{
 "cells": [
  {
   "cell_type": "code",
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    },
    "ExecuteTime": {
     "end_time": "2025-08-11T22:50:03.135959Z",
     "start_time": "2025-08-11T22:49:26.824618Z"
    }
   },
   "source": [
    "%%time\n",
    "import pandas as pd\n",
    "import csv\n",
    "df = pd.read_csv(\"E:\\\\Ziwig Drive\\\\Ziwig Health\\\\Tables de Réf\\\\Professionnels\\\\Table_Réf_Professionnels_250804.txt\",\n",
    "                 sep='|', doublequote=False, quoting=csv.QUOTE_NONE, dtype=str, na_values='', keep_default_na=False)\n",
    "df.index.name = 'index'\n",
    "df.columns"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: total: 35.9 s\n",
      "Wall time: 36.3 s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Index(['Type d'identifiant PP', 'Identifiant PP',\n",
       "       'Identification nationale PP', 'Code civilité d'exercice',\n",
       "       'Libellé civilité d'exercice', 'Code civilité', 'Libellé civilité',\n",
       "       'Nom d'exercice', 'Prénom d'exercice', 'Code profession',\n",
       "       'Libellé profession', 'Code catégorie professionnelle',\n",
       "       'Libellé catégorie professionnelle', 'Code type savoir-faire',\n",
       "       'Libellé type savoir-faire', 'Code savoir-faire',\n",
       "       'Libellé savoir-faire', 'Code mode exercice', 'Libellé mode exercice',\n",
       "       'Numéro SIRET site', 'Numéro SIREN site', 'Numéro FINESS site',\n",
       "       'Numéro FINESS établissement juridique',\n",
       "       'Identifiant technique de la structure', 'Raison sociale site',\n",
       "       'Enseigne commerciale site',\n",
       "       'Complément destinataire (coord. structure)',\n",
       "       'Complément point géographique (coord. structure)',\n",
       "       'Numéro Voie (coord. structure)',\n",
       "       'Indice répétition voie (coord. structure)',\n",
       "       'Code type de voie (coord. structure)',\n",
       "       'Libellé type de voie (coord. structure)',\n",
       "       'Libellé Voie (coord. structure)',\n",
       "       'Mention distribution (coord. structure)',\n",
       "       'Bureau cedex (coord. structure)', 'Code postal (coord. structure)',\n",
       "       'Code commune (coord. structure)', 'Libellé commune (coord. structure)',\n",
       "       'Code pays (coord. structure)', 'Libellé pays (coord. structure)',\n",
       "       'Téléphone (coord. structure)', 'Téléphone 2 (coord. structure)',\n",
       "       'Télécopie (coord. structure)', 'Adresse e-mail (coord. structure)',\n",
       "       'Code Département (structure)', 'Libellé Département (structure)',\n",
       "       'Ancien identifiant de la structure', 'Autorité d'enregistrement',\n",
       "       'Code secteur d'activité', 'Libellé secteur d'activité',\n",
       "       'Code section tableau pharmaciens',\n",
       "       'Libellé section tableau pharmaciens', 'Code rôle', 'Libellé rôle',\n",
       "       'Code genre activité', 'Libellé genre activité', 'Unnamed: 56'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 38
  },
  {
   "cell_type": "code",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "ExecuteTime": {
     "end_time": "2025-08-11T22:53:55.986443Z",
     "start_time": "2025-08-11T22:50:03.157898Z"
    }
   },
   "source": [
    "%%time\n",
    "df2 = df.assign(Nom_Prénom = df[\"Nom d'exercice\"]+\" \"+df[\"Prénom d'exercice\"]) \\\n",
    "        [['Identifiant PP','Nom_Prénom',\"Nom d'exercice\",\"Prénom d'exercice\"]] \\\n",
    "        .groupby('Identifiant PP') \\\n",
    "        .filter(lambda f: f['Nom_Prénom'].nunique()>1) \\\n",
    "        .sort_values(['Identifiant PP','index']) \\\n",
    "        [['Identifiant PP',\"Nom d'exercice\",\"Prénom d'exercice\"]]\n",
    "df2"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: total: 3min 44s\n",
      "Wall time: 3min 52s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "        Identifiant PP Nom d'exercice Prénom d'exercice\n",
       "index                                                  \n",
       "1350393    10000034180  DUWAT-GEORGES         GHISLAINE\n",
       "1350394    10000034180        GEORGES         GHISLAINE\n",
       "259        10000040062          MEYER           Nicolas\n",
       "260        10000040062          MEYER           Nicolas\n",
       "809702     10000040062          MEYER           NICOLAS\n",
       "...                ...            ...               ...\n",
       "2158383    10111077417        D'ELLOY         FRANCETTE\n",
       "537896     10111105358           HOMO             Maddy\n",
       "1889090    10111105358           Homo             Maddy\n",
       "537977     10111110721      ROCHEPEAU            Nadège\n",
       "2158797    10111110721        BARREAU            Nadège\n",
       "\n",
       "[9059 rows x 3 columns]"
      ],
      "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>Identifiant PP</th>\n",
       "      <th>Nom d'exercice</th>\n",
       "      <th>Prénom d'exercice</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>index</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1350393</th>\n",
       "      <td>10000034180</td>\n",
       "      <td>DUWAT-GEORGES</td>\n",
       "      <td>GHISLAINE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1350394</th>\n",
       "      <td>10000034180</td>\n",
       "      <td>GEORGES</td>\n",
       "      <td>GHISLAINE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>259</th>\n",
       "      <td>10000040062</td>\n",
       "      <td>MEYER</td>\n",
       "      <td>Nicolas</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>10000040062</td>\n",
       "      <td>MEYER</td>\n",
       "      <td>Nicolas</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>809702</th>\n",
       "      <td>10000040062</td>\n",
