{ "cells": [ { "cell_type": "markdown", "id": "1331b862", "metadata": {}, "source": [ "## 2022 SAT SCORE DISTRIBUTION BY STATE" ] }, { "cell_type": "code", "execution_count": 152, "id": "9ff897e8", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import geopandas as gpd\n", "import folium \n", "from folium import plugins\n", "from folium.plugins import StripePattern\n", "import numpy as np" ] }, { "cell_type": "markdown", "id": "8a3f4c18", "metadata": {}, "source": [ "First, get Folium's shape files, which supplies mappable state locations:" ] }, { "cell_type": "code", "execution_count": 153, "id": "b8212f03", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idnamegeometry
0ALAlabamaPOLYGON ((-87.35930 35.00118, -85.60667 34.984...
1AKAlaskaMULTIPOLYGON (((-131.60202 55.11798, -131.5691...
2AZArizonaPOLYGON ((-109.04250 37.00026, -109.04798 31.3...
3ARArkansasPOLYGON ((-94.47384 36.50186, -90.15254 36.496...
4CACaliforniaPOLYGON ((-123.23326 42.00619, -122.37885 42.0...
\n", "
" ], "text/plain": [ " id name geometry\n", "0 AL Alabama POLYGON ((-87.35930 35.00118, -85.60667 34.984...\n", "1 AK Alaska MULTIPOLYGON (((-131.60202 55.11798, -131.5691...\n", "2 AZ Arizona POLYGON ((-109.04250 37.00026, -109.04798 31.3...\n", "3 AR Arkansas POLYGON ((-94.47384 36.50186, -90.15254 36.496...\n", "4 CA California POLYGON ((-123.23326 42.00619, -122.37885 42.0..." ] }, "execution_count": 153, "metadata": {}, "output_type": "execute_result" } ], "source": [ "state_geo = (\"https://raw.githubusercontent.com/python-visualization/folium/main/examples/data/us-states.json\")\n", "geoJSON_df = gpd.read_file(state_geo)\n", "geoJSON_df.head()" ] }, { "cell_type": "markdown", "id": "5d3dce7a", "metadata": {}, "source": [ "Now we'll merge the shapes with some columns of SAT data to get everything into one dataframe:" ] }, { "cell_type": "code", "execution_count": 154, "id": "a06af1aa", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateabbrnamegeometryTotalMeanParticipation
0ALAlabamaPOLYGON ((-87.35930 35.00118, -85.60667 34.984...11460.04
1AKAlaskaMULTIPOLYGON (((-131.60202 55.11798, -131.5691...11100.26
2AZArizonaPOLYGON ((-109.04250 37.00026, -109.04798 31.3...11590.14
3ARArkansasPOLYGON ((-94.47384 36.50186, -90.15254 36.496...11910.02
4CACaliforniaPOLYGON ((-123.23326 42.00619, -122.37885 42.0...11150.21
\n", "
" ], "text/plain": [ " stateabbr name geometry \\\n", "0 AL Alabama POLYGON ((-87.35930 35.00118, -85.60667 34.984... \n", "1 AK Alaska MULTIPOLYGON (((-131.60202 55.11798, -131.5691... \n", "2 AZ Arizona POLYGON ((-109.04250 37.00026, -109.04798 31.3... \n", "3 AR Arkansas POLYGON ((-94.47384 36.50186, -90.15254 36.496... \n", "4 CA California POLYGON ((-123.23326 42.00619, -122.37885 42.0... \n", "\n", " TotalMean Participation \n", "0 1146 0.04 \n", "1 1110 0.26 \n", "2 1159 0.14 \n", "3 1191 0.02 \n", "4 1115 0.21 " ] }, "execution_count": 154, "metadata": {}, "output_type": "execute_result" } ], "source": [ "geoJSON_df=geoJSON_df.rename(columns = {\"id\":\"stateabbr\"})\n", "state_scores = \"https://raw.githubusercontent.com/NickKrausStack/SATdata/main/States.csv\"\n", "df = pd.read_csv(state_scores)\n", "df = df[[\"stateabbr\",\"TotalMean\",\"Participation\"]]\n", "final_df = geoJSON_df.merge(df, on = \"stateabbr\")\n", "final_df.head()" ] }, { "cell_type": "markdown", "id": "ce465db0", "metadata": {}, "source": [ "And now we are ready to leverage Folium to produce a choropleth graph, which will provide an interactive account of averages by state." ] }, { "cell_type": "code", "execution_count": 155, "id": "5d45ab56", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Make this Notebook Trusted to load map: File -> Trust Notebook
