+       "      <td>34</td>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>2580</td>\n",
+       "      <td>24950</td>\n",
+       "      <td>41550</td>\n",
+       "      <td>66500</td>\n",
+       "      <td>17849</td>\n",
+       "      <td>...</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'.'</td>\n",
+       "      <td>'2 30% to 50%'</td>\n",
+       "      <td>'West'</td>\n",
+       "      <td>'-5'</td>\n",
+       "      <td>9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>'036000001147'</td>\n",
+       "      <td>43</td>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>2241</td>\n",
+       "      <td>27700</td>\n",
+       "      <td>46150</td>\n",
+       "      <td>73850</td>\n",
+       "      <td>22629</td>\n",
+       "      <td>...</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'.'</td>\n",
+       "      <td>'1 Less than 30%'</td>\n",
+       "      <td>'West'</td>\n",
+       "      <td>'-5'</td>\n",
+       "      <td>9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>'036000001149'</td>\n",
+       "      <td>60</td>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>2577</td>\n",
+       "      <td>24950</td>\n",
+       "      <td>41550</td>\n",
+       "      <td>66500</td>\n",
+       "      <td>17399</td>\n",
+       "      <td>...</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'.'</td>\n",
+       "      <td>'1 Less than 30%'</td>\n",
+       "      <td>'West'</td>\n",
+       "      <td>'-5'</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>'036000001150'</td>\n",
+       "      <td>37</td>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>2241</td>\n",
+       "      <td>22200</td>\n",
+       "      <td>36950</td>\n",
+       "      <td>59100</td>\n",
+       "      <td>14985</td>\n",
+       "      <td>...</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'.'</td>\n",
+       "      <td>'2 30% to 50%'</td>\n",
+       "      <td>'West'</td>\n",
+       "      <td>'-5'</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>'036000001151'</td>\n",
+       "      <td>33</td>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>2580</td>\n",
+       "      <td>27700</td>\n",
+       "      <td>46150</td>\n",
+       "      <td>73850</td>\n",
+       "      <td>22557</td>\n",
+       "      <td>...</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'7 120% AMI +'</td>\n",
+       "      <td>'.'</td>\n",
+       "      <td>'2 30% to 50%'</td>\n",
+       "      <td>'West'</td>\n",
+       "      <td>'-5'</td>\n",
+       "      <td>16</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 100 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          CONTROL  AGE1 METRO3 REGION   LMED   FMR    L30    L50    L80  \\\n",
+       "0  '036000001146'    34    '2'    '4'  84200  2580  24950  41550  66500   \n",
+       "1  '036000001147'    43    '2'    '4'  84200  2241  27700  46150  73850   \n",
+       "2  '036000001149'    60    '2'    '4'  84200  2577  24950  41550  66500   \n",
+       "3  '036000001150'    37    '2'    '4'  84200  2241  22200  36950  59100   \n",
+       "4  '036000001151'    33    '2'    '4'  84200  2580  27700  46150  73850   \n",
+       "\n",
+       "    IPOV  ...  FMTCOST06RELAMICAT  FMTCOST08RELAMICAT FMTCOST12RELAMICAT  \\\n",
+       "0  17849  ...      '7 120% AMI +'      '7 120% AMI +'     '7 120% AMI +'   \n",
+       "1  22629  ...      '7 120% AMI +'      '7 120% AMI +'     '7 120% AMI +'   \n",
+       "2  17399  ...      '7 120% AMI +'      '7 120% AMI +'     '7 120% AMI +'   \n",
+       "3  14985  ...      '7 120% AMI +'      '7 120% AMI +'     '7 120% AMI +'   \n",
+       "4  22557  ...      '7 120% AMI +'      '7 120% AMI +'     '7 120% AMI +'   \n",
+       "\n",
+       "   FMTCOSTMEDRELAMICAT FMTINCRELAMICAT  FMTASSISTED          FMTBURDEN  \\\n",
+       "0       '7 120% AMI +'  '7 120% AMI +'          '.'     '2 30% to 50%'   \n",
+       "1       '7 120% AMI +'  '7 120% AMI +'          '.'  '1 Less than 30%'   \n",
+       "2       '7 120% AMI +'  '7 120% AMI +'          '.'  '1 Less than 30%'   \n",
+       "3       '7 120% AMI +'  '7 120% AMI +'          '.'     '2 30% to 50%'   \n",
+       "4       '7 120% AMI +'  '7 120% AMI +'          '.'     '2 30% to 50%'   \n",
+       "\n",
+       "   FMTREGION  FMTSTATUS  HOUSE_AGE  \n",
+       "0     'West'       '-5'          9  \n",
+       "1     'West'       '-5'          9  \n",
+       "2     'West'       '-5'         10  \n",
+       "3     'West'       '-5'         10  \n",
+       "4     'West'       '-5'         16  \n",
+       "\n",
+       "[5 rows x 100 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_2011, df_2013 = pd.read_csv('thads2011.txt'),pd.read_csv('thads2013n.txt')\n",
+    "df_2011['HOUSE_AGE'], df_2013['HOUSE_AGE'] = 2011 - df_2011['BUILT'], 2013 - df_2013['BUILT']\n",
+    "df = pd.concat([df_2011, df_2013], ignore_index=True)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df[df['OWNRENT'] == \"'1'\"]\n",
+    "df = df[df['FMTSTRUCTURETYPE'] == \"'1 Single Family'\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>METRO3</th>\n",
+       "      <th>REGION</th>\n",
+       "      <th>LMED</th>\n",
+       "      <th>BEDRMS</th>\n",
+       "      <th>HOUSE_AGE</th>\n",
+       "      <th>VALUE</th>\n",
+       "      <th>ROOMS</th>\n",
+       "      <th>PER</th>\n",
+       "      <th>UTILITY</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>4</td>\n",
+       "      <td>9</td>\n",
+       "      <td>720000</td>\n",
+       "      <td>8</td>\n",
+       "      <td>3</td>\n",
+       "      <td>300.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>3</td>\n",
+       "      <td>9</td>\n",
+       "      <td>550000</td>\n",
