{
 "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",
    "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(manufacturer):\n",
    "    def read_csv(file):\n",
    "        return pd.read_csv(file, index_col='VAERS_ID', encoding='latin1', low_memory=False)\n",
    "        \n",
    "    def createPatients():\n",
    "        return pd.concat(\n",
    "            [\n",
    "                read_csv(\"VAERS/2021VAERSData/2021VAERSDATA.csv\"),\n",
    "                read_csv(\"VAERS/2022VAERSData/2022VAERSDATA.csv\")\n",
    "            ])\n",
    "\n",
    "    def createVax():    \n",
    "        return pd.concat(\n",
    "            [\n",
    "                read_csv(\"VAERS/2021VAERSData/2021VAERSVAX.csv\"),\n",
    "                read_csv(\"VAERS/2022VAERSData/2022VAERSVAX.csv\")\n",
    "            ])\n",
    "\n",
    "    df_patients_vax = pd.merge(createPatients(), createVax(), left_index=True, right_index=True)\n",
    "    return df_patients_vax[(df_patients_vax[\"VAX_TYPE\"] == \"COVID19\") & (df_patients_vax[\"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",
    "    return pd.concat(\n",
    "        {\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",
    "        axis=1)"
   ]
  },
  {
   "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": "fdf2ab4b",
   "metadata": {},
   "outputs": [],
   "source": [
    "pivotTable"
   ]
  }
 ],
 "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
}