TD2_Manipuler_Pandas.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "url_incidents = \"https://www.data.gouv.fr/fr/datasets/r/a7e77e63-518e-4429-88ac-0e7255a77fc3\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "url_regularite = \"https://www.data.gouv.fr/fr/datasets/r/2a4f7375-e090-4fbb-bea4-ea280a2d1028\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# si vous n'avez pas wget"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "... il faut le télécharger"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: wget in /Users/lucbertin/anaconda3/lib/python3.6/site-packages (3.2)\n",
      "\u001b[33mWARNING: You are using pip version 19.3.1; however, version 20.0.2 is available.\n",
      "You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install wget"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import wget"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'incidents_sncf.csv'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wget.download(url_incidents, out='incidents_sncf.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'regularite_sncf.csv'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wget.download(url_regularite, out='regularite_sncf.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## lire avec une commande systeme"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "date,famille_transport,ligne,incidents\r",
      "\r\n",
      "2019-01-23,transilien,A,\"['Défaut de signalisation entre Nation et Auber', 'Malaise voyageur à Auber', \"\"Panne d'une rame à Cergy-le-Haut\"\"]\"\r",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!head -n 2 incidents_sncf.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "date,famille_transport,ligne,regularite,explication\r",
      "\r\n",
      "2019-01-23,transilien,global,84.2,\r",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!head -n 2 regularite_sncf.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## rentrer dans le dur "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"regularite_sncf.csv\", sep=',')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = pd.read_csv(\"incidents_sncf.csv\", sep=',')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>incidents</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>['Défaut de signalisation entre Nation et Aube...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>['Intervention de police à Gare-du-Nord pour u...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>[\"Signal d'alarme à Bibiliothèque-François-Mit...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>['Restitution tardive de travaux de nuit à Com...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>E</td>\n",
       "      <td>[\"Signaux d'alarme malveillants à Haussamann-S...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3740</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>[\"Présence d'individus sur le pont-rail du Rhô...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3741</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3742</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3743</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3744</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3745 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            date famille_transport  \\\n",
       "0     2019-01-23        transilien   \n",
       "1     2019-01-23        transilien   \n",
       "2     2019-01-23        transilien   \n",
       "3     2019-01-23        transilien   \n",
       "4     2019-01-23        transilien   \n",
       "...          ...               ...   \n",
       "3740  2020-03-13        intercites   \n",
       "3741  2020-03-13        intercites   \n",
       "3742  2020-03-13        intercites   \n",
       "3743  2020-03-13        intercites   \n",
       "3744  2020-03-13        intercites   \n",
       "\n",
       "                                             ligne  \\\n",
       "0                                                A   \n",
       "1                                                B   \n",
       "2                                                C   \n",
       "3                                                D   \n",
       "4                                                E   \n",
       "...                                            ...   \n",
       "3740                                   Nantes-Lyon   \n",
       "3741                              Toulouse-Bayonne   \n",
       "3742                              Clermont-Béziers   \n",
       "3743  Paris-Toulouse-Latour De Carol/Cerbere/Rodez   \n",
       "3744                                Paris-Briançon   \n",
       "\n",
       "                                              incidents  \n",
       "0     ['Défaut de signalisation entre Nation et Aube...  \n",
       "1     ['Intervention de police à Gare-du-Nord pour u...  \n",
       "2     [\"Signal d'alarme à Bibiliothèque-François-Mit...  \n",
       "3     ['Restitution tardive de travaux de nuit à Com...  \n",
       "4     [\"Signaux d'alarme malveillants à Haussamann-S...  \n",
       "...                                                 ...  \n",
       "3740  [\"Présence d'individus sur le pont-rail du Rhô...  \n",
       "3741                                                NaN  \n",
       "3742                                                NaN  \n",
       "3743                                                NaN  \n",
       "3744                                                NaN  \n",
       "\n",
       "[3745 rows x 4 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "date                  object\n",
       "famille_transport     object\n",
       "ligne                 object\n",
       "regularite           float64\n",
       "explication           object\n",
       "dtype: object"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>84.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>88.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>84.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>74.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4080</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4081</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>87.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4082</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4083</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>83.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4084</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4085 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            date famille_transport  \\\n",
       "0     2019-01-23        transilien   \n",
       "1     2019-01-23        transilien   \n",
       "2     2019-01-23        transilien   \n",
       "3     2019-01-23        transilien   \n",
       "4     2019-01-23        transilien   \n",
       "...          ...               ...   \n",
       "4080  2020-03-13        intercites   \n",
       "4081  2020-03-13        intercites   \n",
       "4082  2020-03-13        intercites   \n",
       "4083  2020-03-13        intercites   \n",
       "4084  2020-03-13        intercites   \n",
       "\n",
       "                                             ligne  regularite explication  \n",
       "0                                           global        84.2         NaN  \n",
       "1                                                A        82.1         NaN  \n",
       "2                                                B        88.9         NaN  \n",
       "3                                                C        84.3         NaN  \n",
       "4                                                D        74.5         NaN  \n",
       "...                                            ...         ...         ...  \n",
       "4080                                   Nantes-Lyon        75.0         NaN  \n",
       "4081                              Toulouse-Bayonne        87.5         NaN  \n",
       "4082                              Clermont-Béziers       100.0         NaN  \n",
       "4083  Paris-Toulouse-Latour De Carol/Cerbere/Rodez        83.3         NaN  \n",
       "4084                                Paris-Briançon       100.0         NaN  \n",
       "\n",