+       "      <td>5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>256.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>5</td>\n",
+       "      <td>10</td>\n",
+       "      <td>720000</td>\n",
+       "      <td>11</td>\n",
+       "      <td>3</td>\n",
+       "      <td>233.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>3</td>\n",
+       "      <td>10</td>\n",
+       "      <td>450000</td>\n",
+       "      <td>5</td>\n",
+       "      <td>2</td>\n",
+       "      <td>152.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>'2'</td>\n",
+       "      <td>'4'</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>4</td>\n",
+       "      <td>16</td>\n",
+       "      <td>700000</td>\n",
+       "      <td>9</td>\n",
+       "      <td>4</td>\n",
+       "      <td>656.166667</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  METRO3 REGION   LMED  BEDRMS  HOUSE_AGE   VALUE  ROOMS  PER     UTILITY\n",
+       "0    '2'    '4'  84200       4          9  720000      8    3  300.000000\n",
+       "1    '2'    '4'  84200       3          9  550000      5    4  256.000000\n",
+       "2    '2'    '4'  84200       5         10  720000     11    3  233.000000\n",
+       "3    '2'    '4'  84200       3         10  450000      5    2  152.000000\n",
+       "4    '2'    '4'  84200       4         16  700000      9    4  656.166667"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "keep_columns = [\n",
+    "    'METRO3',\n",
+    "    'REGION',\n",
+    "    'LMED',\n",
+    "    'BEDRMS',\n",
+    "    'HOUSE_AGE',\n",
+    "    'VALUE',\n",
+    "    'ROOMS',\n",
+    "    'PER',\n",
+    "    'UTILITY',\n",
+    "]\n",
+    "\n",
+    "df = df[keep_columns]\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>METRO3</th>\n",
+       "      <th>REGION</th>\n",
+       "      <th>LMED</th>\n",
+       "      <th>BEDRMS</th>\n",
+       "      <th>HOUSE_AGE</th>\n",
+       "      <th>VALUE</th>\n",
+       "      <th>ROOMS</th>\n",
+       "      <th>PER</th>\n",
+       "      <th>UTILITY</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>4</td>\n",
+       "      <td>9</td>\n",
+       "      <td>720000</td>\n",
+       "      <td>8</td>\n",
+       "      <td>3</td>\n",
+       "      <td>300.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>3</td>\n",
+       "      <td>9</td>\n",
+       "      <td>550000</td>\n",
+       "      <td>5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>256.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>5</td>\n",
+       "      <td>10</td>\n",
+       "      <td>720000</td>\n",
+       "      <td>11</td>\n",
+       "      <td>3</td>\n",
+       "      <td>233.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>3</td>\n",
+       "      <td>10</td>\n",
+       "      <td>450000</td>\n",
+       "      <td>5</td>\n",
+       "      <td>2</td>\n",
+       "      <td>152.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2</td>\n",
+       "      <td>4</td>\n",
+       "      <td>84200</td>\n",
+       "      <td>4</td>\n",
+       "      <td>16</td>\n",
+       "      <td>700000</td>\n",
+       "      <td>9</td>\n",
+       "      <td>4</td>\n",
+       "      <td>656.166667</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   METRO3  REGION   LMED  BEDRMS  HOUSE_AGE   VALUE  ROOMS  PER     UTILITY\n",
+       "0       2       4  84200       4          9  720000      8    3  300.000000\n",
+       "1       2       4  84200       3          9  550000      5    4  256.000000\n",
+       "2       2       4  84200       5         10  720000     11    3  233.000000\n",
+       "3       2       4  84200       3         10  450000      5    2  152.000000\n",
+       "4       2       4  84200       4         16  700000      9    4  656.166667"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['METRO3'] = df['METRO3'].str.replace(\"'\", \"\").astype(int)\n",
+    "df['REGION'] = df['REGION'].str.replace(\"'\", \"\").astype(int)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "region_code = {\n",
+    "    'Northeast': 1,\n",
+    "    'Midwest': 2,\n",
+    "    'South': 3,\n",
+    "    'West': 4,\n",
+    "}\n",
+    "\n",
+    "metro_code = {\n",
+    "    'Central cities of metropolitan areas': 1,\n",
+    "    'Inside metropolitan area, but not in central city': 2,\n",
+    "    'Inside metropolitan area, but not in central city - rural': 3,\n",
+    "    'Outside metropolitan areas, urbanized': 4,\n",
+    "    'Outside metropolitan areas, rural': 5,\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv('hud_dataset.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X, y = df.drop(columns=['VALUE']), df['VALUE']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>METRO3</th>\n",
+       "      <th>REGION</th>\n",
+       "      <th>LMED</th>\n",
+       "      <th>BEDRMS</th>\n",
+       "      <th>HOUSE_AGE</th>\n",
+       "      <th>ROOMS</th>\n",
+       "      <th>PER</th>\n",
+       "      <th>UTILITY</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>22170</th>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>67109</td>\n",
+       "      <td>4</td>\n",
+       "      <td>21</td>\n",
+       "      <td>9</td>\n",
+       "      <td>3</td>\n",
+       "      <td>126.083333</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17193</th>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>62800</td>\n",
+       "      <td>3</td>\n",
+       "      <td>41</td>\n",
+       "      <td>6</td>\n",
+       "      <td>2</td>\n",
+       "      <td>201.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>137803</th>\n",
+       "      <td>4</td>\n",
+       "      <td>1</td>\n",
+       "      <td>84864</td>\n",
+       "      <td>4</td>\n",
