COVID19-exposure.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import glob\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import math\n",
    "from functools import reduce\n",
    "from pandas.tseries.offsets import MonthEnd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "js = [json.load(open(f))['ExposureChecks'] for f in glob.glob(\"../COVID19/Exposure*.json\")]\n",
    "checks = reduce(lambda a, b: a + b, js)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(checks).drop_duplicates()\n",
    "df[\"year\"] = df.Timestamp.map(lambda x: pd.to_datetime(x).year)\n",
    "df[\"month\"] = df.Timestamp.map(lambda x: pd.to_datetime(x).month)\n",
    "df[\"day\"] = df.Timestamp.map(lambda x: pd.to_datetime(x).day)\n",
    "df.reset_index(drop=True)\n",
    "del df[\"DataSource\"]\n",
    "df[:1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#\n",
    "ym = df.groupby([\"year\", \"month\", \"day\"]).sum(\"RandomIDCount\")\n",
    "yms = pd.unique(pd.Series([e[0:2] for e in ym.index]))\n",
    "\n",
    "#\n",
    "def p(k):\n",
    "    s = pd.to_datetime(\"%d-%02d-01\" % k)\n",
    "    idx = [e.day for e in pd.date_range(s, s + MonthEnd(1))]\n",
    "    h = ym.loc[k]\n",
    "    g = h.reindex(index=idx, fill_value=0)\n",
    "#     g[\"MatchCount\"][15] = 1\n",
    "    return g\n",
    "\n",
    "dfs = [(p(k), k) for k in yms]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "R = 0.77\n",
    "s = len(dfs)\n",
    "t = math.ceil(s / 2)\n",
    "fig, axs = plt.subplots(t, 2, figsize=(16*R, 4*R*2))\n",
    "fig.tight_layout(pad=3.5)\n",
    "if s % 2 == 1:\n",
    "    fig.delaxes(axs[t-1, 1])\n",
    "maxRIC = pd.Series([e[0].RandomIDCount.max() for e in dfs]).max()\n",
    "\n",
    "\n",
    "def plot(idx, df, k):\n",
    "    ax = axs[int(idx/t),idx%2]\n",
    "    a = df.plot(kind=\"bar\", ax=ax, grid=True, colormap='Accent', y=\"RandomIDCount\")\n",
    "    right = a.twinx();\n",
    "    df.plot(ax=right, y=\"MatchCount\")\n",
    "#     a.legend(bbox_to_anchor=(0.4,0.8))\n",
    "    a.legend(loc='upper left')\n",
    "    a.set_title(\"%d-%02d\" % k)\n",
    "#     a.set_ylim([0, maxRIC*1.1])\n",
    "    right.set_ylim([0, 2])\n",
    "#     right.get_legend().remove()\n",
    "#     right.set_ylabel(\"MatchCount\")\n",
    "#     a.set_xlabel(\"day\")\n",
    "    return k\n",
    "\n",
    "[plot(i, e[0], e[1]) for i, e in enumerate(dfs)]"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}