       "[4085 rows x 5 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## changer la date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "unedate = \"01/12/2019\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Timestamp('2019-01-12 00:00:00')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_datetime(unedate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "une_autre_date = \"24/01/2020\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Timestamp('2020-01-24 00:00:00')"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_datetime(une_autre_date)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## difference de dates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "diff = pd.to_datetime(une_autre_date) - pd.to_datetime(unedate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Timedelta('377 days 00:00:00')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "377"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diff.days"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ne pas se fier à pd.to_datetime SANS FORMAT !"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_datetime(\"07/10/2019\", format=\"%d/%m/%Y\").day"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_datetime(\"30/10/2019\", format=\"%d/%m/%Y\").day"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## maintenant qu'on sait: convertir la colonne"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.date = pd.to_datetime(df.date, format=\"%Y/%m/%d\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "date                 datetime64[ns]\n",
       "famille_transport            object\n",
       "ligne                        object\n",
       "regularite                  float64\n",
       "explication                  object\n",
       "dtype: object"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['date', 'famille_transport', 'ligne', 'regularite', 'explication'], dtype='object')"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>84.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>88.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>84.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>74.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4080</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4081</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>87.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4082</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4083</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>83.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4084</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4085 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport  \\\n",
       "0    2019-01-23        transilien   \n",
       "1    2019-01-23        transilien   \n",
       "2    2019-01-23        transilien   \n",
       "3    2019-01-23        transilien   \n",
       "4    2019-01-23        transilien   \n",
       "...         ...               ...   \n",
       "4080 2020-03-13        intercites   \n",
       "4081 2020-03-13        intercites   \n",
       "4082 2020-03-13        intercites   \n",
       "4083 2020-03-13        intercites   \n",
       "4084 2020-03-13        intercites   \n",
       "\n",
       "                                             ligne  regularite explication  \n",
       "0                                           global        84.2         NaN  \n",
       "1                                                A        82.1         NaN  \n",
       "2                                                B        88.9         NaN  \n",
       "3                                                C        84.3         NaN  \n",
       "4                                                D        74.5         NaN  \n",
       "...                                            ...         ...         ...  \n",
       "4080                                   Nantes-Lyon        75.0         NaN  \n",
       "4081                              Toulouse-Bayonne        87.5         NaN  \n",
       "4082                              Clermont-Béziers       100.0         NaN  \n",
       "4083  Paris-Toulouse-Latour De Carol/Cerbere/Rodez        83.3         NaN  \n",
       "4084                                Paris-Briançon       100.0         NaN  \n",
       "\n",
       "[4085 rows x 5 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## types de lignes SNCF sur Paris "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "global                                          340\n",
       "Paris-Toulouse-Latour De Carol/Cerbere/Rodez     85\n",
       "Paris-Briançon                                   85\n",
       "Nouvelle-Aquitaine                               85\n",
       "Pays de la Loire                                 85\n",
       "Bourgogne-Franche-Comté                          85\n",
       "Hauts-de-France                                  85\n",
       "sudest                                           85\n",
       "nord                                             85\n",
       "Paris-Clermont                                   85\n",
       "L                                                85\n",
       "T11                                              85\n",
       "Nantes-Bordeaux                                  85\n",
       "europe                                           85\n",
       "Bordeaux-Marseille                               85\n",
       "Toulouse-Bayonne                                 85\n",
       "H                                                85\n",
       "est                                              85\n",
       "Centre-Val de Loire                              85\n",
       "B                                                85\n",
       "N                                                85\n",
       "Grand Est                                        85\n",
       "J                                                85\n",
       "Normandie                                        85\n",
       "Occitanie                                        85\n",
       "Provence-Alpes-Côte d'Azur                       85\n",
       "R                                                85\n",
       "A                                                85\n",
       "Clermont-Béziers                                 85\n",
       "U                                                85\n",
       "D                                                85\n",
       "Auvergne-Rhône-Alpes                             85\n",
       "Paris-Limoges-Toulouse                           85\n",
       "C                                                85\n",
       "atlantique                                       85\n",
       "P                                                85\n",
       "T4                                               85\n",
       "ouigo                                            85\n",
       "Bretagne                                         85\n",
       "K                                                85\n",
       "Nantes-Lyon                                      85\n",
       "E                                                85\n",
       "Paris-Caen-Cherbourg Trouville/Deauville         65\n",
       "Paris-Rouen-Le Havre                             65\n",
       "Paris-Granville                                  65\n",
       "Caen-Le Mans-Tours                               65\n",
       "Name: ligne, dtype: int64"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.ligne.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "transilien    1360\n",
       "intercites    1110\n",
       "ter           1020\n",
       "tgv            595\n",
       "Name: famille_transport, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.famille_transport.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## quelques métriques sur des valeurs continues"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regularite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>count</td>\n",
       "      <td>3935.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>mean</td>\n",
       "      <td>84.640178</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>std</td>\n",
       "      <td>16.431291</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>min</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25%</td>\n",
       "      <td>81.050000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>50%</td>\n",
       "      <td>89.700000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>75%</td>\n",
       "      <td>94.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>max</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        regularite\n",
       "count  3935.000000\n",
       "mean     84.640178\n",
       "std      16.431291\n",
       "min       0.000000\n",