+       "      <td>41</td>\n",
+       "      <td>7</td>\n",
+       "      <td>5</td>\n",
+       "      <td>502.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39271</th>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>64200</td>\n",
+       "      <td>3</td>\n",
+       "      <td>61</td>\n",
+       "      <td>7</td>\n",
+       "      <td>4</td>\n",
+       "      <td>301.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26364</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>61864</td>\n",
+       "      <td>3</td>\n",
+       "      <td>91</td>\n",
+       "      <td>6</td>\n",
+       "      <td>3</td>\n",
+       "      <td>461.166667</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        METRO3  REGION   LMED  BEDRMS  HOUSE_AGE  ROOMS  PER     UTILITY\n",
+       "22170        2       2  67109       4         21      9    3  126.083333\n",
+       "17193        2       2  62800       3         41      6    2  201.000000\n",
+       "137803       4       1  84864       4         41      7    5  502.500000\n",
+       "39271        2       1  64200       3         61      7    4  301.000000\n",
+       "26364        3       2  61864       3         91      6    3  461.166667"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0% (0 of 11) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  9% (1 of 11) |##                       | Elapsed Time: 0:00:35 ETA:   0:05:51\n",
+      " 18% (2 of 11) |####                     | Elapsed Time: 0:01:09 ETA:   0:05:08\n",
+      " 27% (3 of 11) |######                   | Elapsed Time: 0:01:44 ETA:   0:04:38\n",
+      " 36% (4 of 11) |#########                | Elapsed Time: 0:02:22 ETA:   0:04:25\n",
+      " 45% (5 of 11) |###########              | Elapsed Time: 0:02:55 ETA:   0:03:22\n",
+      " 54% (6 of 11) |#############            | Elapsed Time: 0:03:28 ETA:   0:02:43\n",
+      " 63% (7 of 11) |###############          | Elapsed Time: 0:04:01 ETA:   0:02:12\n",
+      " 72% (8 of 11) |##################       | Elapsed Time: 0:04:36 ETA:   0:01:43\n",
+      " 81% (9 of 11) |####################     | Elapsed Time: 0:05:07 ETA:   0:01:02\n",
+      " 90% (10 of 11) |#####################   | Elapsed Time: 0:05:40 ETA:   0:00:33\n",
+      "100% (11 of 11) |########################| Elapsed Time: 0:06:14 Time:  0:06:14\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error: 57308274833.9465\n",
+      "Root Mean Squared Error: 239391.4678\n"
+     ]
+    }
+   ],
+   "source": [
+    "gam_model = LinearGAM(s(0, dtype='categorical') \n",
+    "                      + s(1, dtype='categorical') \n",
+    "                      + s(2, n_splines=250) \n",
+    "                      + s(3, dtype='categorical') \n",
+    "                      + s(4, n_splines=250) \n",
+    "                      + s(5, dtype='categorical') \n",
+    "                      + s(6, dtype='categorical') \n",
+    "                      + s(7, n_splines=250) \n",
+    "                      )\n",
+    "\n",
+    "gam_model.gridsearch(np.array(X_train), y_train)\n",
+    "gam_model.fit(np.array(X_train), y_train)\n",
+    "gam_test_preds = gam_model.predict(X_test)\n",
+    "\n",
+    "mse = mean_squared_error(y_test, gam_test_preds)\n",
+    "print(f\"Mean Squared Error: {mse:.4f}\")\n",
+    "\n",
+    "rmse = np.sqrt(mse)\n",
+    "print(f\"Root Mean Squared Error: {rmse:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('gam_model_hud.pkl', 'wb') as file:\n",
+    "    pickle.dump(gam_model, file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = torch.FloatTensor(X_train.values)\n",
+    "y_train = torch.FloatTensor(y_train.values).reshape(-1, 1)\n",
+    "X_test = torch.FloatTensor(X_test.values)\n",
+    "y_test = torch.FloatTensor(y_test.values).reshape(-1, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class HousePriceModel(nn.Module):\n",
+    "    def __init__(self, input_size):\n",
+    "        super(HousePriceModel, self).__init__()\n",
+    "        self.model = nn.Sequential(\n",
+    "            nn.Linear(input_size, 128),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(128, 64),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(64, 32),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(32, 1)\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.model(x)\n",
+    "        return x\n",
+    "\n",
+    "model = HousePriceModel(X_train.shape[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "criterion = nn.MSELoss()\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.0001)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/100], Loss: 461675626496.0000\n",
+      "Epoch [20/100], Loss: 461912539136.0000\n",
+      "Epoch [30/100], Loss: 465912332288.0000\n",
+      "Epoch [40/100], Loss: 465710579712.0000\n",
+      "Epoch [50/100], Loss: 465482645504.0000\n",
+      "Epoch [60/100], Loss: 465170137088.0000\n",
+      "Epoch [70/100], Loss: 464703356928.0000\n",
+      "Epoch [80/100], Loss: 464297361408.0000\n",
+      "Epoch [90/100], Loss: 463879012352.0000\n",
+      "Epoch [100/100], Loss: 463475539968.0000\n"
+     ]
+    }
+   ],
+   "source": [
+    "num_epochs = 100\n",
+    "batch_size = 32\n",
+    "\n",
+    "for epoch in range(num_epochs):\n",
+    "    for i in range(0, len(X_train), batch_size):\n",
+    "        batch_X = X_train[i:i+batch_size]\n",
+    "        batch_y = y_train[i:i+batch_size]\n",
+    "        \n",
+    "        outputs = model(batch_X)\n",
+    "        loss = criterion(outputs, batch_y)\n",
+    "        \n",
+    "        optimizer.zero_grad()\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "    \n",
+    "    if (epoch + 1) % 10 == 0:\n",
+    "        print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error: 77202161664.0000\n",
