Manipulation_csv.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "06f86c22",
   "metadata": {},
   "source": [
    "# <center> Manipulation du csv </center>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "fb628ca2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c3d02338",
   "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>Auteur</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Pierre Vidal-Naquet</td>\n",
       "      <td>Le choix de l'histoire - pourquoi et comment j...</td>\n",
       "      <td>Arléa</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782869597624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ian Kershaw</td>\n",
       "      <td>Choix fatidiques - dix décisions qui ont chang...</td>\n",
       "      <td>Seuil</td>\n",
       "      <td>2012</td>\n",
       "      <td>9782757829707</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Auteur                                              Titre  \\\n",
       "0  Pierre Vidal-Naquet  Le choix de l'histoire - pourquoi et comment j...   \n",
       "1          Ian Kershaw  Choix fatidiques - dix décisions qui ont chang...   \n",
       "\n",
       "  Edition  Date           ISBN  \n",
       "0   Arléa  2007  9782869597624  \n",
       "1   Seuil  2012  9782757829707  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"56.csv\")\n",
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "d219bec3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Sauvegarde du csv \n",
    "# df.to_csv(\"bibliographie.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "46092b81",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 416648 entries, 0 to 416647\n",
      "Data columns (total 5 columns):\n",
      " #   Column   Non-Null Count   Dtype \n",
      "---  ------   --------------   ----- \n",
      " 0   Auteur   415923 non-null  object\n",
      " 1   Titre    416648 non-null  object\n",
      " 2   Edition  416648 non-null  object\n",
      " 3   Date     416648 non-null  int64 \n",
      " 4   ISBN     416648 non-null  int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 15.9+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "48ee13c0",
   "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>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>118136.000000</td>\n",
       "      <td>1.181360e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1999.226375</td>\n",
       "      <td>9.782592e+12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>10.820716</td>\n",
       "      <td>8.467288e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1885.000000</td>\n",
       "      <td>9.780002e+12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1997.000000</td>\n",
       "      <td>9.782207e+12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2002.000000</td>\n",
       "      <td>9.782729e+12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2006.000000</td>\n",
       "      <td>9.782848e+12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2022.000000</td>\n",
       "      <td>9.791093e+12</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Date          ISBN\n",
       "count  118136.000000  1.181360e+05\n",
       "mean     1999.226375  9.782592e+12\n",
       "std        10.820716  8.467288e+08\n",
       "min      1885.000000  9.780002e+12\n",
       "25%      1997.000000  9.782207e+12\n",
       "50%      2002.000000  9.782729e+12\n",
       "75%      2006.000000  9.782848e+12\n",
       "max      2022.000000  9.791093e+12"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee116970",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d631952",
   "metadata": {},
   "source": [
    "## Changer l'index pour trier par auteur"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9f82b0e6",
   "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>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Auteur(s)</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Jean-Gabriel Ganascia</th>\n",
       "      <td>Le mythe de la singularité - Faut-il craindre ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2017</td>\n",
       "      <td>9782021309997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jean-Gabriel Ganascia</th>\n",
       "      <td>L'intelligence artificielle</td>\n",
       "      <td>Editions Le Cavalier Bleu</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782846701655</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                   Titre  \\\n",
       "Auteur(s)                                                                  \n",
       "Jean-Gabriel Ganascia  Le mythe de la singularité - Faut-il craindre ...   \n",
       "Jean-Gabriel Ganascia                        L'intelligence artificielle   \n",
       "\n",
       "                                         Edition  Date           ISBN  \n",
       "Auteur(s)                                                              \n",
       "Jean-Gabriel Ganascia                        NaN  2017  9782021309997  \n",
       "Jean-Gabriel Ganascia  Editions Le Cavalier Bleu  2007  9782846701655  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_auteur = df.set_index(\"Auteur(s)\")\n",
    "df_auteur.loc[\"Jean-Gabriel Ganascia\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a34070ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Titre      Le choix de l'histoire - pourquoi et comment j...\n",
       "Edition                                                  NaN\n",
       "Date                                                    2007\n",
       "ISBN                                           9782869597624\n",
       "Name: Pierre Vidal-Naquet, dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_auteur.loc[\"Pierre Vidal-Naquet\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "203ae769",
   "metadata": {},
   "source": [
    "## Mettre l'ISBN en index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "7c8aca16",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ISBN</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9782869597624</th>\n",
       "      <td>Pierre Vidal-Naquet</td>\n",
       "      <td>Le choix de l'histoire - pourquoi et comment j...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9782757829707</th>\n",
       "      <td>Ian Kershaw</td>\n",
       "      <td>Choix fatidiques - dix décisions qui ont chang...</td>\n",
       "      <td>Points</td>\n",
       "      <td>2012</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Auteur(s)  \\\n",
       "ISBN                                 \n",
       "9782869597624  Pierre Vidal-Naquet   \n",
       "9782757829707          Ian Kershaw   \n",
       "\n",
       "                                                           Titre Edition  Date  \n",
       "ISBN                                                                            \n",
       "9782869597624  Le choix de l'histoire - pourquoi et comment j...     NaN  2007  \n",
       "9782757829707  Choix fatidiques - dix décisions qui ont chang...  Points  2012  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_ISBN = df.set_index(\"ISBN\")\n",
    "df_ISBN.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00c9c8b3",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "caf2e74d",
   "metadata": {},
   "source": [
