{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "3ab8f7c1", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import csv\n", "from pathlib import Path\n", "import os\n", "import sys" ] }, { "cell_type": "code", "execution_count": 2, "id": "8c22494f", "metadata": {}, "outputs": [], "source": [ "module_path = os.path.abspath(os.path.join(\"..\"))\n", "if module_path not in sys.path:\n", " sys.path.append(module_path)" ] }, { "cell_type": "code", "execution_count": 4, "id": "eb31e9a1", "metadata": {}, "outputs": [], "source": [ "DATA_PATH = Path.cwd().parent / \"data\"\n", "TMP_PATH: Path = DATA_PATH / \"tmp\"\n", "OUTPUT_PATH = DATA_PATH / \"dataset\" / \"ejscreen_2019\"\n", "CENSUS_USA_CSV = DATA_PATH / \"census\" / \"csv\" / \"us.csv\"" ] }, { "cell_type": "code", "execution_count": 5, "id": "95a5f8d8", "metadata": {}, "outputs": [], "source": [ "cbg_usa_df = pd.read_csv(\n", " CENSUS_USA_CSV,\n", " names=[\"GEOID10\"],\n", " dtype={\"GEOID10\": \"string\"},\n", " low_memory=False,\n", " header=None,\n", ")" ] }, { "cell_type": "code", "execution_count": 6, "id": "bdd9ab60", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | GEOID10 | \n", "
---|---|
0 | \n", "100010414002 | \n", "
1 | \n", "100010415002 | \n", "
2 | \n", "100010417011 | \n", "
3 | \n", "100010417012 | \n", "
4 | \n", "100010422011 | \n", "
\n", " | OBJECTID | \n", "GEOID10 | \n", "STATE_NAME | \n", "ST_ABBREV | \n", "REGION | \n", "ACSTOTPOP | \n", "D_PM25_2 | \n", "B_PM25_D2 | \n", "P_PM25_D2 | \n", "D_OZONE_2 | \n", "... | \n", "T_PNPL | \n", "T_PNPL_D2 | \n", "T_PRMP | \n", "T_PRMP_D2 | \n", "T_PTSDF | \n", "T_PTSDF_D2 | \n", "T_PWDIS | \n", "T_PWDIS_D2 | \n", "Shape_Length | \n", "Shape_Area | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "010010201001 | \n", "Alabama | \n", "AL | \n", "4 | \n", "692 | \n", "-1161.544049 | \n", "5 | \n", "43.0 | \n", "-4661.186378 | \n", "... | \n", "0.071 facilities/km distance (79%ile) | \n", "26%ile | \n", "0.085 facilities/km distance (24%ile) | \n", "47%ile | \n", "0.066 facilities/km distance (21%ile) | \n", "48%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "62%ile | \n", "13435.975560 | \n", "6.026828e+06 | \n", "
1 | \n", "2 | \n", "010010201002 | \n", "Alabama | \n", "AL | \n", "4 | \n", "1153 | \n", "-2084.690717 | \n", "4 | \n", "31.0 | \n", "-8365.702519 | \n", "... | \n", "0.064 facilities/km distance (76%ile) | \n", "19%ile | \n", "0.074 facilities/km distance (18%ile) | \n", "41%ile | \n", "0.06 facilities/km distance (18%ile) | \n", "42%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "62%ile | \n", "11945.584679 | \n", "7.848121e+06 | \n", "
2 | \n", "3 | \n", "010010202001 | \n", "Alabama | \n", "AL | \n", "4 | \n", "1020 | \n", "2641.389659 | \n", "9 | \n", "81.0 | \n", "10550.793324 | \n", "... | \n", "0.069 facilities/km distance (78%ile) | \n", "87%ile | \n", "0.078 facilities/km distance (20%ile) | \n", "71%ile | \n", "0.065 facilities/km distance (20%ile) | \n", "71%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "62%ile | \n", "7770.915121 | \n", "2.900774e+06 | \n", "
3 | \n", "4 | \n", "010010202002 | \n", "Alabama | \n", "AL | \n", "4 | \n", "1152 | \n", "693.118534 | \n", "7 | \n", "65.0 | \n", "2768.599617 | \n", "... | \n", "0.076 facilities/km distance (81%ile) | \n", "75%ile | \n", "0.087 facilities/km distance (25%ile) | \n", "63%ile | \n", "0.07 facilities/km distance (23%ile) | \n", "63%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "62%ile | \n", "6506.804784 | \n", "1.793332e+06 | \n", "
4 | \n", "5 | \n", "010010203001 | \n", "Alabama | \n", "AL | \n", "4 | \n", "2555 | \n", "1034.343525 | \n", "7 | \n", "68.0 | \n", "4120.531837 | \n", "... | \n", "0.074 facilities/km distance (80%ile) | \n", "79%ile | \n", "0.08 facilities/km distance (21%ile) | \n", "64%ile | \n", "0.07 facilities/km distance (23%ile) | \n", "65%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "62%ile | \n", "11070.367848 | \n", "5.461602e+06 | \n", "
5 rows × 128 columns
