{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c4205b5d-e052-4863-a46b-20e4757052a7",
   "metadata": {},
   "source": [
    "# Business Data Challenge - Team 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ae3af8e6-ced8-4994-8877-fa98d4297cc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd3184e7-54a1-4463-af42-5850d9517a41",
   "metadata": {},
   "source": [
    "Configuration de l'accès aux données"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b6035982-9ff4-4013-9792-2d50e10db3d1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['bdc2324-data/1/1campaign_stats.csv',\n",
       " 'bdc2324-data/1/1campaigns.csv',\n",
       " 'bdc2324-data/1/1categories.csv',\n",
       " 'bdc2324-data/1/1countries.csv',\n",
       " 'bdc2324-data/1/1currencies.csv',\n",
       " 'bdc2324-data/1/1customer_target_mappings.csv',\n",
       " 'bdc2324-data/1/1customersplus.csv',\n",
       " 'bdc2324-data/1/1event_types.csv',\n",
       " 'bdc2324-data/1/1events.csv',\n",
       " 'bdc2324-data/1/1facilities.csv',\n",
       " 'bdc2324-data/1/1link_stats.csv',\n",
       " 'bdc2324-data/1/1pricing_formulas.csv',\n",
       " 'bdc2324-data/1/1product_packs.csv',\n",
       " 'bdc2324-data/1/1products.csv',\n",
       " 'bdc2324-data/1/1products_groups.csv',\n",
       " 'bdc2324-data/1/1purchases.csv',\n",
       " 'bdc2324-data/1/1representation_category_capacities.csv',\n",
       " 'bdc2324-data/1/1representations.csv',\n",
       " 'bdc2324-data/1/1seasons.csv',\n",
       " 'bdc2324-data/1/1structure_tag_mappings.csv',\n",
       " 'bdc2324-data/1/1suppliers.csv',\n",
       " 'bdc2324-data/1/1tags.csv',\n",
       " 'bdc2324-data/1/1target_types.csv',\n",
       " 'bdc2324-data/1/1targets.csv',\n",
       " 'bdc2324-data/1/1tickets.csv',\n",
       " 'bdc2324-data/1/1type_of_categories.csv',\n",
       " 'bdc2324-data/1/1type_of_pricing_formulas.csv',\n",
       " 'bdc2324-data/1/1type_ofs.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "import s3fs\n",
    "# Create filesystem object\n",
    "S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
    "fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})\n",
    "\n",
    "BUCKET = \"bdc2324-data/1\"\n",
    "fs.ls(BUCKET)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b86c935d-124f-453f-80dd-83ea6770d09c",
   "metadata": {},
   "outputs": [],
   "source": [
    "dic_base=['campaign_stats','campaigns','categories','countries','currencies','customer_target_mappings','customersplus','event_types','events','facilities','link_stats','pricing_formulas','product_packs','products','products_groups','purchases','representation_category_capacities','representations','seasons','structure_tag_mappings','suppliers','tags','target_types','targets','tickets','type_of_categories','type_of_pricing_formulas','type_ofs']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f6d0b27c-0ecd-406b-b042-6c3802dd68fd",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_447/1008972637.py:5: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  globals()[nom_base] = pd.read_csv(file_in, sep=\",\")\n"
     ]
    }
   ],
   "source": [
    "dic_base=['campaign_stats','campaigns','categories','countries','currencies','customer_target_mappings','customersplus','event_types','events','facilities','link_stats','pricing_formulas','product_packs','products','products_groups','purchases','representation_category_capacities','representations','seasons','structure_tag_mappings','suppliers','tags','target_types','targets','tickets','type_of_categories','type_of_pricing_formulas','type_ofs']\n",
    "for nom_base in dic_base:\n",
    "    FILE_PATH_S3_fanta = 'bdc2324-data/1/1' + nom_base + '.csv'\n",
    "    with fs.open(FILE_PATH_S3_fanta, mode=\"rb\") as file_in:\n",
    "        globals()[nom_base] = pd.read_csv(file_in, sep=\",\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2a6b5e22-3370-457f-83b7-dd1e13663229",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'bdc2324-data/1/1type_ofs.csv'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "FILE_PATH_S3_fanta"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79012186-ea51-4252-843e-36a9bbe3847e",
   "metadata": {},
   "source": [
    "# Analyse exploratoire "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a365f29-4766-47d8-9796-24a5271867b2",
   "metadata": {},
   "source": [
    "## I. Base  type_of_pricing_formulas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bcc14f93-2289-44eb-816b-a51049b258df",