    "## Modifications du contenu"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "id": "2d3d90eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.loc[22, \"Edition\"] = \"ENI\"\n",
    "# df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "0e62b903",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Sauvegarde du csv \n",
    "# df.to_csv(\"biblio_ultime.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "e5052af7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# supprimer une colonne définitivement\n",
    "# del df[\"Unnamed: 0\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bad85308",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7b2a543",
   "metadata": {},
   "source": [
    "## <center> Filtres </center>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6b2e734",
   "metadata": {},
   "source": [
    "## Filtre pour l'auteur "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4e95bff0",
   "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>Auteur</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Jean-Gabriel Ganascia</td>\n",
       "      <td>L'intelligence artificielle</td>\n",
       "      <td>Cavalier Bleu</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782846701655</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194</th>\n",
       "      <td>Jean-Gabriel Ganascia</td>\n",
       "      <td>L'intelligence artificielle: un exposé pour c...</td>\n",
       "      <td>Flammarion</td>\n",
       "      <td>1993</td>\n",
       "      <td>9782080351418</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>196</th>\n",
       "      <td>Jean-Gabriel Ganascia</td>\n",
       "      <td>L'âme-machine: les enjeux de l'intelligence a...</td>\n",
       "      <td>Seuil</td>\n",
       "      <td>1990</td>\n",
       "      <td>9782020114707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21979</th>\n",
       "      <td>Jean-Gabriel Ganascia</td>\n",
       "      <td>Les sciences cognitives - Poche</td>\n",
       "      <td>du Pommier</td>\n",
       "      <td>2006</td>\n",
       "      <td>9782746503021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22305</th>\n",
       "      <td>Jean-Gabriel Ganascia</td>\n",
       "      <td>Sciences cognitives (Les)</td>\n",
       "      <td>Flammarion</td>\n",
       "      <td>1998</td>\n",
       "      <td>9782080354181</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Auteur  \\\n",
       "15     Jean-Gabriel Ganascia   \n",
       "194    Jean-Gabriel Ganascia   \n",
       "196    Jean-Gabriel Ganascia   \n",
       "21979  Jean-Gabriel Ganascia   \n",
       "22305  Jean-Gabriel Ganascia   \n",
       "\n",
       "                                                   Titre        Edition  Date  \\\n",
       "15                           L'intelligence artificielle  Cavalier Bleu  2007   \n",
       "194    L'intelligence artificielle: un exposé pour c...     Flammarion  1993   \n",
       "196    L'âme-machine: les enjeux de l'intelligence a...          Seuil  1990   \n",
       "21979                    Les sciences cognitives - Poche     du Pommier  2006   \n",
       "22305                          Sciences cognitives (Les)     Flammarion  1998   \n",
       "\n",
       "                ISBN  \n",
       "15     9782846701655  \n",
       "194    9782080351418  \n",
       "196    9782020114707  \n",
       "21979  9782746503021  \n",
       "22305  9782080354181  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df['Auteur'] == 'Jean-Gabriel Ganascia']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d208189",
   "metadata": {},
   "source": [
    "## Filtre pour la date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d30e5834",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df[df[\"Date\"] == 1942]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1dac78d9",
   "metadata": {},
   "source": [
    "## Filtre pour la maison d'édition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "00023d36",
   "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>Auteur</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Pascal Picq</td>\n",
       "      <td>Il était une fois la paléoanthropologie - Quel...</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2010</td>\n",
       "      <td>9782738124944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Pascal Picq</td>\n",
       "      <td>Lucy et l’obscurantisme</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782738117830</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Auteur                                              Titre  \\\n",
       "4  Pascal Picq  Il était une fois la paléoanthropologie - Quel...   \n",
       "5  Pascal Picq                            Lucy et l’obscurantisme   \n",
       "\n",
       "       Edition  Date           ISBN  \n",
       "4  Odile Jacob  2010  9782738124944  \n",
       "5  Odile Jacob  2007  9782738117830  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"Edition\"] == \"Odile Jacob\"].head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5934655",
   "metadata": {},
   "source": [
    "## Filtre avec 2 données"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "371aeda5",
   "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>Auteur</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ian Kershaw</td>\n",
       "      <td>Choix fatidiques - dix décisions qui ont chang...</td>\n",
       "      <td>Seuil</td>\n",
       "      <td>2012</td>\n",
       "      <td>9782757829707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jean-Claude Barreau</td>\n",
       "      <td>Sans la nation, le chaos</td>\n",
       "      <td>du Toucan</td>\n",
       "      <td>2012</td>\n",
       "      <td>9782810004676</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Auteur                                              Titre  \\\n",
       "1          Ian Kershaw  Choix fatidiques - dix décisions qui ont chang...   \n",
       "2  Jean-Claude Barreau                           Sans la nation, le chaos   \n",
       "\n",
       "     Edition  Date           ISBN  \n",
       "1      Seuil  2012  9782757829707  \n",
       "2  du Toucan  2012  9782810004676  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Les années 2010 et 2012\n",
    "df[df[\"Date\"].isin((2010, 2012))].head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 537,
   "id": "88d47ec5",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Pascal Picq</td>\n",
       "      <td>Il était une fois la paléoanthropologie - Quel...</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2010</td>\n",
       "      <td>9782738124944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Pascal Picq</td>\n",
       "      <td>Lucy et l’obscurantisme</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782738117830</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Auteur(s)                                              Titre  \\\n",
       "4  Pascal Picq  Il était une fois la paléoanthropologie - Quel...   \n",
       "5  Pascal Picq                            Lucy et l’obscurantisme   \n",
       "\n",
       "       Edition  Date           ISBN  \n",
       "4  Odile Jacob  2010  9782738124944  \n",
       "5  Odile Jacob  2007  9782738117830  "
      ]
     },
     "execution_count": 537,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Deux maisons d'éditions différentes\n",
