publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 10:04:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions
j40-cejst-2/data/data-pipeline/data_pipeline/ipython/donut_hole_testing_2024.ipynb

5773 lines
213 KiB
Text
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "markdown",
"id": "75d2705f",
"metadata": {},
"source": [
"# EXPLORATION OF DONUT HOLE WATER BOUNDARY ISSUE"
]
},
{
"cell_type": "markdown",
"id": "dea57328",
"metadata": {},
"source": [
"## Imports, constants, and data load"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "7ac0d5d9",
"metadata": {},
"outputs": [],
"source": [
"import geopandas as gpd\n",
"import pandas as pd\n",
"import numpy as np\n",
"import os\n",
"import sys\n",
"\n",
"module_path = os.path.abspath(os.path.join(\"../..\"))\n",
"if module_path not in sys.path:\n",
" sys.path.append(module_path)\n",
"\n",
"from data_pipeline.config import settings\n",
"from data_pipeline.etl.sources.geo_utils import (\n",
" add_tracts_for_geometries,\n",
" get_tract_geojson,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "16b9ffd5",
"metadata": {},
"outputs": [],
"source": [
"# pull out necessary definitions from field_names.py\n",
"ORIGINAL_TRACT = \"ORIGINAL_TRACT\"\n",
"SCORE_N_COMMUNITIES = \"Definition N (communities)\"\n",
"GEOID_TRACT_FIELD = \"GEOID10_TRACT\"\n",
"ADJACENT_MEAN_SUFFIX = \" (based on adjacency index and low income alone)\"\n",
"ADJACENCY_INDEX_SUFFIX = \" (average of neighbors)\"\n",
"CAM_ID = '48061012305'"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b3c256f9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-11-19 19:29:38,131 [ data_pipeline.etl.sources.geo_utils] DEBUG Loading tract geometry data from census ETL\n"
]
},
{
"data": {
"text/plain": [
"Index(['STATEFP10', 'COUNTYFP10', 'TRACTCE10', 'GEOID10_TRACT', 'NAME10',\n",
" 'NAMELSAD10', 'MTFCC10', 'FUNCSTAT10', 'ALAND10', 'AWATER10',\n",
" 'INTPTLAT10', 'INTPTLON10', 'geometry'],\n",
" dtype='object')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# load Census data\n",
"tract_data = get_tract_geojson()\n",
"tract_data.columns"
]
},
{
"cell_type": "markdown",
"id": "f829c206",
"metadata": {},
"source": [
"## Look at example tract in Cameron, TX"
]
},
{
"cell_type": "markdown",
"id": "f6d133ca",
"metadata": {},
"source": [
"Tract no. 48061012305 in Cameron, TX is an example of a tract that displays the donut hole water boundary issue: all the tracts that it borders are classified as disadvantaged, and it meets the poverty threshold, yet it is being incorrectly categorized as non-disadvantaged due to its water boundary. Here we pull all adjacent tracts, compare to what we see on the map, and then look for solutions."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "106425b6",
"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>STATEFP10</th>\n",
" <th>COUNTYFP10</th>\n",
" <th>TRACTCE10</th>\n",
" <th>ORIGINAL_TRACT</th>\n",
" <th>NAME10</th>\n",
" <th>NAMELSAD10</th>\n",
" <th>MTFCC10</th>\n",
" <th>FUNCSTAT10</th>\n",
" <th>ALAND10</th>\n",
" <th>AWATER10</th>\n",
" <th>INTPTLAT10</th>\n",
" <th>INTPTLON10</th>\n",
" <th>geometry</th>\n",
" <th>Definition N (communities)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" <td>POLYGON ((-97.22490 26.41153, -97.22436 26.411...</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" STATEFP10 COUNTYFP10 TRACTCE10 ORIGINAL_TRACT NAME10 NAMELSAD10 \\\n",
"0 48 061 012305 48061012305 123.05 Census Tract 123.05 \n",
"\n",
" MTFCC10 FUNCSTAT10 ALAND10 AWATER10 INTPTLAT10 INTPTLON10 \\\n",
"0 G5020 S 25920881 324996211 +26.2732070 -097.2763703 \n",
"\n",
" geometry \\\n",
"0 POLYGON ((-97.22490 26.41153, -97.22436 26.411... \n",
"\n",
" Definition N (communities) \n",
"0 False "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"## look at census data for Cameron\n",
"cam_only_df = pd.DataFrame({GEOID_TRACT_FIELD:[CAM_ID], SCORE_N_COMMUNITIES:[False]})\n",
"\n",
"cam_only_df: gpd.GeoDataFrame = tract_data.merge(\n",
" cam_only_df, on=GEOID_TRACT_FIELD\n",
" )\n",
"cam_only_df = cam_only_df.rename(columns={GEOID_TRACT_FIELD: ORIGINAL_TRACT})\n",
"cam_only_df"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "87cdbbaf",
"metadata": {
"scrolled": true
},
"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>STATEFP10_left</th>\n",
" <th>COUNTYFP10_left</th>\n",
" <th>TRACTCE10_left</th>\n",
" <th>ORIGINAL_TRACT</th>\n",
" <th>NAME10_left</th>\n",
" <th>NAMELSAD10_left</th>\n",
" <th>MTFCC10_left</th>\n",
" <th>FUNCSTAT10_left</th>\n",
" <th>ALAND10_left</th>\n",
" <th>AWATER10_left</th>\n",
" <th>...</th>\n",
" <th>TRACTCE10_right</th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th>NAME10_right</th>\n",
" <th>NAMELSAD10_right</th>\n",
" <th>MTFCC10_right</th>\n",
" <th>FUNCSTAT10_right</th>\n",
" <th>ALAND10_right</th>\n",
" <th>AWATER10_right</th>\n",
" <th>INTPTLAT10_right</th>\n",
" <th>INTPTLON10_right</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>+26.2713946</td>\n",
" <td>-097.4414470</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>+26.5154317</td>\n",
" <td>-097.5790835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>+26.5064260</td>\n",
" <td>-097.2240134</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>+25.9786218</td>\n",
" <td>-097.2580863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>+26.0631407</td>\n",
" <td>-097.2184868</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>+26.1581170</td>\n",
" <td>-097.3180348</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>+26.1902408</td>\n",
" <td>-097.1473235</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>7 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" STATEFP10_left COUNTYFP10_left TRACTCE10_left ORIGINAL_TRACT NAME10_left \\\n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"0 48 061 012305 48061012305 123.05 \n",
"\n",
" NAMELSAD10_left MTFCC10_left FUNCSTAT10_left ALAND10_left \\\n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"\n",
" AWATER10_left ... TRACTCE10_right GEOID10_TRACT NAME10_right \\\n",
"0 324996211 ... 010100 48061010100 101 \n",
"0 324996211 ... 950700 48489950700 9507 \n",
"0 324996211 ... 990000 48489990000 9900 \n",
"0 324996211 ... 012700 48061012700 127 \n",
"0 324996211 ... 012304 48061012304 123.04 \n",
"0 324996211 ... 012301 48061012301 123.01 \n",
"0 324996211 ... 990000 48061990000 9900 \n",
"\n",
" NAMELSAD10_right MTFCC10_right FUNCSTAT10_right ALAND10_right \\\n",
"0 Census Tract 101 G5020 S 365458278 \n",
"0 Census Tract 9507 G5020 S 1025415174 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"0 Census Tract 127 G5020 S 129622799 \n",
"0 Census Tract 123.04 G5020 S 5761299 \n",
"0 Census Tract 123.01 G5020 S 137622651 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"\n",
" AWATER10_right INTPTLAT10_right INTPTLON10_right \n",
"0 113041841 +26.2713946 -097.4414470 \n",
"0 377000048 +26.5154317 -097.5790835 \n",
"0 121414926 +26.5064260 -097.2240134 \n",
"0 67725054 +25.9786218 -097.2580863 \n",
"0 6286773 +26.0631407 -097.2184868 \n",
"0 119430273 +26.1581170 -097.3180348 \n",
"0 268272237 +26.1902408 -097.1473235 \n",
"\n",
"[7 rows x 27 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# get all the tracts that are adjacent to cameron\n",
"cam_adjacent_tracts: gpd.GeoDataFrame = cam_only_df.sjoin(\n",
" tract_data, predicate=\"touches\"\n",
" )\n",
"cam_adjacent_tracts"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "af3aa581",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['STATEFP10_left', 'COUNTYFP10_left', 'TRACTCE10_left', 'ORIGINAL_TRACT',\n",
" 'NAME10_left', 'NAMELSAD10_left', 'MTFCC10_left', 'FUNCSTAT10_left',\n",
" 'ALAND10_left', 'AWATER10_left', 'INTPTLAT10_left', 'INTPTLON10_left',\n",
" 'geometry', 'Definition N (communities)', 'index_right',\n",
" 'STATEFP10_right', 'COUNTYFP10_right', 'TRACTCE10_right',\n",
" 'GEOID10_TRACT', 'NAME10_right', 'NAMELSAD10_right', 'MTFCC10_right',\n",
" 'FUNCSTAT10_right', 'ALAND10_right', 'AWATER10_right',\n",
" 'INTPTLAT10_right', 'INTPTLON10_right'],\n",
" dtype='object')"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cam_adjacent_tracts.columns"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "85559ed4",
"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>ORIGINAL_TRACT</th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th>AWATER10_left</th>\n",
" <th>ALAND10_left</th>\n",
" <th>AWATER10_right</th>\n",
" <th>ALAND10_right</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48061010100</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>113041841</td>\n",
" <td>365458278</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48489950700</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>377000048</td>\n",
" <td>1025415174</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48489990000</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>121414926</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48061012700</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>67725054</td>\n",
" <td>129622799</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48061012304</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>6286773</td>\n",
" <td>5761299</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48061012301</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>119430273</td>\n",
" <td>137622651</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>48061990000</td>\n",
" <td>324996211</td>\n",
" <td>25920881</td>\n",
" <td>268272237</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ORIGINAL_TRACT GEOID10_TRACT AWATER10_left ALAND10_left AWATER10_right \\\n",
"0 48061012305 48061010100 324996211 25920881 113041841 \n",
"0 48061012305 48489950700 324996211 25920881 377000048 \n",
"0 48061012305 48489990000 324996211 25920881 121414926 \n",
"0 48061012305 48061012700 324996211 25920881 67725054 \n",
"0 48061012305 48061012304 324996211 25920881 6286773 \n",
"0 48061012305 48061012301 324996211 25920881 119430273 \n",
"0 48061012305 48061990000 324996211 25920881 268272237 \n",
"\n",
" ALAND10_right \n",
"0 365458278 \n",
"0 1025415174 \n",
"0 0 \n",
"0 129622799 \n",
"0 5761299 \n",
"0 137622651 \n",
"0 0 "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cam_adjacent_tracts[['ORIGINAL_TRACT', 'GEOID10_TRACT', \n",
" 'AWATER10_left', 'ALAND10_left', 'AWATER10_right', 'ALAND10_right']]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "60d0801f",
"metadata": {},
"outputs": [],
"source": [
"# # compare to what I see on the map for Cameron:\n",
"\n",
"# 48489950700 Willacy County\n",
"# 48061010100 Cameron County (contains Laguna Atascosa)\n",
"# 48061012301 Cameron County (contains KPIL)\n",
"# 48061012304 Cameron County (contains Port Isabel)\n",
"# 48061012700 Cameron County (contains Boca Chica Village)\n",
"\n",
"# # what about 48489990000 and 48061990000?\n",
"# both have ALAND10 = 0\n",
"# and both tract IDs end in 9990000"
]
},
{
"cell_type": "markdown",
"id": "5201e422",
"metadata": {},
"source": [
"Proposed solution: remove tracts where ALAND10=10 (ie water-only tracts)"
]
},
{
"cell_type": "markdown",
"id": "43dc09e8",
"metadata": {},
"source": [
"## Compare water-only tracts to tracts with land area"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4045bb4f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"367"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# How many of these water-only tracts exist?\n",
"len(tract_data[tract_data.ALAND10==0])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "37fdf29b",
"metadata": {
"scrolled": true
},
"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>STATEFP10</th>\n",
" <th>COUNTYFP10</th>\n",
" <th>TRACTCE10</th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th>NAME10</th>\n",
" <th>NAMELSAD10</th>\n",
" <th>MTFCC10</th>\n",
" <th>FUNCSTAT10</th>\n",
" <th>ALAND10</th>\n",
" <th>AWATER10</th>\n",
" <th>INTPTLAT10</th>\n",
" <th>INTPTLON10</th>\n",
" <th>geometry</th>\n",
" <th>water_only</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>808</th>\n",
