diff --git a/data/data-pipeline/data_pipeline/ipython/scoring_comparison.ipynb b/data/data-pipeline/data_pipeline/ipython/scoring_comparison.ipynb new file mode 100644 index 00000000..bb66c5c7 --- /dev/null +++ b/data/data-pipeline/data_pipeline/ipython/scoring_comparison.ipynb @@ -0,0 +1,4798 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "71c4acd0", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "import collections\n", + "import functools\n", + "import IPython\n", + "import itertools\n", + "import numpy as np\n", + "import os\n", + "import pandas as pd\n", + "import pathlib\n", + "import pypandoc\n", + "import requests\n", + "import string\n", + "import sys\n", + "import time\n", + "import typing\n", + "import us\n", + "import zipfile\n", + "\n", + "from datetime import datetime\n", + "from tqdm.notebook import tqdm_notebook\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.utils import remove_all_from_dir, get_excel_column_name\n", + "from data_pipeline.etl.base import ExtractTransformLoad\n", + "from data_pipeline.etl.sources.census.etl_utils import get_state_information\n", + "from data_pipeline.etl.sources.ejscreen_areas_of_concern.etl import (\n", + " EJSCREENAreasOfConcernETL,\n", + ")\n", + "\n", + "\n", + "from data_pipeline.score import field_names\n", + "\n", + "%load_ext lab_black\n", + "# Turn on TQDM for pandas so that we can have progress bars when running `apply`.\n", + "tqdm_notebook.pandas()" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "2ce3170c", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "# Suppress scientific notation in pandas (this shows up for census tract IDs)\n", + "pd.options.display.float_format = \"{:.2f}\".format\n", + "\n", + "# Set some global parameters\n", + "DATA_DIR = pathlib.Path.cwd().parent / \"data\"\n", + "TEMP_DATA_DIR = DATA_DIR / \"tmp\"\n", + "\n", + "time_str = time.strftime(\"%Y%m%d-%H%M%S\")\n", + "\n", + "COMPARISON_OUTPUTS_DIR = DATA_DIR / \"comparison_outputs\" / time_str\n", + "\n", + "# Make the dirs if they don't exist\n", + "TEMP_DATA_DIR.mkdir(parents=True, exist_ok=True)\n", + "COMPARISON_OUTPUTS_DIR.mkdir(parents=True, exist_ok=True)\n", + "\n", + "CEJST_PRIORITY_COMMUNITY_THRESHOLD = 0.75\n", + "\n", + "# Name fields using variables. (This makes it easy to reference the same fields frequently without using strings\n", + "# and introducing the risk of misspelling the field name.)\n", + "GEOID_STATE_FIELD_NAME = \"GEOID10_STATE\"\n", + "COUNTRY_FIELD_NAME = \"Country\"\n", + "\n", + "# Define some suffixes\n", + "POPULATION_SUFFIX = \" (priority population)\"" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "8bd39090", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/usr/local/Cellar/jupyterlab/3.2.8/libexec/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3251: DtypeWarning: Columns (1) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " exec(code_obj, self.user_global_ns, self.user_ns)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTPersistent Poverty Census TractHousing burden (percent)Total populationMedian household income (% of state median household income)Current asthma among adults aged greater than or equal to 18 yearsCoronary heart disease among adults aged greater than or equal to 18 yearsCancer (excluding skin cancer) among adults aged greater than or equal to 18 yearsCurrent lack of health insurance among adults aged 18-64 yearsDiagnosed diabetes among adults aged greater than or equal to 18 years...Score D (top 25th percentile)Score D (top 30th percentile)Score D (top 35th percentile)Score D (top 40th percentile)Score E (percentile)Score E (top 25th percentile)Score E (top 30th percentile)Score E (top 35th percentile)Score E (top 40th percentile)GEOID10_STATE
001073001100True0.284897.000.7311.207.206.7016.6019.30...FalseFalseFalseFalse0.33FalseFalseFalseFalse01
101073001400True0.181906.000.7111.109.107.3021.4022.40...FalseFalseTrueTrue0.73FalseTrueTrueTrue01
201073002000False0.444215.000.5413.509.506.1025.4022.80...TrueTrueTrueTrue0.93TrueTrueTrueTrue01
301073003802False0.415149.000.7712.006.605.6020.9018.60...TrueTrueTrueTrue0.76TrueTrueTrueTrue01
401073004000True0.472621.000.3713.1010.006.3024.5025.00...TrueTrueTrueTrue0.95TrueTrueTrueTrue01
\n", + "

5 rows × 554 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Persistent Poverty Census Tract Housing burden (percent) \\\n", + "0 01073001100 True 0.28 \n", + "1 01073001400 True 0.18 \n", + "2 01073002000 False 0.44 \n", + "3 01073003802 False 0.41 \n", + "4 01073004000 True 0.47 \n", + "\n", + " Total population \\\n", + "0 4897.00 \n", + "1 1906.00 \n", + "2 4215.00 \n", + "3 5149.00 \n", + "4 2621.00 \n", + "\n", + " Median household income (% of state median household income) \\\n", + "0 0.73 \n", + "1 0.71 \n", + "2 0.54 \n", + "3 0.77 \n", + "4 0.37 \n", + "\n", + " Current asthma among adults aged greater than or equal to 18 years \\\n", + "0 11.20 \n", + "1 11.10 \n", + "2 13.50 \n", + "3 12.00 \n", + "4 13.10 \n", + "\n", + " Coronary heart disease among adults aged greater than or equal to 18 years \\\n", + "0 7.20 \n", + "1 9.10 \n", + "2 9.50 \n", + "3 6.60 \n", + "4 10.00 \n", + "\n", + " Cancer (excluding skin cancer) among adults aged greater than or equal to 18 years \\\n", + "0 6.70 \n", + "1 7.30 \n", + "2 6.10 \n", + "3 5.60 \n", + "4 6.30 \n", + "\n", + " Current lack of health insurance among adults aged 18-64 years \\\n", + "0 16.60 \n", + "1 21.40 \n", + "2 25.40 \n", + "3 20.90 \n", + "4 24.50 \n", + "\n", + " Diagnosed diabetes among adults aged greater than or equal to 18 years \\\n", + "0 19.30 \n", + "1 22.40 \n", + "2 22.80 \n", + "3 18.60 \n", + "4 25.00 \n", + "\n", + " ... Score D (top 25th percentile) Score D (top 30th percentile) \\\n", + "0 ... False False \n", + "1 ... False False \n", + "2 ... True True \n", + "3 ... True True \n", + "4 ... True True \n", + "\n", + " Score D (top 35th percentile) Score D (top 40th percentile) \\\n", + "0 False False \n", + "1 True True \n", + "2 True True \n", + "3 True True \n", + "4 True True \n", + "\n", + " Score E (percentile) Score E (top 25th percentile) \\\n", + "0 0.33 False \n", + "1 0.73 False \n", + "2 0.93 True \n", + "3 0.76 True \n", + "4 0.95 True \n", + "\n", + " Score E (top 30th percentile) Score E (top 35th percentile) \\\n", + "0 False False \n", + "1 True True \n", + "2 True True \n", + "3 True True \n", + "4 True True \n", + "\n", + " Score E (top 40th percentile) GEOID10_STATE \n", + "0 False 01 \n", + "1 True 01 \n", + "2 True 01 \n", + "3 True 01 \n", + "4 True 01 \n", + "\n", + "[5 rows x 554 columns]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load CEJST score data\n", + "cejst_data_path = DATA_DIR / \"score\" / \"csv\" / \"full\" / \"usa.csv\"\n", + "cejst_df = pd.read_csv(\n", + " cejst_data_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "# Create the state ID by taking the first two digits of the FIPS CODE of the tract.\n", + "# For more information, see https://www.census.gov/programs-surveys/geography/guidance/geo-identifiers.html.\n", + "cejst_df.loc[:, GEOID_STATE_FIELD_NAME] = (\n", + " cejst_df.loc[:, ExtractTransformLoad.GEOID_TRACT_FIELD_NAME].astype(str).str[0:2]\n", + ")\n", + "\n", + "cejst_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "a251a0fb", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "EJSCREEN areas of concern data does not exist locally. Not attempting to load data into comparison tool.\n" + ] + } + ], + "source": [ + "# Load EJSCREEN Areas of Concern data.\n", + "\n", + "# Load EJ Screen Areas of Concern\n", + "# Before attempting, check whether or not the EJSCREEN AoC data is available locally.\n", + "# Note: this data is provided privately and is not currently publicly available.\n", + "# To enable the ETL code for EJSCREEN AoCs to run appropriately whether or not the person\n", + "# running it has access to that data, `ejscreen_areas_of_concern_data_exists` checks whether the source file exists.\n", + "# If it does exist, code can and should include this data. If it does not exist, code should\n", + "# not reference this data.\n", + "ejscreen_areas_of_concern_df: pd.DataFrame = None\n", + "\n", + "if EJSCREENAreasOfConcernETL.ejscreen_areas_of_concern_data_exists():\n", + " print(\"Loading EJSCREEN Areas of Concern data for score pipeline.\")\n", + " ejscreen_areas_of_concern_csv = (\n", + " DATA_DIR / \"dataset\" / \"ejscreen_areas_of_concern\" / \"usa.csv\"\n", + " )\n", + " ejscreen_areas_of_concern_df = pd.read_csv(\n", + " ejscreen_areas_of_concern_csv,\n", + " dtype={ExtractTransformLoad.GEOID_FIELD_NAME: \"string\"},\n", + " low_memory=False,\n", + " )\n", + "else:\n", + " print(\n", + " \"EJSCREEN areas of concern data does not exist locally. Not attempting to load data into comparison tool.\"\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "e43a9e23", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTPersistent Poverty Census TractHousing burden (percent)Total populationMedian household income (% of state median household income)Current asthma among adults aged greater than or equal to 18 yearsCoronary heart disease among adults aged greater than or equal to 18 yearsCancer (excluding skin cancer) among adults aged greater than or equal to 18 yearsCurrent lack of health insurance among adults aged 18-64 yearsDiagnosed diabetes among adults aged greater than or equal to 18 years...Score D (top 25th percentile)Score D (top 30th percentile)Score D (top 35th percentile)Score D (top 40th percentile)Score E (percentile)Score E (top 25th percentile)Score E (top 30th percentile)Score E (top 35th percentile)Score E (top 40th percentile)GEOID10_STATE
001073001100True0.284897.000.7311.207.206.7016.6019.30...FalseFalseFalseFalse0.33FalseFalseFalseFalse01
101073001400True0.181906.000.7111.109.107.3021.4022.40...FalseFalseTrueTrue0.73FalseTrueTrueTrue01
201073002000False0.444215.000.5413.509.506.1025.4022.80...TrueTrueTrueTrue0.93TrueTrueTrueTrue01
301073003802False0.415149.000.7712.006.605.6020.9018.60...TrueTrueTrueTrue0.76TrueTrueTrueTrue01
401073004000True0.472621.000.3713.1010.006.3024.5025.00...TrueTrueTrueTrue0.95TrueTrueTrueTrue01
\n", + "

