{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Tech - manipulation de donn\u00e9es avec pandas\n", "\n", "[pandas](https://pandas.pydata.org/) est la librairie incontournable pour manipuler les donn\u00e9es. Elle permet de manipuler aussi bien les donn\u00e9es sous forme de tables qu'elle peut r\u00e9cup\u00e9rer ou exporter en diff\u00e9rents formats. Elle permet \u00e9galement de cr\u00e9er facilement des graphes."]}, {"cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [{"data": {"text/html": ["<div id=\"my_id_menu_nb\">run previous cell, wait for 2 seconds</div>\n", "<script>\n", "function repeat_indent_string(n){\n", "    var a = \"\" ;\n", "    for ( ; n > 0 ; --n)\n", "        a += \"    \";\n", "    return a;\n", "}\n", "// look up into all sections and builds an automated menu //\n", "var update_menu_string = function(begin, lfirst, llast, sformat, send, keep_item, begin_format, end_format) {\n", "    var anchors = document.getElementsByClassName(\"section\");\n", "    if (anchors.length == 0) {\n", "        anchors = document.getElementsByClassName(\"text_cell_render rendered_html\");\n", "    }\n", "    var i,t;\n", "    var text_menu = begin;\n", "    var text_memo = \"<pre>\\nlength:\" + anchors.length + \"\\n\";\n", "    var ind = \"\";\n", "    var memo_level = 1;\n", "    var href;\n", "    var tags = [];\n", "    var main_item = 0;\n", "    var format_open = 0;\n", "    for (i = 0; i <= llast; i++)\n", "        tags.push(\"h\" + i);\n", "\n", "    for (i = 0; i < anchors.length; i++) {\n", "        text_memo += \"**\" + anchors[i].id + \"--\\n\";\n", "\n", "        var child = null;\n", "        for(t = 0; t < tags.length; t++) {\n", "            var r = anchors[i].getElementsByTagName(tags[t]);\n", "            if (r.length > 0) {\n", "child = r[0];\n", "break;\n", "            }\n", "        }\n", "        if (child == null) {\n", "            text_memo += \"null\\n\";\n", "            continue;\n", "        }\n", "        if (anchors[i].hasAttribute(\"id\")) {\n", "            // when converted in RST\n", "            href = anchors[i].id;\n", "            text_memo += \"#1-\" + href;\n", "            // passer \u00e0 child suivant (le chercher)\n", "        }\n", "        else if (child.hasAttribute(\"id\")) {\n", "            // in a notebook\n", "            href = child.id;\n", "            text_memo += \"#2-\" + href;\n", "        }\n", "        else {\n", "            text_memo += \"#3-\" + \"*\" + \"\\n\";\n", "            continue;\n", "        }\n", "        var title = child.textContent;\n", "        var level = parseInt(child.tagName.substring(1,2));\n", "\n", "        text_memo += \"--\" + level + \"?\" + lfirst + \"--\" + title + \"\\n\";\n", "\n", "        if ((level < lfirst) || (level > llast)) {\n", "            continue ;\n", "        }\n", "        if (title.endsWith('\u00b6')) {\n", "            title = title.substring(0,title.length-1).replace(\"<\", \"&lt;\")\n", "         .replace(\">\", \"&gt;\").replace(\"&\", \"&amp;\");\n", "        }\n", "        if (title.length == 0) {\n", "            continue;\n", "        }\n", "\n", "        while (level < memo_level) {\n", "            text_menu += end_format + \"</ul>\\n\";\n", "            format_open -= 1;\n", "            memo_level -= 1;\n", "        }\n", "        if (level == lfirst) {\n", "            main_item += 1;\n", "        }\n", "        if (keep_item != -1 && main_item != keep_item + 1) {\n", "            // alert(main_item + \" - \" + level + \" - \" + keep_item);\n", "            continue;\n", "        }\n", "        while (level > memo_level) {\n", "            text_menu += \"<ul>\\n\";\n", "            memo_level += 1;\n", "        }\n", "        text_menu += repeat_indent_string(level-2);\n", "        text_menu += begin_format + sformat.replace(\"__HREF__\", href).replace(\"__TITLE__\", title);\n", "        format_open += 1;\n", "    }\n", "    while (1 < memo_level) {\n", "        text_menu += end_format + \"</ul>\\n\";\n", "        memo_level -= 1;\n", "        format_open -= 1;\n", "    }\n", "    text_menu += send;\n", "    //text_menu += \"\\n\" + text_memo;\n", "\n", "    while (format_open > 0) {\n", "        text_menu += end_format;\n", "        format_open -= 1;\n", "    }\n", "    return text_menu;\n", "};\n", "var update_menu = function() {\n", "    var sbegin = \"\";\n", "    var sformat = '<a href=\"#__HREF__\">__TITLE__</a>';\n", "    var send = \"\";\n", "    var begin_format = '<li>';\n", "    var end_format = '</li>';\n", "    var keep_item = -1;\n", "    var text_menu = update_menu_string(sbegin, 2, 4, sformat, send, keep_item,\n", "       begin_format, end_format);\n", "    var menu = document.getElementById(\"my_id_menu_nb\");\n", "    menu.innerHTML=text_menu;\n", "};\n", "window.setTimeout(update_menu,2000);\n", "            </script>"], "text/plain": ["<IPython.core.display.HTML object>"]}, "execution_count": 2, "metadata": {}, "output_type": "execute_result"}], "source": ["from jyquickhelper import add_notebook_menu\n", "add_notebook_menu()"]}, {"cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": ["%matplotlib inline"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Enonc\u00e9\n", "\n", "La librairie [pandas](https://pandas.pydata.org/) impl\u00e9mente la classe [DataFrame](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html). C'est une structure de table, chaque colonne porte un nom et contient un seul type de donn\u00e9es. C'est tr\u00e8s similaire au langage [SQL](https://fr.wikipedia.org/wiki/Structured_Query_Language)."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Cr\u00e9ation d'un dataframe\n", "\n", "Il existe une grande vari\u00e9t\u00e9 pour cr\u00e9er un DataFrame. Voici les deux principaux. Le premier : une liste de dictionnaires. Chaque cl\u00e9 est le nom de la colonne."]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>schtroumph</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>schtroumphette</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1            col2\n", "0   0.5      schtroumph\n", "1   0.6  schtroumphette"]}, "execution_count": 4, "metadata": {}, "output_type": "execute_result"}], "source": ["from pandas import DataFrame\n", "\n", "rows = [{'col1': 0.5, 'col2': 'schtroumph'},\n", "        {'col1': 0.6, 'col2': 'schtroumphette'}]\n", "DataFrame(rows)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["La lecture depuis un fichier :"]}, {"cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["Overwriting data.csv\n"]}], "source": ["%%writefile data.csv\n", "\n", "col1,col2\n", "0.5,alpha\n", "0.6,beta"]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [{"data": {"text/plain": ["'C:\\\\xavierdupre\\\\__home_\\\\GitHub\\\\ensae_teaching_cs\\\\_doc\\\\notebooks\\\\td1a_home'"]}, "execution_count": 6, "metadata": {}, "output_type": "execute_result"}], "source": ["import os\n", "os.getcwd()"]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1   col2\n", "0   0.5  alpha\n", "1   0.6   beta"]}, "execution_count": 7, "metadata": {}, "output_type": "execute_result"}], "source": ["from pandas import read_csv\n", "df = read_csv('data.csv')\n", "df"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise des index\n", "\n", "Les index fonctionnent \u00e0 peu pr\u00e8s comme [numpy](https://numpy.org/) mais offre plus d'options puisque les colonnes mais aussi les lignes ont un nom.