{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "title : \"Netflix User Data\"\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "L'ensemble de données fu fichier `Netflix_Userbase.csv` fournit un aperçu d'un échantillon d'utilisateurs de Netflix. \n",
    "\n",
    "Chaque ligne représente un utilisateur unique, identifié par son ID utilisateur. \n",
    "\n",
    "L'ensemble de données comprend les colonnes suivantes :\n",
    "\n",
    "- le type d'abonnement de l'utilisateur (Basic, Standard ou Premium), \n",
    "- le revenu mensuel généré par son abonnement, \n",
    "- la date d'inscription à Netflix, \n",
    "- la date de son dernier paiement et \n",
    "- le pays dans lequel il se trouve. \n",
    "\n",
    "Des colonnes supplémentaires ont été incluses pour fournir des informations sur le comportement et les préférences des utilisateurs, comme le type d'appareil. \n",
    "\n",
    "*Source :* [Kaggle](https://www.kaggle.com/datasets/arnavsmayan/netflix-userbase-dataset?resource=download)  \n",
    "*Disclaimer:* l'ensemble de données sert de représentation synthétique et ne reflète pas les données réelles des utilisateurs de Netflix. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-block alert-info\">\n",
    "\n",
    "## Exercice\n",
    "\n",
    "1. Affichages\n",
    "    - Charger le fichier `Netflix_Userbase.csv` dans un DataFrame.\n",
    "    - Afficher les 20 premières lignes.\n",
    "    - Combien de ligne et de colonnes contient ce fichier ?\n",
    "    - Quels sont les types des colonnes ?\n",
    "    - Pour chaque colonnes, combien de valeurs différentes contient-elle ?\n",
    "    - Y a-t-il des valeurs manquantes ?\n",
    "2. Modification des données\n",
    "    - Ne garder que les utilisateurs europeens.\n",
    "3. Aggregations/Visualisations \n",
    "    - Afficher le nombre d'utilisateurs par pays.\n",
    "    - Afficher le nombre d'utilisateurs par sexe.\n",
    "    - Afficher le nombre d'utilisateurs par devices utilisés.\n",
    "    - Continuer l'analyse des données en affichant des visualisations qui vous semblent pertinentes en combinant les différentes caractéristiques des utilisateurs.\n",
    "\n",
    "4. Conclusion\n",
    "    - Quels sont les insights que vous avez pu tirer de cette analyse ?\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:04.908395Z",
     "iopub.status.busy": "2026-10-30T13:11:04.907965Z",
     "iopub.status.idle": "2026-10-30T13:11:05.941510Z",
     "shell.execute_reply": "2026-10-30T13:11:05.937674Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "# plt.rcParams['figure.figsize'] = (15, 7) # set default size of plots\n",
    "\n",
    "import seaborn as sns\n",
    "\n",
    "import plotly.express as px\n",
    "\n",
    "from IPython.display import display, Markdown"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Affichages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:05.946167Z",
     "iopub.status.busy": "2026-10-30T13:11:05.945856Z",
     "iopub.status.idle": "2026-10-30T13:11:05.964838Z",
     "shell.execute_reply": "2026-10-30T13:11:05.964326Z"
    }
   },
   "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>User ID</th>\n",
       "      <th>Subscription Type</th>\n",
       "      <th>Monthly Revenue</th>\n",
       "      <th>Join Date</th>\n",
       "      <th>Last Payment Date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Device</th>\n",
       "      <th>Plan Duration</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>15-01-22</td>\n",
       "      <td>10-06-23</td>\n",
       "      <td>United States</td>\n",
       "      <td>28</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>05-09-21</td>\n",
       "      <td>22-06-23</td>\n",
       "      <td>Canada</td>\n",
       "      <td>35</td>\n",
       "      <td>Female</td>\n",
       "      <td>Tablet</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>28-02-23</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>42</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>10-07-22</td>\n",
       "      <td>26-06-23</td>\n",
       "      <td>Australia</td>\n",
       "      <td>51</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>01-05-23</td>\n",
       "      <td>28-06-23</td>\n",
       "      <td>Germany</td>\n",
       "      <td>33</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>18-03-22</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>France</td>\n",
       "      <td>29</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>09-12-21</td>\n",
       "      <td>25-06-23</td>\n",
       "      <td>Brazil</td>\n",
       "      <td>46</td>\n",
       "      <td>Male</td>\n",
       "      <td>Tablet</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>02-04-23</td>\n",
       "      <td>24-06-23</td>\n",
       "      <td>Mexico</td>\n",
       "      <td>39</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>20-10-22</td>\n",
       "      <td>23-06-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>37</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>07-01-23</td>\n",
       "      <td>22-06-23</td>\n",
       "      <td>Italy</td>\n",
       "      <td>44</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>16-05-22</td>\n",
       "      <td>22-06-23</td>\n",
       "      <td>United States</td>\n",
       "      <td>31</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>23-03-23</td>\n",
       "      <td>28-06-23</td>\n",
       "      <td>Canada</td>\n",
       "      <td>45</td>\n",
       "      <td>Male</td>\n",
       "      <td>Tablet</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>30-11-21</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>48</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>01-08-22</td>\n",
       "      <td>26-06-23</td>\n",
       "      <td>Australia</td>\n",
       "      <td>27</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>09-05-23</td>\n",
       "      <td>28-06-23</td>\n",
       "      <td>Germany</td>\n",
       "      <td>38</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>16</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>07-04-22</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>France</td>\n",
       "      <td>36</td>\n",
       "      <td>Male</td>\n",
       "      <td>Tablet</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>24-01-22</td>\n",
       "      <td>25-06-23</td>\n",
       "      <td>Brazil</td>\n",
       "      <td>30</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18</td>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>18-10-21</td>\n",
       "      <td>24-06-23</td>\n",
       "      <td>Mexico</td>\n",
       "      <td>43</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19</td>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>15-02-23</td>\n",
       "      <td>23-06-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>32</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>27-05-23</td>\n",
       "      <td>22-06-23</td>\n",
       "      <td>Italy</td>\n",
       "      <td>41</td>\n",
       "      <td>Male</td>\n",
       "      <td>Tablet</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    User ID Subscription Type  Monthly Revenue Join Date Last Payment Date  \\\n",