   "metadata": {},
   "source": [
    "## Detection des valeur manquantes"
   ]
  },
  {
   "cell_type": "raw",
   "id": "ab2ec4c4-9d38-4aeb-8202-9116df3cdd66",
   "metadata": {},
   "source": [
    "dic_prod_princing=['type_of_pricing_formulas','products_groups','pricing_formulas','product_packs','products']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88759b4a-2633-478d-abce-29abeac376d1",
   "metadata": {},
   "source": [
    "def verifier_donnees_manquantes(base):\n",
    "    donnees_manquantes = base.isna().sum()\n",
    "    print(\"Données manquantes pour la base :\")\n",
    "    print(donnees_manquantes)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df3075b4-1490-4cf2-a3fe-c6d4e2144ae3",
   "metadata": {},
   "source": [
    "for nom_base in dic_prod_princing:\n",
    "    verifier_donnees_manquantes(nom_base)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "e0c67c01-e837-4772-b070-d1be0d895a36",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                    0\n",
       "type_of_id            0\n",
       "pricing_formula_id    0\n",
       "created_at            0\n",
       "updated_at            0\n",
       "identifier            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#detection des Nan d\n",
    "\n",
    "type_of_pricing_formulas.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3eaffaa6-1164-4ee9-a671-8b5eb3df797d",
   "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>id</th>\n",
       "      <th>type_of_id</th>\n",
       "      <th>pricing_formula_id</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>127</td>\n",
       "      <td>2021-01-05 11:55:51.226960+01:00</td>\n",
       "      <td>2021-01-05 11:55:51.226960+01:00</td>\n",
       "      <td>cf2918b25e6dcf8c30798ca05c8ec8ed</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2425</td>\n",
       "      <td>2021-01-05 11:55:51.235606+01:00</td>\n",
       "      <td>2021-01-05 11:55:51.235606+01:00</td>\n",
       "      <td>2c8ee3f7c1487d792b6c946314e681f2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2937</td>\n",
       "      <td>2021-01-05 11:55:51.240114+01:00</td>\n",
       "      <td>2021-01-05 11:55:51.240114+01:00</td>\n",
       "      <td>44e55c85e4eb59b3c3c01c137a6b25fc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-01-05 11:55:51.244638+01:00</td>\n",
       "      <td>2021-01-05 11:55:51.244638+01:00</td>\n",
       "      <td>ee3bb93b7e2217cd86a49d547fedf6c6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>2021-01-05 11:55:51.249409+01:00</td>\n",
       "      <td>2021-01-05 11:55:51.249409+01:00</td>\n",
       "      <td>ae701668574f1a653d2b21ddfd250620</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>563</th>\n",
       "      <td>564</td>\n",
       "      <td>4</td>\n",
       "      <td>6656</td>\n",
       "      <td>2022-02-18 16:15:58.872249+01:00</td>\n",
       "      <td>2022-02-18 16:15:58.872249+01:00</td>\n",
       "      <td>f669824cdca9de9697f07ff3ba365a8d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>564</th>\n",
       "      <td>565</td>\n",
       "      <td>4</td>\n",
       "      <td>6607</td>\n",
       "      <td>2022-02-18 16:15:59.231018+01:00</td>\n",
       "      <td>2022-02-18 16:15:59.231018+01:00</td>\n",
       "      <td>6421c8146a598758139153b0e7b921ea</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>565</th>\n",
       "      <td>566</td>\n",
       "      <td>4</td>\n",
       "      <td>6700</td>\n",
       "      <td>2022-02-18 16:15:59.724812+01:00</td>\n",
       "      <td>2022-02-18 16:15:59.724812+01:00</td>\n",
       "      <td>6823f6d4d80b322fbfb8b83545a9f96d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>567</td>\n",
       "      <td>4</td>\n",
       "      <td>8118</td>\n",
       "      <td>2022-02-18 16:16:00.163381+01:00</td>\n",
       "      <td>2022-02-18 16:16:00.163381+01:00</td>\n",
       "      <td>35cfc12584b4d1b94795d97fd0aa56e8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>569</td>\n",
       "      <td>7</td>\n",
       "      <td>48157</td>\n",
       "      <td>2023-03-13 11:30:29.480161+01:00</td>\n",
       "      <td>2023-03-13 11:30:29.480161+01:00</td>\n",
       "      <td>55863541f33fd229ac9b54d9ec1f4874</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>568 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      id  type_of_id  pricing_formula_id                        created_at  \\\n",