+      "Root Mean Squared Error: 277852.7812\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.eval()\n",
+    "with torch.no_grad():\n",
+    "    y_pred = model(X_test)\n",
+    "    mse = criterion(y_pred, y_test)\n",
+    "    rmse = torch.sqrt(mse)\n",
+    "    print(f'Mean Squared Error: {mse.item():.4f}')\n",
+    "    print(f'Root Mean Squared Error: {rmse.item():.4f}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.save(model.state_dict(), 'dnn_model_hud.pth')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>MedInc</th>\n",
+       "      <th>HouseAge</th>\n",
+       "      <th>AveRooms</th>\n",
+       "      <th>AveBedrms</th>\n",
+       "      <th>Population</th>\n",
+       "      <th>AveOccup</th>\n",
+       "      <th>Latitude</th>\n",
+       "      <th>Longitude</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.3252</td>\n",
+       "      <td>41.0</td>\n",
+       "      <td>6.984127</td>\n",
+       "      <td>1.023810</td>\n",
+       "      <td>322.0</td>\n",
+       "      <td>2.555556</td>\n",
+       "      <td>37.88</td>\n",
+       "      <td>-122.23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>8.3014</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>6.238137</td>\n",
+       "      <td>0.971880</td>\n",
+       "      <td>2401.0</td>\n",
+       "      <td>2.109842</td>\n",
+       "      <td>37.86</td>\n",
+       "      <td>-122.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.2574</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>8.288136</td>\n",
+       "      <td>1.073446</td>\n",
+       "      <td>496.0</td>\n",
+       "      <td>2.802260</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>5.6431</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>5.817352</td>\n",
+       "      <td>1.073059</td>\n",
+       "      <td>558.0</td>\n",
+       "      <td>2.547945</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3.8462</td>\n",
+       "      <td>52.0</td>\n",
+       "      <td>6.281853</td>\n",
+       "      <td>1.081081</td>\n",
+       "      <td>565.0</td>\n",
+       "      <td>2.181467</td>\n",
+       "      <td>37.85</td>\n",
+       "      <td>-122.25</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude  \\\n",
+       "0  8.3252      41.0  6.984127   1.023810       322.0  2.555556     37.88   \n",
+       "1  8.3014      21.0  6.238137   0.971880      2401.0  2.109842     37.86   \n",
+       "2  7.2574      52.0  8.288136   1.073446       496.0  2.802260     37.85   \n",
+       "3  5.6431      52.0  5.817352   1.073059       558.0  2.547945     37.85   \n",
+       "4  3.8462      52.0  6.281853   1.081081       565.0  2.181467     37.85   \n",
+       "\n",
+       "   Longitude  \n",
+       "0    -122.23  \n",
+       "1    -122.22  \n",
+       "2    -122.24  \n",
+       "3    -122.25  \n",
+       "4    -122.25  "
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "housing = fetch_california_housing()\n",
+    "\n",
+    "X, y = pd.DataFrame(housing.data), pd.DataFrame(housing.target)\n",
+    "X.columns = housing.feature_names\n",
+    "X.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0% (0 of 11) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--\n",
+      "  9% (1 of 11) |##                       | Elapsed Time: 0:00:36 ETA:   0:06:09\n",
+      " 18% (2 of 11) |####                     | Elapsed Time: 0:01:13 ETA:   0:05:24\n",
+      " 27% (3 of 11) |######                   | Elapsed Time: 0:01:48 ETA:   0:04:46\n",
+      " 36% (4 of 11) |#########                | Elapsed Time: 0:02:25 ETA:   0:04:15\n",
+      " 45% (5 of 11) |###########              | Elapsed Time: 0:03:00 ETA:   0:03:30\n",
+      " 54% (6 of 11) |#############            | Elapsed Time: 0:03:35 ETA:   0:02:55\n",
+      " 63% (7 of 11) |###############          | Elapsed Time: 0:04:13 ETA:   0:02:30\n",
+      " 72% (8 of 11) |##################       | Elapsed Time: 0:04:49 ETA:   0:01:48\n",
+      " 81% (9 of 11) |####################     | Elapsed Time: 0:05:29 ETA:   0:01:20\n",
+      " 90% (10 of 11) |#####################   | Elapsed Time: 0:06:09 ETA:   0:00:40\n",
+      "100% (11 of 11) |########################| Elapsed Time: 0:06:47 Time:  0:06:47\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error: 0.3081\n",
+      "Root Mean Squared Error: 0.5550\n"
+     ]
+    }
+   ],
+   "source": [
+    "gam_model = LinearGAM(s(0, n_splines=250) \n",
+    "                      + s(1, n_splines=250) \n",
+    "                      + s(2, n_splines=250) \n",
+    "                      + s(3, n_splines=250) \n",
+    "                      + s(4, n_splines=250) \n",
+    "                      + s(5, n_splines=250) \n",
+    "                      + s(6, n_splines=250) \n",
+    "                      + s(7, n_splines=250) \n",
+    "                      )\n",
+    "gam_model.gridsearch(np.array(X_train), y_train)\n",
+    "gam_model.fit(np.array(X_train), y_train)\n",
+    "gam_test_preds = gam_model.predict(X_test)\n",
+    "\n",
+    "mse = mean_squared_error(y_test, gam_test_preds)\n",
+    "print(f\"Mean Squared Error: {mse:.4f}\")\n",
+    "\n",
+    "rmse = np.sqrt(mse)\n",
+    "print(f\"Root Mean Squared Error: {rmse:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('gam_model_california.pkl', 'wb') as file:\n",
+    "    pickle.dump(gam_model, file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = torch.FloatTensor(X_train.values)\n",
+    "y_train = torch.FloatTensor(y_train.values).reshape(-1, 1)\n",
+    "X_test = torch.FloatTensor(X_test.values)\n",
+    "y_test = torch.FloatTensor(y_test.values).reshape(-1, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class HousePriceModel(nn.Module):\n",