5 rows × 554 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Persistent Poverty Census Tract Housing burden (percent) \\\n", + "0 01073001100 True 0.28 \n", + "1 01073001400 True 0.18 \n", + "2 01073002000 False 0.44 \n", + "3 01073003802 False 0.41 \n", + "4 01073004000 True 0.47 \n", + "\n", + " Total population \\\n", + "0 4897.00 \n", + "1 1906.00 \n", + "2 4215.00 \n", + "3 5149.00 \n", + "4 2621.00 \n", + "\n", + " Median household income (% of state median household income) \\\n", + "0 0.73 \n", + "1 0.71 \n", + "2 0.54 \n", + "3 0.77 \n", + "4 0.37 \n", + "\n", + " Current asthma among adults aged greater than or equal to 18 years \\\n", + "0 11.20 \n", + "1 11.10 \n", + "2 13.50 \n", + "3 12.00 \n", + "4 13.10 \n", + "\n", + " Coronary heart disease among adults aged greater than or equal to 18 years \\\n", + "0 7.20 \n", + "1 9.10 \n", + "2 9.50 \n", + "3 6.60 \n", + "4 10.00 \n", + "\n", + " Cancer (excluding skin cancer) among adults aged greater than or equal to 18 years \\\n", + "0 6.70 \n", + "1 7.30 \n", + "2 6.10 \n", + "3 5.60 \n", + "4 6.30 \n", + "\n", + " Current lack of health insurance among adults aged 18-64 years \\\n", + "0 16.60 \n", + "1 21.40 \n", + "2 25.40 \n", + "3 20.90 \n", + "4 24.50 \n", + "\n", + " Diagnosed diabetes among adults aged greater than or equal to 18 years \\\n", + "0 19.30 \n", + "1 22.40 \n", + "2 22.80 \n", + "3 18.60 \n", + "4 25.00 \n", + "\n", + " ... Score D (top 25th percentile) Score D (top 30th percentile) \\\n", + "0 ... False False \n", + "1 ... False False \n", + "2 ... True True \n", + "3 ... True True \n", + "4 ... True True \n", + "\n", + " Score D (top 35th percentile) Score D (top 40th percentile) \\\n", + "0 False False \n", + "1 True True \n", + "2 True True \n", + "3 True True \n", + "4 True True \n", + "\n", + " Score E (percentile) Score E (top 25th percentile) \\\n", + "0 0.33 False \n", + "1 0.73 False \n", + "2 0.93 True \n", + "3 0.76 True \n", + "4 0.95 True \n", + "\n", + " Score E (top 30th percentile) Score E (top 35th percentile) \\\n", + "0 False False \n", + "1 True True \n", + "2 True True \n", + "3 True True \n", + "4 True True \n", + "\n", + " Score E (top 40th percentile) GEOID10_STATE \n", + "0 False 01 \n", + "1 True 01 \n", + "2 True 01 \n", + "3 True 01 \n", + "4 True 01 \n", + "\n", + "[5 rows x 554 columns]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Merge EJSCREEN AoCs into CEJST data.\n", + "# Before attempting, check whether or not the EJSCREEN AoC data is available locally.\n", + "if EJSCREENAreasOfConcernETL.ejscreen_areas_of_concern_data_exists():\n", + " # If available, merge EJSCREEN AoC data into CBG dfs.\n", + " # TODO: When we get AoC data at the tract level, fix this.\n", + " # Right now commenting this out to avoid merging CBG-level areas of concern on a tract-level CEJST definition.\n", + " # cejst_df = cejst_df.merge(\n", + " # ejscreen_areas_of_concern_df, on=GEOID_FIELD_NAME, how=\"outer\"\n", + " # )\n", + " pass\n", + "else:\n", + " pass\n", + "\n", + "cejst_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "38c0dc2f", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "~~~~Analysis for field `Percent enrollment in college or graduate school`~~~~\n", + "count 73298.00\n", + "mean 0.08\n", + "std 0.09\n", + "min 0.00\n", + "25% 0.04\n", + "50% 0.06\n", + "75% 0.09\n", + "max 1.00\n", + "Name: Percent enrollment in college or graduate school, dtype: float64\n", + "\n", + "There are 1.16% of values missing.\n", + "\n", + "Quantile at 0.9 is 0.12186292304275304\n", + "AxesSubplot(0.125,0.125;0.775x0.755)\n", + "\n", + "~~~~Analysis for field `Percent individuals age 25 or over with less than high school degree`~~~~\n", + "count 73280.00\n", + "mean 0.13\n", + "std 0.10\n", + "min 0.00\n", + "25% 0.05\n", + "50% 0.10\n", + "75% 0.17\n", + "max 1.00\n", + "Name: Percent individuals age 25 or over with less than high school degree, dtype: float64\n", + "\n", + "There are 1.19% of values missing.\n", + "\n", + "Quantile at 0.9 is 0.2693215167829206\n", + "AxesSubplot(0.125,0.125;0.775x0.755)\n", + "\n", + "~~~~Analysis for field `Median household income as a percent of area median income`~~~~\n", + "count 68232.00\n", + "mean 1.01\n", + "std 0.43\n", + "min 0.04\n", + "25% 0.72\n", + "50% 0.94\n", + "75% 1.21\n", + "max 4.46\n", + "Name: Median household income as a percent of area median income, dtype: float64\n", + "\n", + "There are 7.99% of values missing.\n", + "\n", + "Quantile at 0.9 is 1.5445838485220498\n", + "AxesSubplot(0.125,0.125;0.775x0.755)\n", + "\n", + "~~~~Analysis for field `Percent of individuals below 200% Federal Poverty Line`~~~~\n", + "count 73149.00\n", + "mean 0.33\n", + "std 0.19\n", + "min 0.00\n", + "25% 0.18\n", + "50% 0.30\n", + "75% 0.45\n", + "max 1.00\n", + "Name: Percent of individuals below 200% Federal Poverty Line, dtype: float64\n", + "\n", + "There are 1.36% of values missing.\n", + "\n", + "Quantile at 0.9 is 0.6000566482486579\n", + "AxesSubplot(0.125,0.125;0.775x0.755)\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# Analyze one field at a time (useful for setting thresholds)\n", + "\n", + "quantile = 0.90\n", + "\n", + "for field in [\n", + " field_names.COLLEGE_ATTENDANCE_FIELD,\n", + " field_names.HIGH_SCHOOL_ED_FIELD,\n", + " field_names.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD,\n", + " field_names.POVERTY_LESS_THAN_200_FPL_FIELD,\n", + "]:\n", + " print(f\"\\n~~~~Analysis for field `{field}`~~~~\")\n", + " print(cejst_df[field].describe())\n", + " print(\n", + " f\"\\nThere are {cejst_df[field].isnull().sum() * 100 / len(cejst_df):.2f}% of values missing.\"\n", + " )\n", + " print(\n", + " f\"\\nQuantile at {quantile} is {np.nanquantile(a=cejst_df[field], q=quantile)}\"\n", + " )\n", + " print(cejst_df[field].hist())" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "8c3e462c", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTTotal PopulationCalifornia CountyZIPNearby City \\n(to help approximate location only)LongitudeLatitudecalenviroscreen_scorecalenviroscreen_percentileDRAFT CES 4.0\\nPercentile Range...PovertyPoverty PctlUnemploymentUnemployment PctlHousing BurdenHousing Burden PctlPop. Char.Pop. Char. ScorePop. Char. Pctlcalenviroscreen_priority_community
0060190011002760Fresno93706Fresno-119.7836.7194.61100.0095-100% (highest scores)...76.6098.4316.2097.1530.7090.6193.739.7299.87True
1060770007004177San Joaquin95206Stockton-121.2937.9490.8399.9995-100% (highest scores)...70.6096.4318.5098.4535.2095.6193.409.6899.84True
2060770001004055San Joaquin95202Stockton-121.2937.9585.7599.9795-100% (highest scores)...81.8099.5017.9098.1736.4096.5195.719.9299.97True
3060710016005527San Bernardino91761Ontario-117.6234.0683.5699.9695-100% (highest scores)...67.1094.826.7057.2032.1092.6580.598.3693.06True
4060372049202639Los Angeles90023Los Angeles-118.2034.0282.9099.9595-100% (highest scores)...64.9093.515.6043.8125.0077.9583.958.7095.78True
\n", + "

5 rows × 59 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Total Population California County ZIP \\\n", + "0 06019001100 2760 Fresno 93706 \n", + "1 06077000700 4177 San Joaquin 95206 \n", + "2 06077000100 4055 San Joaquin 95202 \n", + "3 06071001600 5527 San Bernardino 91761 \n", + "4 06037204920 2639 Los Angeles 90023 \n", + "\n", + " Nearby City \\n(to help approximate location only) Longitude Latitude \\\n", + "0 Fresno -119.78 36.71 \n", + "1 Stockton -121.29 37.94 \n", + "2 Stockton -121.29 37.95 \n", + "3 Ontario -117.62 34.06 \n", + "4 Los Angeles -118.20 34.02 \n", + "\n", + " calenviroscreen_score calenviroscreen_percentile \\\n", + "0 94.61 100.00 \n", + "1 90.83 99.99 \n", + "2 85.75 99.97 \n", + "3 83.56 99.96 \n", + "4 82.90 99.95 \n", + "\n", + " DRAFT CES 4.0\\nPercentile Range ... Poverty Poverty Pctl Unemployment \\\n", + "0 95-100% (highest scores) ... 76.60 98.43 16.20 \n", + "1 95-100% (highest scores) ... 70.60 96.43 18.50 \n", + "2 95-100% (highest scores) ... 81.80 99.50 17.90 \n", + "3 95-100% (highest scores) ... 67.10 94.82 6.70 \n", + "4 95-100% (highest scores) ... 64.90 93.51 5.60 \n", + "\n", + " Unemployment Pctl Housing Burden Housing Burden Pctl Pop. Char. \\\n", + "0 97.15 30.70 90.61 93.73 \n", + "1 98.45 35.20 95.61 93.40 \n", + "2 98.17 36.40 96.51 95.71 \n", + "3 57.20 32.10 92.65 80.59 \n", + "4 43.81 25.00 77.95 83.95 \n", + "\n", + " Pop. Char. Score Pop. Char. Pctl calenviroscreen_priority_community \n", + "0 9.72 99.87 True \n", + "1 9.68 99.84 True \n", + "2 9.92 99.97 True \n", + "3 8.36 93.06 True \n", + "4 8.70 95.78 True \n", + "\n", + "[5 rows x 59 columns]" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load CalEnviroScreen 4.0\n", + "CALENVIROSCREEN_SCORE_FIELD = \"calenviroscreen_score\"\n", + "CALENVIROSCREEN_PERCENTILE_FIELD = \"calenviroscreen_percentile\"\n", + "CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD = \"calenviroscreen_priority_community\"\n", + "\n", + "calenviroscreen_data_path = DATA_DIR / \"dataset\" / \"calenviroscreen4\" / \"data06.csv\"\n", + "calenviroscreen_df = pd.read_csv(\n", + " calenviroscreen_data_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "# Convert priority community field to a bool.\n", + "calenviroscreen_df[CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD] = calenviroscreen_df[\n", + " CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD\n", + "].astype(bool)\n", + "\n", + "calenviroscreen_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "b1ac2854-80c8-42a8-85e8-84c5684bbe43", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTMapping for Environmental Justice Final PercentileMapping for Environmental Justice Final ScoreMapping for Environmental Justice Priority Community
05109795040048.1222.70False
15155002000146.2022.17False
25104110020672.5132.90False
35105948100074.8734.25False
45105945140096.4157.83True
\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Mapping for Environmental Justice Final Percentile \\\n", + "0 51097950400 48.12 \n", + "1 51550020001 46.20 \n", + "2 51041100206 72.51 \n", + "3 51059481000 74.87 \n", + "4 51059451400 96.41 \n", + "\n", + " Mapping for Environmental Justice Final Score \\\n", + "0 22.70 \n", + "1 22.17 \n", + "2 32.90 \n", + "3 34.25 \n", + "4 57.83 \n", + "\n", + " Mapping for Environmental Justice Priority Community \n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 False \n", + "4 True " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Mapping for EJ\n", + "mapping_for_ej_path = DATA_DIR / \"dataset\" / \"mapping_for_ej\" / \"co_va.csv\"\n", + "\n", + "mapping_for_ej_df = pd.read_csv(\n", + " mapping_for_ej_path,\n", + " dtype={\n", + " ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\",\n", + " field_names.MAPPING_FOR_EJ_PRIORITY_COMMUNITY_FIELD: \"bool\",\n", + " },\n", + ")\n", + "\n", + "mapping_for_ej_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "d8ec43dc", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTIndividuals in Poverty (percent) (1990)Individuals in Poverty (percent) (2000)Individuals in Poverty (percent) (2010)Persistent Poverty, Tract Level
0010010201000.100.130.09False
1010010202000.200.230.11False
2010010203000.110.080.12False
3010010204000.070.050.03False
4010010205000.060.040.08False
..................