       "25%      81.050000\n",
       "50%      89.700000\n",
       "75%      94.600000\n",
       "max     100.000000"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11391d978>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAD8CAYAAACGsIhGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzt3Xl4XPV97/H3V/u+WIsXeV9YDIQlxpCFJC1pAjQJSQONSXJDExLSNtymTdNbKDe5JE97b2mfJE/b8NDSQgMkgSRkc1sSskDSLGAwGLCNIZaMsWVblmRt1jJav/ePmTFjWfJomTPnSPq8nsePRmfOzHx9RpqPfr/f+f2OuTsiIiKnkxN2ASIiEn0KCxERSUthISIiaSksREQkLYWFiIikpbAQEZG0FBYiIpKWwkJERNJSWIiISFp5YReQKbW1tb569eqwyxARmVOefvrpdnevS7ffvAmL1atXs3379rDLEBGZU8zslansp24oERFJS2EhIiJpKSxERCQthYWIiKSlsBARkbQUFiIikpbCQkRE0lJYiEigHnuxla8+8QpDI2NhlyKzMG8m5YlI9Dz2Yisf/spTAOw50sPfvOe8kCuSmVLLQkQC4e7834f3sL6+jA9cspKvP3mAfW29YZclM6SwEJFAPN/czd7WXj76xjV88vINGPDQ081hlyUzpLAQkUD86IUWcnOMK89bSn1FEW9YX8sPd7WEXZbMkMJCRALxy8ZjXLCiisrifADecmY9+9r7aO7sD7kymQmFhYhkXO/gCDubu3j9upoT2960oRaAXzcdC6ssmQWFhYhk3AuHexhzuHBl1Ylt6+rKKC/M4/nmrhArk5lSWIhIxu081A3AucsqT2zLyTFes6KS5w52h1WWzILCQkQybtehburLC6mvKDpp+/nLq9hzpIfY8GhIlclMKSxEJON2HermvIbKU7afv6KKkTHnhSM9IVQls6GwEJGMGhwZZV97HxuXVZxy38al8W0vtRzPdlkySwoLEcmoA8f6GR1z1teXnXJfQ1Uxxfm5/OaowmKuUViISEY1JZb0WFd3aljk5BgbFpex96iW/ZhrFBYiklFNbX0ArKktnfD+DfXlalnMQQoLEcmoptZellUWUVo48aLWZywuo/X4IN39w1muTGZDYSEiGdXU1su6CcYrkpJjGY1agXZOUViISEbtP9bPqpqSSe9fVRPvnjrQ0ZetkiQDFBYikjHdA8N0DwyzctHkYbFiUTFmsL9dCwrOJQoLEcmYgx3xAFhRPXlYFOblsqyymAMdCou5RGEhIhmTXH58xWlaFgCrakrYf0zdUHOJwkJEMuZgxwAwlbAo5ZVjalnMJQoLEcmYAx39VBTlnbjg0WRW15TQ0TdET0ynz84VgYaFmV1hZi+ZWaOZ3TzB/YVm9o3E/dvMbPW4+1eaWa+ZfTrIOkUkMw529qdtVQAnzpY6oNbFnBFYWJhZLnAHcCWwEbjOzDaO2+0GoNPd1wNfAm4fd/+XgB8EVaOIZNbBjv7TDm4nJU+ffbld4xZzRZAti81Ao7vvc/ch4EHg6nH7XA3cm7j9EHC5mRmAmb0b2AfsDrBGEcmQsTGnuXOAlaeZY5GUbH0c6hoIuizJkCDDogE4mPJ9c2LbhPu4+wjQDdSYWSnwl8DnTvcCZnajmW03s+1tbW0ZK1xEpq+9b5DBkTGWVxen3besMD6ucahTYTFXBBkWNsE2n+I+nwO+5O6nXQ/A3e9y903uvqmurm6GZYpIJrR0xwBYMu7qeJNZVlXMYbUs5oyJV/rKjGZgRcr3y4HDk+zTbGZ5QCXQAVwCXGNmfwdUAWNmFnP3LwdYr4jMQjIsllamb1lA/NoWyXkZEn1BhsVTwAYzWwMcArYA7x+3z1bgeuBx4BrgUXd34LLkDmZ2G9CroBCJtpaeeFgsriyc0v4NVUVse/lYkCVJBgXWDZUYg7gJeATYA3zT3Xeb2efN7F2J3e4mPkbRCHwKOOX0WhGZG1q6Y+TlGLWlUwyL6mKOx0Y012KOCLJlgbs/DDw8bttnU27HgGvTPMdtgRQnIhnV0h1jcUUROTkTDUWeallVvLvqcNcAFUtOP4lPwqcZ3CKSEUe6YyypnNrgNsTHLAANcs8RCgsRyYijPTMLC50+OzcoLERk1tw93rKY4mmzALVlhRTk5nCoKxZgZZIpCgsRmbWe2AgDw6MsnUbLIifHWFJZpG6oOUJhISKzlpxjsXgaLQuIT+BrPa6WxVygsBCRWUvOsZhOywKgvqKQoz2DQZQkGaawEJFZa+mOdyVNZ4Ab4i2Roz0x4nNxJcoUFiIya0cS3VD15dPvhuofGuX44EgQZUkGKSxEZNaO9sTiZzflTe8jpb4iPtu7tUfjFlGnsBCRWYtPyJvaMh+pkgPiLd0at4g6hYWIzFpLd4wlFVNbbTZVcl7GUbUsIk9hISKz1tIzs5ZFshvqqE6fjTyFhYjMSmx4lK7+4SlfxyJVSUEe5UV5HO1WWESdwkJEZmW6V8gbL376rMYsok5hISKzkjxtdrpzLJKWVBSdmNQn0aWwEJFZSQ5OzzQs6isKdersHKCwEJFZOZKBbqjW44OMjWkWd5QpLERkVo72xCgvyqO0cGYX3lxSUcTImHOsbyjDlUkmKSxEZFaOdA/MuFUBUFceP3227bgGuaNMYSEis9IyzcupjldbFg+L9l6FRZQpLERkVlp6pneFvPFqywoAhUXUKSxEZMZGRsdoOz447etYpKotV8tiLlBYiMiMtfUOMuawZAazt5PKC/MoyMuhvVcD3FGmsBCRGXt1Qt7014VKMjPqygpp1wB3pCksRGTGXl3qY+YtC4CasgLadepspCksRGTGWma51EdSrVoWkaewEJEZa+mJUZCXQ3VJ/qyep7asQAPcEaewEJEZi1/0qAgzm9Xz1JYVcqxvSEt+RJjCQkRmbLYT8pJqywoZHXO6BoYzUJUEQWEhIjPW0hOb1RyLJM21iD6FhYjMiLuf6IaaLc3ijj6FhYjMSEffEEOjYyzOSFgkWxY6fTaqFBYiMiPJCXnLqjIYFjp9NrIUFiIyI8k5FktnsdRHUlVxPrk5pm6oCAs0LMzsCjN7ycwazezmCe4vNLNvJO7fZmarE9s3m9mziX/Pmdl7gqxTRKbvSPcAQEYGuHNyjJpSzbWIssDCwsxygTuAK4GNwHVmtnHcbjcAne6+HvgScHti+y5gk7tfAFwB/IuZzewyXCISiCPdMfJyjJqyma8LlaqmrJBjGrOIrCBbFpuBRnff5+5DwIPA1eP2uRq4N3H7IeByMzN373f3kcT2IkAzdUQipqU7xuKKInJzZjchL2lRaT6d/QqLqAoyLBqAgynfNye2TbhPIhy6gRoAM7vEzHYDO4E/TAkPEYmAw90DGemCSqouKaCzX5PyoirIsJjoz43xLYRJ93H3be5+DnAxcIuZnfJTaWY3mtl2M9ve1tY264JFZOoyNXs7aVFpAR1aeTayggyLZmBFyvfLgcOT7ZMYk6gEOlJ3cPc9QB9w7vgXcPe73H2Tu2+qq6vLYOkicjruzpHuzMzeTqouKaB7YJiR0bGMPadkTpBh8RSwwczWmFkBsAXYOm6frcD1idvXAI+6uycekwdgZquAM4H9AdYqItPQ1T/M4MhYRk6bTVpUGp/FrfWhoimwM4zcfcTMbgIeAXKBe9x9t5l9Htju7luBu4H7zayReItiS+LhbwRuNrNhYAz4Y3dvD6pWEZmewxk8bTapOhEWnX1DJybpSXQEejqquz8MPDxu22dTbseAayd43P3A/UHWJiIzl6mLHqVaVBIPC41bRJNmcIvItL261Efmu6F0+mw0KSxEZNpaumPk5lhGu4uSYdHRpzGLKFJYiMi0He4eYHF5YcYm5AFUJS7NqpZFNCksRGTaWrpjLM1gFxRAUX4upQW5GrOIKIWFiExbpifkJVWXFtCpsIgkhYWITIu7x5f6yMBFj8ZbVFpAh7qhIklhISLT0j0wTGx4LJiWRYlaFlGlsBCRaTnclfnTZpPUsoiuKYWFmX3bzH7XzBQuIgvcoa747O2GAMIi3rLQqbNRNNUP/zuB9wN7zexvzeysAGsSkQhr7uwHYHl1EC2LfHoHRxgcGc34c8vsTCks3P0n7v4B4CLiC/r92Mx+bWYfNrP8IAsUkWhp7hygOD/3xCS6TEquD9Wl61pEzpS7lcysBvgD4KPADuAfiIfHjwOpTEQiqbmzn+XVxZhlbkJektaHiq4pLSRoZt8BziK+uN873f1I4q5vmNn2oIoTkeg51DVAQwBdUHDyyrMSLVNddfbfEivInmBmhe4+6O6bAqhLRCKquXOAC1ZUBfLcJ9aH0hlRkTPVbqi/nmDb45ksRESi73hsmK7+YZZXlwTy/NUlallE1WlbFma2BGgAis3sQl69ZnYFEMxPi4hEVpCnzcKriwkeU1hETrpuqLcTH9ReDnwxZftx4K8CqklEIupQZzwsgjhtFiA/N4fywjydDRVBpw0Ld78XuNfM3uvu385STSISUc0nwiK4joXq0gItUx5B6bqhPujuXwVWm9mnxt/v7l+c4GEiMk81d/ZTmJdDbVnm51gkVZfk06mWReSk64YqTXwtC7oQEYm+5s74abNBzLFIqipRyyKK0nVD/Uvi6+eyU46IRNmhroFAu6Ag3rLY194b6GvI9E11IcG/M7MKM8s3s5+aWbuZfTDo4kQkWpo7BwIb3E6qKimgS4sJRs5U51m8zd17gHcAzcAZwF8EVpWIRE7v4AgdfUOBh0V1SQHHB0cYHh0L9HVkeqYaFsnFAq8CHnD3joDqEZGIeuVYHwCra0rT7Dk71aXxjxudPhstUw2L/zCzF4FNwE/NrA6IBVeWiETNK8fiS5Ovqgl2zKKqJLnyrAa5o2SqS5TfDLwO2OTuw0AfcHWQhYlItOxPtCxWBd2ySMzi1umz0TLVhQQBziY+3yL1MfdluB4RiahX2vupLSukrHA6HxvTV61lyiNpqkuU3w+sA54FkpewchQWIgvG/mN9rA64CwpSL4CksIiSqf6JsAnY6O4eZDEiEl2vHOvnDetrA38ddUNF01QHuHcBS4IsRESiKzY8SktPLPDBbYDi/FwK8nLUsoiYqbYsaoEXzOxJYDC50d3fFUhVIhIpBzqycyYUgJkl1odSWETJVMPitiCLEJFo29+enTkWSdUlBeqGipgphYW7/9zMVgEb3P0nZlYC5AZbmohERXKORbbCoqokX91QETPVtaE+BjwE/EtiUwPwvaCKEpFo2dfeS3VJPpUl+el3zgC1LKJnqgPcnwDeAPQAuPteoD7dg8zsCjN7ycwazezmCe4vNLNvJO7fZmarE9t/x8yeNrOdia+/PdX/kIhkXlNrH+vrs3elgqqSArUsImaqYTHo7ifeucTEvNOeRmtmucAdwJXARuA6M9s4brcbgE53Xw98Cbg9sb0deKe7nwdcD9w/xTpFJACNbb2sq8teWCQvgKSz9aNjqmHxczP7K6DYzH4H+BbwH2kesxlodPd9iaB5kFOXCLkauDdx+yHgcjMzd9/h7ocT23cDRWZWOMVaRSSDOvqG6OgbymrLorqkgNExpyc2krXXlNObaljcDLQBO4GPAw8D/zvNYxqAgynfNye2TbiPu48A3UDNuH3eC+xw90FEJOua2uIXIlqXzbDQLO7ImerZUGNm9j3ge+7eNsXnnui6i+PblKfdx8zOId419bYJX8DsRuBGgJUrV06xLBGZjqbWeFisz3I3FMRnca8a/+ejhOK0LQuLu83M2oEXgZfMrM3MPjuF524GVqR8vxw4PNk+iXGQSqAj8f1y4LvAh9y9aaIXcPe73H2Tu2+qq6ubQkkiMl2Nrb0U5uXQUBXsRY9SJZcp18S86EjXDfWnxM+Cutjda9x9EXAJ8AYz+7M0j30K2GBma8ysANgCbB23z1biA9gA1wCPurubWRXwX8At7v6rafx/RCTDmtp6WVtXRk7ORB0BwUi2LNQNFR3pwuJDwHXu/nJyg7vvAz6YuG9SiTGIm4BHgD3AN919t5l93sySy4TcDdSYWSPwKeJjIyQetx74jJk9m/iX9lRdEcm8xrberA5uw6vLlHfqWtyRkW7MIt/d28dvdPc2M0s7O8fdHyY+GJ667bMpt2PAtRM87q+Bv073/CISrNjwKM2dA7z3ouVZfd2K4nzM1LKIknQti9O9U3oXRea5l1qO4w5nLSnP6uvm5hiVxfmaxR0h6VoW55tZzwTbDSgKoB4RiZAXW+K//mcvrcj6a8eX/NDfpFFx2rBwdy0WKLKA7TlynNKCXFZUB780+XjxxQTVsoiKqU7KE5EFaM+RHs5cUp7VM6GSqksKdB3uCFFYiMiE3J09R3o4K4QuKNAy5VGjsBCRCR3pjtETG+HsLA9uJy3SMuWRorAQkQmFObgN8fWhBoZHiQ2PhvL6cjKFhYhMaM+R4wCcGVLLourELG61LqJAYSEiE9rZ3M2qmhLKi7JzdbzxqrU+VKQoLERkQs81d3H+8qrQXr/qxMqzCosoUFiIyCmO9sQ40h3j/BXhhUWyZaFuqGhQWIjIKZ472AXABSsqQ6tB3VDRorAQkVM819xFbo5xzrLwwkID3NGisBCRUzx3sJuzlpRTlB/eij9F+bkU5+dqFndEKCxE5CRjY85zzV1cEOJ4RVJ1Sb66oSJCYSEiJ2ls6+V4bCTUwe2k6tICdUNFhMJCRE6ybd8xAF63tibkSrRMeZQoLETkJE/s62BZZRHLq4vDLkXLlEeIwkJETnB3nth3jEvX1mCW/WXJx1PLIjoUFiJyQmNrL8f6hrhk7aKwSwHiA9zdA8OMjnnYpSx4CgsROeGXje0AvG5tbciVxFWVFOAOPQPqigqbwkJETnjspTbW1pWysib7l1GdSHWp1oeKCoWFiADQPzTCE/uO8Vtn1oddyglVWvIjMhQWIgLA403HGBoZi1RYnFgfqk/dUGFTWIgIAD/Zc5TSglwuXlMddiknVGuZ8shQWIgIw6Nj/GBXC2/duJjCvPDWgxqvulTLlEeFwkJE+FVjO139w7zjNcvCLuUk5YV55OWYWhYRoLAQEf7z+SOUF+XxpjOiccpskplRVZJPp1oWoVNYiCxwseFRHtndwts2LolUF1RSVUkBXWpZhE5hIbLAPbK7heOxEd5zYUPYpUxIy5RHg8JCZIH72rYDrKop4fXrwl9ldiLxloW6ocKmsBBZwBpbe3ny5Q62XLySnJzwFw6ciFoW0aCwEFnAHnzyAHk5xjWvXR52KZOqLimgs28Ydy0mGCaFhcgCFRse5dvPNPP2c5ZQV14YdjmTqiopYGh0jP6h0bBLWdACDQszu8LMXjKzRjO7eYL7C83sG4n7t5nZ6sT2GjN7zMx6zezLQdYoslA9sruFzv5hrtu8MuxSTkuzuKMhsLAws1zgDuBKYCNwnZltHLfbDUCnu68HvgTcntgeAz4DfDqo+kQWuq9vO8DKRdEd2E5KLiaoQe5wBdmy2Aw0uvs+dx8CHgSuHrfP1cC9idsPAZebmbl7n7v/knhoiEiGNbX1su3lDrZsXhHZge2kRaVaeTYKggyLBuBgyvfNiW0T7uPuI0A3EO0/c0TmgQe2xQe2r33tirBLSevVbii1LMIUZFhM9OfK+NMZprLP5C9gdqOZbTez7W1tbdMqTmShSg5sv+2cxZEe2E6qKYvX2H58MORKFrYgw6IZSP2zZTlweLJ9zCwPqAQ6pvoC7n6Xu29y9011dXWzLFdkYfjhrrkxsJ1UVZxPfq7RqrAIVZBh8RSwwczWmFkBsAXYOm6frcD1idvXAI+6TqYWCdR9j+9nTW0pb1gXrUUDJ5OTY9SWFdKmsAhVXlBP7O4jZnYT8AiQC9zj7rvN7PPAdnffCtwN3G9mjcRbFFuSjzez/UAFUGBm7wbe5u4vBFWvyEKw61A3zxzo4jPv2Bj5ge1U9eWFtB7X+S5hCiwsANz9YeDhcds+m3I7Blw7yWNXB1mbyEJ03+P7Kc7PjfSM7YnUlRfR3NkfdhkLmmZwiywQXf1DfP/Zw7z7wgYqi/PDLmda6srVDRU2hYXIAvGt7c0MjozxodetCruUaasvL6Sjf4jh0bGwS1mwFBYiC8Dw6Bhf+fV+Nq9ZxNlLK8IuZ9rqygtxh2O9mpgXFoWFyALwvR2HONQ1wB+9eV3YpcxIfWI+iAa5w6OwEJnnRsecO3/WxMalFbzlzLk5H6m+oghA4xYhUliIzHPf23GIfe19fOK31mM2d06XTVV3omWhsAiLwkJkHusbHOH2H77I+SuquPLcJWGXM2O1ZfHFBNWyCI/CQmQe++KPf0Pr8UE+O8cm4Y1XmJdLdUk+R3s0ZhEWhYXIPPWLvW3c/cuX+R+XruK1q6rDLmfWllUVc7hrIOwyFiyFhcg81Njay/98