       "0         1             Basic               10  15-01-22          10-06-23   \n",
       "1         2           Premium               15  05-09-21          22-06-23   \n",
       "2         3          Standard               12  28-02-23          27-06-23   \n",
       "3         4          Standard               12  10-07-22          26-06-23   \n",
       "4         5             Basic               10  01-05-23          28-06-23   \n",
       "5         6           Premium               15  18-03-22          27-06-23   \n",
       "6         7          Standard               12  09-12-21          25-06-23   \n",
       "7         8             Basic               10  02-04-23          24-06-23   \n",
       "8         9          Standard               12  20-10-22          23-06-23   \n",
       "9        10           Premium               15  07-01-23          22-06-23   \n",
       "10       11             Basic               10  16-05-22          22-06-23   \n",
       "11       12           Premium               15  23-03-23          28-06-23   \n",
       "12       13          Standard               12  30-11-21          27-06-23   \n",
       "13       14             Basic               10  01-08-22          26-06-23   \n",
       "14       15          Standard               12  09-05-23          28-06-23   \n",
       "15       16           Premium               15  07-04-22          27-06-23   \n",
       "16       17             Basic               10  24-01-22          25-06-23   \n",
       "17       18          Standard               12  18-10-21          24-06-23   \n",
       "18       19           Premium               15  15-02-23          23-06-23   \n",
       "19       20             Basic               10  27-05-23          22-06-23   \n",
       "\n",
       "           Country  Age  Gender      Device Plan Duration  \n",
       "0    United States   28    Male  Smartphone       1 Month  \n",
       "1           Canada   35  Female      Tablet       1 Month  \n",
       "2   United Kingdom   42    Male    Smart TV       1 Month  \n",
       "3        Australia   51  Female      Laptop       1 Month  \n",
       "4          Germany   33    Male  Smartphone       1 Month  \n",
       "5           France   29  Female    Smart TV       1 Month  \n",
       "6           Brazil   46    Male      Tablet       1 Month  \n",
       "7           Mexico   39  Female      Laptop       1 Month  \n",
       "8            Spain   37    Male  Smartphone       1 Month  \n",
       "9            Italy   44  Female    Smart TV       1 Month  \n",
       "10   United States   31  Female  Smartphone       1 Month  \n",
       "11          Canada   45    Male      Tablet       1 Month  \n",
       "12  United Kingdom   48  Female      Laptop       1 Month  \n",
       "13       Australia   27    Male  Smartphone       1 Month  \n",
       "14         Germany   38  Female    Smart TV       1 Month  \n",
       "15          France   36    Male      Tablet       1 Month  \n",
       "16          Brazil   30  Female      Laptop       1 Month  \n",
       "17          Mexico   43    Male  Smartphone       1 Month  \n",
       "18           Spain   32  Female    Smart TV       1 Month  \n",
       "19           Italy   41    Male      Tablet       1 Month  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Importer le jeu de données\n",
    "df_complet = pd.read_csv('Netflix_Userbase.csv', sep=',', low_memory=False)\n",
    "\n",
    "# Afficher les 20 premières lignes\n",
    "df_complet.head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:05.999265Z",
     "iopub.status.busy": "2026-10-30T13:11:05.999061Z",
     "iopub.status.idle": "2026-10-30T13:11:06.007019Z",
     "shell.execute_reply": "2026-10-30T13:11:06.006601Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 2500 entries, 0 to 2499\n",
      "Data columns (total 10 columns):\n",
      " #   Column             Non-Null Count  Dtype \n",
      "---  ------             --------------  ----- \n",
      " 0   User ID            2500 non-null   int64 \n",
      " 1   Subscription Type  2500 non-null   object\n",
      " 2   Monthly Revenue    2500 non-null   int64 \n",
      " 3   Join Date          2500 non-null   object\n",
      " 4   Last Payment Date  2500 non-null   object\n",
      " 5   Country            2500 non-null   object\n",
      " 6   Age                2500 non-null   int64 \n",
      " 7   Gender             2500 non-null   object\n",
      " 8   Device             2500 non-null   object\n",
      " 9   Plan Duration      2500 non-null   object\n",
      "dtypes: int64(3), object(7)\n",
      "memory usage: 195.4+ KB\n"
     ]
    }
   ],
   "source": [
    "# display(df_complet.shape)\n",
    "df_complet.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notre jeu de données contient 2500 lignes (= utilisateurs) et 12 colonnes. 3 colonnes sont de type `int`, 7 colonnes sont de type `object`. Notons que les colonnes `date` sont de type `object` et devront être converties en `datetime` pour être exploitées correctement le cas échéant."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Statistiques descriptives pour les colonnes numériques :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.008673Z",
     "iopub.status.busy": "2026-10-30T13:11:06.008520Z",
     "iopub.status.idle": "2026-10-30T13:11:06.018986Z",
     "shell.execute_reply": "2026-10-30T13:11:06.018483Z"
    }
   },
   "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>User ID</th>\n",
       "      <th>Monthly Revenue</th>\n",
       "      <th>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2500.00000</td>\n",
       "      <td>2500.000000</td>\n",
       "      <td>2500.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1250.50000</td>\n",
       "      <td>12.508400</td>\n",
       "      <td>38.795600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>721.83216</td>\n",
       "      <td>1.686851</td>\n",
       "      <td>7.171778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.00000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>26.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>625.75000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>32.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1250.50000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>39.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1875.25000</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>45.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2500.00000</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>51.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          User ID  Monthly Revenue          Age\n",
       "count  2500.00000      2500.000000  2500.000000\n",
       "mean   1250.50000        12.508400    38.795600\n",
       "std     721.83216         1.686851     7.171778\n",
       "min       1.00000        10.000000    26.000000\n",
       "25%     625.75000        11.000000    32.000000\n",
       "50%    1250.50000        12.000000    39.000000\n",
       "75%    1875.25000        14.000000    45.000000\n",