\n", "\n", "Acc\u00e8s par colonne"]}, {"cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1   col2\n", "0   0.5  alpha\n", "1   0.6   beta"]}, "execution_count": 8, "metadata": {}, "output_type": "execute_result"}], "source": ["df"]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [{"data": {"text/plain": ["0    0.5\n", "1    0.6\n", "Name: col1, dtype: float64"]}, "execution_count": 9, "metadata": {}, "output_type": "execute_result"}], "source": ["df['col1']"]}, {"cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1   col2\n", "0   0.5  alpha\n", "1   0.6   beta"]}, "execution_count": 10, "metadata": {}, "output_type": "execute_result"}], "source": ["df[['col1', 'col2']]"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Acc\u00e8s par ligne (uniquement avec ``:``). On se sert principalement de l'op\u00e9rateur ``:`` pour les lignes."]}, {"cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1   col2\n", "0   0.5  alpha"]}, "execution_count": 11, "metadata": {}, "output_type": "execute_result"}], "source": ["df[:1]"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Acc\u00e8s par positions avec [loc](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.loc.html)."]}, {"cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.5"]}, "execution_count": 12, "metadata": {}, "output_type": "execute_result"}], "source": ["df.loc[0, 'col1']"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Acc\u00e8s par positions enti\u00e8res avec [iloc](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.iloc.html)."]}, {"cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.5"]}, "execution_count": 13, "metadata": {}, "output_type": "execute_result"}], "source": ["df.iloc[0, 0]"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise des index des lignes\n", "\n", "La cr\u00e9ation d'un dataframe donne l'impression que les index des lignes sont des entiers mais cela peut \u00eatre changer"]}, {"cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1   col2\n", "0   0.5  alpha\n", "1   0.6   beta"]}, "execution_count": 14, "metadata": {}, "output_type": "execute_result"}], "source": ["df"]}, {"cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "    </tr>\n", "    <tr>\n", "      <th>col2</th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>alpha</th>\n", "      <td>0.5</td>\n", "    </tr>\n", "    <tr>\n", "      <th>beta</th>\n", "      <td>0.6</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["       col1\n", "col2       \n", "alpha   0.5\n", "beta    0.6"]}, "execution_count": 15, "metadata": {}, "output_type": "execute_result"}], "source": ["dfi = df.set_index('col2')\n", "dfi"]}, {"cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [{"data": {"text/plain": ["0.5"]}, "execution_count": 16, "metadata": {}, "output_type": "execute_result"}], "source": ["dfi.loc['alpha', 'col1']"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Il faut se souvenir de cette particularit\u00e9 lors de la fusion de tables."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise des index des colonnes\n", "\n", "Les colonnes sont nomm\u00e9es."]}, {"cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [{"data": {"text/plain": ["Index(['col1', 'col2'], dtype='object')"]}, "execution_count": 17, "metadata": {}, "output_type": "execute_result"}], "source": ["df.columns"]}, {"cell_type": "markdown", "metadata": {}, "source": ["On peut les renommer."]}, {"cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom\n", "0     0.5  alpha\n", "1     0.6   beta"]}, "execution_count": 18, "metadata": {}, "output_type": "execute_result"}], "source": ["df.columns = [\"valeur\", \"nom\"]\n", "df"]}, {"cell_type": "markdown", "metadata": {}, "source": ["L'op\u00e9rateur ``:`` peut \u00e9galement servir pour les colonnes."]}, {"cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom\n", "0     0.5  alpha\n", "1     0.6   beta"]}, "execution_count": 19, "metadata": {}, "output_type": "execute_result"}], "source": ["df.loc[:, 'valeur':'nom']"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Lien vers numpy\n", "\n", "[pandas](https://pandas.pydata.org/) utilise [numpy](https://numpy.org/) pour stocker les donn\u00e9es. Il est possible de r\u00e9cup\u00e9rer des matrices depuis des DataFrame avec [values](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.values.html)."]}, {"cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [{"data": {"text/plain": ["array([[0.5, 'alpha'],\n", "       [0.6, 'beta']], dtype=object)"]}, "execution_count": 20, "metadata": {}, "output_type": "execute_result"}], "source": ["df.values"]}, {"cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [{"data": {"text/plain": ["array([[0.5],\n", "       [0.6]])"]}, "execution_count": 21, "metadata": {}, "output_type": "execute_result"}], "source": ["df[['valeur']].values"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise du nan\n", "\n", "[nan](https://numpy.org/doc/stable/reference/constants.html) est une convention pour d\u00e9signer une valeur manquante."]}, {"cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>schtroumph</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>NaN</td>\n", "      <td>schtroumphette</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1            col2\n", "0   0.5      schtroumph\n", "1   NaN  schtroumphette"]}, "execution_count": 22, "metadata": {}, "output_type": "execute_result"}], "source": ["rows = [{'col1': 0.5, 'col2': 'schtroumph'},\n", "        {'col2': 'schtroumphette'}]\n", "DataFrame(rows)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise des types\n", "\n", "Un dataframe est d\u00e9fini par ses dimensions et chaque colonne a un type potentiellement diff\u00e9rent."]}, {"cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [{"data": {"text/plain": ["valeur    float64\n", "nom        object\n", "dtype: object"]}, "execution_count": 23, "metadata": {}, "output_type": "execute_result"}], "source": ["df.dtypes"]}, {"cell_type": "markdown", "metadata": {}, "source": ["On peut changer un type, donc convertir toutes les valeurs d'une colonne vers un autre type."]}, {"cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [{"data": {"text/plain": ["0    0.5\n", "1    0.6\n", "Name: valeur, dtype: float32"]}, "execution_count": 24, "metadata": {}, "output_type": "execute_result"}], "source": ["import numpy\n", "df['valeur'].astype(numpy.float32)"]}, {"cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [{"data": {"text/plain": ["0    0\n", "1    0\n", "Name: valeur, dtype: int32"]}, "execution_count": 25, "metadata": {}, "output_type": "execute_result"}], "source": ["import numpy\n", "df['valeur'].astype(numpy.int32)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Cr\u00e9ation de colonnes\n", "\n", "On peut facilement cr\u00e9er de nouvelles colonnes."]}, {"cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "      <th>sup055</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "      <td>False</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "      <td>True</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom  sup055\n", "0     0.5  alpha   False\n", "1     0.6   beta    True"]}, "execution_count": 26, "metadata": {}, "output_type": "execute_result"}], "source": ["df['sup055'] = df['valeur'] >= 0.55\n", "df"]}, {"cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "      <th>sup055</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "      <td>0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "      <td>1</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom  sup055\n", "0     0.5  alpha       0\n", "1     0.6   beta       1"]}, "execution_count": 27, "metadata": {}, "output_type": "execute_result"}], "source": ["df['sup055'] = (df['valeur'] >= 0.55).astype(numpy.int64)\n", "df"]}, {"cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "      <th>sup055</th>\n", "      <th>sup055+</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "      <td>0</td>\n", "      <td>0.5</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "      <td>1</td>\n", "      <td>1.6</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom  sup055  sup055+\n", "0     0.5  alpha       0      0.5\n", "1     0.6   beta       1      1.6"]}, "execution_count": 28, "metadata": {}, "output_type": "execute_result"}], "source": ["df['sup055+'] = df['valeur'] + df['sup055']\n", "df"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Modifications de valeurs\n", "\n", "On peut les modifier une \u00e0 une en utilisant les index. Les notations sont souvent intuitives. Elles ne seront pas toutes d\u00e9taill\u00e9es. Ci-dessous un moyen de modifer certaines valeurs selon une condition."]