YAcb6su49XfPDrucjGioKuaQwiI0CguReaaprZcP3b2NvBzj7usvpig/N+ySMqKhuphDnQNordFwKCxE5pFnD3ZxzZ2/Zmh0jHs/spmVNSVhl5QxDVXF9A2N0j2giyCFQWEhMk889mIr1931BOVF+Tz0h6/nnGWVYZeUUcuriwFo7lRXVBgUFiLzwDe3H+Sj921nXX0pD/3R61hdWxp2SRm3rCoeFhq3CEegS5SLSLDcnS8/2sgXfvwbLttQy50ffC1lhfPz17ohGRZqWYRifv5UiSwAo2POZ7+/i69tO8DvXdjA3773NRTkzd/OgkWlBRTl56hlERKFhcgcNDA0yp88uIMfv3CUP3rLOv7X28+cs0t5TJWZxU+fVcsiFAoLkQC1dMf4zo5m3OFd5y9jxaLZn53U0TfEDfc+xbMHu/jcu87h+tevnn2hc8Ty6hKau3TFvDAoLEQCsn1/B3/w70/ROzgCwB2PNfKFa8/nyvOWzvg5dx3q5o+/9gxHe2Lc+YGLuOLcmT/XXLSmtpSn9nfg7vO+JRU187eDUyREBzv6+fC/P0V9eSE//4u38Kubf5uzlpRz0wM7eOyl1mk/n7vz9W0H+L07f83w6BgP3HjpggsKgHX1ZfQPjdKiNaKyTmEhkmHuzp9/6zkA7v3IZlbVlNJQVcy9H9nMWUvK+eOvPsPuw91Tfr7Wnhgfu+9p/uq7O7lkzSL+608u46KVc3+tp5lYVxc/JbiptS/kShYehYVIhj28s4UnX+7g1t89+6QxivKifP79wxdTVZLPx+7dnvaqb+7Od55p5q1f/Dm/2NvGrVedzVc+vJlFpQVB/xcia31dGRBf0kSyS2EhkkGDI6Pc/sMXOWtJOdduWnHK/fXlRfzrhzbR2T/Mjfc9TWx4dMLnOdw1wEfv3c6nvvkcZywu5wefvIyPvWktuXN4mfFMqCsvpLwwT2ERAoWFSAZ99YkDHOjo55arzp70g/3chkq+9L4LePZgF9ff8+RJF/Q5HhvmH3+6l8u/8HN+1dTOZ96xkW98/HWsTfxFvdCZGevqy3ip5XjYpSw4OhtKJEO6++Mf9JdtqOXNZ5z+WtdXnLuEf9hyAX/xred5y98/xhs31DI6Bo83tdM3NMpV5y3hlivPzsiptvPNeQ2VfHfHIcbGfE5f0GmuUViIZMg/PbqXntgwt1w5tetHXH1BA+c1VHLnz5p4+pVOcnKMd56/jPdfspLXLK8KuNq567zlldz/xCu8fKyPdWpxZY3CQiQD9rX18pVf7+d9m1awcVnFlB+3tq6Mv7/2/AArm39eszy+mu7O5m6FRRZpzEJkltydv/mvPRTl5/Lnbzsz7HLmvfV1ZRTl5/Bcc1fYpSwoCguRWfrujkP89MVWPnn5BurKC8MuZ97Ly83hwhXVPN50LOxSFhSFhcgsNLYe5/98fzcXr67mI29cE3Y5C8abzqjjxZbjtGomd9YoLERm6MCxfq6/5ykK83P54u9fsODnQGTTZRtqAfjF3vaQK1k4FBYi0zQ25nz/2UO888u/5HhsmK98+GKd4pplG5dWsLiikId3Hgm7lAVDZ0PJtA2PjpGXY3N+1U93p2dgBAzMID8nh/xcIzfl/xYbHqVnYJjW44M0tfWys7mbH71wlAMd/ZzXUMmX338hq2rm3yVMoy4nx/i9i5Zz13/vo7UnRn1FUdglzXsKC5mSHQc6eeDJA/xybzuHu2Pk5xrr6sq4/Ox6rtu8kuXV0fzL2t3piY1wqHOAfe29NLX20dTWy772Xva19dE/dOpyG2ZQkBtvdA+OjJ10X36u8fp1tXz67WfyjvOWalJYiH5/0wru/FkT9z3+Cp9+u85CC1qgYWFmVwD/AOQC/+bufzvu/kLgPuC1wDHgfe6+P3HfLcANwCjwJ+7+SJC1ysSefLmDf3p0L7/Y205ZYR5vPrOOa+vKGBwZ47mDXdz5sybu/FkTbz17MR954xouWbMoqy0Od+dY3xBNrb00tvXS2NrLoc4B2noHaTse/5f6gW8Wv5bz2royLl69iIaqYswMd2dkzBkaGWN4dIyh0TFwqCjOp7I4n5rSAtbWlbG6toTCvNys/f9kcmtqS3nn+cv4t1/u47pLVp64RrcEI7CwMLNc4A7gd4Bm4Ckz2+ruL6TsdgPQ6e7rzWwLcDvwPjPbCGwBzgGWAT8xszPcfeJV1ySj3J1fNx3jnx7dyxP7OqgtK+CWK8/iA5euoqzw5B+ZQ10DfO2JV3jgyQP86IWjbFxawXWbV/DbZy+e8S+vuzM4MsbA0CiDI2PEhuNf+4ZGONIV42BnP/vb+2hMBERX//CJxxbn57JiUTH15UWsWV1KXXkhdeWFLKksYl1dGWtqSynK14f9fPGXV5zJT/cc5eP3b+frH7uUiqL8sEuat8zdg3lis9cBt7n72xPf3wLg7v8vZZ9HEvs8bmZ5QAtQB9ycum/qfpO93qZNm3z79u2B/F/mu9jwKEd7YrzUcpynX+nk4V1HONgxQF15IX/45nW8f/NKigtO/wEbGx7lezsOcc+vXuY3R+Mrgi6pKGJdfSmLSgspK8wFjKGR+F/tseFRBoZG6R8aoX9olIHh0fjXxLaxND+WNaUFrKsvY319Gevq4l/X15extKJIXUMLzE/3HOXG+59maWURN/3Wei47o04/B9NgZk+7+6Z0+wXZDdUAHEyDxkhyAAAG60lEQVT5vhm4ZLJ93H3EzLqBmsT2J8Y9tiGIIl9s6eGmr+8gUUP8a+oOzinbxu+Xmree2HrStgk++CZ6LT/xWj7Btomea4LXGvf8k9aZ+GbMOXHZT4C8HOPStTX82VvP4Krzlk75r/Ci/Fy2bF7J+y5eQVNbLz97qY0XjvSwr62Pw13dHI+NnBgLyM81ivJzKSnIpaQgj5qywsTtXIrz8+JfT3yfS2F+DoV58duLK4pYsaiYcv0FKQmXn72Yb378Um797i5u/s5OIP5zXF1aQH6OkZtr5OXkkGPM+ZMyJvOWM+r43+/YGOhrBBkWE70r4z82J9tnKo/FzG4EbgRYuXLldOsDoCgvlzMXl59SUWoByR+wk7edvF/qD6GdcgMs8Y2dtI0Jtk2w37gnnNFzTFBncp/askLqywtZXVvKeQ2Vs+qmMTPW15ezvr48/c4iGfLaVYv4wScvY/fhHnYc6ORId4zO/iGGR53RsVf/zVdLszBeE2RYNAOpV39ZDhyeZJ/mRDdUJdAxxcfi7ncBd0G8G2omRa6uLeWOD1w0k4eKSISYGec2VHJuQ2XYpcxLQU7KewrYYGZrzKyA+ID11nH7bAWuT9y+BnjU4/0jW4EtZlZoZmuADcCTAdYqIiKnEVjLIjEGcRPwCPFTZ+9x991m9nlgu7tvBe4G7jezRuItii2Jx+42s28CLwAjwCd0JpSISHgCOxsq23Q2lIjI9E31bCitDSUiImkpLEREJC2FhYiIpKWwEBGRtBQWIiKS1rw5G8rM2oBXZvEUtUAUL7uluqZHdU2P6pqe+VjXKnevS7fTvAmL2TKz7VM5fSzbVNf0qK7pUV3Ts5DrUjeUiIikpbAQEZG0FBavuivsAiahuqZHdU2P6pqeBVuXxixERCQttSxERCStBR0WZnabmR0ys2cT/65Kue8WM2s0s5fM7O1ZruvvzexFM3vezL5rZlWJ7avNbCCl3n/OZl2JGq5IHJNGM7s526+fUscKM3vMzPaY2W4z+2Ri+6TvaRZr229mOxOvvz2xbZGZ/djM9ia+Vme5pjNTjsmzZtZjZn8a1vEys3vMrNXMdqVsm/AYWdw/Jn7mnjezQC5AM0lNkfhdnKS27H5+ufuC/QfcBnx6gu0bgeeAQmAN0ATkZrGutwF5idu3A7cnbq8GdoV4vHITx2ItUJA4RhtDqmUpcFHidjnwm8T7NuF7muXa9gO147b9HXBz4vbNyfc0xPexBVgV1vEC3gRclPrzPNkxAq4CfkD8go+XAtuyWFMkfhcnqS2rn18LumVxGlcDD7r7oLu/DDQCm7P14u7+I3dPXhj7CeJXCoyCzUCju+9z9yHgQeLHKuvc/Yi7P5O4fRzYQ0DXac+Qq4F7E7fvBd4dYi2XA03uPptJrLPi7v9N/Bo2qSY7RlcD93ncE0CVmS3NRk1R+V2c5HhNJpDPL4UF3JRoYt6T0jXQABxM2aeZ8D6IPkL8r6qkNWa2w8x+bmaXZbmWKB2XE8xsNXAhsC2xaaL3NJsc+JGZPW3x68QDLHb3IxAPOqA+hLqStgAPpHwf9vFKmuwYReXnLkq/i0lZ+/ya92FhZj8xs10T/LsauBNYB1wAHAG+kHzYBE+V0dPG0tSV3OdW4lcK/Fpi0xFgpbtfCHwK+LqZVWSyrnRlT7At1NPpzKwM+Dbwp+7ew+TvaTa9wd0vAq4EPmFmbwqhhglZ/BLH7wK+ldgUheOVTug/dxH8XYQsf34FdlnVqHD3t05lPzP7V+A/E982AytS7l4OHM5mXWZ2PfAO4HJPdES6+yAwmLj9tJk1AWcA2bpEYODHZTrMLJ94UHzN3b8D4O5HU+5PfU+zxt0PJ762mtl3iXcBHDWzpe5+JNGF0prtuhKuBJ5JHqcoHK8Ukx2jUH/uIvq7eLr3LpDjNe9bFqczrt/zPUDyTIOtwBYzKzSzNcAG4Mks1nUF8JfAu9y9P2V7nZnlJm6vTdS1L1t1AU8BG8xsTeIv1C3Ej1XWmZkRv4b7Hnf/Ysr2yd7TbNVVamblydvEB0h3ET9O1yd2ux74fjbrSnEdKV1QYR+vcSY7RluBDyXOiroU6E52VwUtwr+L2f/8ytZofhT/AfcDO4HnEwd4acp9txI/i+Al4Mos19VIvM/x2cS/f05sfy+wm/iZDs8A7wzhmF1F/MyjJuDWEN+7NxJvWj+fcpyuOt17mqW61iben+cS79Wtie01wE+BvYmvi0I4ZiXAMaAyZVsox4t4YB0Bhon/JXzDZMeIeLfKHYmfuZ3ApizWFInfxUlqy+rnl2Zwi4hIWgu6G0pERKZGYSEiImkpLEREJC2FhYiIpKWwEBGRtBQWIiKSlsJCRETSUliIiEha/x9/Ap1wuE1D5AAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.regularite.plot(kind=\"density\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### exercices : faire un histogramme nb de valeurs dans famille de transports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_pour_histogram = df.famille_transport.value_counts().plot(kind='bar')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## grouper par catégorie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<pandas.core.groupby.generic.DataFrameGroupBy object at 0x1129cba58>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"famille_transport\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'intercites'"
      ]
     },
     "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>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>35</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>intercites</td>\n",
       "      <td>global</td>\n",
       "      <td>81.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>36</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Limoges-Toulouse</td>\n",
       "      <td>85.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>37</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Clermont</td>\n",
       "      <td>93.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>38</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Bordeaux-Marseille</td>\n",
       "      <td>66.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>39</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Bordeaux</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4080</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4081</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>87.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4082</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4083</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>83.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4084</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1110 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport  \\\n",
       "35   2019-01-23        intercites   \n",
       "36   2019-01-23        intercites   \n",
       "37   2019-01-23        intercites   \n",
       "38   2019-01-23        intercites   \n",
       "39   2019-01-23        intercites   \n",
       "...         ...               ...   \n",
       "4080 2020-03-13        intercites   \n",
       "4081 2020-03-13        intercites   \n",
       "4082 2020-03-13        intercites   \n",
       "4083 2020-03-13        intercites   \n",
       "4084 2020-03-13        intercites   \n",
       "\n",
       "                                             ligne  regularite explication  \n",
       "35                                          global        81.9         NaN  \n",
       "36                          Paris-Limoges-Toulouse        85.0         NaN  \n",
       "37                                  Paris-Clermont        93.8         NaN  \n",
       "38                              Bordeaux-Marseille        66.7         NaN  \n",
       "39                                 Nantes-Bordeaux       100.0         NaN  \n",
       "...                                            ...         ...         ...  \n",
       "4080                                   Nantes-Lyon        75.0         NaN  \n",
       "4081                              Toulouse-Bayonne        87.5         NaN  \n",
       "4082                              Clermont-Béziers       100.0         NaN  \n",