    "df[df['Edition'].isin(('Odile Jacob', 'Grasset'))].head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "390cfb7d",
   "metadata": {},
   "source": [
    "## Affichage groupé"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 538,
   "id": "86998160",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.groupby(\"Edition\").sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 540,
   "id": "4bebd72a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.groupby(\"Date\").sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac80af6c",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f1d2a8d",
   "metadata": {},
   "source": [
    "## Statistiques sur les données "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24823c05",
   "metadata": {},
   "source": [
    "### Moyenne sur les maisons d'édition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "ec259de2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.groupby(\"Edition\").mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "211500c3",
   "metadata": {},
   "source": [
    "### Moyenne de l'année"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "de924c28",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1999.29"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "round(df.Date.mean(), 2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e4ea11ad",
   "metadata": {},
   "source": [
    "#### Médiane de l'année"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "28df53e4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2002.0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Date.median()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50cfd3ca",
   "metadata": {},
   "source": [
    "#### Dates extrêmes "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f472cc47",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Date min : 1885\n",
      "Date max : 2025\n"
     ]
    }
   ],
   "source": [
    "# Minimum\n",
    "date_min = df.Date.min()\n",
    "print(\"Date min :\", date_min)\n",
    "\n",
    "# Maximum\n",
    "\n",
    "date_max = df.Date.max()\n",
    "print(\"Date max :\", date_max)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6747602a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # filtre pour récupérer les dates aberrantes \n",
    "# filtre = df[df['Date'] > 2022]\n",
    "# filtre"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "7671dcd2",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Changer la date d'une ligne\n",
    "# df.loc[64394, 'Date']= 1924\n",
    "# df.to_csv(\"37.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4cbb0c40",
   "metadata": {},
   "source": [
    "### Récupérer les auteurs "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b4738a8d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df['Auteur'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16489c44",
   "metadata": {},
   "source": [
    "### Nombre d'auteurs "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "5ebeb582",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "250293"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Auteur'].nunique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad780386",
   "metadata": {},
   "source": [
    "### Nombre de maisons d'édition différentes "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "54e2c064",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "44739"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Edition'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "9a19192a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Liste complète, il peut y avoir des NaN\n",
    "# df['Edition'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bfad9a3f",
   "metadata": {},
   "source": [
    "## Nombre de livres selon les maisons d'édition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "ed481ea7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Harmattan                                          16672\n",
       "Gallimard                                          14783\n",
       "Seuil                                               7388\n",
       "PUF                                                 7289\n",
       "Flammarion                                          5927\n",
       "                                                   ...  \n",
       "Cerf Volant GF                                         1\n",
       "Traduit par Emmanuel Hocquard, Christine Michel        1\n",
       "Traduit par Philippe Gerval                            1\n",
       "Postface de Luc Vidal                                  1\n",
       "Illustrations de Lefred Thouron                        1\n",
       "Name: Edition, Length: 44739, dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Edition\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "a3262bf6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Version normalisée (valeur comprise en 0 et 1)\n",
    "# df[\"Edition\"].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43b4b99d",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bdc7718e",
   "metadata": {},
   "source": [
    "## <center> Visualisation </center>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3e3c9d12",
   "metadata": {},
   "source": [
    "## Nombre de livres par maison d'édition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "dfffcd1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df[\"Edition\"].value_counts().plot.bar()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "f52f2fcf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Edition'>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Classement des 10 premières maison d'édition\n",
    "top_10 = df.value_counts(\"Edition\", ascending = False).head(10)\n",
    "top_10.plot.bar()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "a3203c2e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9.312859026799885"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Moyenne de livre par maison d'édition \n",
    "moyenne = df.value_counts(\"Edition\").mean()\n",
    "moyenne"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "39b23df2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Camembert avec l'ensemble des maisons d'édition (trop lourd, pas lisible)\n",
    "# df[\"Edition\"].value_counts(normalize=False).plot.pie(legend=False, figsize=(7, 7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "3da18b0d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 10 maisons d'éditions dans la bdd\n",
    "top_edition = df.value_counts(\"Edition\", ascending = False).head(10).plot.pie(legend=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "bfb1d5fb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'whiskers': [<matplotlib.lines.Line2D at 0x21a4d9c5310>,\n",
       "  <matplotlib.lines.Line2D at 0x21a4d9c55e0>],\n",
       " 'caps': [<matplotlib.lines.Line2D at 0x21a4d9c58b0>,\n",
       "  <matplotlib.lines.Line2D at 0x21a4d9c5b80>],\n",
       " 'boxes': [<matplotlib.lines.Line2D at 0x21a4d9c5040>],\n",
       " 'medians': [<matplotlib.lines.Line2D at 0x21a4d9c5e50>],\n",
       " 'fliers': [<matplotlib.lines.Line2D at 0x21a4d9d3160>],\n",
       " 'means': []}"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Diagramme sur 10 maisons d'édition \n",
    "\n",
    "nb_livre_par_maison = df.value_counts(\"Edition\").head(10)\n",
    "\n",