       "max    2500.00000        15.000000    51.000000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_complet.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Statistiques descriptives pour les colonnes catégorielles :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.020740Z",
     "iopub.status.busy": "2026-10-30T13:11:06.020586Z",
     "iopub.status.idle": "2026-10-30T13:11:06.037569Z",
     "shell.execute_reply": "2026-10-30T13:11:06.034701Z"
    }
   },
   "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>Subscription Type</th>\n",
       "      <th>Join Date</th>\n",
       "      <th>Last Payment Date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Device</th>\n",
       "      <th>Plan Duration</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "      <td>2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>3</td>\n",
       "      <td>300</td>\n",
       "      <td>26</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>Basic</td>\n",
       "      <td>05-11-22</td>\n",
       "      <td>28-06-23</td>\n",
       "      <td>United States</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>999</td>\n",
       "      <td>33</td>\n",
       "      <td>164</td>\n",
       "      <td>451</td>\n",
       "      <td>1257</td>\n",
       "      <td>636</td>\n",
       "      <td>2500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Subscription Type Join Date Last Payment Date        Country  Gender  \\\n",
       "count               2500      2500              2500           2500    2500   \n",
       "unique                 3       300                26             10       2   \n",
       "top                Basic  05-11-22          28-06-23  United States  Female   \n",
       "freq                 999        33               164            451    1257   \n",
       "\n",
       "        Device Plan Duration  \n",
       "count     2500          2500  \n",
       "unique       4             1  \n",
       "top     Laptop       1 Month  \n",
       "freq       636          2500  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_complet.describe(include='object')\n",
    "\n",
    "# df_complet.nunique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pour les colonnes dont les valeurs uniques sont inférieures à 20, afficher les possibilités de ces valeurs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.040179Z",
     "iopub.status.busy": "2026-10-30T13:11:06.039910Z",
     "iopub.status.idle": "2026-10-30T13:11:06.046880Z",
     "shell.execute_reply": "2026-10-30T13:11:06.046426Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Subscription Type... ['Basic', 'Premium', 'Standard']\n",
      "Monthly Revenue..... [10, 11, 12, 13, 14, 15]\n",
      "Country............. ['Australia', 'Brazil', 'Canada', 'France', 'Germany', 'Italy', 'Mexico', 'Spain', 'United Kingdom', 'United States']\n",
      "Gender.............. ['Female', 'Male']\n",
      "Device.............. ['Laptop', 'Smart TV', 'Smartphone', 'Tablet']\n",
      "Plan Duration....... ['1 Month']\n"
     ]
    }
   ],
   "source": [
    "masque = [col for col in df_complet.columns if df_complet[col].nunique() < 20]\n",
    "\n",
    "for c in masque:\n",
    "    if df_complet[c].nunique() < 20:\n",
    "        print(f\"{c:.<20}\", sorted(df_complet[c].unique()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.049187Z",
     "iopub.status.busy": "2026-10-30T13:11:06.048995Z",
     "iopub.status.idle": "2026-10-30T13:11:06.067030Z",
     "shell.execute_reply": "2026-10-30T13:11:06.066670Z"
    }
   },
   "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Basic</th>\n",
       "      <td>999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   count\n",
       "Subscription Type       \n",
       "Basic                999\n",
       "Premium              733\n",
       "Standard             768"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Monthly Revenue</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>409</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>388</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>418</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>399</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 count\n",
       "Monthly Revenue       \n",
       "10                 409\n",
       "11                 388\n",
       "12                 455\n",
       "13                 418\n",
       "14                 431\n",
       "15                 399"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Country</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Australia</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Brazil</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Canada</th>\n",
       "      <td>317</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>France</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Germany</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Italy</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mexico</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Spain</th>\n",
       "      <td>451</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>United Kingdom</th>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>United States</th>\n",
       "      <td>451</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                count\n",
       "Country              \n",
       "Australia         183\n",
       "Brazil            183\n",
       "Canada            317\n",
       "France            183\n",
       "Germany           183\n",
       "Italy             183\n",
       "Mexico            183\n",
       "Spain             451\n",
       "United Kingdom    183\n",
       "United States     451"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Female</th>\n",
       "      <td>1257</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Male</th>\n",
       "      <td>1243</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        count\n",
       "Gender       \n",
       "Female   1257\n",
       "Male     1243"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Device</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Laptop</th>\n",
       "      <td>636</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smart TV</th>\n",
       "      <td>610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smartphone</th>\n",
       "      <td>621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tablet</th>\n",
       "      <td>633</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            count\n",
       "Device           \n",
       "Laptop        636\n",
       "Smart TV      610\n",
       "Smartphone    621\n",
       "Tablet        633"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Plan Duration</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1 Month</th>\n",
       "      <td>2500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               count\n",
       "Plan Duration       \n",
       "1 Month         2500"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for col in masque:\n",
    "    display(df_complet[col].value_counts().to_frame().sort_index())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.068913Z",
     "iopub.status.busy": "2026-10-30T13:11:06.068659Z",
     "iopub.status.idle": "2026-10-30T13:11:06.200509Z",
     "shell.execute_reply": "2026-10-30T13:11:06.199870Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Avec Pandas\n",