       "      <td>MEYER</td>\n",
       "      <td>NICOLAS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2158383</th>\n",
       "      <td>10111077417</td>\n",
       "      <td>D'ELLOY</td>\n",
       "      <td>FRANCETTE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>537896</th>\n",
       "      <td>10111105358</td>\n",
       "      <td>HOMO</td>\n",
       "      <td>Maddy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1889090</th>\n",
       "      <td>10111105358</td>\n",
       "      <td>Homo</td>\n",
       "      <td>Maddy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>537977</th>\n",
       "      <td>10111110721</td>\n",
       "      <td>ROCHEPEAU</td>\n",
       "      <td>Nadège</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2158797</th>\n",
       "      <td>10111110721</td>\n",
       "      <td>BARREAU</td>\n",
       "      <td>Nadège</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9059 rows × 3 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 39
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-08-11T22:53:56.801020Z",
     "start_time": "2025-08-11T22:53:56.699295Z"
    }
   },
   "cell_type": "code",
   "source": "df2.to_csv(\"E:\\\\Ziwig Drive\\\\Ziwig Health\\\\Tables de Réf\\\\Professionnels\\\\Table_Réf_Professionnels_250804_Multiple_Names_3-1.csv\", sep='|', index=True, doublequote=False, quoting=csv.QUOTE_NONE, lineterminator='\\n')",
   "outputs": [],
   "execution_count": 40
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-08-11T22:57:28.643070Z",
     "start_time": "2025-08-11T22:53:56.870889Z"
    }
   },
   "cell_type": "code",
   "source": [
    "%%time\n",
    "df3 = df.assign(Nom_Prénom = df[\"Nom d'exercice\"].str.lower()+\" \"+df[\"Prénom d'exercice\"].str.lower()) \\\n",
    "        [['Identifiant PP','Nom_Prénom',\"Nom d'exercice\",\"Prénom d'exercice\"]] \\\n",
    "        .groupby('Identifiant PP') \\\n",
    "        .filter(lambda f: f['Nom_Prénom'].nunique()>1) \\\n",
    "        .sort_values(['Identifiant PP','index']) \\\n",
    "        [['Identifiant PP',\"Nom d'exercice\",\"Prénom d'exercice\"]]\n",
    "df3"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: total: 3min 26s\n",
      "Wall time: 3min 31s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "        Identifiant PP Nom d'exercice Prénom d'exercice\n",
       "index                                                  \n",
       "1350393    10000034180  DUWAT-GEORGES         GHISLAINE\n",
       "1350394    10000034180        GEORGES         GHISLAINE\n",
       "1350470    10000046051         STUDER             AGNES\n",
       "1620048    10000046051         JURION             AGNES\n",
       "269964     10000101518       BARREYRE          SANDRINE\n",
       "...                ...            ...               ...\n",
       "1617156    10110987236         ROGIER          MATHILDE\n",
       "807882     10111077417        DOUVIER         FRANCETTE\n",
       "2158383    10111077417        D'ELLOY         FRANCETTE\n",
       "537977     10111110721      ROCHEPEAU            Nadège\n",
       "2158797    10111110721        BARREAU            Nadège\n",
       "\n",
       "[5395 rows x 3 columns]"
      ],
      "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>Identifiant PP</th>\n",
       "      <th>Nom d'exercice</th>\n",
       "      <th>Prénom d'exercice</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>index</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1350393</th>\n",
       "      <td>10000034180</td>\n",
       "      <td>DUWAT-GEORGES</td>\n",
       "      <td>GHISLAINE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1350394</th>\n",
       "      <td>10000034180</td>\n",
       "      <td>GEORGES</td>\n",
       "      <td>GHISLAINE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1350470</th>\n",
       "      <td>10000046051</td>\n",
       "      <td>STUDER</td>\n",
       "      <td>AGNES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1620048</th>\n",
       "      <td>10000046051</td>\n",
       "      <td>JURION</td>\n",
       "      <td>AGNES</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>269964</th>\n",
       "      <td>10000101518</td>\n",
       "      <td>BARREYRE</td>\n",
       "      <td>SANDRINE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1617156</th>\n",
       "      <td>10110987236</td>\n",
       "      <td>ROGIER</td>\n",
       "      <td>MATHILDE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>807882</th>\n",
       "      <td>10111077417</td>\n",
       "      <td>DOUVIER</td>\n",
       "      <td>FRANCETTE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2158383</th>\n",
       "      <td>10111077417</td>\n",
       "      <td>D'ELLOY</td>\n",
       "      <td>FRANCETTE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>537977</th>\n",
       "      <td>10111110721</td>\n",
       "      <td>ROCHEPEAU</td>\n",
       "      <td>Nadège</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2158797</th>\n",
       "      <td>10111110721</td>\n",
       "      <td>BARREAU</td>\n",
       "      <td>Nadège</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5395 rows × 3 columns</p>\n",
       "</div>"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 41
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-08-11T22:57:29.038232Z",
     "start_time": "2025-08-11T22:57:29.014447Z"
    }
   },
   "cell_type": "code",
   "source": "df3.to_csv(\"E:\\\\Ziwig Drive\\\\Ziwig Health\\\\Tables de Réf\\\\Professionnels\\\\Table_Réf_Professionnels_250804_Multiple_Names_3-2.csv\", sep='|', index=True, doublequote=False, quoting=csv.QUOTE_NONE, lineterminator='\\n')",
   "outputs": [],
   "execution_count": 42
  }
 ],
 "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": "3.8.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}