" <td>36</td>\n",
" <td>063</td>\n",
" <td>990000</td>\n",
" <td>36063990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>1550634668</td>\n",
" <td>+43.4569085</td>\n",
" <td>-078.7926530</td>\n",
" <td>POLYGON ((-78.46554 43.37337, -78.47053 43.372...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1015</th>\n",
" <td>36</td>\n",
" <td>085</td>\n",
" <td>008900</td>\n",
" <td>36085008900</td>\n",
" <td>89</td>\n",
" <td>Census Tract 89</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>100710</td>\n",
" <td>+40.6469814</td>\n",
" <td>-074.1024106</td>\n",
" <td>POLYGON ((-74.10504 40.64808, -74.10025 40.648...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1149</th>\n",
" <td>36</td>\n",
" <td>085</td>\n",
" <td>990100</td>\n",
" <td>36085990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>80255151</td>\n",
" <td>+40.5255512</td>\n",
" <td>-074.1085829</td>\n",
" <td>POLYGON ((-74.25482 40.49390, -74.25308 40.491...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1219</th>\n",
" <td>36</td>\n",
" <td>013</td>\n",
" <td>990000</td>\n",
" <td>36013990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>1015062614</td>\n",
" <td>+42.5006582</td>\n",
" <td>-079.5141161</td>\n",
" <td>POLYGON ((-79.24982 42.53745, -79.24982 42.537...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1226</th>\n",
" <td>36</td>\n",
" <td>075</td>\n",
" <td>990000</td>\n",
" <td>36075990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>724224875</td>\n",
" <td>+43.5955454</td>\n",
" <td>-076.4442549</td>\n",
" <td>POLYGON ((-76.55001 43.45923, -76.55064 43.458...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73379</th>\n",
" <td>23</td>\n",
" <td>015</td>\n",
" <td>990000</td>\n",
" <td>23015990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>375299033</td>\n",
" <td>+43.8029690</td>\n",
" <td>-069.4652520</td>\n",
" <td>POLYGON ((-69.68695 43.81613, -69.68695 43.815...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73399</th>\n",
" <td>23</td>\n",
" <td>031</td>\n",
" <td>990100</td>\n",
" <td>23031990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>567248819</td>\n",
" <td>+43.1483531</td>\n",
" <td>-070.4998364</td>\n",
" <td>POLYGON ((-70.22209 43.46688, -70.22432 43.464...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73509</th>\n",
" <td>23</td>\n",
" <td>023</td>\n",
" <td>990000</td>\n",
" <td>23023990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>161372101</td>\n",
" <td>+43.7084463</td>\n",
" <td>-069.7721513</td>\n",
" <td>POLYGON ((-69.69756 43.81594, -69.69755 43.813...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73527</th>\n",
" <td>23</td>\n",
" <td>013</td>\n",
" <td>990000</td>\n",
" <td>23013990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>1636919697</td>\n",
" <td>+43.9538894</td>\n",
" <td>-068.9327255</td>\n",
" <td>POLYGON ((-68.73563 44.11917, -68.73179 44.117...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73629</th>\n",
" <td>23</td>\n",
" <td>005</td>\n",
" <td>990000</td>\n",
" <td>23005990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>361952519</td>\n",
" <td>+43.6058367</td>\n",
" <td>-070.0776892</td>\n",
" <td>POLYGON ((-70.07870 43.66881, -70.06517 43.673...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>367 rows × 14 columns</p>\n",
"</div>"
],
"text/plain": [
" STATEFP10 COUNTYFP10 TRACTCE10 GEOID10_TRACT NAME10 NAMELSAD10 \\\n",
"808 36 063 990000 36063990000 9900 Census Tract 9900 \n",
"1015 36 085 008900 36085008900 89 Census Tract 89 \n",
"1149 36 085 990100 36085990100 9901 Census Tract 9901 \n",
"1219 36 013 990000 36013990000 9900 Census Tract 9900 \n",
"1226 36 075 990000 36075990000 9900 Census Tract 9900 \n",
"... ... ... ... ... ... ... \n",
"73379 23 015 990000 23015990000 9900 Census Tract 9900 \n",
"73399 23 031 990100 23031990100 9901 Census Tract 9901 \n",
"73509 23 023 990000 23023990000 9900 Census Tract 9900 \n",
"73527 23 013 990000 23013990000 9900 Census Tract 9900 \n",
"73629 23 005 990000 23005990000 9900 Census Tract 9900 \n",
"\n",
" MTFCC10 FUNCSTAT10 ALAND10 AWATER10 INTPTLAT10 INTPTLON10 \\\n",
"808 G5020 S 0 1550634668 +43.4569085 -078.7926530 \n",
"1015 G5020 S 0 100710 +40.6469814 -074.1024106 \n",
"1149 G5020 S 0 80255151 +40.5255512 -074.1085829 \n",
"1219 G5020 S 0 1015062614 +42.5006582 -079.5141161 \n",
"1226 G5020 S 0 724224875 +43.5955454 -076.4442549 \n",
"... ... ... ... ... ... ... \n",
"73379 G5020 S 0 375299033 +43.8029690 -069.4652520 \n",
"73399 G5020 S 0 567248819 +43.1483531 -070.4998364 \n",
"73509 G5020 S 0 161372101 +43.7084463 -069.7721513 \n",
"73527 G5020 S 0 1636919697 +43.9538894 -068.9327255 \n",
"73629 G5020 S 0 361952519 +43.6058367 -070.0776892 \n",
"\n",
" geometry water_only \n",
"808 POLYGON ((-78.46554 43.37337, -78.47053 43.372... True \n",
"1015 POLYGON ((-74.10504 40.64808, -74.10025 40.648... True \n",
"1149 POLYGON ((-74.25482 40.49390, -74.25308 40.491... True \n",
"1219 POLYGON ((-79.24982 42.53745, -79.24982 42.537... True \n",
"1226 POLYGON ((-76.55001 43.45923, -76.55064 43.458... True \n",
"... ... ... \n",
"73379 POLYGON ((-69.68695 43.81613, -69.68695 43.815... True \n",
"73399 POLYGON ((-70.22209 43.46688, -70.22432 43.464... True \n",
"73509 POLYGON ((-69.69756 43.81594, -69.69755 43.813... True \n",
"73527 POLYGON ((-68.73563 44.11917, -68.73179 44.117... True \n",
"73629 POLYGON ((-70.07870 43.66881, -70.06517 43.673... True \n",
"\n",
"[367 rows x 14 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# make a copy of the tract data\n",
"tract_explore = tract_data.copy()\n",
"\n",
"# add bool for whether tract has land area\n",
"tract_explore['water_only'] = tract_explore.ALAND10==0\n",
"\n",
"# preview water tracts\n",
"tract_explore[tract_explore.water_only]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "d0c30aef",
"metadata": {},
"outputs": [],
"source": [
"# confirm we can get the tract code stored in TRACTCE10 by taking last 6 chars of GEOID10_TRACT\n",
"# (because input df may not contain the isolated tract code column)\n",
"tract_explore['tract_code'] = tract_explore.GEOID10_TRACT.apply(lambda x: x[-6:])\n",
"assert all(tract_explore.tract_code==tract_explore.TRACTCE10)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5436fdd6",
"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>GEOID10_TRACT</th>\n",
" <th>TRACTCE10</th>\n",
" <th>tract_code</th>\n",
" <th>tract_code_num</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>20071958100</td>\n",
" <td>958100</td>\n",
" <td>958100</td>\n",
" <td>958100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20175965600</td>\n",
" <td>965600</td>\n",
" <td>965600</td>\n",
" <td>965600</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20175965700</td>\n",
" <td>965700</td>\n",
" <td>965700</td>\n",
" <td>965700</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20043020300</td>\n",
" <td>020300</td>\n",
" <td>020300</td>\n",
" <td>20300</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20043020200</td>\n",
" <td>020200</td>\n",
" <td>020200</td>\n",
" <td>20200</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT TRACTCE10 tract_code tract_code_num\n",
"0 20071958100 958100 958100 958100\n",
"1 20175965600 965600 965600 965600\n",
"2 20175965700 965700 965700 965700\n",
"3 20043020300 020300 020300 20300\n",
"4 20043020200 020200 020200 20200"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# convert tract codes to ints to check ranges\n",
"tract_explore['tract_code_num'] = tract_explore['tract_code'].apply(lambda x: int(x))\n",
"tract_explore[['GEOID10_TRACT', 'TRACTCE10', 'tract_code', 'tract_code_num']].head()"
]
},
{
"cell_type": "markdown",
"id": "a2e1814b",
"metadata": {},
"source": [
"Per Census documentation:\n",
"\n",
"- 000100 to 989900—Basic number range for census tracts\n",
"- 990000 to 990099—Basic number for census tracts in water areas\n",
"- 990100 to 998900—Basic number range for census tracts\n",
"\n",
"source: https://www2.census.gov/geo/pdfs/maps-data/data/tiger/tgrshp2017/TGRSHP2017_TechDoc_Ch3.pdf (page 3-26)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "cf09b1b6",
"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>GEOID10_TRACT</th>\n",
" <th>TRACTCE10</th>\n",
" <th>tract_code</th>\n",
" <th>tract_code_num</th>\n",
" <th>tract_in_water_range</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>20071958100</td>\n",
" <td>958100</td>\n",
" <td>958100</td>\n",
" <td>958100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20175965600</td>\n",
" <td>965600</td>\n",
" <td>965600</td>\n",
" <td>965600</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20175965700</td>\n",
" <td>965700</td>\n",
" <td>965700</td>\n",
" <td>965700</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20043020300</td>\n",
" <td>020300</td>\n",
" <td>020300</td>\n",
" <td>20300</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20043020200</td>\n",
" <td>020200</td>\n",
" <td>020200</td>\n",
" <td>20200</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT TRACTCE10 tract_code tract_code_num tract_in_water_range\n",
"0 20071958100 958100 958100 958100 False\n",
"1 20175965600 965600 965600 965600 False\n",
"2 20175965700 965700 965700 965700 False\n",
"3 20043020300 020300 020300 20300 False\n",
"4 20043020200 020200 020200 20200 False"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def in_water_range(x):\n",
" if x >= 990000 and x <= 990099:\n",
" return True\n",
" return False\n",
"\n",
"tract_explore['tract_in_water_range'] = tract_explore['tract_code_num'].apply(in_water_range)\n",
"tract_explore[['GEOID10_TRACT', 'TRACTCE10', 'tract_code', 'tract_code_num', 'tract_in_water_range']].head()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "1c0fab10",
"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>GEOID10_TRACT</th>\n",
" <th>TRACTCE10</th>\n",
" <th>tract_code</th>\n",
" <th>tract_code_num</th>\n",
" <th>tract_in_water_range</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>808</th>\n",
" <td>36063990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1015</th>\n",
" <td>36085008900</td>\n",
" <td>008900</td>\n",
" <td>008900</td>\n",
" <td>8900</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1149</th>\n",
" <td>36085990100</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1219</th>\n",
" <td>36013990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1226</th>\n",
" <td>36075990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73379</th>\n",
" <td>23015990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73399</th>\n",
" <td>23031990100</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73509</th>\n",
" <td>23023990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73527</th>\n",
" <td>23013990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73629</th>\n",
" <td>23005990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>990000</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>367 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT TRACTCE10 tract_code tract_code_num tract_in_water_range\n",
"808 36063990000 990000 990000 990000 True\n",
"1015 36085008900 008900 008900 8900 False\n",
"1149 36085990100 990100 990100 990100 False\n",
"1219 36013990000 990000 990000 990000 True\n",
"1226 36075990000 990000 990000 990000 True\n",
"... ... ... ... ... ...\n",
"73379 23015990000 990000 990000 990000 True\n",
"73399 23031990100 990100 990100 990100 False\n",
"73509 23023990000 990000 990000 990000 True\n",
"73527 23013990000 990000 990000 990000 True\n",
"73629 23005990000 990000 990000 990000 True\n",
"\n",
"[367 rows x 5 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# look at water-only tracts\n",
"tract_explore[tract_explore.water_only]\\\n",
" [['GEOID10_TRACT', 'TRACTCE10', 'tract_code', 'tract_code_num', 'tract_in_water_range']]"
]
},
{
"cell_type": "markdown",
"id": "4ba84ff5",
"metadata": {},
"source": [
"Some of the tracts with ALAND10=0 have tract numbers not in the water-only range."