\n", "\n", " | GEOID10 | \n", "OBJECTID | \n", "STATE_NAME | \n", "ST_ABBREV | \n", "REGION | \n", "ACSTOTPOP | \n", "D_PM25_2 | \n", "B_PM25_D2 | \n", "P_PM25_D2 | \n", "D_OZONE_2 | \n", "... | \n", "T_PNPL | \n", "T_PNPL_D2 | \n", "T_PRMP | \n", "T_PRMP_D2 | \n", "T_PTSDF | \n", "T_PTSDF_D2 | \n", "T_PWDIS | \n", "T_PWDIS_D2 | \n", "Shape_Length | \n", "Shape_Area | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "100010414002 | \n", "39652.0 | \n", "Delaware | \n", "DE | \n", "3.0 | \n", "1187.0 | \n", "3655.279721 | \n", "10.0 | \n", "90.0 | \n", "22778.314495 | \n", "... | \n", "1.7 facilities/km distance (99%ile) | \n", "100%ile | \n", "0.23 facilities/km distance (40%ile) | \n", "80%ile | \n", "1.6 facilities/km distance (63%ile) | \n", "87%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "69%ile | \n", "4866.135943 | \n", "1.156165e+06 | \n", "
1 | \n", "100010415002 | \n", "39654.0 | \n", "Delaware | \n", "DE | \n", "3.0 | \n", "1088.0 | \n", "100.877666 | \n", "7.0 | \n", "65.0 | \n", "629.604923 | \n", "... | \n", "0.32 facilities/km distance (69%ile) | \n", "66%ile | \n", "0.14 facilities/km distance (20%ile) | \n", "64%ile | \n", "1 facilities/km distance (52%ile) | \n", "66%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "69%ile | \n", "7972.275657 | \n", "2.821805e+06 | \n", "
2 | \n", "100010417011 | \n", "39656.0 | \n", "Delaware | \n", "DE | \n", "3.0 | \n", "1554.0 | \n", "-1256.221548 | \n", "5.0 | \n", "45.0 | \n", "-7833.701886 | \n", "... | \n", "0.21 facilities/km distance (52%ile) | \n", "31%ile | \n", "0.11 facilities/km distance (11%ile) | \n", "53%ile | \n", "1.3 facilities/km distance (58%ile) | \n", "22%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "69%ile | \n", "17643.717513 | \n", "8.143206e+06 | \n", "
3 | \n", "100010417012 | \n", "39657.0 | \n", "Delaware | \n", "DE | \n", "3.0 | \n", "4543.0 | \n", "-2095.065215 | \n", "4.0 | \n", "32.0 | \n", "-13064.667094 | \n", "... | \n", "0.17 facilities/km distance (43%ile) | \n", "25%ile | \n", "0.1 facilities/km distance (7%ile) | \n", "48%ile | \n", "1.1 facilities/km distance (54%ile) | \n", "18%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "69%ile | \n", "15645.341219 | \n", "9.723460e+06 | \n", "
4 | \n", "100010422011 | \n", "39671.0 | \n", "Delaware | \n", "DE | \n", "3.0 | \n", "5153.0 | \n", "-723.497337 | \n", "6.0 | \n", "53.0 | \n", "-4534.212814 | \n", "... | \n", "0.24 facilities/km distance (58%ile) | \n", "41%ile | \n", "0.11 facilities/km distance (8%ile) | \n", "58%ile | \n", "0.3 facilities/km distance (33%ile) | \n", "50%ile | \n", "0 toxicity-weighted concentration/meters dista... | \n", "69%ile | \n", "20959.959236 | \n", "2.066192e+07 | \n", "
5 rows × 128 columns
\n", "\n", " | GEOID10 | \n", "OBJECTID | \n", "STATE_NAME | \n", "ST_ABBREV | \n", "REGION | \n", "ACSTOTPOP | \n", "D_PM25_2 | \n", "B_PM25_D2 | \n", "P_PM25_D2 | \n", "D_OZONE_2 | \n", "... | \n", "T_PNPL | \n", "T_PNPL_D2 | \n", "T_PRMP | \n", "T_PRMP_D2 | \n", "T_PTSDF | \n", "T_PTSDF_D2 | \n", "T_PWDIS | \n", "T_PWDIS_D2 | \n", "Shape_Length | \n", "Shape_Area | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
10614 | \n", "515150501002 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
10615 | \n", "515150501003 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
10627 | \n", "515150501001 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
10628 | \n", "515150501005 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
10629 | \n", "515150501004 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
174140 | \n", "040190029031 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
174143 | \n", "040190027012 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
174184 | \n", "040190027011 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
174242 | \n", "040194105021 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
174243 | \n", "040194105011 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
73 rows × 128 columns
\n", "