{ "cells": [ { "cell_type": "code", "execution_count": null, "id": "20aa3891", "metadata": {}, "outputs": [], "source": [ "from pathlib import Path\n", "import numpy as np\n", "import pandas as pd\n", "import csv\n", "import sys\n", "import os\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 etl.sources.census.etl_utils import get_state_fips_codes\n", "from utils import unzip_file_from_url, remove_all_from_dir\n", "\n", "DATA_PATH = Path.cwd().parent / \"data\"\n", "TMP_PATH = DATA_PATH / \"tmp\"\n", "CALENVIROSCREEN_FTP_URL = \"https://justice40-data.s3.amazonaws.com/CalEnviroScreen/CalEnviroScreen_4.0_2021.zip\"\n", "CSV_PATH = DATA_PATH / \"dataset\" / \"calenviroscreen4\"\n", "\n", "# Definining some variable names\n", "CALENVIROSCREEN_SCORE_FIELD_NAME = \"calenviroscreen_score\"\n", "CALENVIROSCREEN_PERCENTILE_FIELD_NAME = \"calenviroscreen_percentile\"\n", "CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD_NAME = \"calenviroscreen_priority_community\"\n", "GEOID_TRACT_FIELD_NAME = \"GEOID10_TRACT\"\n", "\n", "# Choosing constants.\n", "# None of these numbers are final, but just for the purposes of comparison.\n", "CALENVIROSCREEN_PRIORITY_COMMUNITY_THRESHOLD = 75\n", "\n", "print(DATA_PATH)" ] }, { "cell_type": "code", "execution_count": null, "id": "cc3fb9ec", "metadata": {}, "outputs": [], "source": [ "# download file from ejscreen ftp\n", "unzip_file_from_url(CALENVIROSCREEN_FTP_URL, TMP_PATH, TMP_PATH)" ] }, { "cell_type": "code", "execution_count": null, "id": "15f66756", "metadata": {}, "outputs": [], "source": [ "# Data from https://calenviroscreen-oehha.hub.arcgis.com/#Data, specifically:\n", "# https://oehha.ca.gov/media/downloads/calenviroscreen/document/calenviroscreen40resultsdatadictionaryd12021.zip\n", "calenviroscreen_4_csv_name = \"CalEnviroScreen_4.0_2021.csv\"\n", "calenviroscreen_data_path = TMP_PATH.joinpath(calenviroscreen_4_csv_name)\n", "\n", "# Load comparison index (CalEnviroScreen 4)\n", "calenviroscreen_df = pd.read_csv(\n", " calenviroscreen_data_path, dtype={\"Census Tract\": \"string\"}\n", ")\n", "\n", "calenviroscreen_df.rename(\n", " columns={\n", " \"Census Tract\": GEOID_TRACT_FIELD_NAME,\n", " \"DRAFT CES 4.0 Score\": CALENVIROSCREEN_SCORE_FIELD_NAME,\n", " \"DRAFT CES 4.0 Percentile\": CALENVIROSCREEN_PERCENTILE_FIELD_NAME,\n", " },\n", " inplace=True,\n", ")\n", "\n", "# Add a leading \"0\" to the Census Tract to match our format in other data frames.\n", "\n", "calenviroscreen_df[GEOID_TRACT_FIELD_NAME] = (\n", " \"0\" + calenviroscreen_df[GEOID_TRACT_FIELD_NAME]\n", ")\n", "\n", "# Calculate the top K% of prioritized communities\n", "calenviroscreen_df[CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD_NAME] = (\n", " calenviroscreen_df[CALENVIROSCREEN_PERCENTILE_FIELD_NAME]\n", " >= CALENVIROSCREEN_PRIORITY_COMMUNITY_THRESHOLD\n", ")\n", "\n", "calenviroscreen_df.head()" ] }, { "cell_type": "code", "execution_count": null, "id": "9fa2077a", "metadata": {}, "outputs": [], "source": [ "# write csv\n", "CSV_PATH.mkdir(parents=True, exist_ok=True)\n", "\n", "# Matching other conventions in the ETL scripts, write only for the state (FIPS code 06).\n", "calenviroscreen_df.to_csv(CSV_PATH / \"data06.csv\", index=False)" ] }, { "cell_type": "code", "execution_count": null, "id": "81b977f8", "metadata": {}, "outputs": [], "source": [ "# cleanup\n", "remove_all_from_dir(TMP_PATH)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 5 }