+    "    def __init__(self, input_size):\n",
+    "        super(HousePriceModel, self).__init__()\n",
+    "        self.model = nn.Sequential(\n",
+    "            nn.Linear(input_size, 128),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(128, 64),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(64, 32),\n",
+    "            nn.LeakyReLU(0.2,inplace=True),\n",
+    "            nn.Linear(32, 1)\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.model(x)\n",
+    "        return x\n",
+    "\n",
+    "model = HousePriceModel(X_train.shape[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "criterion = nn.MSELoss()\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.0001)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/100], Loss: 1.0281\n",
+      "Epoch [20/100], Loss: 0.7823\n",
+      "Epoch [30/100], Loss: 0.6930\n",
+      "Epoch [40/100], Loss: 0.7010\n",
+      "Epoch [50/100], Loss: 0.6770\n",
+      "Epoch [60/100], Loss: 0.6713\n",
+      "Epoch [70/100], Loss: 0.6740\n",
+      "Epoch [80/100], Loss: 0.7874\n",
+      "Epoch [90/100], Loss: 0.7111\n",
+      "Epoch [100/100], Loss: 0.6300\n"
+     ]
+    }
+   ],
+   "source": [
+    "num_epochs = 100\n",
+    "batch_size = 32\n",
+    "\n",
+    "for epoch in range(num_epochs):\n",
+    "    for i in range(0, len(X_train), batch_size):\n",
+    "        batch_X = X_train[i:i+batch_size]\n",
+    "        batch_y = y_train[i:i+batch_size]\n",
+    "        \n",
+    "        outputs = model(batch_X)\n",
+    "        loss = criterion(outputs, batch_y)\n",
+    "        \n",
+    "        optimizer.zero_grad()\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "    \n",
+    "    if (epoch + 1) % 10 == 0:\n",
+    "        print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error: 0.9678\n",
+      "Root Mean Squared Error: 0.9838\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.eval()\n",
+    "with torch.no_grad():\n",
+    "    y_pred = model(X_test)\n",
+    "    mse = criterion(y_pred, y_test)\n",
+    "    rmse = torch.sqrt(mse)\n",
+    "    print(f'Mean Squared Error: {mse.item():.4f}')\n",
+    "    print(f'Root Mean Squared Error: {rmse.item():.4f}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.save(model.state_dict(), 'dnn_model_california.pth')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Latitude</th>\n",
+       "      <th>Longitude</th>\n",
+       "      <th>County</th>\n",
+       "      <th>City</th>\n",
+       "      <th>Incorportation_date</th>\n",
+       "      <th>pop_april_1980</th>\n",
+       "      <th>pop_april_1990</th>\n",
+       "      <th>pop_april_2000</th>\n",
+       "      <th>pop_april_2010</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>34.582769</td>\n",
+       "      <td>-117.409214</td>\n",
+       "      <td>San Bernardino</td>\n",
+       "      <td>Adelanto</td>\n",
+       "      <td>1970</td>\n",
+       "      <td>2164.0</td>\n",
+       "      <td>8517</td>\n",
+       "      <td>18130</td>\n",
+       "      <td>31765</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>34.153339</td>\n",
+       "      <td>-118.761675</td>\n",
+       "      <td>Los Angeles</td>\n",
+       "      <td>Agoura Hills</td>\n",
+       "      <td>1982</td>\n",
+       "      <td>20390.0</td>\n",
+       "      <td>20390</td>\n",
+       "      <td>20537</td>\n",
+       "      <td>20330</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>37.765206</td>\n",
+       "      <td>-122.241636</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>1854</td>\n",
+       "      <td>63852.0</td>\n",
+       "      <td>76459</td>\n",
+       "      <td>72259</td>\n",
+       "      <td>73812</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>37.886869</td>\n",
+       "      <td>-122.297747</td>\n",
+       "      <td>Alameda</td>\n",
+       "      <td>Albany</td>\n",
+       "      <td>1908</td>\n",
+       "      <td>15130.0</td>\n",
+       "      <td>16327</td>\n",
+       "      <td>16444</td>\n",
+       "      <td>18539</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>34.095286</td>\n",
+       "      <td>-118.127014</td>\n",
+       "      <td>Los Angeles</td>\n",
+       "      <td>Alhambra</td>\n",
+       "      <td>1903</td>\n",
+       "      <td>64767.0</td>\n",
+       "      <td>82106</td>\n",
+       "      <td>85804</td>\n",
+       "      <td>83089</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Latitude   Longitude          County          City Incorportation_date  \\\n",
+       "0  34.582769 -117.409214  San Bernardino      Adelanto                1970   \n",
+       "1  34.153339 -118.761675     Los Angeles  Agoura Hills                1982   \n",
+       "2  37.765206 -122.241636         Alameda       Alameda                1854   \n",
+       "3  37.886869 -122.297747         Alameda        Albany                1908   \n",
+       "4  34.095286 -118.127014     Los Angeles      Alhambra                1903   \n",
+       "\n",
+       "   pop_april_1980  pop_april_1990  pop_april_2000  pop_april_2010  \n",
+       "0          2164.0            8517           18130           31765  \n",
+       "1         20390.0           20390           20537           20330  \n",
+       "2         63852.0           76459           72259           73812  \n",
+       "3         15130.0           16327           16444           18539  \n",
+       "4         64767.0           82106           85804           83089  "
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('california_cities.csv')\n",
+    "df = df.iloc[:, 1:]\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.groupby(['County']).agg({\n",
+    "    'Latitude': 'mean',\n",