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "320bd044",
"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 tr th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe thead tr:last-of-type th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th colspan=\"2\" halign=\"left\">tract_in_water_range</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>count</th>\n",
" <th>sum</th>\n",
" <th>mean</th>\n",
" </tr>\n",
" <tr>\n",
" <th>water_only</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>False</th>\n",
" <td>73767</td>\n",
" <td>0</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>True</th>\n",
" <td>367</td>\n",
" <td>227</td>\n",
" <td>0.618529</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT tract_in_water_range \n",
" count sum mean\n",
"water_only \n",
"False 73767 0 0.000000\n",
"True 367 227 0.618529"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tract_explore.groupby('water_only').agg({'GEOID10_TRACT': 'count', \n",
" 'tract_in_water_range': ['sum', 'mean']})"
]
},
{
"cell_type": "markdown",
"id": "612c72b8",
"metadata": {},
"source": [
"There are no tracts with land area that have tract codes in the water-only range. But about 38% of tracts with 0 land area have normal tract codes outside the water range."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "e0d5fb77",
"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>STATEFP10</th>\n",
" <th>COUNTYFP10</th>\n",
" <th>TRACTCE10</th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th>NAME10</th>\n",
" <th>NAMELSAD10</th>\n",
" <th>MTFCC10</th>\n",
" <th>FUNCSTAT10</th>\n",
" <th>ALAND10</th>\n",
" <th>AWATER10</th>\n",
" <th>INTPTLAT10</th>\n",
" <th>INTPTLON10</th>\n",
" <th>geometry</th>\n",
" <th>water_only</th>\n",
" <th>tract_code</th>\n",
" <th>tract_code_num</th>\n",
" <th>tract_in_water_range</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1015</th>\n",
" <td>36</td>\n",
" <td>085</td>\n",
" <td>008900</td>\n",
" <td>36085008900</td>\n",
" <td>89</td>\n",
" <td>Census Tract 89</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>100710</td>\n",
" <td>+40.6469814</td>\n",
" <td>-074.1024106</td>\n",
" <td>POLYGON ((-74.10504 40.64808, -74.10025 40.648...</td>\n",
" <td>True</td>\n",
" <td>008900</td>\n",
" <td>8900</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1149</th>\n",
" <td>36</td>\n",
" <td>085</td>\n",
" <td>990100</td>\n",
" <td>36085990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>80255151</td>\n",
" <td>+40.5255512</td>\n",
" <td>-074.1085829</td>\n",
" <td>POLYGON ((-74.25482 40.49390, -74.25308 40.491...</td>\n",
" <td>True</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2840</th>\n",
" <td>36</td>\n",
" <td>047</td>\n",
" <td>990100</td>\n",
" <td>36047990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>17793514</td>\n",
" <td>+40.5649933</td>\n",
" <td>-074.0148865</td>\n",
" <td>POLYGON ((-74.00620 40.59437, -74.00619 40.594...</td>\n",
" <td>True</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3095</th>\n",
" <td>36</td>\n",
" <td>059</td>\n",
" <td>990100</td>\n",
" <td>36059990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>13672168</td>\n",
" <td>+40.8790568</td>\n",
" <td>-073.7020503</td>\n",
" <td>POLYGON ((-73.76050 40.84184, -73.76102 40.841...</td>\n",
" <td>True</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3096</th>\n",
" <td>36</td>\n",
" <td>059</td>\n",
" <td>990200</td>\n",
" <td>36059990200</td>\n",
" <td>9902</td>\n",
" <td>Census Tract 9902</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>27086403</td>\n",
" <td>+40.9078457</td>\n",
" <td>-073.6526612</td>\n",
" <td>POLYGON ((-73.65151 40.88524, -73.66481 40.875...</td>\n",
" <td>True</td>\n",
" <td>990200</td>\n",
" <td>990200</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68946</th>\n",
" <td>15</td>\n",
" <td>009</td>\n",
" <td>990200</td>\n",
" <td>15009990200</td>\n",
" <td>9902</td>\n",
" <td>Census Tract 9902</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>1643042883</td>\n",
" <td>+20.6128423</td>\n",
" <td>-156.5486800</td>\n",
" <td>POLYGON ((-156.70541 20.82632, -156.70658 20.8...</td>\n",
" <td>True</td>\n",
" <td>990200</td>\n",
" <td>990200</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68949</th>\n",
" <td>15</td>\n",
" <td>009</td>\n",
" <td>991200</td>\n",
" <td>15009991200</td>\n",
" <td>9912</td>\n",
" <td>Census Tract 9912</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>482573725</td>\n",
" <td>+20.9476085</td>\n",
" <td>-156.9795251</td>\n",
" <td>POLYGON ((-157.11121 20.87500, -157.11725 20.8...</td>\n",
" <td>True</td>\n",
" <td>991200</td>\n",
" <td>991200</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>70339</th>\n",
" <td>39</td>\n",
" <td>093</td>\n",
" <td>990200</td>\n",
" <td>39093990200</td>\n",
" <td>9902</td>\n",
" <td>Census Tract 9902</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>1094173093</td>\n",
" <td>+41.6347746</td>\n",
" <td>-082.1526215</td>\n",
" <td>POLYGON ((-82.16712 41.47534, -82.16943 41.474...</td>\n",
" <td>True</td>\n",
" <td>990200</td>\n",
" <td>990200</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>70979</th>\n",
" <td>39</td>\n",
" <td>043</td>\n",
" <td>990100</td>\n",
" <td>39043990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>853315204</td>\n",
" <td>+41.5559059</td>\n",
" <td>-082.5241364</td>\n",
" <td>POLYGON ((-82.51199 41.39475, -82.51472 41.395...</td>\n",
" <td>True</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73399</th>\n",
" <td>23</td>\n",
" <td>031</td>\n",
" <td>990100</td>\n",
" <td>23031990100</td>\n",
" <td>9901</td>\n",
" <td>Census Tract 9901</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>567248819</td>\n",
" <td>+43.1483531</td>\n",
" <td>-070.4998364</td>\n",
" <td>POLYGON ((-70.22209 43.46688, -70.22432 43.464...</td>\n",
" <td>True</td>\n",
" <td>990100</td>\n",
" <td>990100</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>140 rows × 17 columns</p>\n",
"</div>"
],
"text/plain": [
" STATEFP10 COUNTYFP10 TRACTCE10 GEOID10_TRACT NAME10 NAMELSAD10 \\\n",
"1015 36 085 008900 36085008900 89 Census Tract 89 \n",
"1149 36 085 990100 36085990100 9901 Census Tract 9901 \n",
"2840 36 047 990100 36047990100 9901 Census Tract 9901 \n",
"3095 36 059 990100 36059990100 9901 Census Tract 9901 \n",
"3096 36 059 990200 36059990200 9902 Census Tract 9902 \n",
"... ... ... ... ... ... ... \n",
"68946 15 009 990200 15009990200 9902 Census Tract 9902 \n",
"68949 15 009 991200 15009991200 9912 Census Tract 9912 \n",
"70339 39 093 990200 39093990200 9902 Census Tract 9902 \n",
"70979 39 043 990100 39043990100 9901 Census Tract 9901 \n",
"73399 23 031 990100 23031990100 9901 Census Tract 9901 \n",
"\n",
" MTFCC10 FUNCSTAT10 ALAND10 AWATER10 INTPTLAT10 INTPTLON10 \\\n",
"1015 G5020 S 0 100710 +40.6469814 -074.1024106 \n",
"1149 G5020 S 0 80255151 +40.5255512 -074.1085829 \n",
"2840 G5020 S 0 17793514 +40.5649933 -074.0148865 \n",
"3095 G5020 S 0 13672168 +40.8790568 -073.7020503 \n",
"3096 G5020 S 0 27086403 +40.9078457 -073.6526612 \n",
"... ... ... ... ... ... ... \n",
"68946 G5020 S 0 1643042883 +20.6128423 -156.5486800 \n",
"68949 G5020 S 0 482573725 +20.9476085 -156.9795251 \n",
"70339 G5020 S 0 1094173093 +41.6347746 -082.1526215 \n",
"70979 G5020 S 0 853315204 +41.5559059 -082.5241364 \n",
"73399 G5020 S 0 567248819 +43.1483531 -070.4998364 \n",
"\n",
" geometry water_only \\\n",
"1015 POLYGON ((-74.10504 40.64808, -74.10025 40.648... True \n",
"1149 POLYGON ((-74.25482 40.49390, -74.25308 40.491... True \n",
"2840 POLYGON ((-74.00620 40.59437, -74.00619 40.594... True \n",
"3095 POLYGON ((-73.76050 40.84184, -73.76102 40.841... True \n",
"3096 POLYGON ((-73.65151 40.88524, -73.66481 40.875... True \n",
"... ... ... \n",
"68946 POLYGON ((-156.70541 20.82632, -156.70658 20.8... True \n",
"68949 POLYGON ((-157.11121 20.87500, -157.11725 20.8... True \n",
"70339 POLYGON ((-82.16712 41.47534, -82.16943 41.474... True \n",
"70979 POLYGON ((-82.51199 41.39475, -82.51472 41.395... True \n",
"73399 POLYGON ((-70.22209 43.46688, -70.22432 43.464... True \n",
"\n",
" tract_code tract_code_num tract_in_water_range \n",
"1015 008900 8900 False \n",
"1149 990100 990100 False \n",
"2840 990100 990100 False \n",
"3095 990100 990100 False \n",
"3096 990200 990200 False \n",
"... ... ... ... \n",
"68946 990200 990200 False \n",
"68949 991200 991200 False \n",
"70339 990200 990200 False \n",
"70979 990100 990100 False \n",
"73399 990100 990100 False \n",
"\n",
"[140 rows x 17 columns]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# view the exceptions (no land area, but tract code not in water range)\n",
"water_exceptions = tract_explore[(tract_explore.water_only==True) & (tract_explore.tract_in_water_range==False)]\n",
"water_exceptions"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "b36fdc0d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"36063990000, 36013990000, 36075990000, 36055990000, 36045990001, 36029990000, 36073990000, 41007990000, 41039990000, 41019990000, 01003990000, 01097990000, 17031990000, 17097990000, 10001990000, 10005990000, 06083990000, 06053990000, 06061990000, 06015990000, 06079990000, 06013990000, 06017990000, 06001990000, 51710990000, 26157990000, 26011990000, 26001990000, 26141990000, 26019990000, 26069990000, 26053990000, 26147990000, 26153990000, 26063990000, 26159990000, 26033990000, 26005990000, 26103990000, 26061990000, 26003990000, 26095990000, 26041990000, 26031990000, 26009990000, 26139990000, 26047990000, 26109990000, 26007990000, 26021990000, 26089990000, 26017990000, 26115990000, 26151990000, 26055990000, 26127990000, 26097990000, 26121990000, 26105990000, 26101990000, 26029990000, 66010990000, 27031990000, 69100990000, 69110990000, 69120990000, 28045990000, 28059990000, 28047990000, 53031990000, 53061990002, 53027990000, 12009990000, 12017990000, 12037990000, 12011990000, 12087990000, 12081990000, 12093990000, 12029990000, 12031990000, 12071990000, 12065990000, 12033990000, 12045990000, 12086990000, 12129990000, 12103990000, 12057990000, 12115990000, 12101990000, 12123990000, 12085990000, 12051990000, 12005990000, 12035990000, 12053990000, 12043990000, 12131990000, 12099990000, 12075990000, 12015990000, 12061990000, 12095990000, 12021990000, 12113990000, 12089990000, 12111990000, 12127990000, 32031990000, 32005990000, 32510990000, 24029990000, 24017990000, 24047990000, 24041990000, 24037990000, 24035990000, 24019990000, 24003990000, 48039990000, 48489990000, 48261990000, 48355990000, 48273990000, 48321990000, 48167990000, 48061990000, 48071990000, 48007990000, 48245990000, 48057990000, 09001990000, 09009990000, 25001990000, 25023990003, 25005990000, 25007990000, 25019990000, 72059990001, 72027990000, 72005990000, 72091990025, 72037990000, 72095990000, 72145990000, 72147990000, 72111990000, 72097990000, 72031990000, 72115990000, 72133990000, 72089990001, 72011990000, 72137990000, 72065990016, 72071990000, 72103990013, 72087990000, 72151990000, 72003990000, 72017990000, 72075990001, 72023990000, 72143990000, 72055990000, 72051990021, 72109990000, 72127990000, 33015990000, 44005990000, 13039990000, 13127990000, 13051990000, 13179990000, 13191990000, 34001990000, 34029990000, 34033990000, 34011990000, 34025990000, 22071990000, 22087990000, 22109990000, 22045990000, 22023990000, 22101990000, 22113990000, 22057990000, 22075990000, 22103990000, 22051990000, 18091990000, 18089990000, 18127990000, 55031990000, 55061990000, 55051990000, 55083990000, 55059990000, 55101990000, 55007990000, 55075990000, 55003990000, 55029990000, 55079990000, 55071990000, 55117990000, 55089990000, 42049990000, 15003990001, 15001990000, 15005990000, 15009990000, 78010990000, 78020990000, 78030990000, 39007990000, 39085990000, 39095990000, 39035990000, 23029990000, 23009990000, 23015990000, 23023990000, 23013990000, 23005990000\n"
]
}
],
"source": [
"# print list of \"normal\" water-only IDs to put into compare tool\n",
"water_normals = tract_explore[(tract_explore.water_only==True) & (tract_explore.tract_in_water_range==True)]\n",
"print(', '.join(water_normals.GEOID10_TRACT.values))"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "e9380f21",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"36063990000, 36085008900, 36085990100, 36013990000, 36075990000, 36055990000, 36045990001, 36047990100, 36059990100, 36059990200, 36059990301, 36059990302, 36059990400, 36081990100, 36029990000, 36073990000, 36103990100, 36117990100, 36011990200, 41007990000, 41057990100, 41039990000, 41041990100, 41015990101, 41011990101, 41019990000, 01003990000, 01097990000, 17031990000, 17097990000, 37031990100, 37031990200, 37053990100, 37019990100, 37055990100, 37055990200, 37129990100, 37095990100, 37095990200, 37141990100, 37137990100, 37133990100, 10001990000, 10005990000, 10003990100, 06083990000, 06053990000, 06061990000, 06059990100, 06097990100, 06045990100, 06073990100, 06041990100, 06015990000, 06081990100, 06079990000, 06013990000, 06111990100, 06017990000, 06001990000, 06075990100, 06087990100, 06023990100, 06037990200, 06037990300, 06037990100, 51103990100, 51115990100, 51650990100, 51131990100, 51735990100, 51810990100, 51133990100, 51001990100, 51001990200, 51119990100, 51199990100, 51710990000, 26157990000, 26011990000, 26163990100, 26163990200, 26001990000, 26141990000, 26011990100, 26019990000, 26069990000, 26053990000, 26147990000, 26153990000, 26063990000, 26159990000, 26033990000, 26033990100, 26131990100, 26005990000, 26103990000, 26099990100, 26061990000, 26061990100, 26003990000, 26095990000, 26041990000, 26031990000, 26009990000, 26083990100, 26139990000, 26041990100, 26047990000, 26109990000, 26007990000, 26021990000, 26089990000, 26017990000, 26115990000, 26151990000, 26013990100, 26055990000, 26127990000, 26097990000, 26121990000, 26105990000, 26101990000, 26029990000, 66010990000, 27137990100, 27031990000, 27075990100, 69100990000, 69110990000, 69120990000, 28045990000, 28059990000, 28047990000, 53061990100, 53035990100, 53057990100, 53009990100, 53067990100, 53049990100, 53031990000, 53033990100, 53061990002, 53029992201, 53027990000, 53055990100, 12009990000, 12017990000, 12037990000, 12037990100, 12011990000, 12087990000, 12081990000, 12093990000, 12029990000, 12031990000, 12071990000, 12065990000, 12033990000, 12045990000, 12103990100, 12086990000, 12129990000, 12103990000, 12057990000, 12057990100, 12115990000, 12101990000, 12109990200, 12109990100, 12123990000, 12085990000, 12085990100, 12051990000, 12005990000, 12035990000, 12053990000, 12043990000, 12131990000, 12099990000, 12075990000, 12015990000, 12099990100, 12061990000, 12095990000, 12021990000, 12113990000, 12089990000, 12111990000, 12127990000, 12091990200, 12091990100, 45013990100, 45053990100, 45019990100, 45029990100, 45043990100, 45051990100, 32031990000, 32031990100, 32005990000, 32510990000, 24029990000, 24017990000, 24047990000, 24041990000, 24039990100, 24037990000, 24035990200, 24035990100, 24035990000, 24019990000, 24003990000, 24009990100, 48039990000, 48489990000, 48261990000, 48355990000, 48273990000, 48321990000, 48167990000, 48061990000, 48071990000, 48007990000, 48245990000, 48057990000, 09001990000, 09011990100, 09007990100, 09009990000, 25001990000, 25023990003, 25005990000, 25025990101, 25009990100, 25007990000, 25019990000, 72049990501, 72059990001, 72027990000, 72033990201, 72053990103, 72113993000, 72015991500, 72005990000, 72091990025, 72013992900, 72037990000, 72095990000, 72145990000, 72117990400, 72147990000, 72111990000, 72097990000, 72079991100, 72031990000, 72115990000, 72133990000, 72089990001, 72011990000, 72123992800, 72137990000, 72065990016, 72071990000, 72103990013, 72087990000, 72069991800, 72151990000, 72003990000, 72057992600, 72017990000, 72075990001, 72119992700, 72023990000, 72143990000, 72055990000, 72051990021, 72109990000, 72127990000, 33015990000, 44009990200, 44009990100, 44005990000, 13039990000, 13127990000, 13051990000, 13179990000, 13191990000, 34001990000, 34029990000, 34033990000, 34011990000, 34009990100, 34025990000, 22071990000, 22087990000, 22109990000, 22045990000, 22023990000, 22101990000, 22113990000, 22057990000, 22051990100, 22075990000, 22103990000, 22051990000, 18091990000, 18089990000, 18127990000, 55031990000, 55061990000, 55051990000, 55083990000, 55059990000, 55101990000, 55007990000, 55025991703, 55025991702, 55075990000, 55003990000, 55029990000, 55079990000, 55071990000, 55117990000, 55089990000, 42049990000, 15003990001, 15001991700, 15001990400, 15001990000, 15001990300, 15001991100, 15001991200, 15001991500, 15001991300, 15001991400, 15001991600, 15001991000, 15001990100, 15001990500, 15001990600, 15001990900, 15001990800, 15001990700, 15005990000, 15007990100, 15007990300, 15007990200, 15009990200, 15009991200, 15009990000, 78010990000, 78020990000, 78030990000, 39007990000, 39085990000, 39093990200, 39043990100, 39095990000, 39035990000, 23029990000, 23009990000, 23015990000, 23031990100, 23023990000, 23013990000, 23005990000\n"
]
}
],
"source": [
"# print list of ALAND10=0 IDs to put into compare tool\n",
"print(', '.join(tract_explore[tract_explore.water_only==True].GEOID10_TRACT.values))"
]
},
{
"cell_type": "markdown",
"id": "8d82e594",
"metadata": {},
"source": [
"Tract comparison tool shoes that 21 of the 140 \"water exception\" tracts are in Hawaii. California next highest with 13. Puerto Rico has 12. (No other territories have \"water exception\" tracts.)"