7307155079990000NaNNaNNaNFalse
7307255083990000NaNNaNNaNFalse
7307355089990000NaNNaNNaNFalse
7307455101990000NaNNaNNaNFalse
7307555117990000NaNNaNNaNFalse
\n", + "

73076 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Individuals in Poverty (percent) (1990) \\\n", + "0 01001020100 0.10 \n", + "1 01001020200 0.20 \n", + "2 01001020300 0.11 \n", + "3 01001020400 0.07 \n", + "4 01001020500 0.06 \n", + "... ... ... \n", + "73071 55079990000 NaN \n", + "73072 55083990000 NaN \n", + "73073 55089990000 NaN \n", + "73074 55101990000 NaN \n", + "73075 55117990000 NaN \n", + "\n", + " Individuals in Poverty (percent) (2000) \\\n", + "0 0.13 \n", + "1 0.23 \n", + "2 0.08 \n", + "3 0.05 \n", + "4 0.04 \n", + "... ... \n", + "73071 NaN \n", + "73072 NaN \n", + "73073 NaN \n", + "73074 NaN \n", + "73075 NaN \n", + "\n", + " Individuals in Poverty (percent) (2010) \\\n", + "0 0.09 \n", + "1 0.11 \n", + "2 0.12 \n", + "3 0.03 \n", + "4 0.08 \n", + "... ... \n", + "73071 NaN \n", + "73072 NaN \n", + "73073 NaN \n", + "73074 NaN \n", + "73075 NaN \n", + "\n", + " Persistent Poverty, Tract Level \n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 False \n", + "4 False \n", + "... ... \n", + "73071 False \n", + "73072 False \n", + "73073 False \n", + "73074 False \n", + "73075 False \n", + "\n", + "[73076 rows x 5 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load persistent poverty data\n", + "persistent_poverty_path = DATA_DIR / \"dataset\" / \"persistent_poverty\" / \"usa.csv\"\n", + "persistent_poverty_df = pd.read_csv(\n", + " persistent_poverty_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "# Since \"Persistent Poverty Census Tract\" is labeled in both the score file (at the CBG level) and this tract file,\n", + "# rename this field so it's easy to access the tract-level scores directly.\n", + "\n", + "PERSISTENT_POVERTY_TRACT_LEVEL_FIELD = \"Persistent Poverty, Tract Level\"\n", + "PERSISTENT_POVERTY_CBG_LEVEL_FIELD = \"Persistent Poverty Census Tract\"\n", + "\n", + "persistent_poverty_df.rename(\n", + " columns={PERSISTENT_POVERTY_CBG_LEVEL_FIELD: PERSISTENT_POVERTY_TRACT_LEVEL_FIELD},\n", + " inplace=True,\n", + " errors=\"raise\",\n", + ")\n", + "\n", + "persistent_poverty_df" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "81826d29", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTPercent of tract that is HOLC Grade DTract is >20% HOLC Grade DTract is >50% HOLC Grade DTract is >75% HOLC Grade D
0010730001000.42TrueFalseFalse
1010730003000.93TrueTrueTrue
2010730004000.36TrueFalseFalse
3010730005000.65TrueTrueFalse
4010730007000.41TrueFalseFalse
..................
7273551390011000.29TrueFalseFalse
7274551390012000.42TrueFalseFalse
7275551390013000.16FalseFalseFalse
7276551390014000.04FalseFalseFalse
7277551390015000.10FalseFalseFalse
\n", + "

7278 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Percent of tract that is HOLC Grade D \\\n", + "0 01073000100 0.42 \n", + "1 01073000300 0.93 \n", + "2 01073000400 0.36 \n", + "3 01073000500 0.65 \n", + "4 01073000700 0.41 \n", + "... ... ... \n", + "7273 55139001100 0.29 \n", + "7274 55139001200 0.42 \n", + "7275 55139001300 0.16 \n", + "7276 55139001400 0.04 \n", + "7277 55139001500 0.10 \n", + "\n", + " Tract is >20% HOLC Grade D Tract is >50% HOLC Grade D \\\n", + "0 True False \n", + "1 True True \n", + "2 True False \n", + "3 True True \n", + "4 True False \n", + "... ... ... \n", + "7273 True False \n", + "7274 True False \n", + "7275 False False \n", + "7276 False False \n", + "7277 False False \n", + "\n", + " Tract is >75% HOLC Grade D \n", + "0 False \n", + "1 True \n", + "2 False \n", + "3 False \n", + "4 False \n", + "... ... \n", + "7273 False \n", + "7274 False \n", + "7275 False \n", + "7276 False \n", + "7277 False \n", + "\n", + "[7278 rows x 5 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load mapping inequality data\n", + "HOLC_FACTORS = [\n", + " field_names.HOLC_GRADE_D_TRACT_20_PERCENT_FIELD,\n", + " field_names.HOLC_GRADE_D_TRACT_50_PERCENT_FIELD,\n", + " field_names.HOLC_GRADE_D_TRACT_75_PERCENT_FIELD,\n", + "]\n", + "mapping_inequality_path = DATA_DIR / \"dataset\" / \"mapping_inequality\" / \"usa.csv\"\n", + "mapping_inequality_df = pd.read_csv(\n", + " mapping_inequality_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "mapping_inequality_df" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "fceb3136", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTSVI - Socioeconomic Index (percentile)SVI - Household Composition Index (percentile)SVI- Minority Status/Language Index (percentile)SVI- Housing Type/Transportation Index (percentile)Overall rank for Social Vulnerability Indices (percentile)At or above 90 for overall percentile ranking according to Social Vulnerability Indices
001015981901NaNNaNNaNNaNNaNFalse
101015981902NaNNaNNaNNaNNaNFalse
201015981903NaNNaNNaNNaNNaNFalse
301097003605NaN0.000.27NaNNaNFalse
401097990000NaNNaNNaNNaNNaNFalse
\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT SVI - Socioeconomic Index (percentile) \\\n", + "0 01015981901 NaN \n", + "1 01015981902 NaN \n", + "2 01015981903 NaN \n", + "3 01097003605 NaN \n", + "4 01097990000 NaN \n", + "\n", + " SVI - Household Composition Index (percentile) \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 0.00 \n", + "4 NaN \n", + "\n", + " SVI- Minority Status/Language Index (percentile) \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 0.27 \n", + "4 NaN \n", + "\n", + " SVI- Housing Type/Transportation Index (percentile) \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + " Overall rank for Social Vulnerability Indices (percentile) \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + " At or above 90 for overall percentile ranking according to Social Vulnerability Indices \n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 False \n", + "4 False " + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cdc_svi_index_path = DATA_DIR / \"dataset\" / \"cdc_svi_index\" / \"usa.csv\"\n", + "cdc_svi_index_df = pd.read_csv(\n", + " cdc_svi_index_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "cdc_svi_index_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "0c290efa", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTMaryland Environmental Justice ScoreMaryland EJSCREEN Priority Community
1379240276011070.66True
1380240276022010.30False
1381240276055040.28False
1382240276069040.43False
1383240276069060.54False
\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Maryland Environmental Justice Score \\\n", + "1379 24027601107 0.66 \n", + "1380 24027602201 0.30 \n", + "1381 24027605504 0.28 \n", + "1382 24027606904 0.43 \n", + "1383 24027606906 0.54 \n", + "\n", + " Maryland EJSCREEN Priority Community \n", + "1379 True \n", + "1380 False \n", + "1381 False \n", + "1382 False \n", + "1383 False " + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load Maryland EJScreen\n", + "maryland_ejscreen_data_path = (\n", + " DATA_DIR / \"dataset\" / \"maryland_ejscreen\" / \"maryland.csv\"\n", + ")\n", + "maryland_ejscreen_df = pd.read_csv(\n", + " maryland_ejscreen_data_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "maryland_ejscreen_df.tail()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "605af1ff", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTEnergy-related alternative definition of communitiesCoal employmentOutage EventsHomelessnessDisabled populationOutage DurationJob AccessFossil energy employmentFood DesertIncomplete PlumbingNon-grid-connected heating fuelParksGreater than 30 min commuteInternet AccessMobile HomeSingle ParentTransportation Costs
035029000500True0.000.000.010.220.00-1.400.021.000.000.360.000.2530.700.530.7545.00
148311950100False0.000.000.010.170.00-1.300.011.000.020.04-1.000.3121.900.330.1834.00
248131950500True0.000.000.010.290.00-1.500.011.000.020.150.000.5433.900.150.4540.00
348247950200False0.001.000.010.221140.00-3.000.010.000.000.010.000.3329.400.110.5337.00
448247950400True0.001.000.010.221140.00-2.700.011.000.010.030.000.3653.100.110.7841.00
.........................................................