       "0      1           1                 127  2021-01-05 11:55:51.226960+01:00   \n",
       "1      2           1                2425  2021-01-05 11:55:51.235606+01:00   \n",
       "2      3           1                2937  2021-01-05 11:55:51.240114+01:00   \n",
       "3      4           1                  48  2021-01-05 11:55:51.244638+01:00   \n",
       "4      5           1                   7  2021-01-05 11:55:51.249409+01:00   \n",
       "..   ...         ...                 ...                               ...   \n",
       "563  564           4                6656  2022-02-18 16:15:58.872249+01:00   \n",
       "564  565           4                6607  2022-02-18 16:15:59.231018+01:00   \n",
       "565  566           4                6700  2022-02-18 16:15:59.724812+01:00   \n",
       "566  567           4                8118  2022-02-18 16:16:00.163381+01:00   \n",
       "567  569           7               48157  2023-03-13 11:30:29.480161+01:00   \n",
       "\n",
       "                           updated_at                        identifier  \n",
       "0    2021-01-05 11:55:51.226960+01:00  cf2918b25e6dcf8c30798ca05c8ec8ed  \n",
       "1    2021-01-05 11:55:51.235606+01:00  2c8ee3f7c1487d792b6c946314e681f2  \n",
       "2    2021-01-05 11:55:51.240114+01:00  44e55c85e4eb59b3c3c01c137a6b25fc  \n",
       "3    2021-01-05 11:55:51.244638+01:00  ee3bb93b7e2217cd86a49d547fedf6c6  \n",
       "4    2021-01-05 11:55:51.249409+01:00  ae701668574f1a653d2b21ddfd250620  \n",
       "..                                ...                               ...  \n",
       "563  2022-02-18 16:15:58.872249+01:00  f669824cdca9de9697f07ff3ba365a8d  \n",
       "564  2022-02-18 16:15:59.231018+01:00  6421c8146a598758139153b0e7b921ea  \n",
       "565  2022-02-18 16:15:59.724812+01:00  6823f6d4d80b322fbfb8b83545a9f96d  \n",
       "566  2022-02-18 16:16:00.163381+01:00  35cfc12584b4d1b94795d97fd0aa56e8  \n",
       "567  2023-03-13 11:30:29.480161+01:00  55863541f33fd229ac9b54d9ec1f4874  \n",
       "\n",
       "[568 rows x 6 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type_of_pricing_formulas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "57298669-8d55-40d5-a5aa-4c5df984eec7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                     int64\n",
       "type_of_id             int64\n",
       "pricing_formula_id     int64\n",
       "created_at            object\n",
       "updated_at            object\n",
       "identifier            object\n",
       "dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#type des variables\n",
    "\n",
    "type_of_pricing_formulas.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c11850cb-8833-44c0-a11d-9695d620a42b",
   "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>id</th>\n",
       "      <th>type_of_id</th>\n",
       "      <th>pricing_formula_id</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [id, type_of_id, pricing_formula_id, created_at, updated_at, identifier]\n",
       "Index: []"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Identification des doublons\n",
    "type_of_pricing_formulas.loc[type_of_pricing_formulas['id'].duplicated(keep=False),:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a40de03-5e18-4d3d-a0f8-da960c29fad8",
   "metadata": {},
   "source": [
    "## II.products_groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "89909175-6734-4e8e-8632-d6f8ca812388",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                    0\n",
       "percent_price         0\n",
       "max_price             0\n",
       "min_price             0\n",
       "category_id           0\n",
       "pricing_formula_id    0\n",
       "representation_id     0\n",
       "created_at            0\n",
       "updated_at            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#detection des Nan \n",
    "\n",
    "products_groups.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "6a187170-96c4-48d2-9568-b270f67e2c27",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                      int64\n",
       "percent_price         float64\n",
       "max_price             float64\n",
       "min_price             float64\n",
       "category_id             int64\n",
       "pricing_formula_id      int64\n",
       "representation_id       int64\n",
       "created_at             object\n",
       "updated_at             object\n",
       "dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#type des variables\n",
    "\n",