+    "    'Longitude': 'mean',\n",
+    "    'pop_april_1990': 'sum',\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv('california_counties.csv')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "cnn_module",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

pages/about.py

@@ -0,0 +1,80 @@
+import streamlit as st
+from streamlit_option_menu import option_menu
+
+def show():
+    st.markdown("# _Explainable AI for Housing Estimates_")
+    
+    st.markdown("""
+    ## Background
+    
+    _This application is designed to demonstrate an understanding of how complex problems can be explained 
+    using Generalized Additive Models (GAMs) and LIME, and when used in conjunction of one another, can sometimes
+    explain even the most complex decision boundaries._
+    """)
+    
+    st.markdown("""
+    ### Generalized Additive Models
+    
+    > GAMs are an extension of linear regression models that allow for non-linear relationships between the 
+    features and target. GAMs use "smooth functions of our feature variables, which can take on a great many 
+    forms, with more detail on what that means in the following section" (Clarke). This is where GAMs differ from 
+    generalized linear models like linear regression. A GAM is "composed of a sum of smooth functions of features 
+    instead of or in addition to the standard linear feature contributions" (Clarke). These smooth functions or
+    spline functions can create non-linear decision boundaries. Spline functions show the partial dependence of 
+    each feature on the target variable, enabling a high-level understanding of the model predictions.  
+    """)
+    
+    st.markdown("""
+    ### Local Interpretable Model-agnostic Explanations (LIME)
+    - Local - explanation should reflect the behavior of the classifier in the neighborhood of the instance being predicted
+    - Interpretable - human is able to make sense of it
+    - Model Agnostic - applied to any machine learning model
+    - Explanation - that helps interpret the model
+    """)
+    
+    st.markdown("""
+    > LIME is a powerful tool that explains some predictions created by a neural network. 
+    However, LIME only explains a local area within the neural network model and does not fully explain the entire decision space of a given model. 
+    This is an important consideration when using LIME, for example, you are only mapping a subset of the entire decision space of a black box model.
+    """)
+    
+    st.markdown("""
+    ### Purpose
+    > This project aims to provide insights into Generalized Additive Models and LIME and how they can be used to create and explain non-linear solutions
+    """)
+    
+    st.markdown("""
+    ### Models
+    > **Neural Network**: 3 linear layers using pytorch  
+    > **GAM**: linear gam using pygam
+    """)
+    
+    st.markdown("""
+    ### Author
+    > Created by Keese Phillips
+    
+    ### Contact
+    > [keese.phillips@duke.edu](mailto:keese.phillips@duke.edu)
+    """)
+    
+    st.markdown("""
+    ### References
+    > Clark, Michael. “Generalized Additive Models.” Generalized Additive Models, m-clark.github.io/generalized-additive-models/introduction.html. Accessed 2 Dec. 2024. 
+    """)
+
+if __name__ == '__main__':
+    st.set_page_config(page_title="Generative Additive Model", page_icon="🚀")
+    page = option_menu(
+        menu_title=None,
+        options=["Home", "About"],
+        icons=["house", "book"],
+        menu_icon="cast",
+        default_index=1,
+        orientation="horizontal",
+    )
+    if page == "Home":
+        st.switch_page("pages/main.py")
+    elif page == "About":
+        show()
+
+    st.info("This app is for explaining the problem domain using Generalized Additive Models")

pages/main.py

@@ -0,0 +1,365 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import StandardScaler,OrdinalEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.metrics import classification_report, recall_score, precision_score, accuracy_score
+from sklearn.metrics import mean_squared_error
+import matplotlib.pyplot as plt
+import seaborn as sns
+import zipfile
+from statsmodels.genmod.generalized_linear_model import GLM
+from statsmodels.genmod.families import Gamma
+from statsmodels.genmod.families.links import Log
+from statsmodels.tools import add_constant
+from pygam import LinearGAM, GammaGAM, s, f
+import pickle
+import streamlit.components.v1 as components
+import streamlit as st
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from streamlit_option_menu import option_menu
+from pygam import LinearGAM
+import lime
+from lime import lime_tabular
+
+
+class HousePriceModel(nn.Module):
+    def __init__(self, input_size):
+        super(HousePriceModel, self).__init__()
+        self.model = nn.Sequential(
+            nn.Linear(input_size, 128),
+            nn.LeakyReLU(0.2,inplace=True),
+            nn.Linear(128, 64),
+            nn.LeakyReLU(0.2,inplace=True),
+            nn.Linear(64, 32),
+            nn.LeakyReLU(0.2,inplace=True),
+            nn.Linear(32, 1)
+        )
+
+    def forward(self, x):
+        x = self.model(x)
+        return x
+
+
+def lime_component(X, input_data, dnn_model, gam_model, terms, y_min, y_max):
+    """
+    Generate and display a LIME (Local Interpretable Model-agnostic Explanations) component.
+
+    :param X: pandas.DataFrame
+        The feature matrix used to train the explainer.
+    :param input_data: list or numpy.array
+        The input data point to explain.
+    :param dnn_model: torch.nn.Module
+        The trained neural network model.
+    :param gam_model: object
+        The trained Generalized Additive Model 
+    :param terms: list
+        List of feature names.