7305155111000500FalseNaNNaNNaN0.12NaNNaNNaNNaN0.000.30NaNNaNNaN0.100.32NaN
7305255111000700FalseNaNNaNNaN0.11NaNNaNNaNNaN0.010.07NaNNaNNaN0.000.25NaN
7305355111000800FalseNaNNaNNaN0.14NaNNaNNaNNaN0.010.46NaNNaNNaN0.050.22NaN
7305455111000900FalseNaNNaNNaN0.11NaNNaNNaNNaN0.030.78NaNNaNNaN0.020.25NaN
7305555117990000FalseNaNNaNNaN0.00NaNNaNNaNNaN0.000.00NaNNaNNaN0.000.00NaN
\n", + "

73056 rows × 18 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Energy-related alternative definition of communities \\\n", + "0 35029000500 True \n", + "1 48311950100 False \n", + "2 48131950500 True \n", + "3 48247950200 False \n", + "4 48247950400 True \n", + "... ... ... \n", + "73051 55111000500 False \n", + "73052 55111000700 False \n", + "73053 55111000800 False \n", + "73054 55111000900 False \n", + "73055 55117990000 False \n", + "\n", + " Coal employment Outage Events Homelessness Disabled population \\\n", + "0 0.00 0.00 0.01 0.22 \n", + "1 0.00 0.00 0.01 0.17 \n", + "2 0.00 0.00 0.01 0.29 \n", + "3 0.00 1.00 0.01 0.22 \n", + "4 0.00 1.00 0.01 0.22 \n", + "... ... ... ... ... \n", + "73051 NaN NaN NaN 0.12 \n", + "73052 NaN NaN NaN 0.11 \n", + "73053 NaN NaN NaN 0.14 \n", + "73054 NaN NaN NaN 0.11 \n", + "73055 NaN NaN NaN 0.00 \n", + "\n", + " Outage Duration Job Access Fossil energy employment Food Desert \\\n", + "0 0.00 -1.40 0.02 1.00 \n", + "1 0.00 -1.30 0.01 1.00 \n", + "2 0.00 -1.50 0.01 1.00 \n", + "3 1140.00 -3.00 0.01 0.00 \n", + "4 1140.00 -2.70 0.01 1.00 \n", + "... ... ... ... ... \n", + "73051 NaN NaN NaN NaN \n", + "73052 NaN NaN NaN NaN \n", + "73053 NaN NaN NaN NaN \n", + "73054 NaN NaN NaN NaN \n", + "73055 NaN NaN NaN NaN \n", + "\n", + " Incomplete Plumbing Non-grid-connected heating fuel Parks \\\n", + "0 0.00 0.36 0.00 \n", + "1 0.02 0.04 -1.00 \n", + "2 0.02 0.15 0.00 \n", + "3 0.00 0.01 0.00 \n", + "4 0.01 0.03 0.00 \n", + "... ... ... ... \n", + "73051 0.00 0.30 NaN \n", + "73052 0.01 0.07 NaN \n", + "73053 0.01 0.46 NaN \n", + "73054 0.03 0.78 NaN \n", + "73055 0.00 0.00 NaN \n", + "\n", + " Greater than 30 min commute Internet Access Mobile Home \\\n", + "0 0.25 30.70 0.53 \n", + "1 0.31 21.90 0.33 \n", + "2 0.54 33.90 0.15 \n", + "3 0.33 29.40 0.11 \n", + "4 0.36 53.10 0.11 \n", + "... ... ... ... \n", + "73051 NaN NaN 0.10 \n", + "73052 NaN NaN 0.00 \n", + "73053 NaN NaN 0.05 \n", + "73054 NaN NaN 0.02 \n", + "73055 NaN NaN 0.00 \n", + "\n", + " Single Parent Transportation Costs \n", + "0 0.75 45.00 \n", + "1 0.18 34.00 \n", + "2 0.45 40.00 \n", + "3 0.53 37.00 \n", + "4 0.78 41.00 \n", + "... ... ... \n", + "73051 0.32 NaN \n", + "73052 0.25 NaN \n", + "73053 0.22 NaN \n", + "73054 0.25 NaN \n", + "73055 0.00 NaN \n", + "\n", + "[73056 rows x 18 columns]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load alternative energy-related definition\n", + "energy_definition_alternative_draft_path = (\n", + " DATA_DIR / \"dataset\" / \"energy_definition_alternative_draft\" / \"usa.csv\"\n", + ")\n", + "energy_definition_alternative_draft_df = pd.read_csv(\n", + " energy_definition_alternative_draft_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "energy_definition_alternative_draft_df" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "fe4a2939", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTMichigan EJSCREEN Score FieldMichigan EJSCREEN Percentile FieldMichigan EJSCREEN Priority Community
02608100390093.991.00True
12607700020291.951.00True
22607700030090.171.00True
32608100380089.501.00True
42608100400087.741.00True
\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Michigan EJSCREEN Score Field \\\n", + "0 26081003900 93.99 \n", + "1 26077000202 91.95 \n", + "2 26077000300 90.17 \n", + "3 26081003800 89.50 \n", + "4 26081004000 87.74 \n", + "\n", + " Michigan EJSCREEN Percentile Field Michigan EJSCREEN Priority Community \n", + "0 1.00 True \n", + "1 1.00 True \n", + "2 1.00 True \n", + "3 1.00 True \n", + "4 1.00 True " + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load Michigan EJSCREEN\n", + "michigan_ejscreen_data_path = (\n", + " DATA_DIR / \"dataset\" / \"michigan_ejscreen\" / \"michigan_ejscreen.csv\"\n", + ")\n", + "michigan_ejscreen_df = pd.read_csv(\n", + " michigan_ejscreen_data_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "michigan_ejscreen_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "b39342aa", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTNumber of facilities affecting the tractNumber of releases affecting the tractNumber of chemicals affecting the tractAverage toxicity-weighted concentration of the cells in the tractRSEI Risk ScoreRSEI Risk Score (Cancer toxicity weights)RSEI Risk Score (Noncancer toxicity weights)Sum of the population of the cells in the tractAt or above 75 for overall percentile for the RSEI scoreRSEI Risk Score (percentile)
03604702320019390496485.18759.71610.32154.856199.22False0.53
1360290072028437681227.3779.5063.0514.811601.87False0.21
24200342920114416242512705.162553.952447.72113.754527.60False0.74
31720100410080365573626.623984.973969.1327.065766.72True0.82
44706501120379358791133.401885.511410.31447.777820.66False0.69
\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Number of facilities affecting the tract \\\n", + "0 36047023200 193 \n", + "1 36029007202 84 \n", + "2 42003429201 144 \n", + "3 17201004100 80 \n", + "4 47065011203 79 \n", + "\n", + " Number of releases affecting the tract \\\n", + "0 904 \n", + "1 376 \n", + "2 1624 \n", + "3 365 \n", + "4 358 \n", + "\n", + " Number of chemicals affecting the tract \\\n", + "0 96 \n", + "1 81 \n", + "2 251 \n", + "3 57 \n", + "4 79 \n", + "\n", + " Average toxicity-weighted concentration of the cells in the tract \\\n", + "0 485.18 \n", + "1 227.37 \n", + "2 2705.16 \n", + "3 3626.62 \n", + "4 1133.40 \n", + "\n", + " RSEI Risk Score RSEI Risk Score (Cancer toxicity weights) \\\n", + "0 759.71 610.32 \n", + "1 79.50 63.05 \n", + "2 2553.95 2447.72 \n", + "3 3984.97 3969.13 \n", + "4 1885.51 1410.31 \n", + "\n", + " RSEI Risk Score (Noncancer toxicity weights) \\\n", + "0 154.85 \n", + "1 14.81 \n", + "2 113.75 \n", + "3 27.06 \n", + "4 447.77 \n", + "\n", + " Sum of the population of the cells in the tract \\\n", + "0 6199.22 \n", + "1 1601.87 \n", + "2 4527.60 \n", + "3 5766.72 \n", + "4 7820.66 \n", + "\n", + " At or above 75 for overall percentile for the RSEI score \\\n", + "0 False \n", + "1 False \n", + "2 False \n", + "3 True \n", + "4 False \n", + "\n", + " RSEI Risk Score (percentile) \n", + "0 0.53 \n", + "1 0.21 \n", + "2 0.74 \n", + "3 0.82 \n", + "4 0.69 " + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load EPA RSEI EJSCREEN\n", + "epa_rsei_data_path = DATA_DIR / \"dataset\" / \"epa_rsei\" / \"usa.csv\"\n", + "epa_rsei_df = pd.read_csv(\n", + " epa_rsei_data_path,\n", + " dtype={ExtractTransformLoad.GEOID_TRACT_FIELD_NAME: \"string\"},\n", + ")\n", + "\n", + "epa_rsei_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "65659c26", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GEOID10_TRACTPersistent Poverty Census TractHousing burden (percent)Total populationMedian household income (% of state median household income)Current asthma among adults aged greater than or equal to 18 yearsCoronary heart disease among adults aged greater than or equal to 18 yearsCancer (excluding skin cancer) among adults aged greater than or equal to 18 yearsCurrent lack of health insurance among adults aged 18-64 yearsDiagnosed diabetes among adults aged greater than or equal to 18 years...Michigan EJSCREEN Priority CommunitySVI - Socioeconomic Index (percentile)SVI - Household Composition Index (percentile)SVI- Minority Status/Language Index (percentile)SVI- Housing Type/Transportation Index (percentile)Overall rank for Social Vulnerability Indices (percentile)At or above 90 for overall percentile ranking according to Social Vulnerability IndicesMapping for Environmental Justice Final PercentileMapping for Environmental Justice Final ScoreMapping for Environmental Justice Priority Community
001073001100True0.284897.000.7311.207.206.7016.6019.30...NaN0.620.980.500.400.69FalseNaNNaNNaN
101073001400True0.181906.000.7111.109.107.3021.4022.40...NaN0.800.570.850.230.68FalseNaNNaNNaN
201073002000False0.444215.000.5413.509.506.1025.4022.80...NaN0.950.820.730.960.97TrueNaNNaNNaN
301073003802False0.415149.000.7712.006.605.6020.9018.60...NaN0.850.810.500.490.76FalseNaNNaNNaN
401073004000True0.472621.000.3713.1010.006.3024.5025.00...NaN0.960.710.860.850.95TrueNaNNaNNaN
\n", + "

5 rows × 661 columns

\n", + "
" + ], + "text/plain": [ + " GEOID10_TRACT Persistent Poverty Census Tract Housing burden (percent) \\\n", + "0 01073001100 True 0.28 \n", + "1 01073001400 True 0.18 \n", + "2 01073002000 False 0.44 \n", + "3 01073003802 False 0.41 \n", + "4 01073004000 True 0.47 \n", + "\n", + " Total population \\\n", + "0 4897.00 \n", + "1 1906.00 \n", + "2 4215.00 \n", + "3 5149.00 \n", + "4 2621.00 \n", + "\n", + " Median household income (% of state median household income) \\\n", + "0 0.73 \n", + "1 0.71 \n", + "2 0.54 \n", + "3 0.77 \n", + "4 0.37 \n", + "\n", + " Current asthma among adults aged greater than or equal to 18 years \\\n", + "0 11.20 \n", + "1 11.10 \n", + "2 13.50 \n", + "3 12.00 \n", + "4 13.10 \n", + "\n", + " Coronary heart disease among adults aged greater than or equal to 18 years \\\n", + "0 7.20 \n", + "1 9.10 \n", + "2 9.50 \n", + "3 6.60 \n", + "4 10.00 \n", + "\n", + " Cancer (excluding skin cancer) among adults aged greater than or equal to 18 years \\\n", + "0 6.70 \n", + "1 7.30 \n", + "2 6.10 \n", + "3 5.60 \n", + "4 6.30 \n", + "\n", + " Current lack of health insurance among adults aged 18-64 years \\\n", + "0 16.60 \n", + "1 21.40 \n", + "2 25.40 \n", + "3 20.90 \n", + "4 24.50 \n", + "\n", + " Diagnosed diabetes among adults aged greater than or equal to 18 years \\\n", + "0 19.30 \n", + "1 22.40 \n", + "2 22.80 \n", + "3 18.60 \n", + "4 25.00 \n", + "\n", + " ... Michigan EJSCREEN Priority Community \\\n", + "0 ... NaN \n", + "1 ... NaN \n", + "2 ... NaN \n", + "3 ... NaN \n", + "4 ... NaN \n", + "\n", + " SVI - Socioeconomic Index (percentile) \\\n", + "0 0.62 \n", + "1 0.80 \n", + "2 0.95 \n", + "3 0.85 \n", + "4 0.96 \n", + "\n", + " SVI - Household Composition Index (percentile) \\\n", + "0 0.98 \n", + "1 0.57 \n", + "2 0.82 \n", + "3 0.81 \n", + "4 0.71 \n", + "\n", + " SVI- Minority Status/Language Index (percentile) \\\n", + "0 0.50 \n", + "1 0.85 \n", + "2 0.73 \n", + "3 0.50 \n", + "4 0.86 \n", + "\n", + " SVI- Housing Type/Transportation Index (percentile) \\\n", + "0 0.40 \n", + "1 0.23 \n", + "2 0.96 \n", + "3 0.49 \n", + "4 0.85 \n", + "\n", + " Overall rank for Social Vulnerability Indices (percentile) \\\n", + "0 0.69 \n", + "1 0.68 \n", + "2 0.97 \n", + "3 0.76 \n", + "4 0.95 \n", + "\n", + " At or above 90 for overall percentile ranking according to Social Vulnerability Indices \\\n", + "0 False \n", + "1 False \n", + "2 True \n", + "3 False \n", + "4 True \n", + "\n", + " Mapping for Environmental Justice Final Percentile \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + " Mapping for Environmental Justice Final Score \\\n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + " Mapping for Environmental Justice Priority Community \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + "[5 rows x 661 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Join all dataframes that use tracts\n", + "census_tract_dfs = [\n", + " cejst_df,\n", + " calenviroscreen_df,\n", + " persistent_poverty_df,\n", + " mapping_inequality_df,\n", + " epa_rsei_df,\n", + " maryland_ejscreen_df,\n", + " energy_definition_alternative_draft_df,\n", + " michigan_ejscreen_df,\n", + " cdc_svi_index_df,\n", + " mapping_for_ej_df,\n", + "]\n", + "\n", + "merged_df = functools.reduce(\n", + " lambda left, right: pd.merge(\n", + " left=left,\n", + " right=right,\n", + " on=ExtractTransformLoad.GEOID_TRACT_FIELD_NAME,\n", + " how=\"outer\",\n", + " ),\n", + " census_tract_dfs,\n", + ")\n", + "\n", + "tract_values = merged_df[ExtractTransformLoad.GEOID_TRACT_FIELD_NAME].str.len().unique()\n", + "if any(tract_values != [11]):\n", + " print(tract_values)\n", + " raise ValueError(\"Some of the census tract data has the wrong length.\")\n", + "\n", + "if len(merged_df) > ExtractTransformLoad.EXPECTED_MAX_CENSUS_TRACTS:\n", + " raise ValueError(f\"Too many rows in the join: {len(merged_df)}.\")\n", + "\n", + "merged_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "2de78f71", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Tract is >20% HOLC Grade DTract is >50% HOLC Grade DTract is >75% HOLC Grade D