    "df_complet['Country'].value_counts().plot(kind='pie', autopct='%1.2f%%', startangle=90, shadow=False, legend=False)\n",
    "plt.title('Répartition des utilisateurs par pays');\n",
    "plt.show()\n",
    "\n",
    "# Avec Seaborn\n",
    "# Note: Seaborn n'a pas de fonction native pour les diagrammes circulaires (pie charts)\n",
    "# sns.countplot(data=df_complet, x='Country');\n",
    "# plt.title('Répartition des utilisateurs par pays');\n",
    "# plt.show()\n",
    "\n",
    "# Avec Plotly\n",
    "# fig = px.pie(df_complet, \n",
    "#              names='Country',\n",
    "#              title='Répartition des utilisateurs par pays'\n",
    "#              ).update_traces(texttemplate='%{label}<br>%{percent:.2%}', \n",
    "#                              textposition='outside').show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Modification des données"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "User ID est une colonne qui ne sert pas à grand chose, on peut la supprimer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.202434Z",
     "iopub.status.busy": "2026-10-30T13:11:06.202205Z",
     "iopub.status.idle": "2026-10-30T13:11:06.205674Z",
     "shell.execute_reply": "2026-10-30T13:11:06.205161Z"
    }
   },
   "outputs": [],
   "source": [
    "df_complet.drop('User ID', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.207524Z",
     "iopub.status.busy": "2026-10-30T13:11:06.207279Z",
     "iopub.status.idle": "2026-10-30T13:11:06.217685Z",
     "shell.execute_reply": "2026-10-30T13:11:06.217223Z"
    }
   },
   "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>Subscription Type</th>\n",
       "      <th>Monthly Revenue</th>\n",
       "      <th>Join Date</th>\n",
       "      <th>Last Payment Date</th>\n",
       "      <th>Country</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Device</th>\n",
       "      <th>Plan Duration</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>28-02-23</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>42</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Basic</td>\n",
       "      <td>10</td>\n",
       "      <td>01-05-23</td>\n",
       "      <td>28-06-23</td>\n",
       "      <td>Germany</td>\n",
       "      <td>33</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>18-03-22</td>\n",
       "      <td>27-06-23</td>\n",
       "      <td>France</td>\n",
       "      <td>29</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Standard</td>\n",
       "      <td>12</td>\n",
       "      <td>20-10-22</td>\n",
       "      <td>23-06-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>37</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Premium</td>\n",
       "      <td>15</td>\n",
       "      <td>07-01-23</td>\n",
       "      <td>22-06-23</td>\n",
       "      <td>Italy</td>\n",
       "      <td>44</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2490</th>\n",
       "      <td>Premium</td>\n",
       "      <td>13</td>\n",
       "      <td>18-07-22</td>\n",
       "      <td>11-07-23</td>\n",
       "      <td>France</td>\n",
       "      <td>41</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2493</th>\n",
       "      <td>Premium</td>\n",
       "      <td>12</td>\n",
       "      <td>21-07-22</td>\n",
       "      <td>15-07-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>36</td>\n",
       "      <td>Male</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2494</th>\n",
       "      <td>Basic</td>\n",
       "      <td>15</td>\n",
       "      <td>23-07-22</td>\n",
       "      <td>12-07-23</td>\n",
       "      <td>Italy</td>\n",
       "      <td>43</td>\n",
       "      <td>Female</td>\n",
       "      <td>Laptop</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2495</th>\n",
       "      <td>Premium</td>\n",
       "      <td>14</td>\n",
       "      <td>25-07-22</td>\n",
       "      <td>12-07-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>28</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2496</th>\n",
       "      <td>Basic</td>\n",
       "      <td>15</td>\n",
       "      <td>04-08-22</td>\n",
       "      <td>14-07-23</td>\n",
       "      <td>Spain</td>\n",
       "      <td>33</td>\n",
       "      <td>Female</td>\n",
       "      <td>Smart TV</td>\n",
       "      <td>1 Month</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1183 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Subscription Type  Monthly Revenue Join Date Last Payment Date  \\\n",
       "2             Standard               12  28-02-23          27-06-23   \n",
       "4                Basic               10  01-05-23          28-06-23   \n",
       "5              Premium               15  18-03-22          27-06-23   \n",
       "8             Standard               12  20-10-22          23-06-23   \n",
       "9              Premium               15  07-01-23          22-06-23   \n",
       "...                ...              ...       ...               ...   \n",
       "2490           Premium               13  18-07-22          11-07-23   \n",
       "2493           Premium               12  21-07-22          15-07-23   \n",
       "2494             Basic               15  23-07-22          12-07-23   \n",
       "2495           Premium               14  25-07-22          12-07-23   \n",
       "2496             Basic               15  04-08-22          14-07-23   \n",
       "\n",
       "             Country  Age  Gender      Device Plan Duration  \n",
       "2     United Kingdom   42    Male    Smart TV       1 Month  \n",
       "4            Germany   33    Male  Smartphone       1 Month  \n",
       "5             France   29  Female    Smart TV       1 Month  \n",
       "8              Spain   37    Male  Smartphone       1 Month  \n",
       "9              Italy   44  Female    Smart TV       1 Month  \n",
       "...              ...  ...     ...         ...           ...  \n",
       "2490          France   41  Female  Smartphone       1 Month  \n",
       "2493           Spain   36    Male    Smart TV       1 Month  \n",
       "2494           Italy   43  Female      Laptop       1 Month  \n",
       "2495           Spain   28  Female    Smart TV       1 Month  \n",
       "2496           Spain   33  Female    Smart TV       1 Month  \n",
       "\n",
       "[1183 rows x 9 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtre = ['United Kingdom', 'Germany', 'France', 'Spain', 'Italy']\n",
    "\n",
    "# mask =  (df_complet['Country'] in filtre) # erreur\n",
    "# mask = df_complet['Country']==filtre[0] | df_complet['Country']==filtre[1] | df_complet['Country']==filtre[2] | df_complet['Country']==filtre[3] | df_complet['Country']==filtre[4] # erreur\n",
    "mask = df_complet['Country'].isin(filtre)\n",
    "df = df_complet[mask].copy()  # .copy() : on va ajouter des colonnes\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Aggregations/Visualisations"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Répartition selon chaque caractéristique\n",
    "\n",
