{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Analyse de l'incidence de la varicelle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    " %matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import isoweek"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": true
   },
   "source": [
    " Les données de l'incidence de la varicelle sont disponibles du site Web du Réseau Sentinelles. Nous les récupérons sous forme d'un fichier en format CSV dont chaque ligne correspond à une semaine de la période demandée. Nous téléchargeons toujours le jeu de données complet, qui commence en 1984 et se termine avec une semaine récente."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-7.csv\"\n",
    "raw_data = pd.read_csv(data_url, encoding='iso-8859-1', skiprows=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     week  indicator    inc  inc_low  inc_up  inc100  inc100_low  inc100_up  \\\n",
      "0  202422          7  11317     7330   15304      17          11         23   \n",
      "1  202421          7   9807     6926   12688      15          11         19   \n",
      "2  202420          7  13661    10209   17113      20          15         25   \n",
      "3  202419          7  10083     6413   13753      15           9         21   \n",
      "4  202418          7  13438     9514   17362      20          14         26   \n",
      "\n",
      "  geo_insee geo_name  \n",
      "0        FR   France  \n",
      "1        FR   France  \n",
      "2        FR   France  \n",
      "3        FR   France  \n",
      "4        FR   France  \n"
     ]
    }
   ],
   "source": [
    "print(raw_data.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = raw_data.dropna().copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert_week(year_and_week_int):\n",
    "    year_and_week_str = str(year_and_week_int)\n",
    "    year = int(year_and_week_str[:4])\n",
    "    week = int(year_and_week_str[4:])\n",
    "    w = isoweek.Week(year, week)\n",
    "    return pd.Period(w.day(0), 'W')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "data['period'] = [convert_week(yw) for yw in data['week']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_data = data.set_index('period').sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "periods = sorted_data.index\n",
    "for p1, p2 in zip(periods[:-1], periods[1:]):\n",
    "    delta = p2.to_timestamp() - p1.end_time\n",
    "    if delta > pd.Timedelta('1s'):\n",
    "        print(p1, p2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_data['inc'].plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_data['inc'][-200:].plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "first_september_week = [pd.Period(pd.Timestamp(y, 9, 1), 'W')\n",
    "                     for y in range(1985, sorted_data.index[-1].year)]\n",
    "\n",
    "year = []\n",
    "yearly_incidence = []\n",
    "for week1, week2 in zip(first_august_week[:-1], first_august_week[1:]):\n",
    "    one_year = sorted_data['inc'][week1:week2-1]\n",
    "    assert abs(len(one_year)-52) < 2\n",
    "    yearly_incidence.append(one_year.sum())\n",
    "    year.append(week2.year)\n",
    "yearly_incidence = pd.Series(data=yearly_incidence, index=year)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "yearly_incidence.plot(style='*')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "yearly_incidence.sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "yearly_incidence.hist(xrot=20)"
   ]
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}