    "products_groups.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2fba2cb0-a6a4-43b2-a854-3be07939c28b",
   "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>id</th>\n",
       "      <th>percent_price</th>\n",
       "      <th>max_price</th>\n",
       "      <th>min_price</th>\n",
       "      <th>category_id</th>\n",
       "      <th>pricing_formula_id</th>\n",
       "      <th>representation_id</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [id, percent_price, max_price, min_price, category_id, pricing_formula_id, representation_id, created_at, updated_at]\n",
       "Index: []"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Identification des doublons\n",
    "products_groups.loc[products_groups[['id','pricing_formula_id','representation_id']].duplicated(keep=False),:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5312ac13-8fbd-4c3f-a98a-8c28f079a599",
   "metadata": {},
   "source": [
    "## III.pricing_formulas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3383a773-0817-4b23-84e7-8d5d0c74b179",
   "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>id</th>\n",
       "      <th>name</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>extra_field</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>41909</td>\n",
       "      <td>visite mécènes 1h30</td>\n",
       "      <td>2022-07-08 07:08:26.802266+02:00</td>\n",
       "      <td>2022-07-08 07:08:26.802266+02:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21d4b0043c12b21952b0797d140991a1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>502</td>\n",
       "      <td>entree mucem tp( expo picasso)</td>\n",
       "      <td>2020-09-03 13:43:59.816765+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>223b09e6c3f1f75dbf8df019af97a555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>504</td>\n",
       "      <td>nombre de personnes cinema</td>\n",
       "      <td>2020-09-03 13:43:59.818198+02:00</td>\n",
       "      <td>2021-01-25 19:16:05.187114+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ba33b7b6d225a75d713a356b49c4d915</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>117</td>\n",
       "      <td>spectacle tarif e famille tr</td>\n",
       "      <td>2020-09-03 13:21:21.400249+02:00</td>\n",
       "      <td>2023-03-13 11:30:29.525335+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a00b61ad933518856f86e63ca91a5750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1496</td>\n",
       "      <td>billet nb famille mecene 1a</td>\n",
       "      <td>2020-09-03 14:29:33.320952+02:00</td>\n",
       "      <td>2021-01-25 19:23:06.816402+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7f6013803c242253a5ccde80f780984f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>551</th>\n",
       "      <td>529</td>\n",
       "      <td>billet nb expo gr</td>\n",
       "      <td>2020-09-03 13:43:59.835944+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7d888e42abe101fc8b21dc88948c8b74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>3153</td>\n",
       "      <td>nb pers visite scolaire rep</td>\n",
       "      <td>2020-09-03 16:32:37.068864+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3cf21731c25eee650d5b232ee4780563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>553</th>\n",
       "      <td>5847</td>\n",
       "      <td>visite scolaire rep1h00</td>\n",
       "      <td>2021-06-09 18:10:49.742531+02:00</td>\n",
       "      <td>2022-02-18 15:55:03.576236+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a7bb5a6892d55f0d5ee4ce5786ae5fc6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>554</th>\n",
       "      <td>5840</td>\n",
       "      <td>france billet - entree ts</td>\n",
       "      <td>2021-06-09 18:10:49.737576+02:00</td>\n",
       "      <td>2022-02-18 16:16:00.199543+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4c53016fc65847646f600eff853593e5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>555</th>\n",
       "      <td>5863</td>\n",
       "      <td>france billet - entree tp</td>\n",
       "      <td>2021-06-09 18:12:49.269924+02:00</td>\n",
       "      <td>2022-02-18 16:16:00.199543+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>90e642c0e1ef6bc9f2bc43089798de00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>556 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id                            name                        created_at  \\\n",