    "Nous voulons le même tableau : effectifs et pourcentages : pour quatre colonnes différentes. Plutôt que de recopier quatre fois les mêmes instructions, écrivons-les **une fois** dans une fonction. C'est plus court, et surtout : si l'on veut changer la présentation, il n'y a qu'un seul endroit à corriger."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.219541Z",
     "iopub.status.busy": "2026-10-30T13:11:06.219322Z",
     "iopub.status.idle": "2026-10-30T13:11:06.238486Z",
     "shell.execute_reply": "2026-10-30T13:11:06.238100Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "**Country**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Nombre</th>\n",
       "      <th>Pourcentage (%)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Country</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Spain</th>\n",
       "      <td>451</td>\n",
       "      <td>38.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>United Kingdom</th>\n",
       "      <td>183</td>\n",
       "      <td>15.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Germany</th>\n",
       "      <td>183</td>\n",
       "      <td>15.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>France</th>\n",
       "      <td>183</td>\n",
       "      <td>15.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Italy</th>\n",
       "      <td>183</td>\n",
       "      <td>15.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Nombre  Pourcentage (%)\n",
       "Country                                \n",
       "Spain              451             38.1\n",
       "United Kingdom     183             15.5\n",
       "Germany            183             15.5\n",
       "France             183             15.5\n",
       "Italy              183             15.5"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "**Gender**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Nombre</th>\n",
       "      <th>Pourcentage (%)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Female</th>\n",
       "      <td>602</td>\n",
       "      <td>50.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Male</th>\n",
       "      <td>581</td>\n",
       "      <td>49.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Nombre  Pourcentage (%)\n",
       "Gender                         \n",
       "Female     602             50.9\n",
       "Male       581             49.1"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "**Device**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Nombre</th>\n",
       "      <th>Pourcentage (%)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Device</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Laptop</th>\n",
       "      <td>316</td>\n",
       "      <td>26.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smart TV</th>\n",
       "      <td>297</td>\n",
       "      <td>25.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smartphone</th>\n",
       "      <td>286</td>\n",
       "      <td>24.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tablet</th>\n",
       "      <td>284</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Nombre  Pourcentage (%)\n",
       "Device                             \n",
       "Laptop         316             26.7\n",
       "Smart TV       297             25.1\n",
       "Smartphone     286             24.2\n",
       "Tablet         284             24.0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "**Subscription Type**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Nombre</th>\n",
       "      <th>Pourcentage (%)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Basic</th>\n",
       "      <td>474</td>\n",
       "      <td>40.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>366</td>\n",
       "      <td>30.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>343</td>\n",
       "      <td>29.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Nombre  Pourcentage (%)\n",
       "Subscription Type                         \n",
       "Basic                 474             40.1\n",
       "Premium               366             30.9\n",
       "Standard              343             29.0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "categorielles = ['Country', 'Gender', 'Device', 'Subscription Type']\n",
    "\n",
    "def repartition(colonne):\n",
    "    \"\"\"Effectifs et pourcentages des modalités d'une colonne.\"\"\"\n",
    "    effectifs = df[colonne].value_counts()\n",
    "    return pd.DataFrame({\n",
    "        'Nombre'          : effectifs,\n",
    "        'Pourcentage (%)' : (effectifs / effectifs.sum() * 100).round(1)\n",
    "    })\n",
    "\n",
    "for colonne in categorielles:\n",
    "    display(Markdown(f\"**{colonne}**\"))\n",
    "    display(repartition(colonne))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Et les quatre camemberts d'un seul coup :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.240299Z",
     "iopub.status.busy": "2026-10-30T13:11:06.240141Z",
     "iopub.status.idle": "2026-10-30T13:11:06.534569Z",
     "shell.execute_reply": "2026-10-30T13:11:06.534080Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1000 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(2, 2, figsize=(12, 10))\n",
    "\n",
    "for ax, colonne in zip(axes.flat, categorielles):\n",
    "    df[colonne].value_counts().plot(kind='pie', autopct='%1.1f%%', ax=ax, ylabel='')\n",
    "    ax.set_title(colonne)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "L'Espagne concentre à elle seule 38 % des abonnés européens, les quatre autres pays se partageant le reste à parts presque égales. En revanche, sexe, appareil et formule d'abonnement sont proches de l'équilibre."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### L'âge : une variable numérique\n",
    "\n",
    "L'âge se traite **autrement**. `value_counts()` produirait ici un tableau d'une ligne par âge distinct : 25 lignes illisibles, où l'on ne verrait rien. Pour une variable numérique, on résume par ses statistiques et on visualise par un **histogramme**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.536689Z",
     "iopub.status.busy": "2026-10-30T13:11:06.536258Z",
     "iopub.status.idle": "2026-10-30T13:11:06.541946Z",
     "shell.execute_reply": "2026-10-30T13:11:06.541557Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    1183.0\n",
       "mean       38.9\n",
       "std         7.2\n",
       "min        27.0\n",
       "25%        33.0\n",
       "50%        39.0\n",
       "75%        45.0\n",
       "max        51.0\n",
       "Name: Age, dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Age'].describe().round(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.543756Z",
     "iopub.status.busy": "2026-10-30T13:11:06.543606Z",
     "iopub.status.idle": "2026-10-30T13:11:06.668895Z",
     "shell.execute_reply": "2026-10-30T13:11:06.668406Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.histplot(data=df, x='Age', bins=12)\n",
    "plt.title(\"Répartition des âges\")\n",
    "plt.xlabel(\"Âge\"); plt.ylabel(\"Nombre d'utilisateurs\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Si l'on tient à un tableau, il faut d'abord **regrouper les âges en tranches** avec `pd.cut` :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.670969Z",
     "iopub.status.busy": "2026-10-30T13:11:06.670776Z",
     "iopub.status.idle": "2026-10-30T13:11:06.684983Z",