    "fig1, ax1 = plt.subplots()\n",
    "ax1.set_title('Visualisation')\n",
    "ax1.boxplot(nb_livre_par_maison)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c912c8d5",
   "metadata": {},
   "source": [
    "## Nombre de livres par auteur"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "93cc1f9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Auteur'>"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Top 10 des auteurs\n",
    "\n",
    "top_10_auteurs = df.value_counts(\"Auteur\", ascending = False).head(10)\n",
    "top_10_auteurs.plot.bar()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "acbb4dd2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Ensemble de tous les auteurs (illisible)\n",
    "# df[\"Auteur(s)\"].value_counts(normalize=False).plot.pie(legend=False, figsize=(7, 7))\n",
    "\n",
    "# top 10 des auteurs\n",
    "top_auteurs = df.value_counts(\"Auteur\", ascending = False).head(10).plot.pie(legend=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "91acf2fa",
   "metadata": {},
   "source": [
    "# Nombre de livres par date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "8b1d4831",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Date'>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Top 10 des dates\n",
    "\n",
    "top_10_date = df.value_counts(\"Date\", ascending = False).head(10)\n",
    "top_10_date.plot.bar()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "1369a58e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Date'>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[\"Date\"].value_counts(normalize=False).plot.pie(legend=False, figsize=(7, 7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "973aeea6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Top 10 des dates \n",
    "top_date = df.value_counts(\"Date\", ascending = False).head(10).plot.pie(legend=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "d63b63d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'whiskers': [<matplotlib.lines.Line2D at 0x21a4f086340>,\n",
       "  <matplotlib.lines.Line2D at 0x21a4f093910>],\n",
       " 'caps': [<matplotlib.lines.Line2D at 0x21a4f093be0>,\n",
       "  <matplotlib.lines.Line2D at 0x21a4f093eb0>],\n",
       " 'boxes': [<matplotlib.lines.Line2D at 0x21a4f093490>],\n",
       " 'medians': [<matplotlib.lines.Line2D at 0x21a4f0a11c0>],\n",
       " 'fliers': [<matplotlib.lines.Line2D at 0x21a4f0a1490>],\n",
       " 'means': []}"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Diagramme sur la colonne DATE\n",
    "\n",
    "fig1, ax1 = plt.subplots()\n",
    "ax1.set_title('Visualisation')\n",
    "ax1.boxplot(df[\"Date\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4dd2ffdf",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b87fd771",
   "metadata": {},
   "source": [
    "# <center>Modification du csv</center>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd064d1b",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fad6a517",
   "metadata": {},
   "source": [
    "## Remplace les caractères spéciaux dans la colonne 'Date'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "0b7ebece",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Il y a des données manquantes dans les dates, il faut les remplacer par O\n",
    "df['Date'] = df['Date'].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "dd398d8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Suppression d'un caractère spécial\n",
    "df['Date'] = df['Date'].str.replace('©','')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "204a9ad9",
   "metadata": {},
   "source": [
    "## Transformer la colonne en int"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 601,
   "id": "a61eb5b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('int64')"
      ]
     },
     "execution_count": 601,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# vérification du type\n",
    "df['Date'].dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 527,
   "id": "a10a4a67",
   "metadata": {},
   "outputs": [],
   "source": [
    "# transformer en int \n",
    "df['Date'] = df['Date'].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "8a3c49e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Vérification des valeurs nulles \n",
    "df[df['Date'].isnull()]\n",
    "\n",
    "# # S'il y a des valeurs nulles faire :\n",
    "df['Date'] = df['Date'].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 627,
   "id": "090c685e",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Auteur(s), Titre, Edition, Date, ISBN]\n",
       "Index: []"
      ]
     },
     "execution_count": 627,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtre = df[df['Date'] == 0  ]\n",
    "filtre"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 526,
   "id": "97b6fe21",
   "metadata": {},
   "outputs": [],
   "source": [
    "# remplacer avec l'index\n",
    "df.loc[1271, \"Edition\"] = \"Documentation Française (La)\"\n",
    "\n",
    "# Sauvegarde du csv \n",
    "df.to_csv(\"bdd.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 630,
   "id": "31fa6810",
   "metadata": {},
   "outputs": [],
   "source": [
    "# replace\n",
    "df['Edition'] = df['Edition'].str.replace('Presses universitaires de France','PUF')\n",
    "\n",
    "# Sauvegarde du csv \n",
    "df.to_csv(\"bdd.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b65d1937",
   "metadata": {},
   "source": [
    "### Remplacer les 0 dans 'Date' par la date véritable "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 597,
   "id": "1e8c1720",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1296</th>\n",
       "      <td>Besse</td>\n",
       "      <td>L'zillettrismey En Questions</td>\n",
       "      <td>Presses Universitaires de Lyon</td>\n",
       "      <td>0</td>\n",
       "      <td>9782729704315</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Auteur(s)                         Titre                         Edition  \\\n",
       "1296     Besse  L'zillettrismey En Questions  Presses Universitaires de Lyon   \n",
       "\n",
       "      Date           ISBN  \n",
       "1296     0  9782729704315  "
      ]
     },
     "execution_count": 597,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Filtre pour repérer les '0'\n",
    "filtre = df[df['Date'] == 0  ]\n",
    "filtre"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 599,
   "id": "947364a4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# remplacer avec l'index\n",
    "df.loc[1296, \"Auteur(s)\"] = \"Jean-Marie Besse\"\n",
    "\n",
    "# Sauvegarde du csv \n",
    "df.to_csv(\"bdd.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 640,
   "id": "e09ef20c",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>218</th>\n",
       "      <td>Yves Coppens</td>\n",
       "      <td>Pré-ambules - les premiers pas de l'homme</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2001</td>\n",
       "      <td>9782738109361</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Auteur(s)                                      Titre      Edition  \\\n",
       "218  Yves Coppens  Pré-ambules - les premiers pas de l'homme  Odile Jacob   \n",
       "\n",
       "     Date           ISBN  \n",
       "218  2001  9782738109361  "
      ]
     },
     "execution_count": 640,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtre = df[df[\"Auteur(s)\"] == \"Yves Coppens\"]\n",