]
},
{
"cell_type": "markdown",
"id": "74544236",
"metadata": {},
"source": [
"## Simulate calculate_tract_adjacency_scores()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "3703ffb1",
"metadata": {},
"outputs": [],
"source": [
"def calculate_tract_adjacency_scores(\n",
" df: pd.DataFrame, score_column: str, tract_data\n",
") -> pd.DataFrame:\n",
" \"\"\"Calculate the mean score of each tract in df based on its neighbors\n",
"\n",
" Args:\n",
" df (pandas.DataFrame): A dataframe with at least the following columns:\n",
" * field_names.GEOID_TRACT_FIELD\n",
" * score_column\n",
"\n",
" score_column (str): The name of the column that contains the scores\n",
" to average\n",
" \n",
" tract_data (GeoDataFrame): tract data normally loaded in first line of \n",
" function: tract_data = get_tract_geojson()\n",
" Returns :\n",
" tuple containing final returned df in actual function, as well as intermediates:\n",
" - returned_donut_bools (pandas.DataFrame): A dataframe with two columns:\n",
" * field_names.GEOID_TRACT_FIELD\n",
" * {score_column}_ADJACENT_MEAN, which is the average of score_column for\n",
" each tract that touches the tract identified\n",
" in field_names.GEOID_TRACT_FIELD\n",
" NB: this is the df that gets returned in the actual function\n",
" - df (pandas.DataFrame): input df after merging with Census data\n",
" - adjacent_tracts (pandas.DataFrame): adjacency df\n",
" \"\"\"\n",
"\n",
" df: gpd.GeoDataFrame = tract_data.merge(\n",
" df, on=GEOID_TRACT_FIELD\n",
" )\n",
" df = df.rename(columns={GEOID_TRACT_FIELD: ORIGINAL_TRACT})\n",
"\n",
"\n",
" adjacent_tracts: gpd.GeoDataFrame = df.sjoin(\n",
" tract_data, predicate=\"touches\"\n",
" )\n",
"\n",
"\n",
" returned_donut_bools = (\n",
" adjacent_tracts.groupby(GEOID_TRACT_FIELD)[[score_column]]\n",
" .mean()\n",
" .reset_index()\n",
" .rename(\n",
" columns={\n",
" score_column: f\"{score_column}{ADJACENCY_INDEX_SUFFIX}\",\n",
" }\n",
" )\n",
" )\n",
" \n",
" return (returned_donut_bools, df, adjacent_tracts)\n"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "d4f50253",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['48061010100',\n",
" '48489950700',\n",
" '48489990000',\n",
" '48061012700',\n",
" '48061012304',\n",
" '48061012301',\n",
" '48061990000']"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# save tract ids that are adjacent to cameron so we can simulate \n",
"# passing them into calculate_tract_adjacency_scores() via df arg\n",
"adjacent_track_id_list_cam = list(cam_adjacent_tracts.GEOID10_TRACT.unique())\n",
"adjacent_track_id_list_cam"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "4bac089c",
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061012305</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48061010100</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>48489950700</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48489990000</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48061012700</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48061012304</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48061012301</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48061990000</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities)\n",
"0 48061012305 False\n",
"1 48061010100 True\n",
"2 48489950700 True\n",
"3 48489990000 False\n",
"4 48061012700 True\n",
"5 48061012304 True\n",
"6 48061012301 True\n",
"7 48061990000 False"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# df is passed into the function, must contain the score column we're looking at\n",
"# (in this case, SCORE_N_COMMUNITIES)\n",
"# here we pass in our water boundary issue example in Cameron TX pluss all its adjacencies.\n",
"# initialize disadvantaged bool as FALSE for our example, and TRUE for others.\n",
"df_cam_plus = pd.DataFrame({GEOID_TRACT_FIELD:[CAM_ID]+adjacent_track_id_list_cam, \n",
" SCORE_N_COMMUNITIES:[False]+([True]*len(adjacent_track_id_list_cam))})\n",
"\n",
"# set disadvantaged bool to False for water tracts\n",
"df_cam_plus.loc[df_cam_plus[GEOID_TRACT_FIELD].isin(['48489990000', '48061990000']), SCORE_N_COMMUNITIES]=False\n",
"\n",
"df_cam_plus"
]
},
{
"cell_type": "markdown",
"id": "ad9570b0",
"metadata": {},
"source": [
"### Simulate v1 run of of calculate_tract_adjacency_scores()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "74826fc9",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"returned_donut_bools__v1, df_census__v1, adjacent_tracts__v1 = calculate_tract_adjacency_scores(\n",
" df=df_cam_plus, score_column=SCORE_N_COMMUNITIES, tract_data=tract_data\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "8e69447f",
"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>STATEFP10_left</th>\n",
" <th>COUNTYFP10_left</th>\n",
" <th>TRACTCE10_left</th>\n",
" <th>ORIGINAL_TRACT</th>\n",
" <th>NAME10_left</th>\n",
" <th>NAMELSAD10_left</th>\n",
" <th>MTFCC10_left</th>\n",
" <th>FUNCSTAT10_left</th>\n",
" <th>ALAND10_left</th>\n",
" <th>AWATER10_left</th>\n",
" <th>...</th>\n",
" <th>TRACTCE10_right</th>\n",
" <th>GEOID10_TRACT</th>\n",
" <th>NAME10_right</th>\n",
" <th>NAMELSAD10_right</th>\n",
" <th>MTFCC10_right</th>\n",
" <th>FUNCSTAT10_right</th>\n",
" <th>ALAND10_right</th>\n",
" <th>AWATER10_right</th>\n",
" <th>INTPTLAT10_right</th>\n",
" <th>INTPTLON10_right</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>...</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>+26.2732070</td>\n",
" <td>-097.2763703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>...</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>+26.5154317</td>\n",
" <td>-097.5790835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>+26.5154317</td>\n",
" <td>-097.5790835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>+26.5154317</td>\n",
" <td>-097.5790835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48261990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>394659578</td>\n",
" <td>+26.9389899</td>\n",
" <td>-097.3234546</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48261990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>394659578</td>\n",
" <td>+26.9389899</td>\n",
" <td>-097.3234546</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>...</td>\n",
" <td>950100</td>\n",
" <td>48261950100</td>\n",
" <td>9501</td>\n",
" <td>Census Tract 9501</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>3777053964</td>\n",
" <td>867877948</td>\n",
" <td>+26.9241932</td>\n",
" <td>-097.6694694</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>950100</td>\n",
" <td>48261950100</td>\n",
" <td>9501</td>\n",
" <td>Census Tract 9501</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>3777053964</td>\n",
" <td>867877948</td>\n",
" <td>+26.9241932</td>\n",
" <td>-097.6694694</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>+26.1902408</td>\n",
" <td>-097.1473235</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>+26.1902408</td>\n",
" <td>-097.1473235</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>+26.1902408</td>\n",
" <td>-097.1473235</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>010201</td>\n",
" <td>48061010201</td>\n",
" <td>102.01</td>\n",
" <td>Census Tract 102.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>138787038</td>\n",
" <td>773532</td>\n",
" <td>+26.2865300</td>\n",
" <td>-097.6765589</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>010201</td>\n",
" <td>48061010201</td>\n",
" <td>102.01</td>\n",
" <td>Census Tract 102.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>138787038</td>\n",
" <td>773532</td>\n",
" <td>+26.2865300</td>\n",
" <td>-097.6765589</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>+26.2713946</td>\n",
" <td>-097.4414470</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>+26.2713946</td>\n",
" <td>-097.4414470</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>...</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>+26.2713946</td>\n",
" <td>-097.4414470</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>950600</td>\n",
" <td>48489950600</td>\n",
" <td>9506</td>\n",
" <td>Census Tract 9506</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>142823217</td>\n",
" <td>867417</td>\n",
" <td>+26.3413027</td>\n",
" <td>-097.6980863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>950600</td>\n",
" <td>48489950600</td>\n",
" <td>9506</td>\n",
" <td>Census Tract 9506</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>142823217</td>\n",
" <td>867417</td>\n",
" <td>+26.3413027</td>\n",
" <td>-097.6980863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>950500</td>\n",
" <td>48489950500</td>\n",
" <td>9505</td>\n",
" <td>Census Tract 9505</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>198663041</td>\n",
" <td>1916760</td>\n",
" <td>+26.4046271</td>\n",
" <td>-097.7275193</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>950400</td>\n",
" <td>48489950400</td>\n",
" <td>9504</td>\n",
" <td>Census Tract 9504</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>95793488</td>\n",
" <td>440761</td>\n",
" <td>+26.4857271</td>\n",
" <td>-097.7274534</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>+26.5064260</td>\n",
" <td>-097.2240134</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>+26.5064260</td>\n",
" <td>-097.2240134</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>990000</td>\n",
" <td>48489990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>121414926</td>\n",
" <td>+26.5064260</td>\n",
" <td>-097.2240134</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>024302</td>\n",
" <td>48215024302</td>\n",
" <td>243.02</td>\n",
" <td>Census Tract 243.02</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>152233383</td>\n",
" <td>10002679</td>\n",
" <td>+26.4228640</td>\n",
" <td>-097.9710985</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>950300</td>\n",
" <td>48489950300</td>\n",
" <td>9503</td>\n",
" <td>Census Tract 9503</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>66833755</td>\n",
" <td>75864</td>\n",
" <td>+26.4851686</td>\n",
" <td>-097.8236397</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>489</td>\n",
" <td>950700</td>\n",
" <td>48489950700</td>\n",
" <td>9507</td>\n",
" <td>Census Tract 9507</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1025415174</td>\n",
" <td>377000048</td>\n",
" <td>...</td>\n",
" <td>024301</td>\n",
" <td>48215024301</td>\n",
" <td>243.01</td>\n",
" <td>Census Tract 243.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1426811393</td>\n",
" <td>527958</td>\n",
" <td>+26.6175624</td>\n",
" <td>-098.1948738</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>990000</td>\n",
" <td>48061990000</td>\n",
" <td>9900</td>\n",
" <td>Census Tract 9900</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>268272237</td>\n",
" <td>...</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>+25.9786218</td>\n",
" <td>-097.2580863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>+25.9786218</td>\n",
" <td>-097.2580863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>...</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>+25.9786218</td>\n",
" <td>-097.2580863</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>+26.0631407</td>\n",
" <td>-097.2184868</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>+26.0631407</td>\n",
" <td>-097.2184868</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>...</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>+26.0631407</td>\n",
" <td>-097.2184868</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012305</td>\n",
" <td>48061012305</td>\n",
" <td>123.05</td>\n",
" <td>Census Tract 123.05</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>25920881</td>\n",
" <td>324996211</td>\n",
" <td>...</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>+26.1581170</td>\n",
" <td>-097.3180348</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>...</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>+26.1581170</td>\n",
" <td>-097.3180348</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>+26.1581170</td>\n",