       "4083  Paris-Toulouse-Latour De Carol/Cerbere/Rodez        83.3         NaN  \n",
       "4084                                Paris-Briançon       100.0         NaN  \n",
       "\n",
       "[1110 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'ter'"
      ]
     },
     "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>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>16</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>ter</td>\n",
       "      <td>global</td>\n",
       "      <td>87.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>17</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>ter</td>\n",
       "      <td>Grand Est</td>\n",
       "      <td>91.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>18</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>ter</td>\n",
       "      <td>Nouvelle-Aquitaine</td>\n",
       "      <td>96.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>19</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>ter</td>\n",
       "      <td>Auvergne-Rhône-Alpes</td>\n",
       "      <td>86.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>20</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>ter</td>\n",
       "      <td>Bourgogne-Franche-Comté</td>\n",
       "      <td>90.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4063</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>ter</td>\n",
       "      <td>Occitanie</td>\n",
       "      <td>91.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4064</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>ter</td>\n",
       "      <td>Hauts-de-France</td>\n",
       "      <td>93.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4065</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>ter</td>\n",
       "      <td>Normandie</td>\n",
       "      <td>94.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4066</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>ter</td>\n",
       "      <td>Pays de la Loire</td>\n",
       "      <td>92.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4067</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>ter</td>\n",
       "      <td>Provence-Alpes-Côte d'Azur</td>\n",
       "      <td>94.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1020 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport                       ligne  regularite  \\\n",
       "16   2019-01-23               ter                      global        87.8   \n",
       "17   2019-01-23               ter                   Grand Est        91.4   \n",
       "18   2019-01-23               ter          Nouvelle-Aquitaine        96.4   \n",
       "19   2019-01-23               ter        Auvergne-Rhône-Alpes        86.5   \n",
       "20   2019-01-23               ter     Bourgogne-Franche-Comté        90.3   \n",
       "...         ...               ...                         ...         ...   \n",
       "4063 2020-03-13               ter                   Occitanie        91.5   \n",
       "4064 2020-03-13               ter             Hauts-de-France        93.6   \n",
       "4065 2020-03-13               ter                   Normandie        94.6   \n",
       "4066 2020-03-13               ter            Pays de la Loire        92.9   \n",
       "4067 2020-03-13               ter  Provence-Alpes-Côte d'Azur        94.4   \n",
       "\n",
       "     explication  \n",
       "16           NaN  \n",
       "17           NaN  \n",
       "18           NaN  \n",
       "19           NaN  \n",
       "20           NaN  \n",
       "...          ...  \n",
       "4063         NaN  \n",
       "4064         NaN  \n",
       "4065         NaN  \n",
       "4066         NaN  \n",
       "4067         NaN  \n",
       "\n",
       "[1020 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'tgv'"
      ]
     },
     "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>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>28</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>tgv</td>\n",
       "      <td>global</td>\n",
       "      <td>52.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>29</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>tgv</td>\n",
       "      <td>nord</td>\n",
       "      <td>11.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>30</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>tgv</td>\n",
       "      <td>est</td>\n",
       "      <td>12.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>tgv</td>\n",
       "      <td>atlantique</td>\n",
       "      <td>88.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>32</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>tgv</td>\n",
       "      <td>sudest</td>\n",
       "      <td>48.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4070</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>tgv</td>\n",
       "      <td>est</td>\n",
       "      <td>87.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4071</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>tgv</td>\n",
       "      <td>atlantique</td>\n",
       "      <td>83.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4072</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>tgv</td>\n",
       "      <td>sudest</td>\n",
       "      <td>95.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4073</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>tgv</td>\n",
       "      <td>ouigo</td>\n",
       "      <td>96.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4074</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>tgv</td>\n",
       "      <td>europe</td>\n",
       "      <td>76.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>595 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport       ligne  regularite explication\n",
       "28   2019-01-23               tgv      global        52.2         NaN\n",
       "29   2019-01-23               tgv        nord        11.8         NaN\n",
       "30   2019-01-23               tgv         est        12.3         NaN\n",
       "31   2019-01-23               tgv  atlantique        88.7         NaN\n",
       "32   2019-01-23               tgv      sudest        48.8         NaN\n",
       "...         ...               ...         ...         ...         ...\n",
       "4070 2020-03-13               tgv         est        87.1         NaN\n",
       "4071 2020-03-13               tgv  atlantique        83.6         NaN\n",
       "4072 2020-03-13               tgv      sudest        95.7         NaN\n",
       "4073 2020-03-13               tgv       ouigo        96.7         NaN\n",
       "4074 2020-03-13               tgv      europe        76.8         NaN\n",
       "\n",
       "[595 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'transilien'"
      ]
     },
     "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>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>84.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>88.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>84.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>74.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4051</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>transilien</td>\n",
       "      <td>P</td>\n",
       "      <td>85.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4052</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>transilien</td>\n",
       "      <td>R</td>\n",
       "      <td>91.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4053</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>transilien</td>\n",
       "      <td>U</td>\n",
       "      <td>97.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4054</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>transilien</td>\n",
       "      <td>T4</td>\n",
       "      <td>87.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4055</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>transilien</td>\n",
       "      <td>T11</td>\n",
       "      <td>85.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1360 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport   ligne  regularite explication\n",
       "0    2019-01-23        transilien  global        84.2         NaN\n",
       "1    2019-01-23        transilien       A        82.1         NaN\n",
       "2    2019-01-23        transilien       B        88.9         NaN\n",
       "3    2019-01-23        transilien       C        84.3         NaN\n",