    "filtre"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 649,
   "id": "e321a7ad",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Pierre Vidal-Naquet</td>\n",
       "      <td>Le choix de l'histoire - pourquoi et comment j...</td>\n",
       "      <td>Arléa</td>\n",
       "      <td>2007</td>\n",
       "      <td>9782869597624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ian Kershaw</td>\n",
       "      <td>Choix fatidiques - dix décisions qui ont chang...</td>\n",
       "      <td>Seuil</td>\n",
       "      <td>2012</td>\n",
       "      <td>9782757829707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Jean-Claude Barreau</td>\n",
       "      <td>Sans la nation, le chaos</td>\n",
       "      <td>Editions du Toucan</td>\n",
       "      <td>2012</td>\n",
       "      <td>9782810004676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>François Bousquet</td>\n",
       "      <td>La Droite buissonnière</td>\n",
       "      <td>Rocher</td>\n",
       "      <td>2017</td>\n",
       "      <td>9782268089898</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Pascal Picq</td>\n",
       "      <td>Il était une fois la paléoanthropologie - Quel...</td>\n",
       "      <td>Odile Jacob</td>\n",
       "      <td>2010</td>\n",
       "      <td>9782738124944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>265</th>\n",
       "      <td>Jean-Philippe Couturier</td>\n",
       "      <td>Lorsque mon patron sera une intelligence artif...</td>\n",
       "      <td>VA</td>\n",
       "      <td>2019</td>\n",
       "      <td>9782360930128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>266</th>\n",
       "      <td>Luc Julia</td>\n",
       "      <td>L'intelligence artificielle n'existe pas</td>\n",
       "      <td>First</td>\n",
       "      <td>2019</td>\n",
       "      <td>9782412043400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>267</th>\n",
       "      <td>Jean-Philippe Desbiolles</td>\n",
       "      <td>L'IA sera ce que tu en feras: les 10 règles d...</td>\n",
       "      <td>Dunod</td>\n",
       "      <td>2019</td>\n",
       "      <td>9782100800438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>268</th>\n",
       "      <td>Daniel Crevier</td>\n",
       "      <td>A la recherche de l'intelligence artificielle</td>\n",
       "      <td>Flammarion</td>\n",
       "      <td>1997</td>\n",
       "      <td>9782080814289</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269</th>\n",
       "      <td>Laurent Alexandre</td>\n",
       "      <td>La guerre des intelligences: comment l'intelli...</td>\n",
       "      <td>LGF</td>\n",
       "      <td>2019</td>\n",
       "      <td>9782253257417</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>270 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Auteur(s)  \\\n",
       "0         Pierre Vidal-Naquet   \n",
       "1                 Ian Kershaw   \n",
       "2         Jean-Claude Barreau   \n",
       "3           François Bousquet   \n",
       "4                 Pascal Picq   \n",
       "..                        ...   \n",
       "265   Jean-Philippe Couturier   \n",
       "266                 Luc Julia   \n",
       "267  Jean-Philippe Desbiolles   \n",
       "268            Daniel Crevier   \n",
       "269         Laurent Alexandre   \n",
       "\n",
       "                                                 Titre             Edition  \\\n",
       "0    Le choix de l'histoire - pourquoi et comment j...               Arléa   \n",
       "1    Choix fatidiques - dix décisions qui ont chang...               Seuil   \n",
       "2                             Sans la nation, le chaos  Editions du Toucan   \n",
       "3                               La Droite buissonnière              Rocher   \n",
       "4    Il était une fois la paléoanthropologie - Quel...         Odile Jacob   \n",
       "..                                                 ...                 ...   \n",
       "265  Lorsque mon patron sera une intelligence artif...                  VA   \n",
       "266           L'intelligence artificielle n'existe pas               First   \n",
       "267  L'IA sera ce que tu en feras: les 10 règles d...               Dunod   \n",
       "268      A la recherche de l'intelligence artificielle          Flammarion   \n",
       "269  La guerre des intelligences: comment l'intelli...                 LGF   \n",
       "\n",
       "     Date           ISBN  \n",
       "0    2007  9782869597624  \n",
       "1    2012  9782757829707  \n",
       "2    2012  9782810004676  \n",
       "3    2017  9782268089898  \n",
       "4    2010  9782738124944  \n",
       "..    ...            ...  \n",
       "265  2019  9782360930128  \n",
       "266  2019  9782412043400  \n",
       "267  2019  9782100800438  \n",
       "268  1997  9782080814289  \n",
       "269  2019  9782253257417  \n",
       "\n",
       "[270 rows x 5 columns]"
      ]
     },
     "execution_count": 649,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(270)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68c9fb6b",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbb36b08",
   "metadata": {},
   "source": [
    "## Changer le nom d'éditeur \".\"\n",
    "\n",
    "Objectifs :\n",
    "- Récupérer chaque index dans une liste\n",
    "- Remplacer par \"None\" dans une boucle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "267f384b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6146 entries, 0 to 6145\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count  Dtype \n",
      "---  ------     --------------  ----- \n",
      " 0   Auteur(s)  6144 non-null   object\n",
      " 1   Titre      6146 non-null   object\n",
      " 2   Edition    6146 non-null   object\n",
      " 3   Date       6146 non-null   int64 \n",
      " 4   ISBN       6146 non-null   int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 240.2+ KB\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df = pd.read_csv('test.csv')\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "630a7230",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Auteur(s), Titre, Edition, Date, ISBN]\n",
       "Index: []"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# filtre auteur == \".\"\n",
    "filtre_point = df[df['Auteur(s)']== \".\"]\n",
    "filtre_point"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "7d4bede1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Nombre d'index dans la liste : 19\n"
     ]
    }
   ],
   "source": [
    "# création d'une liste pour les index\n",
    "liste_index = []\n",
    "for index, row in filtre_point.iterrows(): \n",
    "    liste_index.append(index)\n",
    "    \n",
    "print(\"Nombre d'index dans la liste :\", len(liste_index))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "36e0ac9b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████████████████████████████████████████████████████████████████████████████| 19/19 [00:00<00:00, 28.00it/s]\n"
     ]
    }
   ],
   "source": [
    "# Remplacement par None\n",
    "from tqdm import tqdm\n",
    "\n",
    "for x in tqdm(liste_index) :\n",
    "    df.loc[x, 'Auteur(s)']= \"None\"\n",
    "    df.to_csv(\"test.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8aa92858",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "081d3430",