}, {"cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>valeur</th>\n", "      <th>nom</th>\n", "      <th>sup055</th>\n", "      <th>sup055+</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>alpha</td>\n", "      <td>0</td>\n", "      <td>1000.5</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>0.6</td>\n", "      <td>beta</td>\n", "      <td>1</td>\n", "      <td>1.6</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   valeur    nom  sup055  sup055+\n", "0     0.5  alpha       0   1000.5\n", "1     0.6   beta       1      1.6"]}, "execution_count": 29, "metadata": {}, "output_type": "execute_result"}], "source": ["df.loc[df['nom'] == 'alpha', 'sup055+'] += 1000\n", "df"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Une erreur ou warning fr\u00e9quent"]}, {"cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>0.5</td>\n", "      <td>schtroumph</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>1.5</td>\n", "      <td>schtroumphette</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1            col2\n", "0   0.5      schtroumph\n", "1   1.5  schtroumphette"]}, "execution_count": 30, "metadata": {}, "output_type": "execute_result"}], "source": ["rows = [{'col1': 0.5, 'col2': 'schtroumph'},\n", "        {'col1': 1.5, 'col2': 'schtroumphette'}]\n", "df = DataFrame(rows)\n", "df"]}, {"cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>1.5</td>\n", "      <td>schtroumphette</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1            col2\n", "1   1.5  schtroumphette"]}, "execution_count": 31, "metadata": {}, "output_type": "execute_result"}], "source": ["df1 = df[df['col1'] > 1.]\n", "df1"]}, {"cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["<ipython-input-31-e5d64c4890f8>:1: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", "  df1[\"col3\"] = df1[\"col1\"] + 1.\n"]}, {"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>col1</th>\n", "      <th>col2</th>\n", "      <th>col3</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>1.5</td>\n", "      <td>schtroumphette</td>\n", "      <td>2.5</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   col1            col2  col3\n", "1   1.5  schtroumphette   2.5"]}, "execution_count": 32, "metadata": {}, "output_type": "execute_result"}], "source": ["df1[\"col3\"] = df1[\"col1\"] + 1.\n", "df1"]}, {"cell_type": "markdown", "metadata": {}, "source": ["``A value is trying to be set on a copy of a slice from a DataFrame.`` : Par d\u00e9faut, l'instruction ``df[df['col1'] > 1.]`` ne cr\u00e9e pas un nouveau DataFrame, elle cr\u00e9e ce qu'on appelle une vue pour \u00e9viter de copier les donn\u00e9es. Le r\u00e9sultat ne contient que l'index des lignes qui ont \u00e9t\u00e9 s\u00e9lectionn\u00e9es et un lien vers le dataframe original. L'avertissement stipule que *pandas* ne peut pas modifier le dataframe original mais qu'il doit effectuer une copie."]}, {"cell_type": "markdown", "metadata": {}, "source": ["La solution pour faire dispara\u00eetre ce warning est de copier le dataframe."]}, {"cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": ["df2 = df1.copy()\n", "df2[\"col3\"] = df2[\"col1\"] + 1."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### La ma\u00eetrise des fonctions\n", "\n", "Les fonctions de pandas cr\u00e9ent par d\u00e9faut un nouveau dataframe plut\u00f4t que de modifier un dataframe existant. Cela explique pourquoi parfois la m\u00e9moire se retrouve congestionn\u00e9e. La page [10 minutes to pandas](https://pandas.pydata.org/pandas-docs/stable/user_guide/10min.html) est un bon d\u00e9but.\n", "\n", "* **cr\u00e9ation** : [read_csv](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.read_csv.html), [read_excel](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.read_excel.html)\n", "* **index** : [set_index](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.set_index.html), [reset_index](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.reset_index.html)\n", "* **utilitaires** : [astype](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.astype.html), [isna](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.isna.html), [fillna](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.fillna.html), [to_datetime](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.to_datetime.html), [dtypes](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.dtypes.html), [shape](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.shape.html), [values](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.values.html), [head](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.head.html), [tail](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.tail.html), [isin](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.isin.html), [T](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.T.html), [drop](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.drop.html)\n", "* **concat\u00e9nation** : [concat](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.concat.html)\n", "* **SQL** : [filter](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.filter.html), [groupby](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.groupby.html), [join](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.join.html), [merge](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.merge.html), [pivot](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.pivot.html), [pivot_table](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.pivot_table.html)\n", "* **calcul** : [sum](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.sum.html), [cumsum](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.cumsum.html), [quantile](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.quantile.html), [var](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.var.html)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### On r\u00e9cup\u00e8re les donn\u00e9es du COVID par r\u00e9gion et par \u00e2ge et premier graphe\n", "\n", "A cette adresse : [Donn\u00e9es hospitali\u00e8res relatives \u00e0 l'\u00e9pid\u00e9mie de COVID-19](https://www.data.gouv.fr/en/datasets/donnees-hospitalieres-relatives-a-lepidemie-de-covid-19/)"]}, {"cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>reg</th>\n", "      <th>cl_age90</th>\n", "      <th>jour</th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>108697</th>\n", "      <td>94</td>\n", "      <td>59</td>\n", "      <td>2021-09-17</td>\n", "      <td>6</td>\n", "      <td>0</td>\n", "      <td>3.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>183</td>\n", "      <td>8</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108698</th>\n", "      <td>94</td>\n", "      <td>69</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>3</td>\n", "      <td>4.0</td>\n", "      <td>2.0</td>\n", "      <td>2.0</td>\n", "      <td>219</td>\n", "      <td>23</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108699</th>\n", "      <td>94</td>\n", "      <td>79</td>\n", "      <td>2021-09-17</td>\n", "      <td>8</td>\n", "      <td>1</td>\n", "      <td>5.