       "4    2019-01-23        transilien       D        74.5         NaN\n",
       "...         ...               ...     ...         ...         ...\n",
       "4051 2020-03-13        transilien       P        85.8         NaN\n",
       "4052 2020-03-13        transilien       R        91.9         NaN\n",
       "4053 2020-03-13        transilien       U        97.7         NaN\n",
       "4054 2020-03-13        transilien      T4        87.0         NaN\n",
       "4055 2020-03-13        transilien     T11        85.7         NaN\n",
       "\n",
       "[1360 rows x 5 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for x,y in df.groupby([\"famille_transport\"]):\n",
    "    display(x)\n",
    "    display(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regularite</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>famille_transport</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>intercites</td>\n",
       "      <td>72.995356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>ter</td>\n",
       "      <td>90.004804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>tgv</td>\n",
       "      <td>87.241176</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>transilien</td>\n",
       "      <td>88.283180</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   regularite\n",
       "famille_transport            \n",
       "intercites          72.995356\n",
       "ter                 90.004804\n",
       "tgv                 87.241176\n",
       "transilien          88.283180"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"famille_transport\"]).mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## définir votre propre fonction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fonction(a):\n",
    "    return sum(a)**2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "famille_transport\n",
       "intercites             NaN\n",
       "ter           8.428140e+09\n",
       "tgv           2.694492e+09\n",
       "transilien             NaN\n",
       "Name: regularite, dtype: float64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([\"famille_transport\"])[\"regularite\"].apply(fonction)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## filtrer un dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "loc [ lignes , colonnes]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>84.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>88.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>84.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>74.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        date famille_transport   ligne  regularite explication\n",
       "0 2019-01-23        transilien  global        84.2         NaN\n",
       "1 2019-01-23        transilien       A        82.1         NaN\n",
       "2 2019-01-23        transilien       B        88.9         NaN\n",
       "3 2019-01-23        transilien       C        84.3         NaN\n",
       "4 2019-01-23        transilien       D        74.5         NaN"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ligne                           A\n",
       "regularite                   82.1\n",
       "date          2019-01-23 00:00:00\n",
       "Name: 1, dtype: object"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[1, [\"ligne\", \"regularite\", \"date\"] ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ligne</th>\n",
       "      <th>date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>A</td>\n",
       "      <td>2019-01-23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>B</td>\n",
       "      <td>2019-01-23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>C</td>\n",
       "      <td>2019-01-23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  ligne       date\n",
       "1     A 2019-01-23\n",
       "2     B 2019-01-23\n",
       "3     C 2019-01-23"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[1:3,  [\"ligne\", \"date\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "fin_aout = pd.to_datetime(\"31/08/2019\", format=\"%d/%m/%Y\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "debut_juillet = pd.to_datetime(\"01/06/2019\", format=\"%d/%m/%Y\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "entre = (df[\"date\"] > debut_juillet) & (df[\"date\"]< fin_aout)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "scrolled": false
   },
   "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>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>98</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>90.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>99</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>91.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>100</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>85.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>101</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>92.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>102</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>79.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>103</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>E</td>\n",
       "      <td>95.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>104</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>H</td>\n",
       "      <td>89.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>105</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>J</td>\n",
       "      <td>92.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>106</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>K</td>\n",
       "      <td>95.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>107</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>L</td>\n",
       "      <td>95.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>108</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>N</td>\n",
       "      <td>96.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>109</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>P</td>\n",
       "      <td>90.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>110</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>R</td>\n",
       "      <td>85.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>111</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>U</td>\n",
       "      <td>99.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>112</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>T4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Travaux</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>113</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>transilien</td>\n",
       "      <td>T11</td>\n",
       "      <td>98.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>114</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>global</td>\n",
       "      <td>92.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>115</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Grand Est</td>\n",
       "      <td>96.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>116</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Nouvelle-Aquitaine</td>\n",
       "      <td>91.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>117</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Auvergne-Rhône-Alpes</td>\n",
       "      <td>89.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>118</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Bourgogne-Franche-Comté</td>\n",
       "      <td>93.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>119</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Bretagne</td>\n",
       "      <td>96.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>120</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Centre-Val de Loire</td>\n",
       "      <td>95.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>121</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Occitanie</td>\n",
       "      <td>81.8</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>122</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Hauts-de-France</td>\n",
       "      <td>87.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>123</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Normandie</td>\n",
       "      <td>91.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>124</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Pays de la Loire</td>\n",
       "      <td>90.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>125</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>ter</td>\n",