0TrueFalseFalse
1TrueTrueTrue
2FalseFalseFalse
3TrueFalseFalse
4TrueFalseFalse
\n", + "
" + ], + "text/plain": [ + " Tract is >20% HOLC Grade D Tract is >50% HOLC Grade D \\\n", + "0 True False \n", + "1 True True \n", + "2 False False \n", + "3 True False \n", + "4 True False \n", + "\n", + " Tract is >75% HOLC Grade D \n", + "0 False \n", + "1 True \n", + "2 False \n", + "3 False \n", + "4 False " + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Special handling for HOLC.\n", + "# Fill in the null HOLC values as `False`. Otherwise the comparison tool will not run comparisons in states\n", + "# without HOLC scores, and for HOLC, we'd like to see it across the whole US.\n", + "for holc_factor in HOLC_FACTORS:\n", + " merged_df[holc_factor] = merged_df[holc_factor].fillna(False)\n", + "\n", + "merged_df[HOLC_FACTORS].head()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "980c0f66", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "# Define a namedtuple for indices.\n", + "Index = collections.namedtuple(\n", + " typename=\"Index\",\n", + " field_names=[\n", + " \"method_name\",\n", + " \"priority_communities_field\",\n", + " ],\n", + ")\n", + "\n", + "# Define the indices used for CEJST scoring (`census_block_group_indices`) as well as comparison\n", + "# (`census_tract_indices`).\n", + "definition_l_factors = [\n", + " field_names.L_CLIMATE,\n", + " field_names.L_ENERGY,\n", + " field_names.L_TRANSPORTATION,\n", + " field_names.L_HOUSING,\n", + " field_names.L_POLLUTION,\n", + " field_names.L_WATER,\n", + " field_names.L_HEALTH,\n", + " field_names.L_WORKFORCE,\n", + " # Also include a combined factor for all the non-workforce elements.\n", + " field_names.L_NON_WORKFORCE,\n", + "]\n", + "\n", + "definition_m_factors = [\n", + " field_names.M_CLIMATE,\n", + " field_names.M_ENERGY,\n", + " field_names.M_TRANSPORTATION,\n", + " field_names.M_HOUSING,\n", + " field_names.M_POLLUTION,\n", + " field_names.M_WATER,\n", + " field_names.M_HEALTH,\n", + " field_names.M_WORKFORCE,\n", + " # Also include a combined factor for all the non-workforce elements.\n", + " field_names.M_NON_WORKFORCE,\n", + "]\n", + "\n", + "census_tract_indices = (\n", + " [\n", + " Index(\n", + " method_name=\"Definition M\",\n", + " priority_communities_field=field_names.SCORE_M_COMMUNITIES,\n", + " ),\n", + " ]\n", + " + [\n", + " Index(\n", + " method_name=\"Definition L\",\n", + " priority_communities_field=field_names.SCORE_L_COMMUNITIES,\n", + " ),\n", + " ]\n", + " # Insert indices for each of the factors from Definition M.\n", + " # Note: since these involve no renaming, we write them using list comprehension.\n", + " + [\n", + " Index(\n", + " method_name=factor,\n", + " priority_communities_field=factor,\n", + " )\n", + " for factor in definition_m_factors\n", + " ]\n", + " # Insert indices for each of the factors from Definition L.\n", + " # Note: since these involve no renaming, we write them using list comprehension.\n", + " + [\n", + " Index(\n", + " method_name=factor,\n", + " priority_communities_field=factor,\n", + " )\n", + " for factor in definition_l_factors\n", + " ]\n", + " + [\n", + " Index(\n", + " # Note: we're renaming Score G as NMTC Modified for clarity, since that's what Score G is under the hood.\n", + " method_name=\"NMTC Modified\",\n", + " priority_communities_field=field_names.SCORE_G_COMMUNITIES,\n", + " ),\n", + " Index(\n", + " method_name=\"NMTC\",\n", + " priority_communities_field=\"NMTC (communities)\",\n", + " ),\n", + " Index(\n", + " method_name=\"Score C\",\n", + " priority_communities_field=\"Score C (top 25th percentile)\",\n", + " ),\n", + " Index(\n", + " method_name=\"Score D (30th percentile)\",\n", + " priority_communities_field=\"Score D (top 30th percentile)\",\n", + " ),\n", + " Index(\n", + " method_name=\"Score D (25th percentile)\",\n", + " priority_communities_field=\"Score D (top 25th percentile)\",\n", + " ),\n", + " Index(\n", + " method_name=\"Score F\",\n", + " priority_communities_field=field_names.SCORE_F_COMMUNITIES,\n", + " ),\n", + " Index(\n", + " method_name=\"CalEnviroScreen 4.0\",\n", + " priority_communities_field=\"calenviroscreen_priority_community\",\n", + " ),\n", + " Index(\n", + " method_name=\"Mapping for EJ\",\n", + " priority_communities_field=field_names.MAPPING_FOR_EJ_PRIORITY_COMMUNITY_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=\"EPA RSEI Aggregate Microdata\",\n", + " priority_communities_field=field_names.EPA_RSEI_SCORE_THRESHOLD_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=\"Persistent Poverty\",\n", + " priority_communities_field=PERSISTENT_POVERTY_TRACT_LEVEL_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=\"Maryland EJSCREEN\",\n", + " priority_communities_field=field_names.MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=field_names.ENERGY_RELATED_COMMUNITIES_DEFINITION_ALTERNATIVE,\n", + " priority_communities_field=field_names.ENERGY_RELATED_COMMUNITIES_DEFINITION_ALTERNATIVE,\n", + " ),\n", + " Index(\n", + " method_name=\"CDC SVI Index\",\n", + " priority_communities_field=field_names.CDC_SVI_INDEX_THEMES_PRIORITY_COMMUNITY,\n", + " ),\n", + " Index(\n", + " method_name=\"Michigan EJSCREEN\",\n", + " priority_communities_field=field_names.MICHIGAN_EJSCREEN_PRIORITY_COMMUNITY_FIELD,\n", + " ),\n", + " ]\n", + " # Insert indices for each of the HOLC factors.\n", + " # Note: since these involve no renaming, we write them using list comprehension.\n", + " + [\n", + " Index(\n", + " method_name=factor,\n", + " priority_communities_field=factor,\n", + " )\n", + " for factor in HOLC_FACTORS\n", + " ]\n", + ")\n", + "\n", + "\n", + "ejscreen_areas_of_concern_census_block_group_indices = [\n", + " Index(\n", + " method_name=\"EJSCREEN Areas of Concern, National, 80th percentile\",\n", + " priority_communities_field=field_names.EJSCREEN_AREAS_OF_CONCERN_NATIONAL_80TH_PERCENTILE_COMMUNITIES_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=\"EJSCREEN Areas of Concern, National, 90th percentile\",\n", + " priority_communities_field=field_names.EJSCREEN_AREAS_OF_CONCERN_NATIONAL_90TH_PERCENTILE_COMMUNITIES_FIELD,\n", + " ),\n", + " Index(\n", + " method_name=\"EJSCREEN Areas of Concern, National, 95th percentile\",\n", + " priority_communities_field=field_names.EJSCREEN_AREAS_OF_CONCERN_NATIONAL_95TH_PERCENTILE_COMMUNITIES_FIELD,\n", + " ),\n", + "]\n", + "\n", + "# Before including EJSCREEN AoC indicators are included, check whether or not the EJSCREEN AoC data is available locally.\n", + "if EJSCREENAreasOfConcernETL.ejscreen_areas_of_concern_data_exists():\n", + " # Add EJSCREEN AoCs to all of the CBG indices.\n", + " # TODO: When we get AoC data at the tract level, fix this.\n", + " # Right now commenting this out to avoid merging CBG-level areas of concern on a tract-level CEJST definition.\n", + " # census_block_group_indices.extend(\n", + " # ejscreen_areas_of_concern_census_block_group_indices\n", + " # )\n", + " pass\n", + "else:\n", + " pass\n", + "\n", + "# These fields will be used for statistical comparisons.\n", + "comparison_fields = [\n", + " field_names.POVERTY_LESS_THAN_100_FPL_FIELD,\n", + " field_names.POVERTY_LESS_THAN_200_FPL_FIELD,\n", + " field_names.COLLEGE_ATTENDANCE_FIELD,\n", + " field_names.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD,\n", + " field_names.LINGUISTIC_ISO_FIELD,\n", + " field_names.UNEMPLOYMENT_FIELD,\n", + " field_names.HIGH_SCHOOL_ED_FIELD,\n", + " field_names.MEDIAN_INCOME_FIELD,\n", + " field_names.URBAN_HEURISTIC_FIELD,\n", + " field_names.LIFE_EXPECTANCY_FIELD,\n", + " field_names.HEALTH_INSURANCE_FIELD,\n", + " field_names.PHYS_HEALTH_NOT_GOOD_FIELD,\n", + " field_names.DIABETES_FIELD,\n", + " field_names.LOW_READING_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,\n", + "]" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "4b510cb1", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Converting calenviroscreen_priority_community to boolean.\n", + "Converting Mapping for Environmental Justice Priority Community to boolean.\n", + "Converting At or above 75 for overall percentile for the RSEI score to boolean.\n", + "Converting Persistent Poverty, Tract Level to boolean.\n", + "Converting Maryland EJSCREEN Priority Community to boolean.\n", + "Converting Energy-related alternative definition of communities to boolean.\n", + "Converting At or above 90 for overall percentile ranking according to Social Vulnerability Indices to boolean.\n", + "Converting Michigan EJSCREEN Priority Community to boolean.\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "98501c61ec76447fa7b2e30d230c5886", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/1 [00:00 pd.DataFrame:\n", + " \"\"\"For each boolean field of priority communities, calculate distribution across states and territories.\"\"\"\n", + "\n", + " # Ensure each field is boolean.\n", + " for priority_communities_field in priority_communities_fields:\n", + " if df[priority_communities_field].dtype != bool:\n", + " print(f\"Converting {priority_communities_field} to boolean.\")\n", + "\n", + " # Calculate the population included as priority communities per tract. Will either be 0 or the population.\n", + " df[f\"{priority_communities_field}{POPULATION_SUFFIX}\"] = (\n", + " df[priority_communities_field]\n", + " * df[field_names.COMBINED_CENSUS_TOTAL_POPULATION_2010]\n", + " )\n", + "\n", + " def calculate_state_comparison(\n", + " frame: pd.DataFrame, geography_field: str\n", + " ) -> pd.DataFrame:\n", + " \"\"\"\n", + " This method will be applied to a `group_by` object. Inherits some parameters from outer scope.\n", + "\n", + " \"\"\"\n", + " summary_dict = {}\n", + " summary_dict[COUNTRY_FIELD_NAME] = frame[COUNTRY_FIELD_NAME].unique()[0]\n", + "\n", + " summary_dict[\"Analysis grouped by\"] = geography_field\n", + "\n", + " if geography_field == COUNTRY_FIELD_NAME:\n", + " summary_dict[GEOID_STATE_FIELD_NAME] = \"00\"\n", + " summary_dict[\"Geography name\"] = \"(Entire USA)\"\n", + "\n", + " if geography_field == GEOID_STATE_FIELD_NAME:\n", + " state_id = frame[GEOID_STATE_FIELD_NAME].unique()[0]\n", + " summary_dict[GEOID_STATE_FIELD_NAME] = state_id\n", + " summary_dict[\"Geography name\"] = us.states.lookup(state_id).name\n", + "\n", + " # Also add region information\n", + " region_id = frame[\"region\"].unique()[0]\n", + " summary_dict[\"region\"] = region_id\n", + "\n", + " if geography_field == \"region\":\n", + " region_id = frame[\"region\"].unique()[0]\n", + " summary_dict[\"region\"] = region_id\n", + " summary_dict[\"Geography name\"] = region_id\n", + "\n", + " if geography_field == \"division\":\n", + " division_id = frame[\"division\"].unique()[0]\n", + " summary_dict[\"division\"] = division_id\n", + " summary_dict[\"Geography name\"] = division_id\n", + "\n", + " total_tracts_in_geography = len(frame)\n", + " total_population_in_geography = frame[\n", + " field_names.COMBINED_CENSUS_TOTAL_POPULATION_2010\n", + " ].sum()\n", + "\n", + " if geography_field == field_names.URBAN_HEURISTIC_FIELD:\n", + " urban_flag = frame[field_names.URBAN_HEURISTIC_FIELD].unique()[0]\n", + " summary_dict[\"Urban vs Rural\"] = \"Urban\" if urban_flag else \"Rural\"\n", + " summary_dict[\"Geography name\"] = summary_dict[\"Urban vs Rural\"]\n", + "\n", + " for priority_communities_field in priority_communities_fields:\n", + " summary_dict[f\"{priority_communities_field}{POPULATION_SUFFIX}\"] = frame[\n", + " f\"{priority_communities_field}{POPULATION_SUFFIX}\"\n", + " ].sum()\n", + "\n", + " summary_dict[f\"{priority_communities_field} (total tracts)\"] = frame[\n", + " f\"{priority_communities_field}\"\n", + " ].sum()\n", + "\n", + " # Calculate some combinations of other variables.