" <td>-097.3180348</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012304</td>\n",
" <td>48061012304</td>\n",
" <td>123.04</td>\n",
" <td>Census Tract 123.04</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>5761299</td>\n",
" <td>6286773</td>\n",
" <td>...</td>\n",
" <td>014200</td>\n",
" <td>48061014200</td>\n",
" <td>142</td>\n",
" <td>Census Tract 142</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>229485446</td>\n",
" <td>52743725</td>\n",
" <td>+26.0321232</td>\n",
" <td>-097.3592760</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>014200</td>\n",
" <td>48061014200</td>\n",
" <td>142</td>\n",
" <td>Census Tract 142</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>229485446</td>\n",
" <td>52743725</td>\n",
" <td>+26.0321232</td>\n",
" <td>-097.3592760</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>...</td>\n",
" <td>014200</td>\n",
" <td>48061014200</td>\n",
" <td>142</td>\n",
" <td>Census Tract 142</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>229485446</td>\n",
" <td>52743725</td>\n",
" <td>+26.0321232</td>\n",
" <td>-097.3592760</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>010800</td>\n",
" <td>48061010800</td>\n",
" <td>108</td>\n",
" <td>Census Tract 108</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>24214554</td>\n",
" <td>372874</td>\n",
" <td>+26.2018913</td>\n",
" <td>-097.6365382</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>010203</td>\n",
" <td>48061010203</td>\n",
" <td>102.03</td>\n",
" <td>Census Tract 102.03</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>36355923</td>\n",
" <td>529676</td>\n",
" <td>+26.2392001</td>\n",
" <td>-097.7004164</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>012200</td>\n",
" <td>48061012200</td>\n",
" <td>122</td>\n",
" <td>Census Tract 122</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>181087087</td>\n",
" <td>9690866</td>\n",
" <td>+26.1431884</td>\n",
" <td>-097.4883500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012301</td>\n",
" <td>48061012301</td>\n",
" <td>123.01</td>\n",
" <td>Census Tract 123.01</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>137622651</td>\n",
" <td>119430273</td>\n",
" <td>...</td>\n",
" <td>012200</td>\n",
" <td>48061012200</td>\n",
" <td>122</td>\n",
" <td>Census Tract 122</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>181087087</td>\n",
" <td>9690866</td>\n",
" <td>+26.1431884</td>\n",
" <td>-097.4883500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>010100</td>\n",
" <td>48061010100</td>\n",
" <td>101</td>\n",
" <td>Census Tract 101</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>365458278</td>\n",
" <td>113041841</td>\n",
" <td>...</td>\n",
" <td>011400</td>\n",
" <td>48061011400</td>\n",
" <td>114</td>\n",
" <td>Census Tract 114</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>52595069</td>\n",
" <td>1716432</td>\n",
" <td>+26.1576649</td>\n",
" <td>-097.6030070</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>014100</td>\n",
" <td>48061014100</td>\n",
" <td>141</td>\n",
" <td>Census Tract 141</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>58750542</td>\n",
" <td>1786306</td>\n",
" <td>+25.8820153</td>\n",
" <td>-097.4007135</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>013207</td>\n",
" <td>48061013207</td>\n",
" <td>132.07</td>\n",
" <td>Census Tract 132.07</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>3884436</td>\n",
" <td>409892</td>\n",
" <td>+25.9278897</td>\n",
" <td>-097.4159201</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>013203</td>\n",
" <td>48061013203</td>\n",
" <td>132.03</td>\n",
" <td>Census Tract 132.03</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>1103957</td>\n",
" <td>3034</td>\n",
" <td>+25.9335830</td>\n",
" <td>-097.4379216</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48</td>\n",
" <td>061</td>\n",
" <td>012700</td>\n",
" <td>48061012700</td>\n",
" <td>127</td>\n",
" <td>Census Tract 127</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>129622799</td>\n",
" <td>67725054</td>\n",
" <td>...</td>\n",
" <td>012607</td>\n",
" <td>48061012607</td>\n",
" <td>126.07</td>\n",
" <td>Census Tract 126.07</td>\n",
" <td>G5020</td>\n",
" <td>S</td>\n",
" <td>3230089</td>\n",
" <td>151343</td>\n",
" <td>+25.9479994</td>\n",
" <td>-097.4340712</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" STATEFP10_left COUNTYFP10_left TRACTCE10_left ORIGINAL_TRACT NAME10_left \\\n",
"0 48 489 990000 48489990000 9900 \n",
"1 48 489 950700 48489950700 9507 \n",
"2 48 061 990000 48061990000 9900 \n",
"4 48 061 012304 48061012304 123.04 \n",
"5 48 061 010100 48061010100 101 \n",
"6 48 061 012700 48061012700 127 \n",
"7 48 061 012301 48061012301 123.01 \n",
"0 48 489 990000 48489990000 9900 \n",
"3 48 061 012305 48061012305 123.05 \n",
"5 48 061 010100 48061010100 101 \n",
"0 48 489 990000 48489990000 9900 \n",
"1 48 489 950700 48489950700 9507 \n",
"0 48 489 990000 48489990000 9900 \n",
"1 48 489 950700 48489950700 9507 \n",
"0 48 489 990000 48489990000 9900 \n",
"3 48 061 012305 48061012305 123.05 \n",
"6 48 061 012700 48061012700 127 \n",
"1 48 489 950700 48489950700 9507 \n",
"5 48 061 010100 48061010100 101 \n",
"1 48 489 950700 48489950700 9507 \n",
"3 48 061 012305 48061012305 123.05 \n",
"7 48 061 012301 48061012301 123.01 \n",
"1 48 489 950700 48489950700 9507 \n",
"5 48 061 010100 48061010100 101 \n",
"1 48 489 950700 48489950700 9507 \n",
"1 48 489 950700 48489950700 9507 \n",
"1 48 489 950700 48489950700 9507 \n",
"2 48 061 990000 48061990000 9900 \n",
"3 48 061 012305 48061012305 123.05 \n",
"1 48 489 950700 48489950700 9507 \n",
"1 48 489 950700 48489950700 9507 \n",
"1 48 489 950700 48489950700 9507 \n",
"2 48 061 990000 48061990000 9900 \n",
"3 48 061 012305 48061012305 123.05 \n",
"4 48 061 012304 48061012304 123.04 \n",
"3 48 061 012305 48061012305 123.05 \n",
"6 48 061 012700 48061012700 127 \n",
"7 48 061 012301 48061012301 123.01 \n",
"3 48 061 012305 48061012305 123.05 \n",
"4 48 061 012304 48061012304 123.04 \n",
"5 48 061 010100 48061010100 101 \n",
"4 48 061 012304 48061012304 123.04 \n",
"6 48 061 012700 48061012700 127 \n",
"7 48 061 012301 48061012301 123.01 \n",
"5 48 061 010100 48061010100 101 \n",
"5 48 061 010100 48061010100 101 \n",
"5 48 061 010100 48061010100 101 \n",
"7 48 061 012301 48061012301 123.01 \n",
"5 48 061 010100 48061010100 101 \n",
"6 48 061 012700 48061012700 127 \n",
"6 48 061 012700 48061012700 127 \n",
"6 48 061 012700 48061012700 127 \n",
"6 48 061 012700 48061012700 127 \n",
"\n",
" NAMELSAD10_left MTFCC10_left FUNCSTAT10_left ALAND10_left \\\n",
"0 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"2 Census Tract 9900 G5020 S 0 \n",
"4 Census Tract 123.04 G5020 S 5761299 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"7 Census Tract 123.01 G5020 S 137622651 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"7 Census Tract 123.01 G5020 S 137622651 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"2 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"1 Census Tract 9507 G5020 S 1025415174 \n",
"2 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"4 Census Tract 123.04 G5020 S 5761299 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"7 Census Tract 123.01 G5020 S 137622651 \n",
"3 Census Tract 123.05 G5020 S 25920881 \n",
"4 Census Tract 123.04 G5020 S 5761299 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"4 Census Tract 123.04 G5020 S 5761299 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"7 Census Tract 123.01 G5020 S 137622651 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"7 Census Tract 123.01 G5020 S 137622651 \n",
"5 Census Tract 101 G5020 S 365458278 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"6 Census Tract 127 G5020 S 129622799 \n",
"\n",
" AWATER10_left ... TRACTCE10_right GEOID10_TRACT NAME10_right \\\n",
"0 121414926 ... 012305 48061012305 123.05 \n",
"1 377000048 ... 012305 48061012305 123.05 \n",
"2 268272237 ... 012305 48061012305 123.05 \n",
"4 6286773 ... 012305 48061012305 123.05 \n",
"5 113041841 ... 012305 48061012305 123.05 \n",
"6 67725054 ... 012305 48061012305 123.05 \n",
"7 119430273 ... 012305 48061012305 123.05 \n",
"0 121414926 ... 950700 48489950700 9507 \n",
"3 324996211 ... 950700 48489950700 9507 \n",
"5 113041841 ... 950700 48489950700 9507 \n",
"0 121414926 ... 990000 48261990000 9900 \n",
"1 377000048 ... 990000 48261990000 9900 \n",
"0 121414926 ... 950100 48261950100 9501 \n",
"1 377000048 ... 950100 48261950100 9501 \n",
"0 121414926 ... 990000 48061990000 9900 \n",
"3 324996211 ... 990000 48061990000 9900 \n",
"6 67725054 ... 990000 48061990000 9900 \n",
"1 377000048 ... 010201 48061010201 102.01 \n",
"5 113041841 ... 010201 48061010201 102.01 \n",
"1 377000048 ... 010100 48061010100 101 \n",
"3 324996211 ... 010100 48061010100 101 \n",
"7 119430273 ... 010100 48061010100 101 \n",
"1 377000048 ... 950600 48489950600 9506 \n",
"5 113041841 ... 950600 48489950600 9506 \n",
"1 377000048 ... 950500 48489950500 9505 \n",
"1 377000048 ... 950400 48489950400 9504 \n",
"1 377000048 ... 990000 48489990000 9900 \n",
"2 268272237 ... 990000 48489990000 9900 \n",
"3 324996211 ... 990000 48489990000 9900 \n",
"1 377000048 ... 024302 48215024302 243.02 \n",
"1 377000048 ... 950300 48489950300 9503 \n",
"1 377000048 ... 024301 48215024301 243.01 \n",
"2 268272237 ... 012700 48061012700 127 \n",
"3 324996211 ... 012700 48061012700 127 \n",
"4 6286773 ... 012700 48061012700 127 \n",
"3 324996211 ... 012304 48061012304 123.04 \n",
"6 67725054 ... 012304 48061012304 123.04 \n",
"7 119430273 ... 012304 48061012304 123.04 \n",
"3 324996211 ... 012301 48061012301 123.01 \n",
"4 6286773 ... 012301 48061012301 123.01 \n",
"5 113041841 ... 012301 48061012301 123.01 \n",
"4 6286773 ... 014200 48061014200 142 \n",
"6 67725054 ... 014200 48061014200 142 \n",
"7 119430273 ... 014200 48061014200 142 \n",
"5 113041841 ... 010800 48061010800 108 \n",
"5 113041841 ... 010203 48061010203 102.03 \n",
"5 113041841 ... 012200 48061012200 122 \n",
"7 119430273 ... 012200 48061012200 122 \n",
"5 113041841 ... 011400 48061011400 114 \n",
"6 67725054 ... 014100 48061014100 141 \n",
"6 67725054 ... 013207 48061013207 132.07 \n",
"6 67725054 ... 013203 48061013203 132.03 \n",
"6 67725054 ... 012607 48061012607 126.07 \n",
"\n",
" NAMELSAD10_right MTFCC10_right FUNCSTAT10_right ALAND10_right \\\n",
"0 Census Tract 123.05 G5020 S 25920881 \n",
"1 Census Tract 123.05 G5020 S 25920881 \n",
"2 Census Tract 123.05 G5020 S 25920881 \n",
"4 Census Tract 123.05 G5020 S 25920881 \n",
"5 Census Tract 123.05 G5020 S 25920881 \n",
"6 Census Tract 123.05 G5020 S 25920881 \n",
"7 Census Tract 123.05 G5020 S 25920881 \n",
"0 Census Tract 9507 G5020 S 1025415174 \n",
"3 Census Tract 9507 G5020 S 1025415174 \n",
"5 Census Tract 9507 G5020 S 1025415174 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 9900 G5020 S 0 \n",
"0 Census Tract 9501 G5020 S 3777053964 \n",
"1 Census Tract 9501 G5020 S 3777053964 \n",
"0 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 9900 G5020 S 0 \n",
"6 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 102.01 G5020 S 138787038 \n",
"5 Census Tract 102.01 G5020 S 138787038 \n",
"1 Census Tract 101 G5020 S 365458278 \n",
"3 Census Tract 101 G5020 S 365458278 \n",
"7 Census Tract 101 G5020 S 365458278 \n",
"1 Census Tract 9506 G5020 S 142823217 \n",
"5 Census Tract 9506 G5020 S 142823217 \n",
"1 Census Tract 9505 G5020 S 198663041 \n",
"1 Census Tract 9504 G5020 S 95793488 \n",
"1 Census Tract 9900 G5020 S 0 \n",
"2 Census Tract 9900 G5020 S 0 \n",
"3 Census Tract 9900 G5020 S 0 \n",
"1 Census Tract 243.02 G5020 S 152233383 \n",
"1 Census Tract 9503 G5020 S 66833755 \n",
"1 Census Tract 243.01 G5020 S 1426811393 \n",
"2 Census Tract 127 G5020 S 129622799 \n",
"3 Census Tract 127 G5020 S 129622799 \n",
"4 Census Tract 127 G5020 S 129622799 \n",
"3 Census Tract 123.04 G5020 S 5761299 \n",
"6 Census Tract 123.04 G5020 S 5761299 \n",
"7 Census Tract 123.04 G5020 S 5761299 \n",
"3 Census Tract 123.01 G5020 S 137622651 \n",