+    :param y_min: float
+        Minimum y-axis value 
+    :param y_max: float
+        Maximum y-axis value 
+
+    :return: None
+    """
+    def nn_prediction(input_data):
+        input_tensor = torch.FloatTensor(input_data)
+        dnn_model.eval()
+        with torch.no_grad():
+            output = dnn_model(input_tensor)
+        
+        return output.cpu().numpy()
+
+    kernel_width = 3
+    explainer = lime.lime_tabular.LimeTabularExplainer(X.values,mode='regression',feature_names=terms, kernel_width=kernel_width)
+    exp = explainer.explain_instance(np.array(input_data), nn_prediction, num_features=len(input_data))
+
+    feature_importance = exp.as_list()
+    intercept = exp.intercept[0]
+    formula = f"> _**y =** {intercept:.4f}"
+    i = 0
+    for feature, importance in feature_importance:
+        if importance > 0:
+            formula += f" + {importance:.4f} * **{terms[i]}**"
+        else:
+            formula += f" - {abs(importance):.4f} * **{terms[i]}**"
+        i += 1
+    formula += '_'
+    st.markdown(formula)
+
+    lime_graph = exp.as_pyplot_figure()
+    st.pyplot(lime_graph)
+    
+        
+def spline_component(X, input_data, dnn_model, gam_model, terms, y_min, y_max):
+    """
+    Generate the spline functions in a component.
+
+    :param X: pandas.DataFrame
+        The feature matrix used to train the explainer.
+    :param input_data: list or numpy.array
+        The input data point to explain.
+    :param dnn_model: torch.nn.Module
+        The trained neural network model.
+    :param gam_model: object
+        The trained Generalized Additive Model 
+    :param terms: list
+        List of feature names.
+    :param y_min: float
+        Minimum y-axis value 
+    :param y_max: float
+        Maximum y-axis value 
+
+    :return: None
+    """
+    col1, col2 = st.columns(2)
+
+    for i in range(len(terms)):
+        XX = gam_model.generate_X_grid(term=i)
+        pdep, confi = gam_model.partial_dependence(term=i, X=XX, width=0.95)
+        fig, ax = plt.subplots(figsize=(6, 6))
+        
+        # Plot partial dependence
+        ax.plot(XX[:, i], pdep, label='Partial Dependence')
+        ax.plot(XX[:, i], confi, c='r', ls='--', label='Confidence Interval')
+        
+        # Find y-value corresponding to user input
+        user_x = input_data[i]
+        user_y = np.interp(user_x, XX[:, i], pdep)
+        
+        # Plot vertical and horizontal lines
+        ax.axvline(x=user_x, color='b', linestyle='--', label='Model Input',ymin=0, ymax=(user_y-y_min)/(y_max-y_min))
+        ax.axhline(y=user_y, color='b', linestyle='--', xmin=0, xmax=(user_x - XX[0, i]) / (XX[-1, i] - XX[0, i]))
+        ax.annotate(f'{user_y:.2f}', (user_x, user_y), textcoords="offset points", xytext=(0,20), ha='center')
+        
+        ax.set_title(f'{terms[i]}')
+        ax.set_xlabel(terms[i])
+        ax.set_ylabel('Partial Dependence')
+        ax.legend(loc='best', fontsize='x-small')
+        
+        # Set consistent y-axis limits
+        ax.set_ylim(y_min, y_max)
+        plt.tight_layout(pad=1.5)
+        
+        # Alternate between columns
+        if i % 2 == 0:
+            with col1:
+                st.write(f"Spline function: {terms[i]}:")
+                st.pyplot(fig)
+                
+        else:
+            with col2:
+                st.write(f"Spline function: {terms[i]}:")
+                st.pyplot(fig)
+        
+        plt.close(fig)
+
+def prediction_component(X, input_data, dnn_model, gam_model, terms, y_min, y_max, scale=1):
+    """
+    Generates the main component for the spline functions and LIME based upon the GAM and 
+    the neural network.
+
+    :param X: pandas.DataFrame
+        The feature matrix used to train the explainer.
+    :param input_data: list or numpy.array
+        The input data point to explain.
+    :param dnn_model: torch.nn.Module
+        The trained neural network model.
+    :param gam_model: object
+        The trained Generalized Additive Model 
+    :param terms: list
+        List of feature names.
