{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "20aa3891",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import requests\n",
    "import zipfile\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import csv\n",
    "\n",
    "data_path = Path.cwd().parent / \"data\"\n",
    "fips_csv_path = data_path / \"fips_states_2010.csv\"\n",
    "csv_path = data_path / \"dataset\" / \"ejscreen_2020\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "67a58c24",
   "metadata": {},
   "outputs": [],
   "source": [
    "download = requests.get(\n",
    "    \"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\",\n",
    "    verify=False,\n",
    ")\n",
    "file_contents = download.content\n",
    "zip_file_path = data_path / \"tmp\"\n",
    "zip_file = open(zip_file_path / \"downloaded.zip\", \"wb\")\n",
    "zip_file.write(file_contents)\n",
    "zip_file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cc3fb9ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "with zipfile.ZipFile(zip_file_path / \"downloaded.zip\", \"r\") as zip_ref:\n",
    "    zip_ref.extractall(zip_file_path)\n",
    "ejscreen_csv = data_path / \"tmp\" / \"EJSCREEN_2020_StatePctile.csv\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b25738bb",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(ejscreen_csv, dtype={\"ID\": \"string\"}, low_memory=False)"
   ]
  },
  {
   "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",
    "with open(fips_csv_path) as csv_file:\n",
    "    csv_reader = csv.reader(csv_file, delimiter=\",\")\n",
    "    line_count = 0\n",
    "\n",
    "    for row in csv_reader:\n",
    "        if line_count == 0:\n",
    "            line_count += 1\n",
    "        else:\n",
    "            fips = row[0].strip()\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": []
  }
 ],
 "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": "3.9.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}