{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9de5907f-18f5-4cb1-903e-26028ff1fa03",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "pd.set_option('display.max_rows', 100)\n",
    "pd.set_option('display.max_columns', None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "233bc590",
   "metadata": {},
   "outputs": [],
   "source": [
    "def createDataFrame(baseDir, manufacturer):\n",
    "    def read_csv(file, usecols):\n",
    "        return pd.read_csv(file, index_col='VAERS_ID', encoding='latin1', low_memory=False, usecols=usecols)\n",
    "        \n",
    "    def createDataFrameForYear(year):\n",
    "        folder = baseDir + \"/VAERS/\" + year + \"VAERSData/\"\n",
    "        return pd.merge(\n",
    "            read_csv(folder + year + \"VAERSDATA.csv\", ['VAERS_ID','DIED', 'L_THREAT', 'DISABLE']),\n",
    "            read_csv(folder + year + \"VAERSVAX.csv\", ['VAERS_ID','VAX_TYPE', 'VAX_MANU', 'VAX_LOT']),\n",
    "            left_index=True,\n",
    "            right_index=True)\n",
    "        \n",
    "    df = pd.concat([createDataFrameForYear(\"2021\"), createDataFrameForYear(\"2022\")])\n",
    "    return df[(df[\"VAX_TYPE\"] == \"COVID19\") & (df[\"VAX_MANU\"] == manufacturer)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99945ca8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def createPivotTable(df):\n",
    "    def filter(df, col):\n",
    "        return df[df[col] == 'Y'][['VAX_LOT']]\n",
    "\n",
    "    pivotTableDict = {\n",
    "        'ADRs': df[['VAX_LOT']].value_counts(),\n",
    "        'DEATHS': filter(df, 'DIED').value_counts(),\n",
    "        'DISABILITIES': filter(df, 'DISABLE').value_counts(),\n",
    "        'LIFE THREATENING ILLNESSES': filter(df, 'L_THREAT').value_counts()\n",
    "    }\n",
    "    return pd.concat(pivotTableDict, axis=1).replace(to_replace=np.nan, value=0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86e0e4f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_moderna = createDataFrame(\".\", \"MODERNA\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab170c16",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_moderna"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d9191d12",
   "metadata": {},
   "outputs": [],
   "source": [
    "pivotTable = createPivotTable(df_moderna)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bb7b2963",
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "pivotTable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f506ac8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import unittest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e14465d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pandas.testing import assert_frame_equal\n",
    "\n",
    "\n",
    "class HowBadIsMyBatchTest(unittest.TestCase):\n",
    "\n",
    "    def test_createPivotTable(self):\n",
    "        # Given\n",
    "        pivotTable = createPivotTable(createDataFrame(\"test\", \"MODERNA\"))\n",
    "\n",
    "        # When\n",
    "        pivotTableExpected = pd.DataFrame(\n",
    "            {\n",
    "                'ADRs': [2, 1],\n",
    "                'DEATHS': [0, 1],\n",
    "                'DISABILITIES': [2, 0],\n",
    "                'LIFE THREATENING ILLNESSES': [0.0, 0.0]\n",
    "            },\n",
    "            index=pd.MultiIndex.from_arrays([['025L20A', '037K20A']], names=('VAX_LOT',)))\n",
    "        display(\"actual:\", pivotTable)\n",
    "        display(\"expected:\", pivotTableExpected)\n",
    "\n",
    "        # Then\n",
    "        assert_frame_equal(pivotTable, pivotTableExpected, check_dtype=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef8f99c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "unittest.main(argv=[''], verbosity=2, exit=False)"
   ]
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}