"4 Census Tract 123.01 G5020 S 137622651 \n",
"5 Census Tract 123.01 G5020 S 137622651 \n",
"4 Census Tract 142 G5020 S 229485446 \n",
"6 Census Tract 142 G5020 S 229485446 \n",
"7 Census Tract 142 G5020 S 229485446 \n",
"5 Census Tract 108 G5020 S 24214554 \n",
"5 Census Tract 102.03 G5020 S 36355923 \n",
"5 Census Tract 122 G5020 S 181087087 \n",
"7 Census Tract 122 G5020 S 181087087 \n",
"5 Census Tract 114 G5020 S 52595069 \n",
"6 Census Tract 141 G5020 S 58750542 \n",
"6 Census Tract 132.07 G5020 S 3884436 \n",
"6 Census Tract 132.03 G5020 S 1103957 \n",
"6 Census Tract 126.07 G5020 S 3230089 \n",
"\n",
" AWATER10_right INTPTLAT10_right INTPTLON10_right \n",
"0 324996211 +26.2732070 -097.2763703 \n",
"1 324996211 +26.2732070 -097.2763703 \n",
"2 324996211 +26.2732070 -097.2763703 \n",
"4 324996211 +26.2732070 -097.2763703 \n",
"5 324996211 +26.2732070 -097.2763703 \n",
"6 324996211 +26.2732070 -097.2763703 \n",
"7 324996211 +26.2732070 -097.2763703 \n",
"0 377000048 +26.5154317 -097.5790835 \n",
"3 377000048 +26.5154317 -097.5790835 \n",
"5 377000048 +26.5154317 -097.5790835 \n",
"0 394659578 +26.9389899 -097.3234546 \n",
"1 394659578 +26.9389899 -097.3234546 \n",
"0 867877948 +26.9241932 -097.6694694 \n",
"1 867877948 +26.9241932 -097.6694694 \n",
"0 268272237 +26.1902408 -097.1473235 \n",
"3 268272237 +26.1902408 -097.1473235 \n",
"6 268272237 +26.1902408 -097.1473235 \n",
"1 773532 +26.2865300 -097.6765589 \n",
"5 773532 +26.2865300 -097.6765589 \n",
"1 113041841 +26.2713946 -097.4414470 \n",
"3 113041841 +26.2713946 -097.4414470 \n",
"7 113041841 +26.2713946 -097.4414470 \n",
"1 867417 +26.3413027 -097.6980863 \n",
"5 867417 +26.3413027 -097.6980863 \n",
"1 1916760 +26.4046271 -097.7275193 \n",
"1 440761 +26.4857271 -097.7274534 \n",
"1 121414926 +26.5064260 -097.2240134 \n",
"2 121414926 +26.5064260 -097.2240134 \n",
"3 121414926 +26.5064260 -097.2240134 \n",
"1 10002679 +26.4228640 -097.9710985 \n",
"1 75864 +26.4851686 -097.8236397 \n",
"1 527958 +26.6175624 -098.1948738 \n",
"2 67725054 +25.9786218 -097.2580863 \n",
"3 67725054 +25.9786218 -097.2580863 \n",
"4 67725054 +25.9786218 -097.2580863 \n",
"3 6286773 +26.0631407 -097.2184868 \n",
"6 6286773 +26.0631407 -097.2184868 \n",
"7 6286773 +26.0631407 -097.2184868 \n",
"3 119430273 +26.1581170 -097.3180348 \n",
"4 119430273 +26.1581170 -097.3180348 \n",
"5 119430273 +26.1581170 -097.3180348 \n",
"4 52743725 +26.0321232 -097.3592760 \n",
"6 52743725 +26.0321232 -097.3592760 \n",
"7 52743725 +26.0321232 -097.3592760 \n",
"5 372874 +26.2018913 -097.6365382 \n",
"5 529676 +26.2392001 -097.7004164 \n",
"5 9690866 +26.1431884 -097.4883500 \n",
"7 9690866 +26.1431884 -097.4883500 \n",
"5 1716432 +26.1576649 -097.6030070 \n",
"6 1786306 +25.8820153 -097.4007135 \n",
"6 409892 +25.9278897 -097.4159201 \n",
"6 3034 +25.9335830 -097.4379216 \n",
"6 151343 +25.9479994 -097.4340712 \n",
"\n",
"[53 rows x 27 columns]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"adjacent_tracts__v1"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "f3033c5d",
"metadata": {},
"outputs": [],
"source": [
"### check for duplicates\n",
"assert len(adjacent_tracts__v1[['ORIGINAL_TRACT', 'GEOID10_TRACT']].drop_duplicates()) == len(adjacent_tracts__v1[['ORIGINAL_TRACT', 'GEOID10_TRACT']])"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "4b1770de",
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>48061010100</td>\n",
" <td>0.666667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48061010201</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>48061010203</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>48061010800</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>48061011400</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>48061012200</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>48061012301</td>\n",
" <td>0.666667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>48061012304</td>\n",
" <td>0.666667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>0.714286</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>48061012607</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>48061012700</td>\n",
" <td>0.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>48061013203</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>48061013207</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>48061014100</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>48061014200</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>48061990000</td>\n",
" <td>0.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>48215024301</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>48215024302</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>48261950100</td>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>48261990000</td>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>48489950300</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>48489950400</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>48489950500</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>48489950600</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>48489950700</td>\n",
" <td>0.333333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>48489990000</td>\n",
" <td>0.333333</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"0 48061010100 0.666667\n",
"1 48061010201 1.000000\n",
"2 48061010203 1.000000\n",
"3 48061010800 1.000000\n",
"4 48061011400 1.000000\n",
"5 48061012200 1.000000\n",
"6 48061012301 0.666667\n",
"7 48061012304 0.666667\n",
"8 48061012305 0.714286\n",
"9 48061012607 1.000000\n",
"10 48061012700 0.333333\n",
"11 48061013203 1.000000\n",
"12 48061013207 1.000000\n",
"13 48061014100 1.000000\n",
"14 48061014200 1.000000\n",
"15 48061990000 0.333333\n",
"16 48215024301 1.000000\n",
"17 48215024302 1.000000\n",
"18 48261950100 0.500000\n",
"19 48261990000 0.500000\n",
"20 48489950300 1.000000\n",
"21 48489950400 1.000000\n",
"22 48489950500 1.000000\n",
"23 48489950600 1.000000\n",
"24 48489950700 0.333333\n",
"25 48489990000 0.333333"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"returned_donut_bools__v1"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "c2aa4682",
"metadata": {
"scrolled": true
},
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>0.714286</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 0.714286"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check result for our example tract\n",
"returned_donut_bools__v1[returned_donut_bools__v1.GEOID10_TRACT==CAM_ID]"
]
},
{
"cell_type": "markdown",
"id": "936d0ebc",
"metadata": {},
"source": [
"Demonstrates that because 2 of the 7 adjacent tracts have meaningless water-only non-disadvantaged status, the average of neighbors is less than 1. This is why our example tract isn't being classified as disadvantaged in v1."
]
},
{
"cell_type": "markdown",
"id": "a02b6194",
"metadata": {},
"source": [
"### Simulate proposed v2 implementations of calculate_tract_adjacency_scores()"
]
},
{
"cell_type": "markdown",
"id": "5688387a",
"metadata": {},
"source": [
"Testing three ways to do this: filtering tract_data, filtering df, and filtering both. For the first two ways, we'll test both land area and tract ID range methods."
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "72963a39",
"metadata": {},
"outputs": [],
"source": [
"def view_results(returned_donut_bools, post_merge_df, adjacent_tracts):\n",
" # function to print what we need to see after each experiment\n",
" \n",
" print(f'Length of input df after Census merge: {len(post_merge_df)}') \n",
" print(f'That is {len(df_census__v1) - len(post_merge_df)} less than in v1')\n",
" \n",
" print(f'\\nLength of adjacency frame: {len(adjacent_tracts)}')\n",
" print(f'That is {len(adjacent_tracts__v1) - len(adjacent_tracts)} less than in v1')\n",
" \n",
" n_dupes = len(adjacent_tracts[['ORIGINAL_TRACT', 'GEOID10_TRACT']])\\\n",
" - len(adjacent_tracts[['ORIGINAL_TRACT', 'GEOID10_TRACT']].drop_duplicates())\n",
" if n_dupes>0:\n",
" print(\"ALERT: duplicates present in adjacency frame!\")\n",
"\n",
" \n",
" print(f'\\nLength of returned frame with donut bools: {len(returned_donut_bools)}')\n",
" if len(returned_donut_bools__v1) == len(returned_donut_bools):\n",
" print('Returning same number of final bools as in v1')\n",
" else:\n",
" print(f'ALERT: returning {len(returned_donut_bools__v1) - len(returned_donut_bools)} less than in v1')\n",
"\n",
" cam_return = returned_donut_bools[returned_donut_bools.GEOID10_TRACT==CAM_ID]\n",
" display(cam_return)\n",
"\n",
" if cam_return['Definition N (communities) (average of neighbors)'].values[0]==1:\n",
" print('SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS')\n",
" else:\n",
" print('ALERT: CAMERON, TX EXAMPLE IS STILL BEING MARKED NON-DISADVANTAGED')"
]
},
{
"cell_type": "markdown",
"id": "c1712378",
"metadata": {},
"source": [
"#### Implementation 1a: Filter water-only tracts out of tract_data using ALAND10"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "9e0401e1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of input df after Census merge: 6\n",
"That is 2 less than in v1\n",
"\n",
"Length of adjacency frame: 40\n",
"That is 13 less than in v1\n",
"\n",
"Length of returned frame with donut bools: 23\n",
"ALERT: returning 3 less than in v1\n"
]
},
{
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS\n"
]
}
],
"source": [
"tract_data_land_area_only = tract_data.copy()\n",
"tract_data_land_area_only = tract_data_land_area_only[tract_data_land_area_only.ALAND10>0]\n",
"\n",
"returned_donut_bools__filter_tracts_aland10,\\\n",
"df_census__filter_tracts_aland10,\\\n",
"adjacent_tracts__filter_tracts_aland10 =calculate_tract_adjacency_scores(\n",
" df=df_cam_plus, \n",
" score_column=SCORE_N_COMMUNITIES, \n",
" tract_data=tract_data_land_area_only\n",
")\n",
"\n",
"view_results(returned_donut_bools=returned_donut_bools__filter_tracts_aland10, \n",
" post_merge_df=df_census__filter_tracts_aland10, \n",
" adjacent_tracts=adjacent_tracts__filter_tracts_aland10)"
]
},
{
"cell_type": "markdown",
"id": "f277cc9a",
"metadata": {},
"source": [
"#### Implementation 1b: Filter water-only tracts out of df using tract range"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "0ea48370",
"metadata": {},
"outputs": [],
"source": [
"def full_geo_id_to_water_range_bool(x:str):\n",
" num_x = int(x[-6:])\n",
" return(in_water_range(num_x))"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "a2ef8844",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of input df after Census merge: 6\n",
"That is 2 less than in v1\n",
"\n",
"Length of adjacency frame: 40\n",
"That is 13 less than in v1\n",
"\n",
"Length of returned frame with donut bools: 23\n",
"ALERT: returning 3 less than in v1\n"
]
},
{
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS\n"
]
}
],
"source": [
"tract_data_non_water_range_only = tract_data.copy()\n",
"tract_data_non_water_range_only = tract_data_non_water_range_only[tract_data_non_water_range_only.GEOID10_TRACT\\\n",
" .apply(full_geo_id_to_water_range_bool)\\\n",
" ==False]\n",
"\n",
"returned_donut_bools__filter_tracts_id_range,\\\n",
"df_census__filter_tracts_id_range,\\\n",
"adjacent_tracts__filter_tracts_id_range =calculate_tract_adjacency_scores(\n",
" df=df_cam_plus, \n",
" score_column=SCORE_N_COMMUNITIES, \n",
" tract_data=tract_data_non_water_range_only\n",
")\n",
"\n",
"view_results(returned_donut_bools=returned_donut_bools__filter_tracts_id_range, \n",
" post_merge_df=df_census__filter_tracts_id_range, \n",
" adjacent_tracts=adjacent_tracts__filter_tracts_id_range)"
]
},
{
"cell_type": "markdown",
"id": "1fcee2e2",
"metadata": {},
"source": [
"#### Implementation 2a: Filter water-only tracts out of df using ALAND10"
]
},
{
"cell_type": "markdown",
"id": "477a886c",
"metadata": {},
"source": [
"Note: we can't filter the input df based on ALAND10 using the standard calculate_tract_adjacency_scores() function, because it doesn't have the ALAND10 column until after it is merged with tract data. Need to write a new test function for this method."