+    :param y_min: float
+        Minimum y-axis value 
+    :param y_max: float
+        Maximum y-axis value 
+    :param scale: int
+        The scale of the model's dataset's price 
+
+    :return: None
+    """
+    input_array = np.array(input_data).reshape(1, -1)
+    
+    dnn_prediction = dnn_model(torch.FloatTensor(input_array))[0][0]
+    gam_prediction = gam_model.predict(input_array)[0]
+    
+    st.markdown("# Predictions")
+    st.write(f"- _General Additive Model Prediction:_ ${gam_prediction*scale:.2f}")
+    st.write(f"- _Neural Network Prediction:_ ${dnn_prediction*scale:.2f}")
+    st.markdown("----------------")
+    
+    st.markdown("## Spline Functions")
+    spline_component(X, input_data, dnn_model, gam_model, terms, y_min, y_max)
+    st.markdown("----------------")
+    st.markdown("## LIME Explanation for Neural Network")
+    
+    lime_component(X, input_data, dnn_model, gam_model, terms, y_min, y_max)
+
+
+def show():
+    st.markdown("# _Explainable AI for Housing Costs_")
+    st.markdown("""
+            ## _Models_
+            ### California Housing Dataset:
+            > This dataset is more concentrated and is far less sparse as the dataset includes a smaller population from 1990 and only in California
+            ### HUD Housing Dataset:
+            > This dataset is far more sparse and is calculated over the entire country with data from all the different regions of the country 
+            """)
+    st.markdown("----------------")
+
+    model_versions = ['California Housing Dataset', 'HUD Housing Dataset']    
+    value = st.selectbox(f"Select model version", model_versions)
+    st.markdown("----------------")
+    
+    st.write('Generate model predictions:')
+    if value == 'HUD Housing Dataset':
+        dnn_model = HousePriceModel(8)
+        dnn_model.load_state_dict(torch.load('models/dnn_model_hud.pth'))
+        dnn_model.eval()
+
+        with open('models/gam_model_hud.pkl', 'rb') as file:
+            gam_model = pickle.load(file)
+            
+        dnn_mse = 77202161664.0000
+        gam_mse = 57308274833.9465
+
+        input_data = [None] * 8
+
+        terms = [
+            'City/Suburban Status',
+            'Census Region',
+            'Area median income (average)',
+            '# of bedrooms in unit',
+            'Age of the house (years)',
+            '# of rooms in unit',
+            '# of Persons in Household',
+            'Monthly utility cost'
+        ]
+
+        region_code = {
+            'Northeast': 1,
+            'Midwest': 2,
+            'South': 3,
+            'West': 4,
+        }
+
+        metro_code = {
+            'Central cities of metropolitan areas': 1,
+            'Inside metropolitan area, but not in central city': 2,
+            'Inside metropolitan area, but not in central city - rural': 3,
+            'Outside metropolitan areas, urbanized': 4,
+            'Outside metropolitan areas, rural': 5,
+        }
+
+        with st.sidebar:
+            st.title("Model Inputs")
+            value = st.selectbox(f"{terms[0]}", metro_code.keys())
+            input_data[0] =metro_code[value]
+            value = st.selectbox(f"{terms[0]}", region_code.keys())
+            input_data[1] =region_code[value]
+            value = st.number_input(f"{terms[2]}", value=84200)
+            input_data[2] =value
+            value = st.number_input(f"{terms[3]}", value=4)
+            input_data[3] =value
+            value = st.number_input(f"{terms[4]}", value=9)
+            input_data[4] =value
+            value = st.number_input(f"{terms[5]}", value=8)
+            input_data[5] =value
+            value = st.number_input(f"{terms[6]}", value=3)
+            input_data[6] =value
+            value = st.number_input(f"{terms[7]}", value=300)
+            input_data[7] =value
+
+        df = pd.read_csv('data/hud_dataset.csv', index_col=False)
+        X, y = df.drop(columns=['VALUE']), df['VALUE']
+
+        if st.button("Predict"):
+            st.markdown("# Model Loss")
+            st.write(f"- _Mean Squared Error (Generalized Additive Model):_ {gam_mse:.3f}")
+            st.write(f"- _Mean Squared Error (Neural Network Model):_ {dnn_mse:.3f}")
+            st.markdown("----------------")
+            prediction_component(X, input_data, dnn_model, gam_model, terms, y_min = -500000, y_max = 500000)
+                
+    else: 
+        dnn_model = HousePriceModel(8)
+        dnn_model.load_state_dict(torch.load('models/dnn_model_california.pth'))
+        dnn_model.eval()
+
+        with open('models/gam_model_california.pkl', 'rb') as file:
+            gam_model = pickle.load(file)
+            
+        dnn_mse = 0.9678
+        gam_mse = 0.3081
+
+        input_data = [None] * 8
+
+        terms = [
+            'Median Income',
+            'House Age (years)',
+            'Average Rooms',
+            'Average Bedrooms',
+            'Population (average of census block group per county)',
+            'Average Occupancy',
+            'Latitude',
+            'Longitude'
+        ]
+        
+        counties = pd.read_csv('data/california_counties.csv')
+        distinct_counties = list(counties['County'].unique())
+
+        with st.sidebar:
+            st.title("Model Inputs")
+            county = st.selectbox(f"{terms[0]}", distinct_counties)
+            counties = counties[counties['County'] == county]
+            county_vals = counties.values[0]
+            population = county_vals[4] / 442
+            lat = county_vals[2]
+            long = county_vals[3]
+            value = st.number_input(f"{terms[0]}", value=84200)
+            input_data[0] =value/10000
+            value = st.number_input(f"{terms[1]}", value=4)
+            input_data[1] =value
+            value = st.number_input(f"{terms[2]}", value=9)
+            input_data[2] =value
+            value = st.number_input(f"{terms[3]}", value=8)
+            input_data[3] =value
+            input_data[4] = population
+            value = st.number_input(f"{terms[5]}", value=3)
+            input_data[5] =value
+            input_data[6] = lat
+            input_data[7] = long
+            
+        housing = fetch_california_housing()
+        X, y = pd.DataFrame(housing.data), pd.DataFrame(housing.target)
+        X.columns = housing.feature_names
+
+        if st.button("Predict"):
+            st.markdown("# Model Loss")
+            st.write(f"- _Mean Squared Error (Generalized Additive Model):_ {gam_mse:.3f}")
+            st.write(f"- _Mean Squared Error (Neural Network Model):_ {dnn_mse:.3f}")
+            st.markdown("----------------")
+            prediction_component(X, input_data, dnn_model, gam_model, terms, y_min = -10, y_max = 10, scale=100000)
+            
+if __name__ == '__main__':
+    st.set_page_config(page_title="Generalized Additive Models", page_icon="🚀")
+    page = option_menu(
+        menu_title=None,
+        options=["Home", "About"],
+        icons=["house", "book"],
+        menu_icon="cast",
+        default_index=0,
+        orientation="horizontal",
+    )
+    if page == "Home":
+        show()
+    elif page == "About":
+        st.switch_page("pages/about.py")
+
+    st.info("This app is for explaining the problem domain using Generalized Additive Models")