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>245</td>\n", "      <td>56</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108700</th>\n", "      <td>94</td>\n", "      <td>89</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>1</td>\n", "      <td>8.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>220</td>\n", "      <td>91</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108701</th>\n", "      <td>94</td>\n", "      <td>90</td>\n", "      <td>2021-09-17</td>\n", "      <td>7</td>\n", "      <td>0</td>\n", "      <td>4.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>88</td>\n", "      <td>50</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        reg  cl_age90        jour  hosp  rea  HospConv  SSR_USLD  autres  rad  \\\n", "108697   94        59  2021-09-17     6    0       3.0       3.0     0.0  183   \n", "108698   94        69  2021-09-17    11    3       4.0       2.0     2.0  219   \n", "108699   94        79  2021-09-17     8    1       5.0       2.0     0.0  245   \n", "108700   94        89  2021-09-17    11    1       8.0       2.0     0.0  220   \n", "108701   94        90  2021-09-17     7    0       4.0       3.0     0.0   88   \n", "\n", "        dc  \n", "108697   8  \n", "108698  23  \n", "108699  56  \n", "108700  91  \n", "108701  50  "]}, "execution_count": 34, "metadata": {}, "output_type": "execute_result"}], "source": ["# https://www.data.gouv.fr/en/datasets/r/63352e38-d353-4b54-bfd1-f1b3ee1cabd7\n", "from pandas import read_csv\n", "url = \"https://www.data.gouv.fr/en/datasets/r/08c18e08-6780-452d-9b8c-ae244ad529b3\"\n", "covid = read_csv(url, sep=\";\")\n", "covid.tail()"]}, {"cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [{"data": {"text/plain": ["reg           int64\n", "cl_age90      int64\n", "jour         object\n", "hosp          int64\n", "rea           int64\n", "HospConv    float64\n", "SSR_USLD    float64\n", "autres      float64\n", "rad           int64\n", "dc            int64\n", "dtype: object"]}, "execution_count": 35, "metadata": {}, "output_type": "execute_result"}], "source": ["covid.dtypes"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Les dates sont consid\u00e9r\u00e9es comme des cha\u00eenes de caract\u00e8res. Il est plus simple pour r\u00e9aliser des op\u00e9rations de convertir la colonne sous forme de dates."]}, {"cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>reg</th>\n", "      <th>cl_age90</th>\n", "      <th>jour</th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>108697</th>\n", "      <td>94</td>\n", "      <td>59</td>\n", "      <td>2021-09-17</td>\n", "      <td>6</td>\n", "      <td>0</td>\n", "      <td>3.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>183</td>\n", "      <td>8</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108698</th>\n", "      <td>94</td>\n", "      <td>69</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>3</td>\n", "      <td>4.0</td>\n", "      <td>2.0</td>\n", "      <td>2.0</td>\n", "      <td>219</td>\n", "      <td>23</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108699</th>\n", "      <td>94</td>\n", "      <td>79</td>\n", "      <td>2021-09-17</td>\n", "      <td>8</td>\n", "      <td>1</td>\n", "      <td>5.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>245</td>\n", "      <td>56</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108700</th>\n", "      <td>94</td>\n", "      <td>89</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>1</td>\n", "      <td>8.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>220</td>\n", "      <td>91</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108701</th>\n", "      <td>94</td>\n", "      <td>90</td>\n", "      <td>2021-09-17</td>\n", "      <td>7</td>\n", "      <td>0</td>\n", "      <td>4.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>88</td>\n", "      <td>50</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        reg  cl_age90       jour  hosp  rea  HospConv  SSR_USLD  autres  rad  \\\n", "108697   94        59 2021-09-17     6    0       3.0       3.0     0.0  183   \n", "108698   94        69 2021-09-17    11    3       4.0       2.0     2.0  219   \n", "108699   94        79 2021-09-17     8    1       5.0       2.0     0.0  245   \n", "108700   94        89 2021-09-17    11    1       8.0       2.0     0.0  220   \n", "108701   94        90 2021-09-17     7    0       4.0       3.0     0.0   88   \n", "\n", "        dc  \n", "108697   8  \n", "108698  23  \n", "108699  56  \n", "108700  91  \n", "108701  50  "]}, "execution_count": 36, "metadata": {}, "output_type": "execute_result"}], "source": ["from pandas import to_datetime\n", "covid['jour'] = to_datetime(covid['jour'])\n", "covid.tail()"]}, {"cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [{"data": {"text/plain": ["reg                  int64\n", "cl_age90             int64\n", "jour        datetime64[ns]\n", "hosp                 int64\n", "rea                  int64\n", "HospConv           float64\n", "SSR_USLD           float64\n", "autres             float64\n", "rad                  int64\n", "dc                   int64\n", "dtype: object"]}, "execution_count": 37, "metadata": {}, "output_type": "execute_result"}], "source": ["covid.dtypes"]}, {"cell_type": "markdown", "metadata": {}, "source": ["On supprime les colonnes relatives aux r\u00e9gions et \u00e0 l'\u00e2ge puis on aggr\u00e8ge par jour."]}, {"cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "    <tr>\n", "      <th>jour</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2021-09-13</th>\n", "      <td>19929</td>\n", "      <td>4202</td>\n", "      <td>9829.0</td>\n", "      <td>5408.0</td>\n", "      <td>490.0</td>\n", "      <td>825603</td>\n", "      <td>177260</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-14</th>\n", "      <td>19433</td>\n", "      <td>3996</td>\n", "      <td>9552.0</td>\n", "      <td>5383.0</td>\n", "      <td>502.0</td>\n", "      <td>827024</td>\n", "      <td>177450</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-15</th>\n", "      <td>19065</td>\n", "      <td>3914</td>\n", "      <td>9264.0</td>\n", "      <td>5385.0</td>\n", "      <td>502.0</td>\n", "      <td>828103</td>\n", "      <td>177604</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-16</th>\n", "      <td>18550</td>\n", "      <td>3900</td>\n", "      <td>8769.0</td>\n", "      <td>5379.0</td>\n", "      <td>502.0</td>\n", "      <td>829146</td>\n", "      <td>177733</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-17</th>\n", "      <td>18096</td>\n", "      <td>3777</td>\n", "      <td>8472.0</td>\n", "      <td>5347.0</td>\n", "      <td>500.0</td>\n", "      <td>830154</td>\n", "      <td>177866</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["             hosp   rea  HospConv  SSR_USLD  autres     rad      dc\n", "jour                                                               \n", "2021-09-13  19929  4202    9829.0    5408.0   490.0  825603  177260\n", "2021-09-14  19433  3996    9552.0    5383.0   502.0  827024  177450\n", "2021-09-15  19065  3914    9264.0    5385.0   502.0  828103  177604\n", "2021-09-16  18550  3900    8769.0    5379.0   502.0  829146  177733\n", "2021-09-17  18096  3777    8472.0    5347.0   500.0  830154  177866"]}, "execution_count": 38, "metadata": {}, "output_type": "execute_result"}], "source": ["agg_par_jour = covid.drop(['reg', 'cl_age90'], axis=1).groupby('jour').sum()\n", "agg_par_jour.tail()"]}, {"cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["agg_par_jour.plot(title=\"Evolution des hospitalisations par jour\",\n", "                  figsize=(14, 4));"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Avec \u00e9chelle logarithmique."]