     "shell.execute_reply": "2026-10-30T13:11:06.684563Z"
    }
   },
   "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>Nombre</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tranche_age</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>[25, 30)</th>\n",
       "      <td>134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>[30, 35)</th>\n",
       "      <td>246</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>[35, 40)</th>\n",
       "      <td>241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>[40, 45)</th>\n",
       "      <td>240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>[45, 50)</th>\n",
       "      <td>235</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>[50, 55)</th>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Nombre\n",
       "tranche_age        \n",
       "[25, 30)        134\n",
       "[30, 35)        246\n",
       "[35, 40)        241\n",
       "[40, 45)        240\n",
       "[45, 50)        235\n",
       "[50, 55)         87"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['tranche_age'] = pd.cut(df['Age'], bins=[25, 30, 35, 40, 45, 50, 55], right=False)\n",
    "\n",
    "df['tranche_age'].value_counts().sort_index().to_frame('Nombre')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Les abonnés ont entre 27 et 51 ans, assez uniformément répartis entre 30 et 50. Le jeu de données ne contient ni adolescents ni personnes âgées : encore un indice de son caractère synthétique."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Les dates d'inscription et de paiement\n",
    "\n",
    "Les colonnes `Join Date` et `Last Payment Date` ont été lues comme du **texte** : telles quelles, on ne peut ni les comparer, ni en extraire un mois. Il faut les convertir."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.687052Z",
     "iopub.status.busy": "2026-10-30T13:11:06.686585Z",
     "iopub.status.idle": "2026-10-30T13:11:06.690961Z",
     "shell.execute_reply": "2026-10-30T13:11:06.690635Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "avant conversion : **object**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "exemples : **['28-02-23', '01-05-23', '18-03-22']**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(Markdown(f\"avant conversion : **{df['Join Date'].dtype}**\"))\n",
    "display(Markdown(f\"exemples : **{df['Join Date'].head(3).tolist()}**\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Le format `15-01-22` est ambigu : jour-mois-année ou mois-jour-année ? Ici c'est le premier, que l'on indique explicitement avec `format` : il vaut toujours mieux le préciser que laisser pandas deviner."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.692762Z",
     "iopub.status.busy": "2026-10-30T13:11:06.692614Z",
     "iopub.status.idle": "2026-10-30T13:11:06.704705Z",
     "shell.execute_reply": "2026-10-30T13:11:06.704199Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "après conversion : **datetime64[ns]**"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Join Date</th>\n",
       "      <th>Last Payment Date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-02-28</td>\n",
       "      <td>2023-06-27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-05-01</td>\n",
       "      <td>2023-06-28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2022-03-18</td>\n",
       "      <td>2023-06-27</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Join Date Last Payment Date\n",
       "2 2023-02-28        2023-06-27\n",
       "4 2023-05-01        2023-06-28\n",
       "5 2022-03-18        2023-06-27"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Join Date']         = pd.to_datetime(df['Join Date'],         format='%d-%m-%y')\n",
    "df['Last Payment Date'] = pd.to_datetime(df['Last Payment Date'], format='%d-%m-%y')\n",
    "\n",
    "display(Markdown(f\"après conversion : **{df['Join Date'].dtype}**\"))\n",
    "df[['Join Date', 'Last Payment Date']].head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Une fois la colonne en type date, l'accesseur `.dt` donne accès à l'année, au mois, au jour de la semaine :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.706416Z",
     "iopub.status.busy": "2026-10-30T13:11:06.706267Z",
     "iopub.status.idle": "2026-10-30T13:11:06.859659Z",
     "shell.execute_reply": "2026-10-30T13:11:06.859076Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "inscriptions = df['Join Date'].dt.to_period('M').value_counts().sort_index()\n",
    "\n",
    "inscriptions.plot(kind='bar', color='steelblue')\n",
    "plt.title(\"Nombre d'inscriptions par mois\")\n",
    "plt.xlabel(\"\"); plt.ylabel(\"Inscriptions\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Les inscriptions se concentrent massivement entre juin et novembre 2022 ; avant et après, il n'y en a presque aucune. Là encore, aucune plateforme réelle ne recrute de cette façon : c'est la fenêtre de génération des données."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Enfin, la différence entre deux dates donne une durée, dont on extrait le nombre de jours avec `.dt.days` :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.861510Z",
     "iopub.status.busy": "2026-10-30T13:11:06.861321Z",
     "iopub.status.idle": "2026-10-30T13:11:06.868486Z",
     "shell.execute_reply": "2026-10-30T13:11:06.868021Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    1183.0\n",
       "mean      307.0\n",
       "std        65.0\n",
       "min         8.0\n",
       "25%       260.0\n",
       "50%       307.0\n",
       "75%       356.0\n",
       "max       574.0\n",
       "Name: anciennete_jours, dtype: float64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['anciennete_jours'] = (df['Last Payment Date'] - df['Join Date']).dt.days\n",
    "\n",
    "df['anciennete_jours'].describe().round(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Nombre d'utilisateurs par type d'abonnement et genre**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.870255Z",
     "iopub.status.busy": "2026-10-30T13:11:06.870107Z",
     "iopub.status.idle": "2026-10-30T13:11:06.881236Z",
     "shell.execute_reply": "2026-10-30T13:11:06.880805Z"
    }
   },
   "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>Gender</th>\n",
       "      <th>Female</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Basic</th>\n",
       "      <td>0.207101</td>\n",
       "      <td>0.193576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>0.161454</td>\n",
       "      <td>0.147929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>0.140321</td>\n",
       "      <td>0.149620</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Gender               Female      Male\n",
       "Subscription Type                    \n",
       "Basic              0.207101  0.193576\n",
       "Premium            0.161454  0.147929\n",
       "Standard           0.140321  0.149620"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pd.crosstab(df['Subscription Type'], df['Gender']) # tableau de contingence\n",
    "# pd.crosstab(df['Subscription Type'], df['Gender'], normalize='index') # pourcentage par ligne\n",
    "# pd.crosstab(df['Subscription Type'], df['Gender'], normalize='columns') # pourcentage par colonne\n",