       "0    41909             visite mécènes 1h30  2022-07-08 07:08:26.802266+02:00   \n",
       "1      502  entree mucem tp( expo picasso)  2020-09-03 13:43:59.816765+02:00   \n",
       "2      504      nombre de personnes cinema  2020-09-03 13:43:59.818198+02:00   \n",
       "3      117    spectacle tarif e famille tr  2020-09-03 13:21:21.400249+02:00   \n",
       "4     1496     billet nb famille mecene 1a  2020-09-03 14:29:33.320952+02:00   \n",
       "..     ...                             ...                               ...   \n",
       "551    529               billet nb expo gr  2020-09-03 13:43:59.835944+02:00   \n",
       "552   3153     nb pers visite scolaire rep  2020-09-03 16:32:37.068864+02:00   \n",
       "553   5847         visite scolaire rep1h00  2021-06-09 18:10:49.742531+02:00   \n",
       "554   5840       france billet - entree ts  2021-06-09 18:10:49.737576+02:00   \n",
       "555   5863       france billet - entree tp  2021-06-09 18:12:49.269924+02:00   \n",
       "\n",
       "                           updated_at  extra_field  \\\n",
       "0    2022-07-08 07:08:26.802266+02:00          NaN   \n",
       "1    2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "2    2021-01-25 19:16:05.187114+01:00          NaN   \n",
       "3    2023-03-13 11:30:29.525335+01:00          NaN   \n",
       "4    2021-01-25 19:23:06.816402+01:00          NaN   \n",
       "..                                ...          ...   \n",
       "551  2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "552  2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "553  2022-02-18 15:55:03.576236+01:00          NaN   \n",
       "554  2022-02-18 16:16:00.199543+01:00          NaN   \n",
       "555  2022-02-18 16:16:00.199543+01:00          NaN   \n",
       "\n",
       "                           identifier  \n",
       "0    21d4b0043c12b21952b0797d140991a1  \n",
       "1    223b09e6c3f1f75dbf8df019af97a555  \n",
       "2    ba33b7b6d225a75d713a356b49c4d915  \n",
       "3    a00b61ad933518856f86e63ca91a5750  \n",
       "4    7f6013803c242253a5ccde80f780984f  \n",
       "..                                ...  \n",
       "551  7d888e42abe101fc8b21dc88948c8b74  \n",
       "552  3cf21731c25eee650d5b232ee4780563  \n",
       "553  a7bb5a6892d55f0d5ee4ce5786ae5fc6  \n",
       "554  4c53016fc65847646f600eff853593e5  \n",
       "555  90e642c0e1ef6bc9f2bc43089798de00  \n",
       "\n",
       "[556 rows x 6 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pricing_formulas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d8130c73-6c5f-45b1-93ae-db7679c8ca56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id             0.0\n",
       "name           0.0\n",
       "created_at     0.0\n",
       "updated_at     0.0\n",
       "extra_field    1.0\n",
       "identifier     0.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#detection des Nan \n",
    "\n",
    "pricing_formulas.isna().sum()/pricing_formulas.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "44f1dbfd-c3cf-464b-9877-f37fcc61da92",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id               int64\n",
       "name            object\n",
       "created_at      object\n",
       "updated_at      object\n",
       "extra_field    float64\n",
       "identifier      object\n",
       "dtype: object"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#type des variables\n",
    "\n",
    "pricing_formulas.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6784b41b-da74-4fae-832e-16641ae710c1",
   "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>id</th>\n",
       "      <th>name</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>extra_field</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [id, name, created_at, updated_at, extra_field, identifier]\n",
       "Index: []"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Identification des doublons\n",
    "pricing_formulas.loc[pricing_formulas[['id']].duplicated(keep=False),:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2145b0a4-b73d-4530-8c12-a78b1cf86eae",
   "metadata": {},
   "source": [
    "## IV. product_packs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e36b07a7-4f0b-4711-86a0-12a1d8158eef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id            0.0\n",
       "name          1.0\n",
       "type_of       0.0\n",
       "created_at    0.0\n",
       "updated_at    0.0\n",
       "identifier    0.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#detection des Nan \n",