}, {"cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["agg_par_jour.plot(title=\"Evolution des hospitalisations par jour\",\n", "                  figsize=(14, 4), logy=True);"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q1 : refaire le graphique pr\u00e9c\u00e9dent pour votre classe d'\u00e2ge"]}, {"cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q2 : faire de m\u00eame avec les s\u00e9ries diff\u00e9renci\u00e9es"]}, {"cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q3 : faire de m\u00eame avec des s\u00e9ries liss\u00e9es sur sur 7 jours"]}, {"cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q4 : fusion de tables par d\u00e9partements"]}, {"cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["## R\u00e9ponses"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q1 : refaire le graphique pr\u00e9c\u00e9dent pour votre classe d'\u00e2ge"]}, {"cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [{"data": {"text/plain": ["{0, 9, 19, 29, 39, 49, 59, 69, 79, 89, 90}"]}, "execution_count": 45, "metadata": {}, "output_type": "execute_result"}], "source": ["set(covid['cl_age90'])"]}, {"cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "    <tr>\n", "      <th>jour</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2021-09-13</th>\n", "      <td>730</td>\n", "      <td>239</td>\n", "      <td>371.0</td>\n", "      <td>86.0</td>\n", "      <td>34.0</td>\n", "      <td>34875</td>\n", "      <td>942</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-14</th>\n", "      <td>695</td>\n", "      <td>225</td>\n", "      <td>347.0</td>\n", "      <td>87.0</td>\n", "      <td>36.0</td>\n", "      <td>34969</td>\n", "      <td>945</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-15</th>\n", "      <td>659</td>\n", "      <td>220</td>\n", "      <td>317.0</td>\n", "      <td>86.0</td>\n", "      <td>36.0</td>\n", "      <td>35044</td>\n", "      <td>946</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-16</th>\n", "      <td>632</td>\n", "      <td>215</td>\n", "      <td>295.0</td>\n", "      <td>86.0</td>\n", "      <td>36.0</td>\n", "      <td>35096</td>\n", "      <td>947</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-17</th>\n", "      <td>622</td>\n", "      <td>207</td>\n", "      <td>294.0</td>\n", "      <td>86.0</td>\n", "      <td>35.0</td>\n", "      <td>35144</td>\n", "      <td>949</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["            hosp  rea  HospConv  SSR_USLD  autres    rad   dc\n", "jour                                                         \n", "2021-09-13   730  239     371.0      86.0    34.0  34875  942\n", "2021-09-14   695  225     347.0      87.0    36.0  34969  945\n", "2021-09-15   659  220     317.0      86.0    36.0  35044  946\n", "2021-09-16   632  215     295.0      86.0    36.0  35096  947\n", "2021-09-17   622  207     294.0      86.0    35.0  35144  949"]}, "execution_count": 46, "metadata": {}, "output_type": "execute_result"}], "source": ["covid49 = covid[covid.cl_age90 == 49]\n", "agg_par_jour49 = covid49.drop(['reg', 'cl_age90'], axis=1).groupby('jour').sum()\n", "agg_par_jour49.tail()"]}, {"cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["agg_par_jour49.plot(title=\"Evolution des hospitalisations par jour\\nage=49\",\n", "                    figsize=(14, 4), logy=True);"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q2 : faire de m\u00eame avec les s\u00e9ries diff\u00e9renci\u00e9es"]}, {"cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>reg</th>\n", "      <th>cl_age90</th>\n", "      <th>jour</th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>108697</th>\n", "      <td>94</td>\n", "      <td>59</td>\n", "      <td>2021-09-17</td>\n", "      <td>6</td>\n", "      <td>0</td>\n", "      <td>3.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>183</td>\n", "      <td>8</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108698</th>\n", "      <td>94</td>\n", "      <td>69</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>3</td>\n", "      <td>4.0</td>\n", "      <td>2.0</td>\n", "      <td>2.0</td>\n", "      <td>219</td>\n", "      <td>23</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108699</th>\n", "      <td>94</td>\n", "      <td>79</td>\n", "      <td>2021-09-17</td>\n", "      <td>8</td>\n", "      <td>1</td>\n", "      <td>5.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>245</td>\n", "      <td>56</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108700</th>\n", "      <td>94</td>\n", "      <td>89</td>\n", "      <td>2021-09-17</td>\n", "      <td>11</td>\n", "      <td>1</td>\n", "      <td>8.0</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>220</td>\n", "      <td>91</td>\n", "    </tr>\n", "    <tr>\n", "      <th>108701</th>\n", "      <td>94</td>\n", "      <td>90</td>\n", "      <td>2021-09-17</td>\n", "      <td>7</td>\n", "      <td>0</td>\n", "      <td>4.0</td>\n", "      <td>3.0</td>\n", "      <td>0.0</td>\n", "      <td>88</td>\n", "      <td>50</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        reg  cl_age90       jour  hosp  rea  HospConv  SSR_USLD  autres  rad  \\\n", "108697   94        59 2021-09-17     6    0       3.0       3.0     0.0  183   \n", "108698   94        69 2021-09-17    11    3       4.0       2.0     2.0  219   \n", "108699   94        79 2021-09-17     8    1       5.0       2.0     0.0  245   \n", "108700   94        89 2021-09-17    11    1       8.0       2.0     0.0  220   \n", "108701   94        90 2021-09-17     7    0       4.0       3.0     0.0   88   \n", "\n", "        dc  \n", "108697   8  \n", "108698  23  \n", "108699  56  \n", "108700  91  \n", "108701  50  "]}, "execution_count": 48, "metadata": {}, "output_type": "execute_result"}], "source": ["covid.tail()"]}, {"cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "    <tr>\n", "      <th>jour</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2021-09-16</th>\n", "      <td>-515.0</td>\n", "      <td>-14.0</td>\n", "      <td>-495.0</td>\n", "      <td>-6.0</td>\n", "      <td>0.0</td>\n", "      <td>1043.0</td>\n", "      <td>129.0</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-17</th>\n", "      <td>-454.0</td>\n", "      <td>-123.0</td>\n", "      <td>-297.0</td>\n", "      <td>-32.0</td>\n", "      <td>-2.0</td>\n", "      <td>1008.0</td>\n", "      <td>133.0</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["             hosp    rea  HospConv  SSR_USLD  autres     rad     dc\n", "jour                                                               \n", "2021-09-16 -515.0  -14.0    -495.0      -6.0     0.0  1043.0  129.0\n", "2021-09-17 -454.0 -123.0    -297.0     -32.0    -2.0  1008.0  133.0"]}, "execution_count": 49, "metadata": {}, "output_type": "execute_result"}], "source": ["diff = covid.drop(['reg', 'cl_age90'], axis=1).groupby(\n", "    ['jour']).sum().diff()\n", "diff.tail(n=2)"]}, {"cell_type": "code", "execution_count": 49, "metadata": {"scrolled": false}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["diff.plot(title=\"S\u00e9ries diff\u00e9renci\u00e9es\", figsize=(14, 4));"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q3 : faire de m\u00eame avec des s\u00e9ries liss\u00e9es sur sur 7 jours"]}, {"cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [{"data": {"text/plain": ["Rolling [window=7,center=False,axis=0,method=single]"]}, "execution_count": 