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "9ad212d3",
"metadata": {},
"outputs": [],
"source": [
"def calculate_tract_adjacency_scores__filter_df_aland10(\n",
" df: pd.DataFrame, score_column: str, tract_data\n",
") -> pd.DataFrame:\n",
" \"\"\"Calculate the mean score of each tract in df based on its neighbors\n",
"\n",
" Args:\n",
" df (pandas.DataFrame): A dataframe with at least the following columns:\n",
" * field_names.GEOID_TRACT_FIELD\n",
" * score_column\n",
"\n",
" score_column (str): The name of the column that contains the scores\n",
" to average\n",
" \n",
" tract_data (GeoDataFrame): tract data normally loaded in first line of \n",
" function: tract_data = get_tract_geojson()\n",
" Returns :\n",
" tuple containing final returned df in actual function, as well as intermediates:\n",
" - returned_donut_bools (pandas.DataFrame): A dataframe with two columns:\n",
" * field_names.GEOID_TRACT_FIELD\n",
" * {score_column}_ADJACENT_MEAN, which is the average of score_column for\n",
" each tract that touches the tract identified\n",
" in field_names.GEOID_TRACT_FIELD\n",
" NB: this is the df that gets returned in the actual function\n",
" - df (pandas.DataFrame): input df after merging with Census data\n",
" - adjacent_tracts (pandas.DataFrame): adjacency df\n",
" \"\"\"\n",
"\n",
" df: gpd.GeoDataFrame = tract_data.merge(\n",
" df, on=GEOID_TRACT_FIELD\n",
" )\n",
" df = df.rename(columns={GEOID_TRACT_FIELD: ORIGINAL_TRACT})\n",
" \n",
" \n",
" # remove water areas from input frame\n",
" df = df[df['ALAND10']>0]\n",
"\n",
"\n",
" adjacent_tracts: gpd.GeoDataFrame = df.sjoin(\n",
" tract_data, predicate=\"touches\"\n",
" )\n",
"\n",
"\n",
" returned_donut_bools = (\n",
" adjacent_tracts.groupby(GEOID_TRACT_FIELD)[[score_column]]\n",
" .mean()\n",
" .reset_index()\n",
" .rename(\n",
" columns={\n",
" score_column: f\"{score_column}{ADJACENCY_INDEX_SUFFIX}\",\n",
" }\n",
" )\n",
" )\n",
" \n",
" return (returned_donut_bools, df, adjacent_tracts)\n"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "ff9d13cd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of input df after Census merge: 6\n",
"That is 2 less than in v1\n",
"\n",
"Length of adjacency frame: 45\n",
"That is 8 less than in v1\n",
"\n",
"Length of returned frame with donut bools: 26\n",
"Returning same number of final bools as in v1\n"
]
},
{
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS\n"
]
}
],
"source": [
"returned_donut_bools__filter_df_aland10,\\\n",
"df_census__filter_df_aland10,\\\n",
"adjacent_tracts__filter_df_aland10 = calculate_tract_adjacency_scores__filter_df_aland10(\n",
" df=df_cam_plus, \n",
" score_column=SCORE_N_COMMUNITIES, \n",
" tract_data=tract_data\n",
")\n",
"\n",
"view_results(returned_donut_bools=returned_donut_bools__filter_df_aland10, \n",
" post_merge_df=df_census__filter_df_aland10, \n",
" adjacent_tracts=adjacent_tracts__filter_df_aland10)"
]
},
{
"cell_type": "markdown",
"id": "c7401f01",
"metadata": {},
"source": [
"#### Implementation 2b: Filter water-only tracts out of df using tract range"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "3cb027ab",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of input df after Census merge: 6\n",
"That is 2 less than in v1\n",
"\n",
"Length of adjacency frame: 45\n",
"That is 8 less than in v1\n",
"\n",
"Length of returned frame with donut bools: 26\n",
"Returning same number of final bools as in v1\n"
]
},
{
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS\n"
]
}
],
"source": [
"df_cam_plus_no_water = df_cam_plus.copy()\n",
"df_cam_plus_no_water = df_cam_plus_no_water[df_cam_plus_no_water.GEOID10_TRACT\\\n",
" .apply(full_geo_id_to_water_range_bool)\\\n",
" ==False]\n",
"\n",
"returned_donut_bools__filter_df_id_range,\\\n",
"df_census__filter_df_id_range,\\\n",
"adjacent_tracts__filter_df_id_range = calculate_tract_adjacency_scores(\n",
" df=df_cam_plus_no_water, \n",
" score_column=SCORE_N_COMMUNITIES, \n",
" tract_data=tract_data\n",
")\n",
"\n",
"view_results(returned_donut_bools=returned_donut_bools__filter_df_id_range, \n",
" post_merge_df=df_census__filter_df_id_range, \n",
" adjacent_tracts=adjacent_tracts__filter_df_id_range)"
]
},
{
"cell_type": "markdown",
"id": "c0f94a03",
"metadata": {},
"source": [
"#### Implementation 3: Filter water-only tracts out of both tract_data and df"
]
},
{
"cell_type": "markdown",
"id": "e96c981f",
"metadata": {},
"source": [
"Note: test id method for simplicity"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "8e385e22",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Length of input df after Census merge: 6\n",
"That is 2 less than in v1\n",
"\n",
"Length of adjacency frame: 40\n",
"That is 13 less than in v1\n",
"\n",
"Length of returned frame with donut bools: 23\n",
"ALERT: returning 3 less than in v1\n"
]
},
{
"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>GEOID10_TRACT</th>\n",
" <th>Definition N (communities) (average of neighbors)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>48061012305</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT Definition N (communities) (average of neighbors)\n",
"8 48061012305 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUCCESSFULLY RE-ASSIGNING CAMERON, TX EXAMPLE TO DISADVANTAGED STATUS\n"
]
}
],
"source": [
"returned_donut_bools__filter_both,\\\n",
"df_census__filter_both,\\\n",
"adjacent_tracts__filter_both =calculate_tract_adjacency_scores(\n",
" df=df_cam_plus_no_water, \n",
" score_column=SCORE_N_COMMUNITIES, \n",
" tract_data=tract_data_non_water_range_only\n",
")\n",
"\n",
"view_results(returned_donut_bools=returned_donut_bools__filter_both, \n",
" post_merge_df=df_census__filter_both, \n",
" adjacent_tracts=adjacent_tracts__filter_both)"
]
},
{
"cell_type": "markdown",
"id": "dde21850",
"metadata": {},
"source": [
"#### Summary of results: All solutions successfully re-assigned our example tract to disadvantaged status. Only implementations 2a & 2b (filtering on the dataframe) also preserved the number of tracts that the function returns"
]
},
{
"cell_type": "markdown",
"id": "04d07bdb",
"metadata": {},
"source": [
"## Compare full scoring runs from different methods"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "aa462404",
"metadata": {
"scrolled": true
},
"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>GEOID10_TRACT</th>\n",
" <th>dac_adj_avg_prod</th>\n",
" <th>dac_adj_avg_local</th>\n",
" <th>is_donut_hole_prod</th>\n",
" <th>is_donut_hole_local</th>\n",
" <th>final_dac_prod</th>\n",
" <th>final_dac_local</th>\n",
" <th>class_change</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>332</th>\n",
" <td>12087971001</td>\n",
" <td>0.67</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>370</th>\n",
" <td>12101030202</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>376</th>\n",
" <td>12101030303</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>419</th>\n",
" <td>12127081102</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>806</th>\n",
" <td>26069000200</td>\n",
" <td>0.86</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>812</th>\n",
" <td>26083000100</td>\n",
" <td>0.33</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>912</th>\n",
" <td>28047001400</td>\n",
" <td>0.88</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1138</th>\n",
" <td>39007000602</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1654</th>\n",
" <td>41041950303</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1739</th>\n",
" <td>48061012305</td>\n",
" <td>0.71</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1766</th>\n",
" <td>51001090600</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1780</th>\n",
" <td>51131930200</td>\n",
" <td>0.67</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1944</th>\n",
" <td>55101000100</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2012</th>\n",
" <td>72013301000</td>\n",
" <td>0.71</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2037</th>\n",
" <td>72037160100</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT dac_adj_avg_prod dac_adj_avg_local is_donut_hole_prod \\\n",
"332 12087971001 0.67 1.0 False \n",
"370 12101030202 0.83 1.0 False \n",
"376 12101030303 0.83 1.0 False \n",
"419 12127081102 0.75 1.0 False \n",
"806 26069000200 0.86 1.0 False \n",
"812 26083000100 0.33 1.0 False \n",
"912 28047001400 0.88 1.0 False \n",
"1138 39007000602 0.75 1.0 False \n",
"1654 41041950303 0.75 1.0 False \n",
"1739 48061012305 0.71 1.0 False \n",
"1766 51001090600 0.83 1.0 False \n",
"1780 51131930200 0.67 1.0 False \n",
"1944 55101000100 0.75 1.0 False \n",
"2012 72013301000 0.71 1.0 False \n",
"2037 72037160100 0.83 1.0 False \n",
"\n",
" is_donut_hole_local final_dac_prod final_dac_local class_change \n",
"332 True False True True \n",
"370 True False True True \n",
"376 True False True True \n",
"419 True False True True \n",
"806 True False True True \n",
"812 True False True True \n",
"912 True False True True \n",
"1138 True False True True \n",
"1654 True False True True \n",
"1739 True False True True \n",
"1766 True False True True \n",
"1780 True False True True \n",
"1944 True False True True \n",
"2012 True False True True \n",
"2037 True False True True "
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# read in CSV with deltas from implementation 1a \n",
"# (water areas filtered from tract_data via ALAND10)\n",
"deltas__tract_area = pd.read_csv('../data/tmp/Comparator/Score/deltas__tract_area.csv')\n",
"\n",
"# rename key columns\n",
"deltas__tract_area.rename(columns = {'Unnamed: 0': 'GEOID10_TRACT',\n",
" 'Definition N community, including adjacency index tracts': 'final_dac_prod',\n",
" 'Definition N community, including adjacency index tracts.1': 'final_dac_local',\n",
" 'Definition N (communities) (average of neighbors)': 'dac_adj_avg_prod',\n",
" 'Definition N (communities) (average of neighbors).1': 'dac_adj_avg_local',\n",
" 'Is the tract surrounded by disadvantaged communities?': 'is_donut_hole_prod',\n",
" 'Is the tract surrounded by disadvantaged communities?.1': 'is_donut_hole_local'\n",
" },\n",
" inplace=True) \n",
"\n",
"# drop first two rows, which old column information\n",
"deltas__tract_area.drop(index=[0,1], inplace=True)\n",
"\n",
"# create bool to store whether final DAC designation was updated\n",
"deltas__tract_area['class_change'] = deltas__tract_area.final_dac_prod!=deltas__tract_area.final_dac_local\n",
"\n",
"# set class change bool to false where both designations are null\n",
"deltas__tract_area.loc[((deltas__tract_area.final_dac_prod.isna()==True)\\\n",
" & (deltas__tract_area.final_dac_local.isna()==True)), \n",
" 'class_change'] = False\n",
"\n",
"# view tracts that had their status updated with this method\n",
"deltas__tract_area[deltas__tract_area.class_change][['GEOID10_TRACT', \n",
" 'dac_adj_avg_prod', 'dac_adj_avg_local',\n",
" 'is_donut_hole_prod', 'is_donut_hole_local',\n",
" 'final_dac_prod', 'final_dac_local',\n",
" 'class_change']]"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "3dc9500a",
"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>GEOID10_TRACT</th>\n",
" <th>dac_adj_avg_prod</th>\n",
" <th>dac_adj_avg_local</th>\n",
" <th>is_donut_hole_prod</th>\n",
" <th>is_donut_hole_local</th>\n",
" <th>final_dac_prod</th>\n",
" <th>final_dac_local</th>\n",
" <th>class_change</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>312</th>\n",
" <td>12087971001</td>\n",
" <td>0.67</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>346</th>\n",
" <td>12101030202</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>352</th>\n",
" <td>12101030303</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>388</th>\n",
" <td>12127081102</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>741</th>\n",
" <td>26069000200</td>\n",
" <td>0.86</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>747</th>\n",
" <td>26083000100</td>\n",
" <td>0.33</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>836</th>\n",
" <td>28047001400</td>\n",
" <td>0.88</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1044</th>\n",
" <td>39007000602</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1559</th>\n",
" <td>41041950303</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1643</th>\n",
" <td>48061012305</td>\n",
" <td>0.71</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1668</th>\n",
" <td>51001090600</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1679</th>\n",
" <td>51131930200</td>\n",
" <td>0.67</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1828</th>\n",
" <td>55101000100</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1894</th>\n",
" <td>72013301000</td>\n",
" <td>0.71</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1919</th>\n",
" <td>72037160100</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT dac_adj_avg_prod dac_adj_avg_local is_donut_hole_prod \\\n",
"312 12087971001 0.67 1.0 False \n",
"346 12101030202 0.83 1.0 False \n",