\n", + " summary_dict[f\"{priority_communities_field} (percent tracts)\"] = (\n", + " summary_dict[f\"{priority_communities_field} (total tracts)\"]\n", + " / total_tracts_in_geography\n", + " )\n", + "\n", + " summary_dict[f\"{priority_communities_field} (percent population)\"] = (\n", + " summary_dict[f\"{priority_communities_field}{POPULATION_SUFFIX}\"]\n", + " / total_population_in_geography\n", + " )\n", + "\n", + " unwanted_keys = [\n", + " f\"{priority_communities_field}{POPULATION_SUFFIX}\",\n", + " f\"{priority_communities_field} (total tracts)\",\n", + " ]\n", + "\n", + " # Remove unneeded columns:\n", + " for unwanted_key in unwanted_keys:\n", + " del summary_dict[unwanted_key]\n", + "\n", + " df = pd.DataFrame(summary_dict, index=[0])\n", + "\n", + " return df\n", + "\n", + " # Add a field for country so we can do aggregations across the entire country.\n", + " df[COUNTRY_FIELD_NAME] = \"USA\"\n", + "\n", + " # First, run the comparison by the whole country\n", + " usa_grouped_df = df.groupby(COUNTRY_FIELD_NAME)\n", + "\n", + " # Run the comparison function on the groups.\n", + " usa_distribution_df = usa_grouped_df.progress_apply(\n", + " lambda frame: calculate_state_comparison(\n", + " frame, geography_field=COUNTRY_FIELD_NAME\n", + " )\n", + " )\n", + "\n", + " # Next, run the comparison by state\n", + " state_grouped_df = df.groupby(GEOID_STATE_FIELD_NAME)\n", + "\n", + " # Run the comparison function on the groups.\n", + " state_distribution_df = state_grouped_df.progress_apply(\n", + " lambda frame: calculate_state_comparison(\n", + " frame, geography_field=GEOID_STATE_FIELD_NAME\n", + " )\n", + " )\n", + "\n", + " # Next, run the comparison by region\n", + " region_grouped_df = df.groupby(\"region\")\n", + "\n", + " # Run the comparison function on the groups.\n", + " region_distribution_df = region_grouped_df.progress_apply(\n", + " lambda frame: calculate_state_comparison(frame, geography_field=\"region\")\n", + " )\n", + "\n", + " # Next, run the comparison by division\n", + " division_grouped_df = df.groupby(\"division\")\n", + "\n", + " # Run the comparison function on the groups.\n", + " division_distribution_df = division_grouped_df.progress_apply(\n", + " lambda frame: calculate_state_comparison(frame, geography_field=\"division\")\n", + " )\n", + "\n", + " # Next, run the comparison by urban/rural\n", + " urban_grouped_df = df.groupby(field_names.URBAN_HEURISTIC_FIELD)\n", + "\n", + " # Run the comparison function on the groups.\n", + " urban_grouped_df = urban_grouped_df.progress_apply(\n", + " lambda frame: calculate_state_comparison(\n", + " frame, geography_field=field_names.URBAN_HEURISTIC_FIELD\n", + " )\n", + " )\n", + "\n", + " # Combine the five\n", + " combined_df = pd.concat(\n", + " [\n", + " usa_distribution_df,\n", + " state_distribution_df,\n", + " region_distribution_df,\n", + " division_distribution_df,\n", + " urban_grouped_df,\n", + " ]\n", + " )\n", + "\n", + " return combined_df\n", + "\n", + "\n", + "def write_state_distribution_excel(\n", + " state_distribution_df: pd.DataFrame, file_path: pathlib.PosixPath\n", + ") -> None:\n", + " \"\"\"Write the dataframe to excel with special formatting.\"\"\"\n", + " # Create a Pandas Excel writer using XlsxWriter as the engine.\n", + " writer = pd.ExcelWriter(file_path, engine=\"xlsxwriter\")\n", + "\n", + " # Convert the dataframe to an XlsxWriter Excel object. We also turn off the\n", + " # index column at the left of the output dataframe.\n", + " state_distribution_df.to_excel(writer, sheet_name=\"Sheet1\", index=False)\n", + "\n", + " # Get the xlsxwriter workbook and worksheet objects.\n", + " workbook = writer.book\n", + " worksheet = writer.sheets[\"Sheet1\"]\n", + " worksheet.autofilter(\n", + " 0, 0, state_distribution_df.shape[0], state_distribution_df.shape[1]\n", + " )\n", + "\n", + " # Set a width parameter for all columns\n", + " # Note: this is parameterized because every call to `set_column` requires setting the width.\n", + " column_width = 15\n", + "\n", + " for column in state_distribution_df.columns:\n", + " # Turn the column index into excel ranges (e.g., column #95 is \"CR\" and the range may be \"CR2:CR53\").\n", + " column_index = state_distribution_df.columns.get_loc(column)\n", + " column_character = get_excel_column_name(column_index)\n", + "\n", + " # Set all columns to larger width\n", + " worksheet.set_column(f\"{column_character}:{column_character}\", column_width)\n", + "\n", + " # Special formatting for all percent columns\n", + " # Note: we can't just search for `percent`, because that's included in the word `percentile`.\n", + " if \"percent \" in column or \"(percent)\" in column:\n", + " # Make these columns percentages.\n", + " percentage_format = workbook.add_format({\"num_format\": \"0%\"})\n", + " worksheet.set_column(\n", + " f\"{column_character}:{column_character}\",\n", + " column_width,\n", + " percentage_format,\n", + " )\n", + "\n", + " # Special formatting for columns that capture the percent of population considered priority.\n", + " if \"(percent population)\" in column:\n", + " column_ranges = (\n", + " f\"{column_character}2:{column_character}{len(state_distribution_df)+1}\"\n", + " )\n", + "\n", + " # Add green to red conditional formatting.\n", + " worksheet.conditional_format(\n", + " column_ranges,\n", + " # Min: green, max: red.\n", + " {\n", + " \"type\": \"2_color_scale\",\n", + " \"min_color\": \"#00FF7F\",\n", + " \"max_color\": \"#C82538\",\n", + " },\n", + " )\n", + "\n", + " header_format = workbook.add_format(\n", + " {\"bold\": True, \"text_wrap\": True, \"valign\": \"bottom\"}\n", + " )\n", + "\n", + " # Overwrite both the value and the format of each header cell\n", + " # This is because xlsxwriter / pandas has a known bug where it can't wrap text for a dataframe.\n", + " # See https://stackoverflow.com/questions/42562977/xlsxwriter-text-wrap-not-working.\n", + " for col_num, value in enumerate(state_distribution_df.columns.values):\n", + " worksheet.write(0, col_num, value, header_format)\n", + "\n", + " writer.save()\n", + "\n", + "\n", + "fields_to_analyze = [index.priority_communities_field for index in census_tract_indices]\n", + "\n", + "# Convert all indices to boolean\n", + "for field_to_analyze in fields_to_analyze:\n", + " if \"Areas of Concern\" in field_to_analyze:\n", + " print(f\"Converting {field_to_analyze} to boolean.\")\n", + "\n", + " merged_df[field_to_analyze] = merged_df[field_to_analyze].fillna(value=0)\n", + " merged_df[field_to_analyze] = merged_df[field_to_analyze].astype(bool)\n", + "\n", + "\n", + "state_fips_codes = get_state_information(DATA_DIR)\n", + "\n", + "merged_with_state_information_df = merged_df.merge(\n", + " right=state_fips_codes, left_on=GEOID_STATE_FIELD_NAME, right_on=\"fips\"\n", + ")\n", + "\n", + "state_distribution_df = get_state_distributions(\n", + " df=merged_with_state_information_df,\n", + " priority_communities_fields=fields_to_analyze,\n", + ")\n", + "\n", + "file_prefix = \"Priority Tracts – Different geographic groupings\"\n", + "\n", + "state_distribution_df.to_csv(\n", + " path_or_buf=COMPARISON_OUTPUTS_DIR / f\"{file_prefix}.csv\",\n", + " na_rep=\"\",\n", + " index=False,\n", + ")\n", + "\n", + "write_state_distribution_excel(\n", + " state_distribution_df=state_distribution_df,\n", + " file_path=COMPARISON_OUTPUTS_DIR / f\"{file_prefix}.xlsx\",\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "2bcbcabf", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Basic stats for Definition M\n", + "Basic stats for Definition L\n", + "Basic stats for Climate Factor (Definition M)\n", + "Basic stats for Energy Factor (Definition M)\n", + "Basic stats for Transportation Factor (Definition M)\n", + "Basic stats for Housing Factor (Definition M)\n", + "Basic stats for Pollution Factor (Definition M)\n", + "Basic stats for Water Factor (Definition M)\n", + "Basic stats for Health Factor (Definition M)\n", + "Basic stats for Workforce Factor (Definition M)\n", + "Basic stats for Any Non-Workforce Factor (Definition M)\n", + "Basic stats for Climate Factor (Definition L)\n", + "Basic stats for Energy Factor (Definition L)\n", + "Basic stats for Transportation Factor (Definition L)\n", + "Basic stats for Housing Factor (Definition L)\n", + "Basic stats for Pollution Factor (Definition L)\n", + "Basic stats for Water Factor (Definition L)\n", + "Basic stats for Health Factor (Definition L)\n", + "Basic stats for Workforce Factor (Definition L)\n", + "Basic stats for Any Non-Workforce Factor (Definition L)\n", + "Basic stats for NMTC Modified\n", + "Basic stats for NMTC\n", + "Basic stats for Score C\n", + "Basic stats for Score D (30th percentile)\n", + "Basic stats for Score D (25th percentile)\n", + "Basic stats for Score F\n", + "Basic stats for CalEnviroScreen 4.0\n", + "Basic stats for Mapping for EJ\n", + "Basic stats for EPA RSEI Aggregate Microdata\n", + "Basic stats for Persistent Poverty\n", + "Basic stats for Maryland EJSCREEN\n", + "Basic stats for Energy-related alternative definition of communities\n", + "Basic stats for CDC SVI Index\n", + "Basic stats for Michigan EJSCREEN\n", + "Basic stats for Tract is >20% HOLC Grade D\n", + "Basic stats for Tract is >50% HOLC Grade D\n", + "Basic stats for Tract is >75% HOLC Grade D\n" + ] + } + ], + "source": [ + "directory = COMPARISON_OUTPUTS_DIR / \"tracts_basic_stats\"\n", + "directory.mkdir(parents=True, exist_ok=True)\n", + "\n", + "# TODO: this Excel-writing function is extremely similar to other Excel-writing functions in this notebook.\n", + "# Refactor to use the same Excel-writing function.\n", + "def write_basic_stats_excel(\n", + " basic_stats_df: pd.DataFrame, file_path: pathlib.PosixPath\n", + ") -> None:\n", + " \"\"\"Write the dataframe to excel with special formatting.\"\"\"\n", + " # Create a Pandas Excel writer using XlsxWriter as the engine.\n", + " writer = pd.ExcelWriter(file_path, engine=\"xlsxwriter\")\n", + "\n", + " # Convert the dataframe to an XlsxWriter Excel object. We also turn off the\n", + " # index column at the left of the output dataframe.\n", + " basic_stats_df.to_excel(writer, sheet_name=\"Sheet1\", index=False)\n", + "\n", + " # Get the xlsxwriter workbook and worksheet objects.\n", + " workbook = writer.book\n", + " worksheet = writer.sheets[\"Sheet1\"]\n", + " worksheet.autofilter(0, 0, basic_stats_df.shape[0], basic_stats_df.shape[1])\n", + "\n", + " # Set a width parameter for all columns\n", + " # Note: this is parameterized because every call to `set_column` requires setting the width.\n", + " column_width = 15\n", + "\n", + " for column in basic_stats_df.columns:\n", + " # Turn the column index into excel ranges (e.g., column #95 is \"CR\" and the range may be \"CR2:CR53\").\n", + " column_index = basic_stats_df.columns.get_loc(column)\n", + " column_character = get_excel_column_name(column_index)\n", + "\n", + " # Set all columns to larger width\n", + " worksheet.set_column(f\"{column_character}:{column_character}\", column_width)\n", + "\n", + " # Add green to red conditional formatting.\n", + " column_ranges = f\"{column_character}2:{column_character}{len(basic_stats_df)+1}\"\n", + " worksheet.conditional_format(\n", + " column_ranges,\n", + " # Min: green, max: red.