51, "metadata": {}, "output_type": "execute_result"}], "source": ["diff.rolling(7)"]}, {"cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "    <tr>\n", "      <th>jour</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2021-09-16</th>\n", "      <td>-292.428571</td>\n", "      <td>-68.857143</td>\n", "      <td>-217.285714</td>\n", "      <td>-5.428571</td>\n", "      <td>-0.857143</td>\n", "      <td>933.571429</td>\n", "      <td>135.857143</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-17</th>\n", "      <td>-298.000000</td>\n", "      <td>-74.000000</td>\n", "      <td>-209.571429</td>\n", "      <td>-13.857143</td>\n", "      <td>-0.571429</td>\n", "      <td>904.714286</td>\n", "      <td>132.285714</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["                  hosp        rea    HospConv   SSR_USLD    autres  \\\n", "jour                                                                 \n", "2021-09-16 -292.428571 -68.857143 -217.285714  -5.428571 -0.857143   \n", "2021-09-17 -298.000000 -74.000000 -209.571429 -13.857143 -0.571429   \n", "\n", "                   rad          dc  \n", "jour                                \n", "2021-09-16  933.571429  135.857143  \n", "2021-09-17  904.714286  132.285714  "]}, "execution_count": 52, "metadata": {}, "output_type": "execute_result"}], "source": ["roll = diff.rolling(7).mean()\n", "roll.tail(n=2)"]}, {"cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["roll.plot(title=\"S\u00e9ries diff\u00e9renci\u00e9es liss\u00e9es\", figsize=(14, 4));"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Petit apart\u00e9\n", "\n", "On veut savoir combien de temps les gens restent \u00e0 l'h\u00f4pital avant de sortir, en supposant que le temps de gu\u00e9rison est \u00e0 peu pr\u00e8s identique au temps pass\u00e9 lorsque l'issue est tout autre. Je pensais calculer les corr\u00e9lations entre la s\u00e9rie des d\u00e9c\u00e8s et celles de r\u00e9animations d\u00e9cal\u00e9es de plusieurs jours en me disant qu'un pic de corr\u00e9lation pourrait indiquer une sorte de dur\u00e9e moyenne de r\u00e9animation."]}, {"cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "    <tr>\n", "      <th>jour</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2021-09-16</th>\n", "      <td>-22.857143</td>\n", "      <td>-7.285714</td>\n", "      <td>-16.142857</td>\n", "      <td>0.142857</td>\n", "      <td>0.428571</td>\n", "      <td>59.714286</td>\n", "      <td>1.285714</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2021-09-17</th>\n", "      <td>-17.857143</td>\n", "      <td>-6.000000</td>\n", "      <td>-12.000000</td>\n", "      <td>0.000000</td>\n", "      <td>0.142857</td>\n", "      <td>54.571429</td>\n", "      <td>1.571429</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["                 hosp       rea   HospConv  SSR_USLD    autres        rad  \\\n", "jour                                                                        \n", "2021-09-16 -22.857143 -7.285714 -16.142857  0.142857  0.428571  59.714286   \n", "2021-09-17 -17.857143 -6.000000 -12.000000  0.000000  0.142857  54.571429   \n", "\n", "                  dc  \n", "jour                  \n", "2021-09-16  1.285714  \n", "2021-09-17  1.571429  "]}, "execution_count": 54, "metadata": {}, "output_type": "execute_result"}], "source": ["data = agg_par_jour49.diff().rolling(7).mean()\n", "data.tail(n=2)"]}, {"cell_type": "code", "execution_count": 54, "metadata": {"scrolled": false}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 432x288 with 1 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["data_last = data.tail(n=90)\n", "cor = []\n", "for i in range(0, 35):\n", "    ts = DataFrame(dict(rea=data_last.rea, dc=data_last.dc,\n", "                        dclag=data_last[\"dc\"].shift(i),\n", "                        realag=data_last[\"rea\"].shift(i)))\n", "    ts_cor = ts.corr()\n", "    cor.append(dict(delay=i, corr_dc=ts_cor.iloc[1, 3],\n", "                    corr_rea=ts_cor.iloc[0, 3]))\n", "DataFrame(cor).set_index('delay').plot(title=\"Corr\u00e9lation entre d\u00e9c\u00e8s et r\u00e9animation\");"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Il appara\u00eet que ces corr\u00e9lations sont tr\u00e8s diff\u00e9rentes selon qu'on les calcule sur les derni\u00e8res donn\u00e9es et les premi\u00e8res semaines. Cela semblerait indiquer que les donn\u00e9es m\u00e9dicales sont tr\u00e8s diff\u00e9rentes. On pourrait chercher plusieurs jours mais le plus simple serait sans de g\u00e9n\u00e9rer des donn\u00e9es artificielles avec un mod\u00e8le [SIR](https://fr.wikipedia.org/wiki/Mod%C3%A8les_compartimentaux_en_%C3%A9pid%C3%A9miologie) et v\u00e9rifier si ce raisonnement tient la route sur des donn\u00e9es propres."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q4 : fusion de tables par d\u00e9partements\n", "\n", "On r\u00e9cup\u00e8re deux jeux de donn\u00e9es :\n", "* [Donn\u00e9es hospitali\u00e8res relatives \u00e0 l'\u00e9pid\u00e9mie de COVID-19](https://www.data.gouv.fr/en/datasets/donnees-hospitalieres-relatives-a-lepidemie-de-covid-19/)\n", "* [Indicateurs de suivi de l\u2019\u00e9pid\u00e9mie de COVID-19](https://www.data.gouv.fr/fr/datasets/indicateurs-de-suivi-de-lepidemie-de-covid-19/)"]}, {"cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>dep</th>\n", "      <th>sexe</th>\n", "      <th>jour</th>\n", "      <th>hosp</th>\n", "      <th>rea</th>\n", "      <th>HospConv</th>\n", "      <th>SSR_USLD</th>\n", "      <th>autres</th>\n", "      <th>rad</th>\n", "      <th>dc</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>167440</th>\n", "      <td>976</td>\n", "      <td>0</td>\n", "      <td>2021-09-17</td>\n", "      <td>7</td>\n", "      <td>1</td>\n", "      <td>6.0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>1288</td>\n", "      <td>133</td>\n", "    </tr>\n", "    <tr>\n", "      <th>167441</th>\n", "      <td>976</td>\n", "      <td>1</td>\n", "      <td>2021-09-17</td>\n", "      <td>4</td>\n", "      <td>0</td>\n", "      <td>4.0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>583</td>\n", "      <td>78</td>\n", "    </tr>\n", "    <tr>\n", "      <th>167442</th>\n", "      <td>976</td>\n", "      <td>2</td>\n", "      <td>2021-09-17</td>\n", "      <td>3</td>\n", "      <td>1</td>\n", "      <td>2.0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>684</td>\n", "      <td>54</td>\n", "    </tr>\n", "    <tr>\n", "      <th>167443</th>\n", "      <td>978</td>\n", "      <td>0</td>\n", "      <td>2021-09-17</td>\n", "      <td>0</td>\n", "      <td>0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>0</td>\n", "      <td>1</td>\n", "    </tr>\n", "    <tr>\n", "      <th>167444</th>\n", "      <td>978</td>\n", "      <td>1</td>\n", "      <td>2021-09-17</td>\n", "      <td>0</td>\n", "      <td>0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>0.0</td>\n", "      <td>0</td>\n", "      <td>1</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["        dep  sexe        jour  hosp  rea  HospConv  SSR_USLD  autres   rad  \\\n", "167440  976     0  2021-09-17     7    1       6.0       0.0     0.0  1288   \n", "167441  976     1  2021-09-17     4    0       4.0       0.0     0.0   583   \n", "167442  976     2  2021-09-17     3    1       2.0       0.0     0.0   684   \n", "167443  978     0  2021-09-17     0    0       0.0       0.0     0.0     0   \n", "167444  978     1  2021-09-17     0    0       0.0       0.0     0.0     0   \n", "\n", "         dc  \n", "167440  133  \n", "167441   78  \n", "167442   54  \n", "167443    1  \n", "167444    1  "]}, "execution_count": 56, "metadata": {}, "output_type": "execute_result"}], "source": ["hosp = read_csv(\"https://www.data.gouv.fr/en/datasets/r/63352e38-d353-4b54-bfd1-f1b3ee1cabd7\",\n", "               sep=\";\")\n", "hosp.tail()"]}, {"cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>extract_date</th>\n", "      <th>departement</th>\n", "      <th>region</th>\n", "      <th>libelle_reg</th>\n", "      <th>libelle_dep</th>\n", "      <th>tx_incid</th>\n", "      <th>R</th>\n", "      <th>taux_occupation_sae</th>\n", "      <th>tx_pos</th>\n", "      <th>tx_incid_couleur</th>\n", "      <th>R_couleur</th>\n", "      <th>taux_occupation_sae_couleur</th>\n", "      <th>tx_pos_couleur</th>\n", "      <th>nb_orange</th>\n", "      <th>nb_rouge</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>55444</th>\n", "      <td>2020-11-08</td>\n", "      <td>84</td>\n", "      <td>93</td>\n", "      <td>Provence Alpes C\u00c3\u00b4te d'Azur</td>\n", "      <td>Vaucluse</td>\n", "      <td>641.89</td>\n", "      <td>NaN</td>\n", "      <td>107.2</td>\n", "      <td>17.565854</td>\n", "      <td>rouge</td>\n", "      <td>NaN</td>\n", "      <td>rouge</td>\n", "      <td>rouge</td>\n", "      <td>0</td>\n", "      <td>3</td>\n", "    </tr>\n", "    <tr>\n", "      <th>55445</th>\n", "      <td>2020-10-26</td>\n", "      <td>84</td>\n", "      <td>93</td>\n", "      <td>Provence Alpes C\u00c3\u00b4te d'Azur</td>\n", "      <td>Vaucluse</td>\n", "      <td>540.47</td>\n", "      <td>NaN</td>\n", "      <td>65.9</td>\n", "      <td>18.461913</td>\n", "      <td>rouge</td>\n", "      <td>NaN</td>\n", "      <td>rouge</td>\n", "      <td>rouge</td>\n", "      <td>0</td>\n", "      <td>3</td>\n", "    </tr>\n", "    <tr>\n", "      <th>55446</th>\n", "      <td>2020-10-27</td>\n", "      <td>84</td>\n", "      <td>93</td>\n", "      <td>Provence Alpes C\u00c3\u00b4te d'Azur</td>\n", "      <td>Vaucluse</td>\n", "      <td>626.21</td>\n", "      <td>1.48</td>\n", "      <td>66.5</td>\n", "      <td>19.402408</td>\n", "      <td>rouge</td>\n", "      <td>orange</td>\n", "      <td>rouge</td>\n", "      <td>rouge</td>\n", "      <td>1</td>\n", "      <td>3</td>\n", "    </tr>\n", "    <tr>\n", "      <th>55447</th>\n", "      <td>2020-10-28</td>\n", "      <td>84</td>\n", "      <td>93</td>\n", "      <td>Provence Alpes C\u00c3\u00b4te d'Azur</td>\n", "      <td>Vaucluse</td>\n", "      <td>672.20</td>\n", "      <td>NaN</td>\n", "      <td>68.5</td>\n", "      <td>19.795276</td>\n", "      <td>rouge</td>\n", "      <td>NaN</td>\n", "      <td>rouge</td>\n", "      <td>rouge</td>\n", "      <td>0</td>\n", "      <td>3</td>\n", "    </tr>\n", "    <tr>\n", "      <th>55448</th>\n", "      <td>2020-10-25</td>\n", "      <td>84</td>\n", "      <td>93</td>\n", "      <td>Provence Alpes C\u00c3\u00b4te d'Azur</td>\n", "      <td>Vaucluse</td>\n", "      <td>439.75</td>\n", "      <td>NaN</td>\n", "      <td>61.3</td>\n", "      <td>16.519352</td>\n", "      <td>rouge</td>\n", "      <td>NaN</td>\n", "      <td>rouge</td>\n", "      <td>rouge</td>\n", "      <td>0</td>\n", "      <td>3</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["      extract_date departement  region                  libelle_reg  \\\n", "55444   2020-11-08          84      93  Provence Alpes C\u00c3\u00b4te d'Azur   \n", "55445   2020-10-26          84      93  Provence Alpes C\u00c3\u00b4te d'Azur   \n", "55446   2020-10-27          84      93  Provence Alpes C\u00c3\u00b4te d'Azur   \n", "55447   2020-10-28          84      93  Provence Alpes C\u00c3\u00b4te d'Azur   \n", "55448   2020-10-25          84      93  Provence Alpes C\u00c3\u00b4te d'Azur   \n", "\n", "      libelle_dep  tx_incid     R  taux_occupation_sae     tx_pos  \\\n", "55444    Vaucluse    641.89   NaN                107.2  17.565854   \n", "55445    Vaucluse    540.47   NaN                 65.9  18.461913   \n", "55446    Vaucluse    626.21  1.48                 66.5  19.402408   \n", "55447    Vaucluse    672.20   NaN                 68.5  19.795276   \n", "55448    Vaucluse    439.75   NaN                 61.3  16.519352   \n", "\n", "      tx_incid_couleur R_couleur taux_occupation_sae_couleur tx_pos_couleur  \\\n", "55444            rouge       NaN                       rouge          rouge   \n", "55445            rouge       NaN                       rouge          rouge   \n", "55446            rouge    orange                       rouge          rouge   \n", "55447            rouge       NaN                       rouge          rouge   \n", "55448            rouge       NaN                       rouge          rouge   \n", "\n", "       nb_orange  nb_rouge  \n", "55444          0         3  \n", "55445          0         3  \n", "55446          1         3  \n", "55447          0         3  \n", "55448          0         3  "]}, "execution_count": 57, "metadata": {}, "output_type": "execute_result"}], "source": ["indic = read_csv(\"https://www.data.gouv.fr/fr/datasets/r/4acad602-d8b1-4516-bc71-7d5574d5f33e\",\n", "                encoding=\"ISO-8859-1\")\n", "indic.tail()"]}, {"cell_type": "markdown", "metadata": {}, "source": ["Le code suivant explique comment trouver la valeur ``ISO-8859-1``."]}, {"cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [], "source": ["# import chardet\n", "# with open(\"indicateurs-covid19-dep.csv\", \"rb\") as f:\n", "#     content = f.read()\n", "# chardet.detect(content)  # {'encoding': 'ISO-8859-1', 'confidence': 0.73, 'language': ''}"]}, {"cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [], "source": []}, {"cell_type": "markdown", "metadata": {}, "source": ["### Q5 : une carte ?\n", "\n", "Tracer une carte n'est jamais simple. Il faut tout d'abord r\u00e9cup\u00e9rer les coordonn\u00e9es des d\u00e9partements : [Contours des d\u00e9partements fran\u00e7ais issus d'OpenStreetMap](https://www.data.gouv.fr/en/datasets/contours-des-departements-francais-issus-d-openstreetmap/). Ensuite... de ces fichiers ont \u00e9t\u00e9 extraits les barycentres de chaque d\u00e9partement fran\u00e7ais : [departement_french_2018.csv](https://github.com/sdpython/ensae_teaching_cs/blob/master/src/ensae_teaching_cs/data/data_shp/departement_french_2018.csv). Ce fichier a \u00e9t\u00e9 cr\u00e9\u00e9 avec la fonction impl\u00e9ment\u00e9e dans le fichier [data_shape_files.py](https://github.com/sdpython/ensae_teaching_cs/blob/master/src/ensae_teaching_cs/data/data_shape_files.py). Ce qui suit est une approximation de carte : on suppose que l\u00e0 o\u00f9 se trouve, les coordonn\u00e9es longitude et latitude ne sont pas trop \u00e9loign\u00e9es de ce qu'elles pourraient \u00eatre si elles \u00e9taient projet\u00e9es sur une sph\u00e8re."]