    "pd.crosstab(df['Subscription Type'], df['Gender'], normalize='all') # pourcentage total"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Type d'abonnement par pays, genre et device**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.883151Z",
     "iopub.status.busy": "2026-10-30T13:11:06.882781Z",
     "iopub.status.idle": "2026-10-30T13:11:06.894775Z",
     "shell.execute_reply": "2026-10-30T13:11:06.894283Z"
    }
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <th colspan=\"4\" halign=\"left\">Female</th>\n",
       "      <th colspan=\"4\" halign=\"left\">Male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Device</th>\n",
       "      <th>Laptop</th>\n",
       "      <th>Smart TV</th>\n",
       "      <th>Smartphone</th>\n",
       "      <th>Tablet</th>\n",
       "      <th>Laptop</th>\n",
       "      <th>Smart TV</th>\n",
       "      <th>Smartphone</th>\n",
       "      <th>Tablet</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Country</th>\n",
       "      <th></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>France</th>\n",
       "      <td>29</td>\n",
       "      <td>25</td>\n",
       "      <td>24</td>\n",
       "      <td>13</td>\n",
       "      <td>23</td>\n",
       "      <td>18</td>\n",
       "      <td>23</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Germany</th>\n",
       "      <td>27</td>\n",
       "      <td>26</td>\n",
       "      <td>17</td>\n",
       "      <td>24</td>\n",
       "      <td>36</td>\n",
       "      <td>16</td>\n",
       "      <td>19</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Italy</th>\n",
       "      <td>20</td>\n",
       "      <td>31</td>\n",
       "      <td>20</td>\n",
       "      <td>20</td>\n",
       "      <td>30</td>\n",
       "      <td>15</td>\n",
       "      <td>27</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Spain</th>\n",
       "      <td>56</td>\n",
       "      <td>63</td>\n",
       "      <td>49</td>\n",
       "      <td>65</td>\n",
       "      <td>51</td>\n",
       "      <td>63</td>\n",
       "      <td>53</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>United Kingdom</th>\n",
       "      <td>22</td>\n",
       "      <td>16</td>\n",
       "      <td>27</td>\n",
       "      <td>28</td>\n",
       "      <td>22</td>\n",
       "      <td>24</td>\n",
       "      <td>27</td>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Gender         Female                              Male                      \\\n",
       "Device         Laptop Smart TV Smartphone Tablet Laptop Smart TV Smartphone   \n",
       "Country                                                                       \n",
       "France             29       25         24     13     23       18         23   \n",
       "Germany            27       26         17     24     36       16         19   \n",
       "Italy              20       31         20     20     30       15         27   \n",
       "Spain              56       63         49     65     51       63         53   \n",
       "United Kingdom     22       16         27     28     22       24         27   \n",
       "\n",
       "Gender                 \n",
       "Device         Tablet  \n",
       "Country                \n",
       "France             28  \n",
       "Germany            18  \n",
       "Italy              20  \n",
       "Spain              51  \n",
       "United Kingdom     17  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.pivot_table(df, index='Country', columns=['Gender','Device'], values='Subscription Type', aggfunc='count')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Type d'abonnement par pays et genre**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:06.896556Z",
     "iopub.status.busy": "2026-10-30T13:11:06.896407Z",
     "iopub.status.idle": "2026-10-30T13:11:07.025880Z",
     "shell.execute_reply": "2026-10-30T13:11:07.025300Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(data=df, x='Subscription Type', hue='Gender');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:07.027992Z",
     "iopub.status.busy": "2026-10-30T13:11:07.027510Z",
     "iopub.status.idle": "2026-10-30T13:11:07.308601Z",
     "shell.execute_reply": "2026-10-30T13:11:07.308039Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for i,c in enumerate(['Gender','Device']):\n",
    "    plt.subplot(1,2,i+1)\n",
    "    sns.countplot(data=df, x=c, hue='Subscription Type');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Peut-on tout corréler ? Un contre-exemple\n",
    "\n",
    "Une idée séduisante pour repérer d'un coup d'œil quelles caractéristiques « vont ensemble » : convertir toutes les colonnes textuelles en nombres, puis calculer la matrice de corrélation. Essayons : et surtout, vérifions ce que le résultat vaut."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:07.310432Z",
     "iopub.status.busy": "2026-10-30T13:11:07.310242Z",
     "iopub.status.idle": "2026-10-30T13:11:07.559737Z",
     "shell.execute_reply": "2026-10-30T13:11:07.559114Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 900x700 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# On travaille sur une COPIE : l'encodage détruirait les libellés dont nous avons encore besoin\n",
    "df_code = df.copy()\n",
    "\n",
    "for col in df_code.select_dtypes(include='object').columns:\n",
    "    df_code[col] = df_code[col].astype('category').cat.codes\n",
    "\n",
    "# on ne garde que les colonnes numériques : les dates et la tranche d'âge\n",
    "# (de type « catégorie ») n'entrent pas dans une matrice de corrélation\n",
    "corr = df_code.select_dtypes(include='number').corr()\n",
    "\n",
    "plt.figure(figsize=(9, 7))\n",
    "sns.heatmap(corr, annot=True, fmt='.2f', cmap='coolwarm', center=0)\n",
    "plt.title(\"Matrice de corrélation sur variables encodées\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Tous les coefficients sont proches de zéro. La conclusion semble sans appel : **aucune caractéristique n'est liée à une autre.**\n",
    "\n",
    "Vérifions cette conclusion par un tableau croisé, en reprenant les libellés d'origine."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:07.561735Z",
     "iopub.status.busy": "2026-10-30T13:11:07.561550Z",
     "iopub.status.idle": "2026-10-30T13:11:07.574855Z",
     "shell.execute_reply": "2026-10-30T13:11:07.574309Z"
    }
   },
   "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>Country</th>\n",
       "      <th>France</th>\n",
       "      <th>Germany</th>\n",
       "      <th>Italy</th>\n",
       "      <th>Spain</th>\n",
       "      <th>United Kingdom</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</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>Basic</th>\n",
       "      <td>19.7</td>\n",
       "      <td>81.4</td>\n",
       "      <td>96.2</td>\n",
       "      <td>24.4</td>\n",
       "      <td>1.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>80.3</td>\n",
       "      <td>1.6</td>\n",
       "      <td>2.2</td>\n",
       "      <td>47.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>0.0</td>\n",
       "      <td>16.9</td>\n",
       "      <td>1.6</td>\n",
       "      <td>28.6</td>\n",