   "metadata": {},
   "source": [
    "# Remplacer les \"None\" par les noms des auteurs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "1c298000",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6146 entries, 0 to 6145\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count  Dtype \n",
      "---  ------     --------------  ----- \n",
      " 0   Auteur(s)  6144 non-null   object\n",
      " 1   Titre      6146 non-null   object\n",
      " 2   Edition    6146 non-null   object\n",
      " 3   Date       6146 non-null   int64 \n",
      " 4   ISBN       6146 non-null   int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 240.2+ KB\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df = pd.read_csv(\"test.csv\")\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "a065d2a6",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>None</td>\n",
       "      <td>La danse d'amour du vieux corbeau</td>\n",
       "      <td>Denoël</td>\n",
       "      <td>1983</td>\n",
       "      <td>9782207228180</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>None</td>\n",
       "      <td>Le pornographe timide</td>\n",
       "      <td>Traduit par Marc de Gouvenain, Lena Grumbach</td>\n",
       "      <td>2000</td>\n",
       "      <td>9782742726400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>None</td>\n",
       "      <td>**Yvelines**</td>\n",
       "      <td>Ponchet Plan Net éditions</td>\n",
       "      <td>2000</td>\n",
       "      <td>9782846670760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>None</td>\n",
       "      <td>Costa Brava/Andorre/Perpignan - 1/200.000</td>\n",
       "      <td>Marco Polo</td>\n",
       "      <td>2000</td>\n",
       "      <td>9783895252310</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>None</td>\n",
       "      <td>New Appartment design /multilingue</td>\n",
       "      <td>Daab</td>\n",
       "      <td>2005</td>\n",
       "      <td>9783937718170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6095</th>\n",
       "      <td>None</td>\n",
       "      <td>Abécédaire de l'Apocalypse [Board book] Parnov...</td>\n",
       "      <td>Traduit par Bernard Kreise</td>\n",
       "      <td>2008</td>\n",
       "      <td>9782355860010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6096</th>\n",
       "      <td>None</td>\n",
       "      <td>Un pont sur la Loire</td>\n",
       "      <td>Table Ronde</td>\n",
       "      <td>2006</td>\n",
       "      <td>9782710328490</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6100</th>\n",
       "      <td>None</td>\n",
       "      <td>Villa Argane</td>\n",
       "      <td>Presses du Midi</td>\n",
       "      <td>2001</td>\n",
       "      <td>9782878673050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6122</th>\n",
       "      <td>None</td>\n",
       "      <td>Sept jours pour expier</td>\n",
       "      <td>Traduit par Jean Bonnefoy</td>\n",
       "      <td>1993</td>\n",
       "      <td>9782207240960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6141</th>\n",
       "      <td>None</td>\n",
       "      <td>La correspondance pratique espagnole</td>\n",
       "      <td>Langues pour tous</td>\n",
       "      <td>2006</td>\n",
       "      <td>9782266161190</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>496 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Auteur(s)                                              Titre  \\\n",
       "2         None                  La danse d'amour du vieux corbeau   \n",
       "10        None                              Le pornographe timide   \n",
       "11        None                                       **Yvelines**   \n",
       "34        None          Costa Brava/Andorre/Perpignan - 1/200.000   \n",
       "38        None                 New Appartment design /multilingue   \n",
       "...        ...                                                ...   \n",
       "6095      None  Abécédaire de l'Apocalypse [Board book] Parnov...   \n",
       "6096      None                               Un pont sur la Loire   \n",
       "6100      None                                       Villa Argane   \n",
       "6122      None                             Sept jours pour expier   \n",
       "6141      None               La correspondance pratique espagnole   \n",
       "\n",
       "                                           Edition  Date           ISBN  \n",
       "2                                           Denoël  1983  9782207228180  \n",
       "10    Traduit par Marc de Gouvenain, Lena Grumbach  2000  9782742726400  \n",
       "11                       Ponchet Plan Net éditions  2000  9782846670760  \n",
       "34                                      Marco Polo  2000  9783895252310  \n",
       "38                                            Daab  2005  9783937718170  \n",
       "...                                            ...   ...            ...  \n",
       "6095                    Traduit par Bernard Kreise  2008  9782355860010  \n",
       "6096                                   Table Ronde  2006  9782710328490  \n",
       "6100                               Presses du Midi  2001  9782878673050  \n",
       "6122                     Traduit par Jean Bonnefoy  1993  9782207240960  \n",
       "6141                             Langues pour tous  2006  9782266161190  \n",
       "\n",
       "[496 rows x 5 columns]"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# afficher les None \n",
    "filtre = df[df['Auteur(s)']==\"None\"]\n",
    "filtre"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad5a24d6",
   "metadata": {},
   "source": [
    "### Avec ISBNLIB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "06884b26",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import isbnlib\n",
    "from isbnlib import canonical, meta\n",
    "import csv\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fdc55c05",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1249"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# liste récupérant les ISBN du filtre 'None'\n",
    "liste_ISBN = [x for x in filtre['ISBN']]\n",
    "\n",
    "len(liste_ISBN)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc5a18f9",
   "metadata": {},
   "source": [
    "## Correction des 'None' (suite)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "617c6ae8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "107dad62cba242328af5f09a637aa5d0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "0it [00:00, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Nb d'erreurs : 120\n"
     ]
    }
   ],
   "source": [
    "from isbnlib import canonical, meta\n",
    "import csv\n",
    "from tqdm.notebook import tqdm_notebook\n",
    "\n",
    "erreur = 0\n",
    "\n",
    "# MODIFICATION DE LA SOURCE\n",
    "SERVICE = 'goob'\n",
    "\n",
    "for index, row in tqdm_notebook(filtre.iterrows()):\n",
    "    isbn = str(row[4])\n",
    "    try : \n",
    "        data = meta(isbn, SERVICE)\n",
    "\n",
    "        try :\n",
    "            if len(data[\"Authors\"]) == 1 :\n",
    "                            for x in data[\"Authors\"] :\n",
    "\n",
    "                                filtre.loc[index, \"Auteur(s)\"] = str(x)\n",