}, {"cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>code_insee</th>\n", "      <th>nom</th>\n", "      <th>nuts3</th>\n", "      <th>wikipedia</th>\n", "      <th>surf_km2</th>\n", "      <th>DEPLONG</th>\n", "      <th>DEPLAT</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>97</th>\n", "      <td>56</td>\n", "      <td>Morbihan</td>\n", "      <td>FR524</td>\n", "      <td>fr:Morbihan</td>\n", "      <td>6870.0</td>\n", "      <td>-2.812320</td>\n", "      <td>47.846846</td>\n", "    </tr>\n", "    <tr>\n", "      <th>98</th>\n", "      <td>25</td>\n", "      <td>Doubs</td>\n", "      <td>FR431</td>\n", "      <td>fr:Doubs (d\u00e9partement)</td>\n", "      <td>5256.0</td>\n", "      <td>6.362722</td>\n", "      <td>47.165964</td>\n", "    </tr>\n", "    <tr>\n", "      <th>99</th>\n", "      <td>39</td>\n", "      <td>Jura</td>\n", "      <td>FR432</td>\n", "      <td>fr:Jura (d\u00e9partement)</td>\n", "      <td>5049.0</td>\n", "      <td>5.697361</td>\n", "      <td>46.729368</td>\n", "    </tr>\n", "    <tr>\n", "      <th>100</th>\n", "      <td>07</td>\n", "      <td>Ard\u00e8che</td>\n", "      <td>FR712</td>\n", "      <td>fr:Ard\u00e8che (d\u00e9partement)</td>\n", "      <td>5566.0</td>\n", "      <td>4.425582</td>\n", "      <td>44.752771</td>\n", "    </tr>\n", "    <tr>\n", "      <th>101</th>\n", "      <td>30</td>\n", "      <td>Gard</td>\n", "      <td>FR812</td>\n", "      <td>fr:Gard</td>\n", "      <td>5875.0</td>\n", "      <td>4.179861</td>\n", "      <td>43.993601</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["    code_insee       nom  nuts3                 wikipedia  surf_km2   DEPLONG  \\\n", "97          56  Morbihan  FR524               fr:Morbihan    6870.0 -2.812320   \n", "98          25     Doubs  FR431    fr:Doubs (d\u00e9partement)    5256.0  6.362722   \n", "99          39      Jura  FR432     fr:Jura (d\u00e9partement)    5049.0  5.697361   \n", "100         07   Ard\u00e8che  FR712  fr:Ard\u00e8che (d\u00e9partement)    5566.0  4.425582   \n", "101         30      Gard  FR812                   fr:Gard    5875.0  4.179861   \n", "\n", "        DEPLAT  \n", "97   47.846846  \n", "98   47.165964  \n", "99   46.729368  \n", "100  44.752771  \n", "101  43.993601  "]}, "execution_count": 60, "metadata": {}, "output_type": "execute_result"}], "source": ["dep_pos = read_csv(\"https://raw.githubusercontent.com/sdpython/ensae_teaching_cs/\"\n", "                   \"master/src/ensae_teaching_cs/data/data_shp/departement_french_2018.csv\")\n", "dep_pos.tail()"]}, {"cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [{"data": {"text/plain": ["'2021-09-17'"]}, "execution_count": 61, "metadata": {}, "output_type": "execute_result"}], "source": ["last_extract_date = max(set(indic.extract_date))\n", "last_extract_date"]}, {"cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>code_insee</th>\n", "      <th>nom</th>\n", "      <th>DEPLONG</th>\n", "      <th>DEPLAT</th>\n", "      <th>taux_occupation_sae</th>\n", "      <th>R</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>0</th>\n", "      <td>01</td>\n", "      <td>Ain</td>\n", "      <td>5.348764</td>\n", "      <td>46.099799</td>\n", "      <td>30.2</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>1</th>\n", "      <td>03</td>\n", "      <td>Allier</td>\n", "      <td>3.187644</td>\n", "      <td>46.393637</td>\n", "      <td>30.2</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2</th>\n", "      <td>07</td>\n", "      <td>Ard\u00e8che</td>\n", "      <td>4.425582</td>\n", "      <td>44.752771</td>\n", "      <td>30.2</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>3</th>\n", "      <td>15</td>\n", "      <td>Cantal</td>\n", "      <td>2.669045</td>\n", "      <td>45.051247</td>\n", "      <td>30.2</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>4</th>\n", "      <td>26</td>\n", "      <td>Dr\u00f4me</td>\n", "      <td>5.167364</td>\n", "      <td>44.685239</td>\n", "      <td>30.2</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>...</th>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "      <td>...</td>\n", "    </tr>\n", "    <tr>\n", "      <th>95</th>\n", "      <td>05</td>\n", "      <td>Hautes-Alpes</td>\n", "      <td>6.265318</td>\n", "      <td>44.663965</td>\n", "      <td>69.1</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>96</th>\n", "      <td>06</td>\n", "      <td>Alpes-Maritimes</td>\n", "      <td>7.116532</td>\n", "      <td>43.937937</td>\n", "      <td>69.1</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>97</th>\n", "      <td>13</td>\n", "      <td>Bouches-du-Rh\u00f4ne</td>\n", "      <td>5.086225</td>\n", "      <td>43.543055</td>\n", "      <td>69.1</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>98</th>\n", "      <td>83</td>\n", "      <td>Var</td>\n", "      <td>6.244490</td>\n", "      <td>43.441656</td>\n", "      <td>69.1</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "    <tr>\n", "      <th>99</th>\n", "      <td>84</td>\n", "      <td>Vaucluse</td>\n", "      <td>5.177329</td>\n", "      <td>44.007176</td>\n", "      <td>69.1</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "<p>95 rows \u00d7 6 columns</p>\n", "</div>"], "text/plain": ["   code_insee               nom   DEPLONG     DEPLAT  taux_occupation_sae   R\n", "0          01               Ain  5.348764  46.099799                 30.2 NaN\n", "1          03            Allier  3.187644  46.393637                 30.2 NaN\n", "2          07           Ard\u00e8che  4.425582  44.752771                 30.2 NaN\n", "3          15            Cantal  2.669045  45.051247                 30.2 NaN\n", "4          26             Dr\u00f4me  5.167364  44.685239                 30.2 NaN\n", "..        ...               ...       ...        ...                  ...  ..\n", "95         05      Hautes-Alpes  6.265318  44.663965                 69.1 NaN\n", "96         06   Alpes-Maritimes  7.116532  43.937937                 69.1 NaN\n", "97         13  Bouches-du-Rh\u00f4ne  5.086225  43.543055                 69.1 NaN\n", "98         83               Var  6.244490  43.441656                 69.1 NaN\n", "99         84          Vaucluse  5.177329  44.007176                 69.1 NaN\n", "\n", "[95 rows x 6 columns]"]}, "execution_count": 62, "metadata": {}, "output_type": "execute_result"}], "source": ["indic_last = indic[indic.extract_date == last_extract_date]\n", "merge = indic_last.merge(dep_pos, left_on='departement', right_on='code_insee')\n", "final = merge[['code_insee', 'nom', 'DEPLONG', 'DEPLAT', 'taux_occupation_sae', 'R']]\n", "metro = final[final.DEPLAT > 40]\n", "metro"]}, {"cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 2 Axes>"]}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}], "source": ["import matplotlib.pyplot as plt\n", "fig, ax = plt.subplots(1, 2, figsize=(14, 4))\n", "bigR1 = metro.R >= 1\n", "bigR2 = metro.R >= 1.4\n", "ax[0].scatter(metro.loc[bigR2, 'DEPLONG'], metro.loc[bigR2, 'DEPLAT'], c='red', label='R>=1.4');\n", "ax[0].scatter(metro.loc[bigR1 & ~bigR2, 'DEPLONG'], metro.loc[bigR1 & ~bigR2, 'DEPLAT'], c='orange', label='1.3>=R>=1');\n", "ax[0].scatter(metro.loc[~bigR1, 'DEPLONG'], metro.loc[~bigR1, 'DEPLAT'], c='blue', label='R<1');\n", "ax[0].legend()\n", "\n", "bigR1 = metro.taux_occupation_sae >= 25\n", "bigR2 = metro.taux_occupation_sae >= 45\n", "ax[1].scatter(metro.loc[bigR2, 'DEPLONG'], metro.loc[bigR2, 'DEPLAT'], c='red', label='SAE>=45');\n", "ax[1].scatter(metro.loc[bigR1 & ~bigR2, 'DEPLONG'], metro.loc[bigR1 & ~bigR2, 'DEPLAT'], c='orange', label='45>SAE>=25');\n", "ax[1].scatter(metro.loc[~bigR1, 'DEPLONG'], metro.loc[~bigR1, 'DEPLAT'], c='blue', label='SAE<25');\n", "ax[1].legend();"]}, {"cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>code_insee</th>\n", "      <th>nom</th>\n", "      <th>DEPLONG</th>\n", "      <th>DEPLAT</th>\n", "      <th>taux_occupation_sae</th>\n", "      <th>R</th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>31</th>\n", "      <td>08</td>\n", "      <td>Ardennes</td>\n", "      <td>4.640751</td>\n", "      <td>49.616226</td>\n", "      <td>22.4</td>\n", "      <td>NaN</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["   code_insee       nom   DEPLONG     DEPLAT  taux_occupation_sae   R\n", "31         08  Ardennes  4.640751  49.616226                 22.4 NaN"]}, "execution_count": 64, "metadata": {}, "output_type": "execute_result"}], "source": ["metro[metro.nom == \"Ardennes\"]"]}, {"cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [], "source": []}], "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": "3.9.5"}}, "nbformat": 4, "nbformat_minor": 2}