       "      <td>Provence-Alpes-Côte d'Azur</td>\n",
       "      <td>93.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>126</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>global</td>\n",
       "      <td>86.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>127</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>nord</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>128</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>est</td>\n",
       "      <td>96.6</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>129</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>atlantique</td>\n",
       "      <td>86.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>130</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>sudest</td>\n",
       "      <td>79.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>131</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>ouigo</td>\n",
       "      <td>90.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>132</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>tgv</td>\n",
       "      <td>europe</td>\n",
       "      <td>91.2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>133</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>global</td>\n",
       "      <td>68.9</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>134</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Limoges-Toulouse</td>\n",
       "      <td>85.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>135</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Clermont</td>\n",
       "      <td>57.1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>136</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Bordeaux-Marseille</td>\n",
       "      <td>66.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>137</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Bordeaux</td>\n",
       "      <td>83.3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>138</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>139</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>62.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>140</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>141</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Caen-Cherbourg Trouville/Deauville</td>\n",
       "      <td>47.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>142</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Rouen-Le Havre</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>143</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Granville</td>\n",
       "      <td>80.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>144</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Caen-Le Mans-Tours</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>145</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>146</td>\n",
       "      <td>2019-07-09</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          date famille_transport  \\\n",
       "98  2019-07-09        transilien   \n",
       "99  2019-07-09        transilien   \n",
       "100 2019-07-09        transilien   \n",
       "101 2019-07-09        transilien   \n",
       "102 2019-07-09        transilien   \n",
       "103 2019-07-09        transilien   \n",
       "104 2019-07-09        transilien   \n",
       "105 2019-07-09        transilien   \n",
       "106 2019-07-09        transilien   \n",
       "107 2019-07-09        transilien   \n",
       "108 2019-07-09        transilien   \n",
       "109 2019-07-09        transilien   \n",
       "110 2019-07-09        transilien   \n",
       "111 2019-07-09        transilien   \n",
       "112 2019-07-09        transilien   \n",
       "113 2019-07-09        transilien   \n",
       "114 2019-07-09               ter   \n",
       "115 2019-07-09               ter   \n",
       "116 2019-07-09               ter   \n",
       "117 2019-07-09               ter   \n",
       "118 2019-07-09               ter   \n",
       "119 2019-07-09               ter   \n",
       "120 2019-07-09               ter   \n",
       "121 2019-07-09               ter   \n",
       "122 2019-07-09               ter   \n",
       "123 2019-07-09               ter   \n",
       "124 2019-07-09               ter   \n",
       "125 2019-07-09               ter   \n",
       "126 2019-07-09               tgv   \n",
       "127 2019-07-09               tgv   \n",
       "128 2019-07-09               tgv   \n",
       "129 2019-07-09               tgv   \n",
       "130 2019-07-09               tgv   \n",
       "131 2019-07-09               tgv   \n",
       "132 2019-07-09               tgv   \n",
       "133 2019-07-09        intercites   \n",
       "134 2019-07-09        intercites   \n",
       "135 2019-07-09        intercites   \n",
       "136 2019-07-09        intercites   \n",
       "137 2019-07-09        intercites   \n",
       "138 2019-07-09        intercites   \n",
       "139 2019-07-09        intercites   \n",
       "140 2019-07-09        intercites   \n",
       "141 2019-07-09        intercites   \n",
       "142 2019-07-09        intercites   \n",
       "143 2019-07-09        intercites   \n",
       "144 2019-07-09        intercites   \n",
       "145 2019-07-09        intercites   \n",
       "146 2019-07-09        intercites   \n",
       "\n",
       "                                            ligne  regularite explication  \n",
       "98                                         global        90.0         NaN  \n",
       "99                                              A        91.9         NaN  \n",
       "100                                             B        85.6         NaN  \n",
       "101                                             C        92.4         NaN  \n",
       "102                                             D        79.2         NaN  \n",
       "103                                             E        95.8         NaN  \n",
       "104                                             H        89.1         NaN  \n",
       "105                                             J        92.4         NaN  \n",
       "106                                             K        95.0         NaN  \n",
       "107                                             L        95.4         NaN  \n",
       "108                                             N        96.0         NaN  \n",
       "109                                             P        90.9         NaN  \n",
       "110                                             R        85.5         NaN  \n",
       "111                                             U        99.0         NaN  \n",
       "112                                            T4         NaN     Travaux  \n",
       "113                                           T11        98.0         NaN  \n",
       "114                                        global        92.0         NaN  \n",
       "115                                     Grand Est        96.8         NaN  \n",
       "116                            Nouvelle-Aquitaine        91.5         NaN  \n",
       "117                          Auvergne-Rhône-Alpes        89.9         NaN  \n",
       "118                       Bourgogne-Franche-Comté        93.2         NaN  \n",
       "119                                      Bretagne        96.9         NaN  \n",
       "120                           Centre-Val de Loire        95.8         NaN  \n",
       "121                                     Occitanie        81.8         NaN  \n",
       "122                               Hauts-de-France        87.9         NaN  \n",
       "123                                     Normandie        91.9         NaN  \n",
       "124                              Pays de la Loire        90.4         NaN  \n",
       "125                    Provence-Alpes-Côte d'Azur        93.2         NaN  \n",
       "126                                        global        86.3         NaN  \n",
       "127                                          nord        82.1         NaN  \n",
       "128                                           est        96.6         NaN  \n",
       "129                                    atlantique        86.1         NaN  \n",
       "130                                        sudest        79.4         NaN  \n",
       "131                                         ouigo        90.4         NaN  \n",
       "132                                        europe        91.2         NaN  \n",