"352 12101030303 0.83 1.0 False \n",
"388 12127081102 0.75 1.0 False \n",
"741 26069000200 0.86 1.0 False \n",
"747 26083000100 0.33 1.0 False \n",
"836 28047001400 0.88 1.0 False \n",
"1044 39007000602 0.75 1.0 False \n",
"1559 41041950303 0.75 1.0 False \n",
"1643 48061012305 0.71 1.0 False \n",
"1668 51001090600 0.83 1.0 False \n",
"1679 51131930200 0.67 1.0 False \n",
"1828 55101000100 0.75 1.0 False \n",
"1894 72013301000 0.71 1.0 False \n",
"1919 72037160100 0.83 1.0 False \n",
"\n",
" is_donut_hole_local final_dac_prod final_dac_local class_change \n",
"312 True False True True \n",
"346 True False True True \n",
"352 True False True True \n",
"388 True False True True \n",
"741 True False True True \n",
"747 True False True True \n",
"836 True False True True \n",
"1044 True False True True \n",
"1559 True False True True \n",
"1643 True False True True \n",
"1668 True False True True \n",
"1679 True False True True \n",
"1828 True False True True \n",
"1894 True False True True \n",
"1919 True False True True "
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# read in CSV with deltas from implementation 2a \n",
"# (water areas filtered from input df via ALAND10)\n",
"deltas__df_area = pd.read_csv('../data/tmp/Comparator/Score/deltas__df_area.csv')\n",
"\n",
"# rename key columns\n",
"deltas__df_area.rename(columns = {'Unnamed: 0': 'GEOID10_TRACT',\n",
" 'Definition N community, including adjacency index tracts': 'final_dac_prod',\n",
" 'Definition N community, including adjacency index tracts.1': 'final_dac_local',\n",
" 'Definition N (communities) (average of neighbors)': 'dac_adj_avg_prod',\n",
" 'Definition N (communities) (average of neighbors).1': 'dac_adj_avg_local',\n",
" 'Is the tract surrounded by disadvantaged communities?': 'is_donut_hole_prod',\n",
" 'Is the tract surrounded by disadvantaged communities?.1': 'is_donut_hole_local'\n",
" },\n",
" inplace=True) \n",
"\n",
"# drop first two rows, which old column information\n",
"deltas__df_area.drop(index=[0,1], inplace=True)\n",
"\n",
"# create bool to store whether final DAC designation was updated\n",
"deltas__df_area['class_change'] = deltas__df_area.final_dac_prod!=deltas__df_area.final_dac_local\n",
"\n",
"# set class change bool to false where both designations are null\n",
"deltas__df_area.loc[((deltas__df_area.final_dac_prod.isna()==True)\\\n",
" & (deltas__df_area.final_dac_local.isna()==True)), \n",
" 'class_change'] = False\n",
"\n",
"# view tracts that had their status updated with this method\n",
"deltas__df_area[deltas__df_area.class_change][['GEOID10_TRACT', \n",
" 'dac_adj_avg_prod', 'dac_adj_avg_local',\n",
" 'is_donut_hole_prod', 'is_donut_hole_local',\n",
" 'final_dac_prod', 'final_dac_local',\n",
" 'class_change']]"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "5187abcb",
"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>GEOID10_TRACT</th>\n",
" <th>dac_adj_avg_prod</th>\n",
" <th>dac_adj_avg_local</th>\n",
" <th>is_donut_hole_prod</th>\n",
" <th>is_donut_hole_local</th>\n",
" <th>final_dac_prod</th>\n",
" <th>final_dac_local</th>\n",
" <th>class_change</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>228</th>\n",
" <td>12087971001</td>\n",
" <td>0.67</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>261</th>\n",
" <td>12101030202</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>267</th>\n",
" <td>12101030303</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>292</th>\n",
" <td>12127081102</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>570</th>\n",
" <td>26069000200</td>\n",
" <td>0.86</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>648</th>\n",
" <td>28047001400</td>\n",
" <td>0.88</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>755</th>\n",
" <td>39007000602</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1281</th>\n",
" <td>48061012305</td>\n",
" <td>0.71</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1388</th>\n",
" <td>55101000100</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1470</th>\n",
" <td>72037160100</td>\n",
" <td>0.83</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" GEOID10_TRACT dac_adj_avg_prod dac_adj_avg_local is_donut_hole_prod \\\n",
"228 12087971001 0.67 1.0 False \n",
"261 12101030202 0.83 1.0 False \n",
"267 12101030303 0.83 1.0 False \n",
"292 12127081102 0.75 1.0 False \n",
"570 26069000200 0.86 1.0 False \n",
"648 28047001400 0.88 1.0 False \n",
"755 39007000602 0.75 1.0 False \n",
"1281 48061012305 0.71 1.0 False \n",
"1388 55101000100 0.75 1.0 False \n",
"1470 72037160100 0.83 1.0 False \n",
"\n",
" is_donut_hole_local final_dac_prod final_dac_local class_change \n",
"228 True False True True \n",
"261 True False True True \n",
"267 True False True True \n",
"292 True False True True \n",
"570 True False True True \n",
"648 True False True True \n",
"755 True False True True \n",
"1281 True False True True \n",
"1388 True False True True \n",
"1470 True False True True "
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# read in CSV with deltas from implementation 2b \n",
"# (water areas filtered from input df via IDs)\n",
"deltas__df_id = pd.read_csv('../data/tmp/Comparator/Score/deltas__df_id.csv')\n",
"\n",
"# rename key columns\n",
"deltas__df_id.rename(columns = {'Unnamed: 0': 'GEOID10_TRACT',\n",
" 'Definition N community, including adjacency index tracts': 'final_dac_prod',\n",
" 'Definition N community, including adjacency index tracts.1': 'final_dac_local',\n",
" 'Definition N (communities) (average of neighbors)': 'dac_adj_avg_prod',\n",
" 'Definition N (communities) (average of neighbors).1': 'dac_adj_avg_local',\n",
" 'Is the tract surrounded by disadvantaged communities?': 'is_donut_hole_prod',\n",
" 'Is the tract surrounded by disadvantaged communities?.1': 'is_donut_hole_local'\n",
" },\n",
" inplace=True) \n",
"\n",
"# drop first two rows, which old column information\n",
"deltas__df_id.drop(index=[0,1], inplace=True)\n",
"\n",
"# create bool to store whether final DAC designation was updated\n",
"deltas__df_id['class_change'] = deltas__df_id.final_dac_prod!=deltas__df_id.final_dac_local\n",
"\n",
"# set class change bool to false where both designations are null\n",
"deltas__df_id.loc[((deltas__df_id.final_dac_prod.isna()==True)\\\n",
" & (deltas__df_id.final_dac_local.isna()==True)), \n",
" 'class_change'] = False\n",
"\n",
"# view tracts that had their status updated with this method\n",
"deltas__df_id[deltas__df_id.class_change][['GEOID10_TRACT', \n",
" 'dac_adj_avg_prod', 'dac_adj_avg_local',\n",
" 'is_donut_hole_prod', 'is_donut_hole_local',\n",
" 'final_dac_prod', 'final_dac_local',\n",
" 'class_change']]"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "6d1c7b0e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"12087971001, 12101030202, 12101030303, 12127081102, 26069000200, 26083000100, 28047001400, 39007000602, 41041950303, 48061012305, 51001090600, 51131930200, 55101000100, 72013301000, 72037160100\n"
]
}
],
"source": [
"# print list of tract IDs where status was updated by method 1a\n",
"updated_ids__tract_area = deltas__tract_area[deltas__tract_area.class_change]['GEOID10_TRACT'].values\n",
"print(', '.join(updated_ids__tract_area))"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "a1ea1384",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"12087971001, 12101030202, 12101030303, 12127081102, 26069000200, 26083000100, 28047001400, 39007000602, 41041950303, 48061012305, 51001090600, 51131930200, 55101000100, 72013301000, 72037160100\n"
]
}
],
"source": [
"# print list of tract IDs where status was updated by method 2a\n",
"updated_ids__df_area = deltas__df_area[deltas__df_area.class_change]['GEOID10_TRACT'].values\n",
"print(', '.join(updated_ids__df_area))"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "f6516263",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"12087971001, 12101030202, 12101030303, 12127081102, 26069000200, 28047001400, 39007000602, 48061012305, 55101000100, 72037160100\n"
]
}
],
"source": [
"# print list of tract IDs where status was updated by method 2b\n",
"updated_ids__df_id = deltas__df_id[deltas__df_id.class_change]['GEOID10_TRACT'].values\n",
"print(', '.join(updated_ids__df_id))"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "f540133f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many tracts updated by method 1a?\n",
"len(updated_ids__tract_area)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "ffb41759",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many tracts updated by method 2a?\n",
"len(updated_ids__df_area)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "4e5099ff",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"10"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many tracts updated by method 2b?\n",
"len(updated_ids__df_id)"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "8534563c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many tracts are changed by both 1a and 2a?\n",
"len(set(updated_ids__tract_area) & set(updated_ids__df_area))"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "b8270c9a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"10"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many tracts are changed by all 3?\n",
"len(set(updated_ids__tract_area) & set(updated_ids__df_id))"
]
},
{
"cell_type": "markdown",
"id": "6494e4c3",
"metadata": {},
"source": [
"Implementations 1a & 2a result in the same designations. They makes all the same changes as implementation 2b, plus 5 more."
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "8c80b1d6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'26083000100', '41041950303', '51001090600', '51131930200', '72013301000'}"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# view the tracts that are changed with 1a/2a but not with 2b\n",
"\n",
"set(updated_ids__tract_area) - set(updated_ids__df_id)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "bb4a3c4b",
"metadata": {},
"outputs": [],
"source": [
"### VA:\n",
"# 51001090600\n",
"# https://screeningtool.geoplatform.gov/en/#9.26/37.7027/-75.8891\n",
"# 51131930200\n",
"# https://screeningtool.geoplatform.gov/en/#9.84/37.3186/-75.9043\n",
"\n",
"### MI: \n",
"# 26083000100\n",
"# https://screeningtool.geoplatform.gov/en/#8.87/47.3424/-88.1965\n",
"\n",
"### OR:\n",
"# 41041950303\n",
"# https://screeningtool.geoplatform.gov/en/#11.94/45.015/-123.98189\n",
"\n",
"### PR:\n",
"# 72013301000\n",
"# https://screeningtool.geoplatform.gov/en/#13.45/18.47558/-66.75585"
]
},
{
"cell_type": "markdown",
"id": "9c3e7297",
"metadata": {},
"source": [
"These all look like they should be re-classified. Indicates we should not go with 2b."
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "67bbb703",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'12087971001',\n",
" '12101030202',\n",
" '12101030303',\n",
" '12127081102',\n",
" '26069000200',\n",
" '28047001400',\n",
" '39007000602',\n",
" '48061012305',\n",
" '55101000100',\n",
" '72037160100'}"
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check the rest of the changed tracts\n",
"set(updated_ids__tract_area) & set(updated_ids__df_id)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "b51cfa18",
"metadata": {},
"outputs": [],
"source": [
"### FL:\n",
"# 12087971001\n",
"# https://screeningtool.geoplatform.gov/en/#12.3/24.73756/-81.0061\n",
"# 12101030202\n",
"# https://screeningtool.geoplatform.gov/en/#13.28/28.34631/-82.71162\n",
"# 12101030303\n",
"# https://screeningtool.geoplatform.gov/en/#12.8/28.22897/-82.75138\n",
"# 12127081102\n",
"# https://screeningtool.geoplatform.gov/en/#13.54/29.24789/-81.02269\n",
"\n",
"### MI:\n",
"# 26069000200\n",
"# https://screeningtool.geoplatform.gov/en/#9.71/44.3623/-83.5055\n",
"\n",
"### MS:\n",
"# 28047001400\n",
"# https://screeningtool.geoplatform.gov/en/#11.54/30.3705/-89.0511\n",
"\n",
"### OH:\n",
"# 39007000602\n",
"# https://screeningtool.geoplatform.gov/en/#12.33/41.89305/-80.82678\n",
"\n",
"### TX:\n",
"# 48061012305\n",
"# https://screeningtool.geoplatform.gov/en/#9.76/26.2291/-97.2455\n",
"\n",
"### WI:\n",
"# 55101000100\n",
"# https://screeningtool.geoplatform.gov/en/#13.44/42.7299/-87.77935\n",
"\n",
"### PR:\n",
"# 72037160100\n",
"# https://screeningtool.geoplatform.gov/en/#11.59/18.2405/-65.6222"
]
},
{
"cell_type": "markdown",
"id": "3410f026",
"metadata": {},
"source": [
"These all look like legitimate donut holes."
]
},
{
"cell_type": "markdown",
"id": "327894d4",
"metadata": {},
"source": [
"#### Final recommendation: Use implementation 2a (filter the input df using ALAND10). This will allow us to update the status of all 15 of the above Census tracts, and will also let the function continue to return rows for the water tracts (as we currently do in prod)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4455847a",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in a new issue View git blame Copy permalink