\n", + " {\n", + " \"type\": \"2_color_scale\",\n", + " \"min_color\": \"#00FF7F\",\n", + " \"max_color\": \"#C82538\",\n", + " },\n", + " )\n", + "\n", + " # Special formatting for all percent columns\n", + " # Note: we can't just search for `percent`, because that's included in the word `percentile`.\n", + " if \"percent \" in column or \"(percent)\" in column or \"Percent \" in column:\n", + " # Make these columns percentages.\n", + " percentage_format = workbook.add_format({\"num_format\": \"0%\"})\n", + " worksheet.set_column(\n", + " f\"{column_character}:{column_character}\",\n", + " column_width,\n", + " percentage_format,\n", + " )\n", + "\n", + " header_format = workbook.add_format(\n", + " {\"bold\": True, \"text_wrap\": True, \"valign\": \"bottom\"}\n", + " )\n", + "\n", + " # Overwrite both the value and the format of each header cell\n", + " # This is because xlsxwriter / pandas has a known bug where it can't wrap text for a dataframe.\n", + " # See https://stackoverflow.com/questions/42562977/xlsxwriter-text-wrap-not-working.\n", + " for col_num, value in enumerate(basic_stats_df.columns.values):\n", + " worksheet.write(0, col_num, value, header_format)\n", + "\n", + " writer.save()\n", + "\n", + "\n", + "for index in census_tract_indices:\n", + " print(f\"Basic stats for {index.method_name}\")\n", + " temp_df = merged_df\n", + " temp_df[index.priority_communities_field] = (\n", + " temp_df[index.priority_communities_field] == True\n", + " )\n", + "\n", + " grouped_df = temp_df.groupby(index.priority_communities_field).mean().reset_index()\n", + " result_df = grouped_df[[index.priority_communities_field] + comparison_fields]\n", + " result_df.to_csv(directory / f\"{index.method_name} Basic Stats.csv\", index=False)\n", + " write_basic_stats_excel(\n", + " basic_stats_df=result_df,\n", + " file_path=directory / f\"{index.method_name} Basic Stats.xlsx\",\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "d1eec560", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Definition L', priority_communities_field='Definition L (communities)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Definition M', priority_communities_field='Definition M (communities)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Definition L', priority_communities_field='Definition L (communities)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition M)', priority_communities_field='Climate Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition M)', priority_communities_field='Energy Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition M)', priority_communities_field='Transportation Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition M)', priority_communities_field='Housing Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition M)', priority_communities_field='Pollution Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition M)', priority_communities_field='Water Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition M)', priority_communities_field='Health Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition M)', priority_communities_field='Workforce Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition M)', priority_communities_field='Any Non-Workforce Factor (Definition M)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Climate Factor (Definition L)', priority_communities_field='Climate Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Energy Factor (Definition L)', priority_communities_field='Energy Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Transportation Factor (Definition L)', priority_communities_field='Transportation Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Housing Factor (Definition L)', priority_communities_field='Housing Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Pollution Factor (Definition L)', priority_communities_field='Pollution Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Water Factor (Definition L)', priority_communities_field='Water Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Health Factor (Definition L)', priority_communities_field='Health Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Workforce Factor (Definition L)', priority_communities_field='Workforce Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Any Non-Workforce Factor (Definition L)', priority_communities_field='Any Non-Workforce Factor (Definition L)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='NMTC', priority_communities_field='NMTC (communities)').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC Modified', priority_communities_field='Score G (communities)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='NMTC', priority_communities_field='NMTC (communities)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Score C', priority_communities_field='Score C (top 25th percentile)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (30th percentile)', priority_communities_field='Score D (top 30th percentile)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Score F', priority_communities_field='Score F (communities)').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Score D (25th percentile)', priority_communities_field='Score D (top 25th percentile)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Score F', priority_communities_field='Score F (communities)') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='CalEnviroScreen 4.0', priority_communities_field='calenviroscreen_priority_community') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Mapping for EJ', priority_communities_field='Mapping for Environmental Justice Priority Community') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='EPA RSEI Aggregate Microdata', priority_communities_field='At or above 75 for overall percentile for the RSEI score') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Persistent Poverty', priority_communities_field='Persistent Poverty, Tract Level') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Maryland EJSCREEN', priority_communities_field='Maryland EJSCREEN Priority Community') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities') and Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices').\n", + "Comparing Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Energy-related alternative definition of communities', priority_communities_field='Energy-related alternative definition of communities') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices') and Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community').\n", + "Comparing Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='CDC SVI Index', priority_communities_field='At or above 90 for overall percentile ranking according to Social Vulnerability Indices') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community') and Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D').\n", + "Comparing Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Michigan EJSCREEN', priority_communities_field='Michigan EJSCREEN Priority Community') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D') and Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D').\n", + "Comparing Index(method_name='Tract is >20% HOLC Grade D', priority_communities_field='Tract is >20% HOLC Grade D') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n", + "Comparing Index(method_name='Tract is >50% HOLC Grade D', priority_communities_field='Tract is >50% HOLC Grade D') and Index(method_name='Tract is >75% HOLC Grade D', priority_communities_field='Tract is >75% HOLC Grade D').\n" + ] + } + ], + "source": [ + "# Compare census tract scores to each other, running secondary analysis on\n", + "# characteristics of census tracts prioritized by one but not the other.\n", + "def get_census_tracts_score_comparison_df(\n", + " df: pd.DataFrame,\n", + " method_a_priority_census_tracts_field: str,\n", + " method_b_priority_census_tracts_field: str,\n", + " comparison_fields: typing.List[str],\n", + ") -> pd.DataFrame:\n", + " \"\"\"Compare tract scores to each other.\n", + "\n", + " This comparison method analyzes characteristics of those census tracts, based on whether or not they are prioritized\n", + " or not by Method A and/or Method B.\n", + "\n", + " E.g., it might show that tracts prioritized by A but not B have a higher average income,\n", + " or that tracts prioritized by B but not A have a lower percent of unemployed people.\n", + " \"\"\"\n", + " fields_to_group_by = [\n", + " method_a_priority_census_tracts_field,\n", + " method_b_priority_census_tracts_field,\n", + " ]\n", + "\n", + " df_subset = df[fields_to_group_by + comparison_fields]\n", + "\n", + " grouped_df = df_subset.groupby(\n", + " fields_to_group_by,\n", + " dropna=False,\n", + " )\n", + "\n", + " # Take the mean of all fields.\n", + " comparison_df = grouped_df.mean()\n", + "\n", + " # Also add in the count of census tracts.\n", + " count_field_name = \"Count of census tracts\"\n", + " comparison_df[count_field_name] = grouped_df.size().to_frame(count_field_name)\n", + "\n", + " comparison_df = comparison_df.reset_index()\n", + "\n", + " criteria_description_field_name = \"Description of criteria\"\n", + " comparison_df[criteria_description_field_name] = comparison_df.apply(\n", + " func=lambda row: f\"Tracts that are {'not ' if row[method_a_priority_census_tracts_field] is False else ''}\"\n", + " + f\"prioritized by {method_a_priority_census_tracts_field} \"\n", + " + f\"and are {'not ' if row[method_b_priority_census_tracts_field] is False else ''}\"\n", + " + f\"prioritized by {method_b_priority_census_tracts_field}\",\n", + " axis=1,\n", + " )\n", + "\n", + " # Put criteria description column first.\n", + " columns_to_put_first = (\n", + " [criteria_description_field_name] + fields_to_group_by + [count_field_name]\n", + " )\n", + " new_column_order = columns_to_put_first + [\n", + " col for col in comparison_df.columns if col not in columns_to_put_first\n", + " ]\n", + "\n", + " comparison_df = comparison_df[new_column_order]\n", + "\n", + " # Rename fields to reflect the mean aggregation\n", + " comparison_df.rename(\n", + " mapper={\n", + " comparison_field: f\"{comparison_field} (mean of tracts)\"\n", + " for comparison_field in comparison_fields\n", + " },\n", + " axis=1,\n", + " inplace=True,\n", + " )\n", + "\n", + " return comparison_df\n", + "\n", + "\n", + "def write_census_tracts_score_comparison_excel(\n", + " census_tracts_score_comparison_df: pd.DataFrame,\n", + " file_path: pathlib.PosixPath,\n", + ") -> None:\n", + " \"\"\"Write the dataframe to excel with special formatting.\"\"\"\n", + " # Create a Pandas Excel writer using XlsxWriter as the engine.\n", + " writer = pd.ExcelWriter(file_path, engine=\"xlsxwriter\")\n", + "\n", + " # Convert the dataframe to an XlsxWriter Excel object. We also turn off the\n", + " # index column at the left of the output dataframe.\n", + " census_tracts_score_comparison_df.to_excel(writer, sheet_name=\"Sheet1\", index=False)\n", + "\n", + " # Get the xlsxwriter workbook and worksheet objects.\n", + " workbook = writer.book\n", + " worksheet = writer.sheets[\"Sheet1\"]\n", + " worksheet.autofilter(\n", + " 0,\n", + " 0,\n", + " census_tracts_score_comparison_df.shape[0],\n", + " census_tracts_score_comparison_df.shape[1],\n", + " )\n", + "\n", + " # Set a width parameter for all columns\n", + " # Note: this is parameterized because every call to `set_column` requires setting the width.\n", + " column_width = 15\n", + "\n", + " for column in census_tracts_score_comparison_df.columns:\n", + " # Turn the column index into excel ranges (e.g., column #95 is \"CR\" and the range may be \"CR2:CR53\").\n", + " column_index = census_tracts_score_comparison_df.columns.get_loc(column)\n", + " column_character = get_excel_column_name(column_index)\n", + "\n", + " # Set all columns to larger width\n", + " worksheet.set_column(f\"{column_character}:{column_character}\", column_width)\n", + "\n", + " # Add green to red conditional formatting.