    "                                filtre.to_csv(\"copie_noms.csv\", index=False)\n",
    "            else : \n",
    "                filtre.loc[index, \"Auteur(s)\"] = data[\"Authors\"]\n",
    "\n",
    "        except :\n",
    "            erreur += 1\n",
    "            continue\n",
    "    \n",
    "    except :\n",
    "        erreur += 1\n",
    "        continue\n",
    "\n",
    "\n",
    "print(\"Nb d'erreurs :\", erreur)\n",
    "\n",
    "# Sauvegarde\n",
    "filtre.to_csv(\"filtre.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55ae29a5",
   "metadata": {},
   "source": [
    "## Suppression des lignes "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2733f9b9",
   "metadata": {},
   "source": [
    "**Objectif :** maintenant que nous avons retravaillé les 'None', on peut récupérer les index des lignes grâce au précédent filtre. Une fois les index ajoutés à une liste, on peut les supprimer dans le df. Il ne nous reste plus qu'à concaténer le df avec le nouveau .csv (sans les 'None')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "701b1520",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Nombre d'index dans la liste : 496\n"
     ]
    }
   ],
   "source": [
    "# Premier filtre \n",
    "# filtre = df[df['Auteur(s)']==\"None\"]\n",
    "\n",
    "# création d'une liste pour les index\n",
    "liste_index = []\n",
    "for index, row in filtre.iterrows(): \n",
    "    liste_index.append(index)\n",
    "    \n",
    "print(\"Nombre d'index dans la liste :\", len(liste_index))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "acf1a26e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2, 10, 11, 34, 38, 42, 48, 50, 53, 61, 73, 76, 84, 93, 98, 111, 112, 121, 151, 191, 204, 219, 225, 230, 238, 247, 253, 259, 270, 278, 301, 317, 319, 324, 343, 358, 374, 407, 415, 438, 449, 450, 471, 491, 494, 502, 553, 556, 587, 616, 632, 635, 638, 647, 653, 660, 664, 690, 691, 712, 721, 744, 747, 769, 778, 779, 789, 802, 813, 848, 849, 880, 909, 922, 931, 942, 946, 951, 956, 957, 977, 979, 984, 994, 1004, 1005, 1019, 1035, 1038, 1057, 1071, 1078, 1101, 1140, 1159, 1165, 1166, 1187, 1188, 1196, 1198, 1199, 1208, 1214, 1227, 1230, 1243, 1245, 1254, 1262, 1277, 1280, 1287, 1306, 1319, 1378, 1419, 1449, 1461, 1474, 1481, 1488, 1511, 1524, 1544, 1570, 1586, 1589, 1603, 1612, 1628, 1635, 1639, 1655, 1660, 1695, 1700, 1704, 1746, 1755, 1776, 1789, 1790, 1814, 1817, 1834, 1854, 1867, 1903, 1908, 1935, 1970, 1971, 1998, 2006, 2008, 2009, 2058, 2074, 2077, 2079, 2104, 2126, 2131, 2138, 2159, 2161, 2165, 2166, 2175, 2179, 2183, 2184, 2228, 2237, 2243, 2261, 2264, 2265, 2277, 2295, 2301, 2303, 2319, 2332, 2338, 2351, 2356, 2359, 2377, 2381, 2382, 2389, 2404, 2431, 2438, 2458, 2466, 2468, 2480, 2490, 2492, 2495, 2504, 2512, 2514, 2520, 2521, 2569, 2585, 2600, 2604, 2607, 2623, 2637, 2665, 2676, 2680, 2704, 2732, 2751, 2752, 2757, 2773, 2791, 2805, 2843, 2874, 2890, 2893, 2920, 2922, 2945, 2949, 2973, 2979, 2980, 2987, 2990, 2999, 3002, 3009, 3014, 3025, 3034, 3041, 3051, 3052, 3058, 3084, 3095, 3103, 3108, 3115, 3123, 3124, 3127, 3134, 3140, 3142, 3211, 3218, 3232, 3245, 3261, 3270, 3278, 3294, 3303, 3309, 3312, 3316, 3317, 3328, 3338, 3343, 3347, 3358, 3372, 3378, 3383, 3408, 3434, 3440, 3460, 3463, 3480, 3481, 3482, 3493, 3496, 3502, 3510, 3523, 3551, 3557, 3569, 3576, 3585, 3590, 3601, 3609, 3622, 3632, 3642, 3647, 3657, 3709, 3712, 3716, 3721, 3726, 3730, 3742, 3769, 3772, 3779, 3791, 3795, 3804, 3837, 3843, 3844, 3858, 3879, 3893, 3906, 3938, 3941, 3947, 3954, 3991, 3998, 4048, 4058, 4097, 4109, 4110, 4113, 4115, 4119, 4196, 4197, 4204, 4212, 4233, 4249, 4279, 4293, 4295, 4325, 4328, 4336, 4344, 4346, 4352, 4374, 4411, 4444, 4447, 4468, 4501, 4507, 4520, 4526, 4573, 4578, 4584, 4591, 4601, 4603, 4610, 4612, 4614, 4636, 4640, 4653, 4704, 4707, 4727, 4781, 4782, 4783, 4813, 4816, 4844, 4846, 4849, 4865, 4879, 4895, 4899, 4906, 4913, 4926, 4937, 4941, 4951, 4969, 4986, 4987, 4994, 5003, 5023, 5039, 5076, 5085, 5093, 5094, 5113, 5154, 5178, 5185, 5188, 5206, 5244, 5246, 5247, 5302, 5312, 5314, 5324, 5346, 5350, 5372, 5394, 5404, 5409, 5410, 5413, 5421, 5445, 5453, 5496, 5503, 5515, 5530, 5540, 5541, 5542, 5558, 5571, 5578, 5609, 5622, 5658, 5661, 5666, 5668, 5675, 5677, 5738, 5742, 5748, 5754, 5771, 5782, 5784, 5791, 5794, 5796, 5801, 5818, 5825, 5836, 5841, 5846, 5847, 5863, 5883, 5885, 5893, 5895, 5896, 5902, 5905, 5914, 5924, 5952, 5955, 5963, 5966, 5973, 5974, 5980, 5993, 6009, 6016, 6045, 6054, 6076, 6095, 6096, 6100, 6122, 6141]\n"
     ]
    }
   ],
   "source": [
    "print(liste_index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "12ff55d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6146 entries, 0 to 6145\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count  Dtype \n",
      "---  ------     --------------  ----- \n",
      " 0   Auteur(s)  6144 non-null   object\n",
      " 1   Titre      6146 non-null   object\n",
      " 2   Edition    6146 non-null   object\n",
      " 3   Date       6146 non-null   int64 \n",
      " 4   ISBN       6146 non-null   int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 240.2+ KB\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('test.csv')\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "bce71def",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 5650 entries, 0 to 6145\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count  Dtype \n",
      "---  ------     --------------  ----- \n",
      " 0   Auteur(s)  5648 non-null   object\n",
      " 1   Titre      5650 non-null   object\n",
      " 2   Edition    5650 non-null   object\n",
      " 3   Date       5650 non-null   int64 \n",
      " 4   ISBN       5650 non-null   int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 264.8+ KB\n"
     ]
    }
   ],
   "source": [
    "# Suppression des lignes\n",
    "df.drop([2, 10, 11, 34, 38, 42, 48, 50, 53, 61, 73, 76, 84, 93, 98, 111, 112, 121, 151, 191, 204, 219, 225, 230, 238, 247, 253, 259, 270, 278, 301, 317, 319, 324, 343, 358, 374, 407, 415, 438, 449, 450, 471, 491, 494, 502, 553, 556, 587, 616, 632, 635, 638, 647, 653, 660, 664, 690, 691, 712, 721, 744, 747, 769, 778, 779, 789, 802, 813, 848, 849, 880, 909, 922, 931, 942, 946, 951, 956, 957, 977, 979, 984, 994, 1004, 1005, 1019, 1035, 1038, 1057, 1071, 1078, 1101, 1140, 1159, 1165, 1166, 1187, 1188, 1196, 1198, 1199, 1208, 1214, 1227, 1230, 1243, 1245, 1254, 1262, 1277, 1280, 1287, 1306, 1319, 1378, 1419, 1449, 1461, 1474, 1481, 1488, 1511, 1524, 1544, 1570, 1586, 1589, 1603, 1612, 1628, 1635, 1639, 1655, 1660, 1695, 1700, 1704, 1746, 1755, 1776, 1789, 1790, 1814, 1817, 1834, 1854, 1867, 1903, 1908, 1935, 1970, 1971, 1998, 2006, 2008, 2009, 2058, 2074, 2077, 2079, 2104, 2126, 2131, 2138, 2159, 2161, 2165, 2166, 2175, 2179, 2183, 2184, 2228, 2237, 2243, 2261, 2264, 2265, 2277, 2295, 2301, 2303, 2319, 2332, 2338, 2351, 2356, 2359, 2377, 2381, 2382, 2389, 2404, 2431, 2438, 2458, 2466, 2468, 2480, 2490, 2492, 2495, 2504, 2512, 2514, 2520, 2521, 2569, 2585, 2600, 2604, 2607, 2623, 2637, 2665, 2676, 2680, 2704, 2732, 2751, 2752, 2757, 2773, 2791, 2805, 2843, 2874, 2890, 2893, 2920, 2922, 2945, 2949, 2973, 2979, 2980, 2987, 2990, 2999, 3002, 3009, 3014, 3025, 3034, 3041, 3051, 3052, 3058, 3084, 3095, 3103, 3108, 3115, 3123, 3124, 3127, 3134, 3140, 3142, 3211, 3218, 3232, 3245, 3261, 3270, 3278, 3294, 3303, 3309, 