" ], "text/plain": [ "" ] }, "execution_count": 155, "metadata": {}, "output_type": "execute_result" } ], "source": [ "m = folium.Map(location=[50, -102], zoom_start=2.5, tiles=\"openstreet map\")\n", "\n", "folium.Choropleth(\n", " geo_data=final_df,\n", " data=final_df,\n", " columns=[\"stateabbr\", \"TotalMean\"],\n", " key_on=\"feature.properties.stateabbr\",\n", " fill_color=\"RdYlGn\",\n", " fill_opacity=0.5,\n", " line_opacity=0.2,\n", " legend_name=\"SAT Scores\",\n", ").add_to(m)\n", "\n", "style_function = lambda x: {'fillColor': '#ffffff', \n", " 'color':'#000000', \n", " 'fillOpacity': 0.1, \n", " 'weight': 0.1}\n", "highlight_function = lambda x: {'fillColor': '#000000', \n", " 'color':'#000000', \n", " 'fillOpacity': 0.50, \n", " 'weight': 0.1}\n", "NIL = folium.features.GeoJson(\n", " data = final_df,\n", " style_function=style_function, \n", " control=False,\n", " highlight_function=highlight_function, \n", " tooltip=folium.features.GeoJsonTooltip(\n", " fields=['name','TotalMean'],\n", " aliases=['name','TotalMean'],\n", " style=(\"background-color: white; color: #333333; font-family: arial; font-size: 12px; padding: 10px;\") \n", " )\n", ")\n", "m.add_child(NIL)\n", "m.keep_in_front(NIL)\n", "\n", "m" ] }, { "cell_type": "markdown", "id": "08f5bb7b", "metadata": {}, "source": [ "Similar code to create the choropleth graph comparing participation by state:" ] }, { "cell_type": "code", "execution_count": 156, "id": "a189c86a", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
Make this Notebook Trusted to load map: File -> Trust Notebook
" ], "text/plain": [ "" ] }, "execution_count": 156, "metadata": {}, "output_type": "execute_result" } ], "source": [ "m = folium.Map(location=[50, -102], zoom_start=2.5, tiles=\"openstreet map\")\n", "\n", "folium.Choropleth(\n", " geo_data=final_df,\n", " data=final_df,\n", " columns=[\"stateabbr\", \"Participation\"],\n", " key_on=\"feature.properties.stateabbr\",\n", " fill_color=\"RdYlGn\",\n", " fill_opacity=0.5,\n", " line_opacity=0.2,\n", " legend_name=\"SAT Participation Rate\",\n", ").add_to(m)\n", "\n", "style_function = lambda x: {'fillColor': '#ffffff', \n", " 'color':'#000000', \n", " 'fillOpacity': 0.1, \n", " 'weight': 0.1}\n", "highlight_function = lambda x: {'fillColor': '#000000', \n", " 'color':'#000000', \n", " 'fillOpacity': 0.20, \n", " 'weight': 0.1}\n", "NIL = folium.features.GeoJson(\n", " data = final_df,\n", " style_function=style_function, \n", " control=False,\n", " highlight_function=highlight_function, \n", " tooltip=folium.features.GeoJsonTooltip(\n", " fields=['name','Participation'],\n", " aliases=['name','Participation'],\n", " style=(\"background-color: white; color: #333333; font-family: arial; font-size: 12px; padding: 10px;\") \n", " )\n", ")\n", "m.add_child(NIL)\n", "m.keep_in_front(NIL)\n", "\n", "m" ] }, { "cell_type": "markdown", "id": "1f28f687", "metadata": {}, "source": [ "Use Pandas functionality to calculate separate averages for the cluster states and the rest of the states:" ] }, { "cell_type": "code", "execution_count": 151, "id": "12f916fa", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "avg participation, cluster states: 0.06615384615384617\n", "avg participation, non cluster states: 0.4848648648648649\n" ] } ], "source": [ "midweststates = ['Montana', 'Wyoming', 'North Dakota', 'South Dakota', 'Nebraska', 'Kansas', 'Utah', 'Minnesota', 'Wisconsin', 'Missouri', 'Kentucky', 'Tennessee', 'Mississippi']\n", "midwestdf = final_df[final_df['name'].isin(midweststates)]\n", "nomidwestdf = final_df[~final_df['name'].isin(midwest)]\n", "print('avg participation, cluster states: ', midwestdf['Participation'].mean())\n", "print('avg participation, non cluster states: ', nomidwestdf['Participation'].mean())" ] }, { "cell_type": "markdown", "id": "a1c938da", "metadata": {}, "source": [ "Now we produce the meanscore/participation line graph using matplotlib." ] }, { "cell_type": "code", "execution_count": 141, "id": "958ec16a", "metadata": { "scrolled": true }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "plt.plot(df['Participation'], df['TotalMean'])\n", "plt.xlabel('Participation rate')\n", "plt.ylabel('MeanScore')\n", "plt.rcParams['figure.figsize'] = [3,3]\n", "plt.show()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.11.2" } }, "nbformat": 4, "nbformat_minor": 5 }