    "\n",
    "product_packs.isna().sum()/product_packs.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "8707396a-f86b-476d-a9f9-c39f8de1d02e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id              int64\n",
       "name          float64\n",
       "type_of         int64\n",
       "created_at     object\n",
       "updated_at     object\n",
       "identifier     object\n",
       "dtype: object"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#type des variables\n",
    "\n",
    "product_packs.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "4b102bd3-924b-43da-8915-be7664c23f97",
   "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>id</th>\n",
       "      <th>name</th>\n",
       "      <th>type_of</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [id, name, type_of, created_at, updated_at, identifier]\n",
       "Index: []"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Identification des doublons\n",
    "product_packs.loc[product_packs[['id']].duplicated(keep=False),:]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cfe0c525-896b-4731-b38e-306ff6ea0c65",
   "metadata": {},
   "source": [
    "## V.products"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "968beb24-f70c-4eb6-8b1e-4b04bc7fe9c9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                    0.0\n",
       "amount                0.0\n",
       "is_full_price         0.0\n",
       "representation_id     0.0\n",
       "pricing_formula_id    0.0\n",
       "created_at            0.0\n",
       "updated_at            0.0\n",
       "category_id           0.0\n",
       "apply_price           0.0\n",
       "products_group_id     0.0\n",
       "product_pack_id       0.0\n",
       "extra_field           1.0\n",
       "amount_consumption    1.0\n",
       "identifier            0.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#detection des Nan \n",
    "\n",
    "products.isna().sum()/products.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "15bc6ac6-67e8-4e2c-9641-7ee8bb2581a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                      int64\n",
       "amount                float64\n",
       "is_full_price            bool\n",
       "representation_id       int64\n",
       "pricing_formula_id      int64\n",
       "created_at             object\n",
       "updated_at             object\n",
       "category_id             int64\n",
       "apply_price           float64\n",
       "products_group_id       int64\n",
       "product_pack_id         int64\n",
       "extra_field           float64\n",
       "amount_consumption    float64\n",
       "identifier             object\n",
       "dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#type des variables\n",
    "\n",
    "products.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "7daa4f1a-e429-4daf-a2e1-1e311b487e09",
   "metadata": {},
   "outputs": [],
   "source": [
    "#dic_prod_princing=['type_of_pricing_formulas','products_groups','pricing_formulas','product_packs','products']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "dc12b746-6708-4708-826a-acb5a8e665a1",
   "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>id</th>\n",
       "      <th>name</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "      <th>extra_field</th>\n",
       "      <th>identifier</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>41909</td>\n",
       "      <td>visite mécènes 1h30</td>\n",
       "      <td>2022-07-08 07:08:26.802266+02:00</td>\n",
       "      <td>2022-07-08 07:08:26.802266+02:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21d4b0043c12b21952b0797d140991a1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>502</td>\n",
       "      <td>entree mucem tp( expo picasso)</td>\n",
       "      <td>2020-09-03 13:43:59.816765+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>223b09e6c3f1f75dbf8df019af97a555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>504</td>\n",
       "      <td>nombre de personnes cinema</td>\n",
       "      <td>2020-09-03 13:43:59.818198+02:00</td>\n",
       "      <td>2021-01-25 19:16:05.187114+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ba33b7b6d225a75d713a356b49c4d915</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>117</td>\n",
       "      <td>spectacle tarif e famille tr</td>\n",
       "      <td>2020-09-03 13:21:21.400249+02:00</td>\n",
