{
 "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",
    "HUD_RECAP_CSV_URL = \"https://opendata.arcgis.com/api/v3/datasets/56de4edea8264fe5a344da9811ef5d6e_0/downloads/data?format=csv&spatialRefId=4326\"\n",
    "CSV_PATH = DATA_PATH / \"dataset\" / \"hud_recap\"\n",
    "\n",
    "# Definining some variable names\n",
    "GEOID_TRACT_FIELD_NAME = \"GEOID10_TRACT\"\n",
    "HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME = \"hud_recap_priority_community\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b9455da5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data from https://hudgis-hud.opendata.arcgis.com/datasets/HUD::racially-or-ethnically-concentrated-areas-of-poverty-r-ecaps/about\n",
    "df = pd.read_csv(HUD_RECAP_CSV_URL, dtype={\"GEOID\": \"string\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ca63e66c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Rename some fields\n",
    "df.rename(\n",
    "    columns={\n",
    "        \"GEOID\": GEOID_TRACT_FIELD_NAME,\n",
    "        # Interestingly, there's no data dictionary for the RECAP data that I could find.\n",
    "        # However, this site (http://www.schousing.com/library/Tax%20Credit/2020/QAP%20Instructions%20(2).pdf)\n",
    "        # suggests:\n",
    "        # \"If RCAP_Current for the tract in which the site is located is 1, the tract is an R/ECAP. If RCAP_Current is 0, it is not.\"\n",
    "        \"RCAP_Current\": HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME,\n",
    "    },\n",
    "    inplace=True,\n",
    ")\n",
    "\n",
    "# Convert to boolean\n",
    "df[HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME] = df[\n",
    "    HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME\n",
    "].astype(\"bool\")\n",
    "\n",
    "df[HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME].value_counts()\n",
    "\n",
    "df.sort_values(by=GEOID_TRACT_FIELD_NAME, inplace=True)\n",
    "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",
    "# Drop unnecessary columns.\n",
    "df[[GEOID_TRACT_FIELD_NAME, HUD_RECAP_PRIORITY_COMMUNITY_FIELD_NAME]].to_csv(\n",
    "    CSV_PATH / \"usa.csv\", index=False\n",
    ")"
   ]
  }
 ],
 "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
}