       "133                                        global        68.9         NaN  \n",
       "134                        Paris-Limoges-Toulouse        85.0         NaN  \n",
       "135                                Paris-Clermont        57.1         NaN  \n",
       "136                            Bordeaux-Marseille        66.7         NaN  \n",
       "137                               Nantes-Bordeaux        83.3         NaN  \n",
       "138                                   Nantes-Lyon        75.0         NaN  \n",
       "139                              Toulouse-Bayonne        62.5         NaN  \n",
       "140                              Clermont-Béziers       100.0         NaN  \n",
       "141      Paris-Caen-Cherbourg Trouville/Deauville        47.4         NaN  \n",
       "142                          Paris-Rouen-Le Havre        75.0         NaN  \n",
       "143                               Paris-Granville        80.0         NaN  \n",
       "144                            Caen-Le Mans-Tours       100.0         NaN  \n",
       "145  Paris-Toulouse-Latour De Carol/Cerbere/Rodez       100.0         NaN  \n",
       "146                                Paris-Briançon       100.0         NaN  "
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[ entre, :]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### exercice: filtrer sur les RER A, B, C, D, E et F"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_que_RER = df.loc[ df[\"ligne\"].isin([\"A\",\"B\",\"C\",\"D\",\"E\"]) , :   ]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## fonctions utiles / splits et joins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "string = \"2019-02-01\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2019', '02', '01']"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "string.split('-')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "liste = [\"2019\", \"01\", \"30\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2019/01/30'"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"/\".join(liste)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## appliquer une fonction sur une colonne"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "def retrouve_le_mois_a_partir_de_strin(une_date):\n",
    "    return une_date.split(\"-\")[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'01'"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "retrouve_le_mois_a_partir_de_strin(\"2019-01-30\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "def retrouve_le_mois(une_date_DATETIME):\n",
    "    return une_date_DATETIME.month"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"mois\"] = df.date.apply(lambda x: x.month)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>famille_transport</th>\n",
       "      <th>ligne</th>\n",
       "      <th>regularite</th>\n",
       "      <th>explication</th>\n",
       "      <th>mois</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>global</td>\n",
       "      <td>84.2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>A</td>\n",
       "      <td>82.1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>B</td>\n",
       "      <td>88.9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>C</td>\n",
       "      <td>84.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>2019-01-23</td>\n",
       "      <td>transilien</td>\n",
       "      <td>D</td>\n",
       "      <td>74.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\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",
       "      <td>4080</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Nantes-Lyon</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4081</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Toulouse-Bayonne</td>\n",
       "      <td>87.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4082</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Clermont-Béziers</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4083</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Toulouse-Latour De Carol/Cerbere/Rodez</td>\n",
       "      <td>83.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4084</td>\n",
       "      <td>2020-03-13</td>\n",
       "      <td>intercites</td>\n",
       "      <td>Paris-Briançon</td>\n",
       "      <td>100.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4085 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date famille_transport  \\\n",
       "0    2019-01-23        transilien   \n",
       "1    2019-01-23        transilien   \n",
       "2    2019-01-23        transilien   \n",
       "3    2019-01-23        transilien   \n",
       "4    2019-01-23        transilien   \n",
       "...         ...               ...   \n",
       "4080 2020-03-13        intercites   \n",
       "4081 2020-03-13        intercites   \n",
       "4082 2020-03-13        intercites   \n",
       "4083 2020-03-13        intercites   \n",
       "4084 2020-03-13        intercites   \n",
       "\n",
       "                                             ligne  regularite explication  \\\n",
       "0                                           global        84.2         NaN   \n",
       "1                                                A        82.1         NaN   \n",
       "2                                                B        88.9         NaN   \n",
       "3                                                C        84.3         NaN   \n",
       "4                                                D        74.5         NaN   \n",
       "...                                            ...         ...         ...   \n",
       "4080                                   Nantes-Lyon        75.0         NaN   \n",
       "4081                              Toulouse-Bayonne        87.5         NaN   \n",
       "4082                              Clermont-Béziers       100.0         NaN   \n",
       "4083  Paris-Toulouse-Latour De Carol/Cerbere/Rodez        83.3         NaN   \n",
       "4084                                Paris-Briançon       100.0         NaN   \n",
       "\n",
       "      mois  \n",
       "0        1  \n",
       "1        1  \n",
       "2        1  \n",
       "3        1  \n",
       "4        1  \n",
       "...    ...  \n",
       "4080     3  \n",
       "4081     3  \n",
       "4082     3  \n",
       "4083     3  \n",
       "4084     3  \n",
       "\n",
       "[4085 rows x 6 columns]"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Mapping de valeurs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "dico_mapping_mois= {1:\"Janvier\",2:\"Février\",\n",
    "                   3: \"Mars\", 4: \"Avril\",\n",
    "                   5: \"Mai\", 6:\"Juin\",\n",
    "                   7:\"Juillet\", 8:\"Aout\",\n",
    "                   9:\"Septembre\", 10: \"Octobre\",\n",
    "                   11:\"Novembre\", 12: \"Décembre\"}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1: 'Janvier',\n",
       " 2: 'Février',\n",
       " 3: 'Mars',\n",
       " 4: 'Avril',\n",
       " 5: 'Mai',\n",
       " 6: 'Juin',\n",
       " 7: 'Juillet',\n",
       " 8: 'Aout',\n",
       " 9: 'Septembre',\n",
       " 10: 'Octobre',\n",
       " 11: 'Novembre',\n",
       " 12: 'Décembre'}"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dico_mapping_mois"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"mois\"]=df.mois.replace(dico_mapping_mois)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x112bb16d8>"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[ df[\"ligne\"].isin([\"A\",\"B\",\"C\",\"D\",\"E\",\"F\"])].groupby([\"ligne\", \"mois\"]).mean().unstack().plot(kind='bar', stacked=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[master 0ed755b] manipuler pandas\n",
      " 1 file changed, 3207 insertions(+)\n",
      " create mode 100644 TD2_Manipuler_Pandas.ipynb\n",
      "Enumerating objects: 4, done.\n",
      "Counting objects: 100% (4/4), done.\n",
      "Delta compression using up to 8 threads\n",
      "Compressing objects: 100% (3/3), done.\n",
      "Writing objects: 100% (3/3), 41.43 KiB | 10.36 MiB/s, done.\n",
      "Total 3 (delta 1), reused 0 (delta 0)\n",
      "remote: Resolving deltas: 100% (1/1), completed with 1 local object.\u001b[K\n",
      "To https://github.com/Luc-Bertin/TDs_ESILV.git\n",
      "   bf19f88..0ed755b  master -> master\n"
     ]
    }
   ],
   "source": [
    "!git add TD2_Manipuler_Pandas.ipynb\n",
    "!git commit -m \"manipuler pandas\"\n",
    "!git push origin master"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}