       "      <td>98.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Country            France  Germany  Italy  Spain  United Kingdom\n",
       "Subscription Type                                               \n",
       "Basic                19.7     81.4   96.2   24.4             1.6\n",
       "Premium              80.3      1.6    2.2   47.0             0.0\n",
       "Standard              0.0     16.9    1.6   28.6            98.4"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.crosstab(df['Subscription Type'], df['Country'], normalize='columns').mul(100).round(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-block alert-danger\">\n",
    "\n",
    "**La matrice se trompait complètement.**\n",
    "\n",
    "Le tableau croisé montre une association massive : **96 %** des abonnés italiens ont une formule *Basic*, **98 %** des britanniques une formule *Standard* et aucun une *Premium*, tandis qu'en France **80 %** sont en *Premium* et aucun en *Standard*. L'écart atteint **98 points de pourcentage** : le pays détermine presque entièrement le type d'abonnement.\n",
    "\n",
    "Et la corrélation correspondante valait $0{,}02$.\n",
    "\n",
    "**Pourquoi ?** Le coefficient de Pearson mesure si deux *nombres* varient ensemble de façon **linéaire**. En codant les pays `France=0, Germany=1, Italy=2, Spain=3, United Kingdom=4`, on lui demande si le numéro de l'abonnement croît proportionnellement au numéro du pays : question dépourvue de sens, puisque l'ordre des pays est celui de l'alphabet. L'association est bien réelle, mais elle n'est pas linéaire dans un ordre arbitraire : le coefficient ne peut pas la voir.\n",
    "\n",
    "Le piège est d'autant plus dangereux que le calcul **n'émet aucun avertissement** et produit un graphique d'apparence professionnelle.\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Le problème touche même les variables **ordinales**, dont les modalités ont pourtant un ordre naturel. `cat.codes` classe par ordre alphabétique, ce qui donne ici `Basic=0, Premium=1, Standard=2` : la formule la plus chère se retrouve **au milieu**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:07.576770Z",
     "iopub.status.busy": "2026-10-30T13:11:07.576464Z",
     "iopub.status.idle": "2026-10-30T13:11:07.583877Z",
     "shell.execute_reply": "2026-10-30T13:11:07.583372Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "codage alphabétique (Basic, Premium, Standard) : r =  0.0145"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "ordre naturel       (Basic, Standard, Premium) : r =  0.0458"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "alphabetique = df['Subscription Type'].astype('category').cat.codes\n",
    "naturel      = df['Subscription Type'].map({'Basic': 0, 'Standard': 1, 'Premium': 2})\n",
    "\n",
    "display(Markdown(f\"codage alphabétique (Basic, Premium, Standard) : r = {alphabetique.corr(df['Monthly Revenue']): .4f}\"))\n",
    "display(Markdown(f\"ordre naturel       (Basic, Standard, Premium) : r = {naturel.corr(df['Monthly Revenue']): .4f}\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Le coefficient triple simplement parce qu'on a rangé les modalités dans le bon ordre. Si vous encodez une variable ordinale, faites-le **explicitement** avec un dictionnaire, jamais avec `cat.codes`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### La bonne façon de faire\n",
    "\n",
    "Pour deux variables catégorielles, l'outil adapté est le **tableau croisé normalisé**, que nous avons déjà utilisé plus haut. Il se lit directement et ne repose sur aucun codage arbitraire."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-30T13:11:07.585821Z",
     "iopub.status.busy": "2026-10-30T13:11:07.585574Z",
     "iopub.status.idle": "2026-10-30T13:11:07.606723Z",
     "shell.execute_reply": "2026-10-30T13:11:07.606232Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "**Type d'abonnement selon `Device`** (% par colonne)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Device</th>\n",
       "      <th>Laptop</th>\n",
       "      <th>Smart TV</th>\n",
       "      <th>Smartphone</th>\n",
       "      <th>Tablet</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Basic</th>\n",
       "      <td>42.4</td>\n",
       "      <td>35.7</td>\n",
       "      <td>38.8</td>\n",
       "      <td>43.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>30.4</td>\n",
       "      <td>35.4</td>\n",
       "      <td>29.0</td>\n",
       "      <td>28.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>27.2</td>\n",
       "      <td>29.0</td>\n",
       "      <td>32.2</td>\n",
       "      <td>27.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Device             Laptop  Smart TV  Smartphone  Tablet\n",
       "Subscription Type                                      \n",
       "Basic                42.4      35.7        38.8    43.3\n",
       "Premium              30.4      35.4        29.0    28.9\n",
       "Standard             27.2      29.0        32.2    27.8"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "**Type d'abonnement selon `Gender`** (% par colonne)"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Gender</th>\n",
       "      <th>Female</th>\n",
       "      <th>Male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Subscription Type</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Basic</th>\n",
       "      <td>40.7</td>\n",
       "      <td>39.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Premium</th>\n",
       "      <td>31.7</td>\n",
       "      <td>30.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Standard</th>\n",
       "      <td>27.6</td>\n",
       "      <td>30.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Gender             Female  Male\n",
       "Subscription Type              \n",
       "Basic                40.7  39.4\n",
       "Premium              31.7  30.1\n",
       "Standard             27.6  30.5"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for colonne in ['Device', 'Gender']:\n",
    "    display(Markdown(f\"**Type d'abonnement selon `{colonne}`** (% par colonne)\"))\n",
    "    display(pd.crosstab(df['Subscription Type'], df[colonne], normalize='columns').mul(100).round(1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Contrairement au pays, ni l'appareil ni le sexe ne structurent le type d'abonnement : d'une colonne à l'autre, le profil reste le même, environ 40 % de *Basic*, 30 % de *Premium*, 29 % de *Standard*. C'est précisément cette **stabilité d'une colonne à l'autre** qui signale l'absence de lien, et non le fait que les trois formules soient à égalité. Ici, l'absence de lien est une vraie conclusion, lisible sans ambiguïté."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-block alert-warning\">\n",
    "\n",
    "**Un mot sur ces données.** Une répartition aussi tranchée : 98 % d'une seule formule dans un pays, 0 % d'une autre : ne s'observe jamais sur des abonnés réels. C'est un **artefact de génération** : le jeu de données est synthétique, comme l'indique l'avertissement en tête de ce notebook.\n",
    "\n",
    "Conservez ce réflexe pour vos propres analyses : un résultat trop propre doit déclencher une vérification, pas une conclusion.\n",
    "\n",
    "</div>"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}