{
 "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",
    "EJSCREEN_FTP_URL = (\n",
    "    \"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\"\n",
    ")\n",
    "EJSCREEN_CSV = TMP_PATH / \"EJSCREEN_2020_StatePctile.csv\"\n",
    "CSV_PATH = DATA_PATH / \"dataset\" / \"ejscreen_2020\"\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(EJSCREEN_FTP_URL, TMP_PATH, TMP_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b25738bb",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    EJSCREEN_CSV,\n",
    "    dtype={\"ID\": \"string\"},\n",
    "    # EJSCREEN writes the word \"None\" for NA data.\n",
    "    na_values=[\"None\"],\n",
    "    low_memory=False,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9fa2077a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# write nationwide csv\n",
    "CSV_PATH.mkdir(parents=True, exist_ok=True)\n",
    "df.to_csv(CSV_PATH / f\"usa.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5e5cc12a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# write per state csvs\n",
    "for fips in get_state_fips_codes(DATA_PATH):\n",
    "    print(f\"Generating data{fips} csv\")\n",
    "    df1 = df[df.ID.str[:2] == fips]\n",
    "    # we need to name the file data01.csv for ogr2ogr csv merge to work\n",
    "    df1.to_csv(CSV_PATH / f\"data{fips}.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
}