\n", + " column_ranges = f\"{column_character}2:{column_character}{len(census_tracts_score_comparison_df)+1}\"\n", + " worksheet.conditional_format(\n", + " column_ranges,\n", + " # Min: green, max: red.\n", + " {\n", + " \"type\": \"2_color_scale\",\n", + " \"min_color\": \"#00FF7F\",\n", + " \"max_color\": \"#C82538\",\n", + " },\n", + " )\n", + "\n", + " # Special formatting for all percent columns\n", + " # Note: we can't just search for `percent`, because that's included in the word `percentile`.\n", + " if \"percent \" in column or \"(percent)\" in column or \"Percent \" in column:\n", + " # Make these columns percentages.\n", + " percentage_format = workbook.add_format({\"num_format\": \"0%\"})\n", + " worksheet.set_column(\n", + " f\"{column_character}:{column_character}\",\n", + " column_width,\n", + " percentage_format,\n", + " )\n", + "\n", + " header_format = workbook.add_format(\n", + " {\"bold\": True, \"text_wrap\": True, \"valign\": \"bottom\"}\n", + " )\n", + "\n", + " # Overwrite both the value and the format of each header cell\n", + " # This is because xlsxwriter / pandas has a known bug where it can't wrap text for a dataframe.\n", + " # See https://stackoverflow.com/questions/42562977/xlsxwriter-text-wrap-not-working.\n", + " for col_num, value in enumerate(census_tracts_score_comparison_df.columns.values):\n", + " worksheet.write(0, col_num, value, header_format)\n", + "\n", + " writer.save()\n", + "\n", + "\n", + "def compare_census_tracts_scores(\n", + " df: pd.DataFrame,\n", + " index_a: Index,\n", + " index_b: Index,\n", + " output_dir: pathlib.PosixPath,\n", + " comparison_fields: typing.List[str],\n", + "):\n", + " # Secondary comparison DF\n", + " census_tracts_score_comparison_df = get_census_tracts_score_comparison_df(\n", + " df=df,\n", + " method_a_priority_census_tracts_field=index_a.priority_communities_field,\n", + " method_b_priority_census_tracts_field=index_b.priority_communities_field,\n", + " comparison_fields=comparison_fields,\n", + " )\n", + "\n", + " # Write secondary comparison to CSV.\n", + " file_name_part = f\"Census tracts comparison output - {index_a.method_name} and {index_b.method_name}\"\n", + " output_dir.mkdir(parents=True, exist_ok=True)\n", + " file_path = output_dir / (file_name_part + \".csv\")\n", + " file_path_xlsx = output_dir / (file_name_part + \".xlsx\")\n", + "\n", + " census_tracts_score_comparison_df.to_csv(\n", + " path_or_buf=file_path,\n", + " na_rep=\"\",\n", + " index=False,\n", + " )\n", + "\n", + " write_census_tracts_score_comparison_excel(\n", + " census_tracts_score_comparison_df=census_tracts_score_comparison_df,\n", + " file_path=file_path_xlsx,\n", + " )\n", + "\n", + "\n", + "for (index_a, index_b) in itertools.combinations(census_tract_indices, 2):\n", + " print(f\"Comparing {index_a} and {index_b}.\")\n", + " compare_census_tracts_scores(\n", + " df=merged_df,\n", + " index_a=index_a,\n", + " index_b=index_b,\n", + " comparison_fields=comparison_fields,\n", + " output_dir=COMPARISON_OUTPUTS_DIR / \"census_tracts_score_comparisons\",\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "48005fad", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/z6/9czv8cpx2hvcycd6slvfp4ph0000gq/T/ipykernel_35872/2594933895.py:125: RuntimeWarning: invalid value encountered in long_scalars\n", + " f\"{true_true_census_tracts} ({true_true_census_tracts / total_census_tracts:.0%}) \"\n", + "/var/folders/z6/9czv8cpx2hvcycd6slvfp4ph0000gq/T/ipykernel_35872/2594933895.py:128: RuntimeWarning: invalid value encountered in long_scalars\n", + " f\"{true_false_census_tracts} ({true_false_census_tracts / total_census_tracts:.0%}) \"\n", + "/var/folders/z6/9czv8cpx2hvcycd6slvfp4ph0000gq/T/ipykernel_35872/2594933895.py:131: RuntimeWarning: invalid value encountered in long_scalars\n", + " f\"{false_true_census_tracts} ({false_true_census_tracts / total_census_tracts:.0%}) \"\n", + "/var/folders/z6/9czv8cpx2hvcycd6slvfp4ph0000gq/T/ipykernel_35872/2594933895.py:134: RuntimeWarning: invalid value encountered in long_scalars\n", + " f\"{false_false_census_tracts} ({false_false_census_tracts / total_census_tracts:.0%}) \"\n" + ] + }, + { + "data": { + "text/plain": [ + "PosixPath('/Users/emmausds/Desktop/justice40-tool/data/data-pipeline/data_pipeline/data/comparison_outputs/20220217-115053/Comparison report - All census tract indices.docx')" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def write_markdown_and_docx_content(\n", + " markdown_content: str,\n", + " file_dir: pathlib.PosixPath,\n", + " file_name_without_extension: str,\n", + ") -> pathlib.PosixPath:\n", + " \"\"\"Write Markdown content to both .md and .docx files.\"\"\"\n", + " # Set the file paths for both files.\n", + " markdown_file_path = file_dir / f\"{file_name_without_extension}.md\"\n", + " docx_file_path = file_dir / f\"{file_name_without_extension}.docx\"\n", + "\n", + " # Write the markdown content to file.\n", + " with open(markdown_file_path, \"w\") as text_file:\n", + " text_file.write(markdown_content)\n", + "\n", + " # Convert markdown file to Word doc.\n", + " pypandoc.convert_file(\n", + " source_file=str(markdown_file_path),\n", + " to=\"docx\",\n", + " outputfile=str(docx_file_path),\n", + " extra_args=[],\n", + " )\n", + "\n", + " return docx_file_path\n", + "\n", + "\n", + "def get_markdown_comparing_census_tract_indices(\n", + " census_tract_indices=typing.List[Index],\n", + " df=pd.DataFrame,\n", + " state_field=GEOID_STATE_FIELD_NAME,\n", + ") -> str:\n", + " \"\"\"Generate a Markdown string of analysis of multiple census tract indices.\"\"\"\n", + " count_field_name = \"Count of census tracts\"\n", + "\n", + " # Create markdown content for comparisons.\n", + " markdown_content = f\"\"\"\n", + "# Comparing multiple indices at the census tract level\n", + "\n", + "(This report was calculated on {datetime.today().strftime('%Y-%m-%d')}.)\n", + "\n", + "This report compares the following indices: {\", \".join([index.method_name for index in census_tract_indices])}.\n", + "\n", + "\"\"\"\n", + "\n", + " for (index1, index2) in itertools.combinations(census_tract_indices, 2):\n", + " # First, find out geographic overlap in indices by finding all state and territory\n", + " # names where both indices are not null.\n", + " df_subset_for_states = df[\n", + " [\n", + " state_field,\n", + " index1.priority_communities_field,\n", + " index2.priority_communities_field,\n", + " ]\n", + " ]\n", + "\n", + " df_subset_for_states = df_subset_for_states.dropna()\n", + "\n", + " # List of all states/territories in their FIPS codes:\n", + " # TODO: move \"This report analyzes the following US states and territories\" inside the comparison?\n", + " state_ids = sorted(df_subset_for_states[state_field].unique())\n", + " this_comparison_state_names = \", \".join(\n", + " [us.states.lookup(state_id).name for state_id in state_ids]\n", + " )\n", + "\n", + " # Group all data by their different values on Priority Communities Field for Index1 vs Priority Communities Field for Index2.\n", + " count_df = (\n", + " df.groupby(\n", + " [\n", + " index1.priority_communities_field,\n", + " index2.priority_communities_field,\n", + " ]\n", + " )[ExtractTransformLoad.GEOID_TRACT_FIELD_NAME]\n", + " .count()\n", + " .reset_index(name=count_field_name)\n", + " )\n", + "\n", + " total_census_tracts = count_df[count_field_name].sum()\n", + "\n", + " # Returns a series\n", + " true_true_census_tracts_series = count_df.loc[\n", + " count_df[index1.priority_communities_field]\n", + " & count_df[index2.priority_communities_field],\n", + " count_field_name,\n", + " ]\n", + " true_false_census_tracts_series = count_df.loc[\n", + " count_df[index1.priority_communities_field]\n", + " & ~count_df[index2.priority_communities_field],\n", + " count_field_name,\n", + " ]\n", + " false_true_census_tracts_series = count_df.loc[\n", + " ~count_df[index1.priority_communities_field]\n", + " & count_df[index2.priority_communities_field],\n", + " count_field_name,\n", + " ]\n", + " false_false_census_tracts_series = count_df.loc[\n", + " ~count_df[index1.priority_communities_field]\n", + " & ~count_df[index2.priority_communities_field],\n", + " count_field_name,\n", + " ]\n", + "\n", + " # Convert from series to a scalar value, including accounting for if no data exists for that pairing.\n", + " true_true_census_tracts = (\n", + " true_true_census_tracts_series.iloc[0]\n", + " if len(true_true_census_tracts_series) > 0\n", + " else 0\n", + " )\n", + " true_false_census_tracts = (\n", + " true_false_census_tracts_series.iloc[0]\n", + " if len(true_false_census_tracts_series) > 0\n", + " else 0\n", + " )\n", + " false_true_census_tracts = (\n", + " false_true_census_tracts_series.iloc[0]\n", + " if len(false_true_census_tracts_series) > 0\n", + " else 0\n", + " )\n", + " false_false_census_tracts = (\n", + " false_false_census_tracts_series.iloc[0]\n", + " if len(false_false_census_tracts_series) > 0\n", + " else 0\n", + " )\n", + "\n", + " markdown_content += (\n", + " \"*** \\n\\n\"\n", + " \"There are \"\n", + " f\"{true_true_census_tracts} ({true_true_census_tracts / total_census_tracts:.0%}) \"\n", + " f\"census tracts that are both {index1.method_name} priority communities and {index2.method_name} priority communities.\\n\\n\"\n", + " \"There are \"\n", + " f\"{true_false_census_tracts} ({true_false_census_tracts / total_census_tracts:.0%}) \"\n", + " f\"census tracts that are {index1.method_name} priority communities but not {index2.method_name} priority communities.\\n\\n\"\n", + " \"There are \"\n", + " f\"{false_true_census_tracts} ({false_true_census_tracts / total_census_tracts:.0%}) \"\n", + " f\"census tracts that are not {index1.method_name} priority communities but are {index2.method_name} priority communities.\\n\\n\"\n", + " \"There are \"\n", + " f\"{false_false_census_tracts} ({false_false_census_tracts / total_census_tracts:.0%}) \"\n", + " f\"census tracts that are neither {index1.method_name} priority communities nor {index2.method_name} priority communities.\\n\\n\"\n", + " f\"This comparison analyzed the following US states and territories: {this_comparison_state_names}.\\n\\n\"\n", + " \"\\n\\n\"\n", + " )\n", + "\n", + " return markdown_content\n", + "\n", + "\n", + "def get_comparison_census_tract_indices(\n", + " census_tract_indices=typing.List[Index],\n", + " df=pd.DataFrame,\n", + " state_field=GEOID_STATE_FIELD_NAME,\n", + ") -> pathlib.PosixPath:\n", + " markdown_content = get_markdown_comparing_census_tract_indices(\n", + " census_tract_indices=census_tract_indices,\n", + " df=df,\n", + " )\n", + "\n", + " comparison_docx_file_path = write_markdown_and_docx_content(\n", + " markdown_content=markdown_content,\n", + " file_dir=COMPARISON_OUTPUTS_DIR,\n", + " file_name_without_extension=f\"Comparison report - All census tract indices\",\n", + " )\n", + "\n", + " return comparison_docx_file_path\n", + "\n", + "\n", + "# Compare multiple scores at the census tract level\n", + "get_comparison_census_tract_indices(\n", + " census_tract_indices=census_tract_indices,\n", + " df=merged_with_state_information_df,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "7d095ebd", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Note: this is helpful because this file is long-running, so it alerts the user when the\n", + "# data analysis is done. Can be removed when converted into scripts. -LMB.\n", + "import os\n", + "\n", + "os.system(\"say 'data analysis is written.'\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "40821ff3-0a06-4881-a33c-f9db487ac3b2", + "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": "3.9.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}