3312, 3316, 3317, 3328, 3338, 3343, 3347, 3358, 3372, 3378, 3383, 3408, 3434, 3440, 3460, 3463, 3480, 3481, 3482, 3493, 3496, 3502, 3510, 3523, 3551, 3557, 3569, 3576, 3585, 3590, 3601, 3609, 3622, 3632, 3642, 3647, 3657, 3709, 3712, 3716, 3721, 3726, 3730, 3742, 3769, 3772, 3779, 3791, 3795, 3804, 3837, 3843, 3844, 3858, 3879, 3893, 3906, 3938, 3941, 3947, 3954, 3991, 3998, 4048, 4058, 4097, 4109, 4110, 4113, 4115, 4119, 4196, 4197, 4204, 4212, 4233, 4249, 4279, 4293, 4295, 4325, 4328, 4336, 4344, 4346, 4352, 4374, 4411, 4444, 4447, 4468, 4501, 4507, 4520, 4526, 4573, 4578, 4584, 4591, 4601, 4603, 4610, 4612, 4614, 4636, 4640, 4653, 4704, 4707, 4727, 4781, 4782, 4783, 4813, 4816, 4844, 4846, 4849, 4865, 4879, 4895, 4899, 4906, 4913, 4926, 4937, 4941, 4951, 4969, 4986, 4987, 4994, 5003, 5023, 5039, 5076, 5085, 5093, 5094, 5113, 5154, 5178, 5185, 5188, 5206, 5244, 5246, 5247, 5302, 5312, 5314, 5324, 5346, 5350, 5372, 5394, 5404, 5409, 5410, 5413, 5421, 5445, 5453, 5496, 5503, 5515, 5530, 5540, 5541, 5542, 5558, 5571, 5578, 5609, 5622, 5658, 5661, 5666, 5668, 5675, 5677, 5738, 5742, 5748, 5754, 5771, 5782, 5784, 5791, 5794, 5796, 5801, 5818, 5825, 5836, 5841, 5846, 5847, 5863, 5883, 5885, 5893, 5895, 5896, 5902, 5905, 5914, 5924, 5952, 5955, 5963, 5966, 5973, 5974, 5980, 5993, 6009, 6016, 6045, 6054, 6076, 6095, 6096, 6100, 6122, 6141], axis=0, inplace=True)\n",
    "df.info()\n",
    "# Sauvegarde\n",
    "df.to_csv(\"test.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "c09357c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Concaténation des 2 df\n",
    "df = pd.concat(\n",
    "    map(pd.read_csv, ['40.csv', 'test_2.csv']), ignore_index=True)\n",
    "\n",
    "# Sauvegarde\n",
    "df.to_csv(\"41.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "b029fb53",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 111990 entries, 0 to 111989\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count   Dtype \n",
      "---  ------     --------------   ----- \n",
      " 0   Auteur(s)  111410 non-null  object\n",
      " 1   Titre      111990 non-null  object\n",
      " 2   Edition    111812 non-null  object\n",
      " 3   Date       111990 non-null  int64 \n",
      " 4   ISBN       111990 non-null  int64 \n",
      "dtypes: int64(2), object(3)\n",
      "memory usage: 4.3+ MB\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('40.csv')\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "489c7734",
   "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>Auteur(s)</th>\n",
       "      <th>Titre</th>\n",
       "      <th>Edition</th>\n",
       "      <th>Date</th>\n",
       "      <th>ISBN</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>None</td>\n",
       "      <td>La danse d'amour du vieux corbeau</td>\n",
       "      <td>Denoël</td>\n",
       "      <td>1983</td>\n",
       "      <td>9782207228180</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>None</td>\n",
       "      <td>Le pornographe timide</td>\n",
       "      <td>Traduit par Marc de Gouvenain, Lena Grumbach</td>\n",
       "      <td>2000</td>\n",
       "      <td>9782742726400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>None</td>\n",
       "      <td>**Yvelines**</td>\n",
       "      <td>Ponchet Plan Net éditions</td>\n",
       "      <td>2000</td>\n",
       "      <td>9782846670760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>None</td>\n",
       "      <td>Costa Brava/Andorre/Perpignan - 1/200.000</td>\n",
       "      <td>Marco Polo</td>\n",
       "      <td>2000</td>\n",
       "      <td>9783895252310</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>None</td>\n",
       "      <td>New Appartment design /multilingue</td>\n",
       "      <td>Daab</td>\n",
       "      <td>2005</td>\n",
       "      <td>9783937718170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12282</th>\n",
       "      <td>None</td>\n",
       "      <td>La ligne de feu</td>\n",
       "      <td>Traduit par Jacques Fontaine, Ivan Steenhout</td>\n",
       "      <td>2000</td>\n",
       "      <td>9782842612160</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12285</th>\n",
       "      <td>None</td>\n",
       "      <td>Les Amis de Milosz, numéro 27</td>\n",
       "      <td>Rocher</td>\n",
       "      <td>1998</td>\n",
       "      <td>9782850552250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12288</th>\n",
       "      <td>None</td>\n",
       "      <td>Nouveau paradis</td>\n",
       "      <td>Seuil Jeunesse</td>\n",
       "      <td>1937</td>\n",
       "      <td>9782020033510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12295</th>\n",
       "      <td>None</td>\n",
       "      <td>Sept jours pour expier</td>\n",
       "      <td>Traduit par Jean Bonnefoy</td>\n",
       "      <td>1993</td>\n",
       "      <td>9782207240960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12296</th>\n",
       "      <td>None</td>\n",
       "      <td>La correspondance pratique espagnole</td>\n",
       "      <td>Langues pour tous</td>\n",
       "      <td>2006</td>\n",
       "      <td>9782266161190</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>597 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Auteur(s)                                      Titre  \\\n",
       "2          None          La danse d'amour du vieux corbeau   \n",
       "10         None                      Le pornographe timide   \n",
       "11         None                               **Yvelines**   \n",
       "34         None  Costa Brava/Andorre/Perpignan - 1/200.000   \n",
       "38         None         New Appartment design /multilingue   \n",
       "...         ...                                        ...   \n",
       "12282      None                            La ligne de feu   \n",
       "12285      None              Les Amis de Milosz, numéro 27   \n",
       "12288      None                            Nouveau paradis   \n",
       "12295      None                     Sept jours pour expier   \n",
       "12296      None       La correspondance pratique espagnole   \n",
       "\n",
       "                                            Edition  Date           ISBN  \n",
       "2                                            Denoël  1983  9782207228180  \n",
       "10     Traduit par Marc de Gouvenain, Lena Grumbach  2000  9782742726400  \n",
       "11                        Ponchet Plan Net éditions  2000  9782846670760  \n",
       "34                                       Marco Polo  2000  9783895252310  \n",
       "38                                             Daab  2005  9783937718170  \n",
       "...                                             ...   ...            ...  \n",
       "12282  Traduit par Jacques Fontaine, Ivan Steenhout  2000  9782842612160  \n",
       "12285                                        Rocher  1998  9782850552250  \n",
       "12288                                Seuil Jeunesse  1937  9782020033510  \n",
       "12295                     Traduit par Jean Bonnefoy  1993  9782207240960  \n",
       "12296                             Langues pour tous  2006  9782266161190  \n",
       "\n",
       "[597 rows x 5 columns]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df['Auteur(s)']== \"None\"]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}