       "      <td>2023-03-13 11:30:29.525335+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a00b61ad933518856f86e63ca91a5750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1496</td>\n",
       "      <td>billet nb famille mecene 1a</td>\n",
       "      <td>2020-09-03 14:29:33.320952+02:00</td>\n",
       "      <td>2021-01-25 19:23:06.816402+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7f6013803c242253a5ccde80f780984f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>551</th>\n",
       "      <td>529</td>\n",
       "      <td>billet nb expo gr</td>\n",
       "      <td>2020-09-03 13:43:59.835944+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7d888e42abe101fc8b21dc88948c8b74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>3153</td>\n",
       "      <td>nb pers visite scolaire rep</td>\n",
       "      <td>2020-09-03 16:32:37.068864+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3cf21731c25eee650d5b232ee4780563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>553</th>\n",
       "      <td>5847</td>\n",
       "      <td>visite scolaire rep1h00</td>\n",
       "      <td>2021-06-09 18:10:49.742531+02:00</td>\n",
       "      <td>2022-02-18 15:55:03.576236+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a7bb5a6892d55f0d5ee4ce5786ae5fc6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>554</th>\n",
       "      <td>5840</td>\n",
       "      <td>france billet - entree ts</td>\n",
       "      <td>2021-06-09 18:10:49.737576+02:00</td>\n",
       "      <td>2022-02-18 16:16:00.199543+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4c53016fc65847646f600eff853593e5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>555</th>\n",
       "      <td>5863</td>\n",
       "      <td>france billet - entree tp</td>\n",
       "      <td>2021-06-09 18:12:49.269924+02:00</td>\n",
       "      <td>2022-02-18 16:16:00.199543+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>90e642c0e1ef6bc9f2bc43089798de00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>556 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id                            name                        created_at  \\\n",
       "0    41909             visite mécènes 1h30  2022-07-08 07:08:26.802266+02:00   \n",
       "1      502  entree mucem tp( expo picasso)  2020-09-03 13:43:59.816765+02:00   \n",
       "2      504      nombre de personnes cinema  2020-09-03 13:43:59.818198+02:00   \n",
       "3      117    spectacle tarif e famille tr  2020-09-03 13:21:21.400249+02:00   \n",
       "4     1496     billet nb famille mecene 1a  2020-09-03 14:29:33.320952+02:00   \n",
       "..     ...                             ...                               ...   \n",
       "551    529               billet nb expo gr  2020-09-03 13:43:59.835944+02:00   \n",
       "552   3153     nb pers visite scolaire rep  2020-09-03 16:32:37.068864+02:00   \n",
       "553   5847         visite scolaire rep1h00  2021-06-09 18:10:49.742531+02:00   \n",
       "554   5840       france billet - entree ts  2021-06-09 18:10:49.737576+02:00   \n",
       "555   5863       france billet - entree tp  2021-06-09 18:12:49.269924+02:00   \n",
       "\n",
       "                           updated_at  extra_field  \\\n",
       "0    2022-07-08 07:08:26.802266+02:00          NaN   \n",
       "1    2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "2    2021-01-25 19:16:05.187114+01:00          NaN   \n",
       "3    2023-03-13 11:30:29.525335+01:00          NaN   \n",
       "4    2021-01-25 19:23:06.816402+01:00          NaN   \n",
       "..                                ...          ...   \n",
       "551  2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "552  2022-02-18 15:57:55.792581+01:00          NaN   \n",
       "553  2022-02-18 15:55:03.576236+01:00          NaN   \n",
       "554  2022-02-18 16:16:00.199543+01:00          NaN   \n",
       "555  2022-02-18 16:16:00.199543+01:00          NaN   \n",
       "\n",
       "                           identifier  \n",
       "0    21d4b0043c12b21952b0797d140991a1  \n",
       "1    223b09e6c3f1f75dbf8df019af97a555  \n",
       "2    ba33b7b6d225a75d713a356b49c4d915  \n",
       "3    a00b61ad933518856f86e63ca91a5750  \n",
       "4    7f6013803c242253a5ccde80f780984f  \n",
       "..                                ...  \n",
       "551  7d888e42abe101fc8b21dc88948c8b74  \n",
       "552  3cf21731c25eee650d5b232ee4780563  \n",
       "553  a7bb5a6892d55f0d5ee4ce5786ae5fc6  \n",
       "554  4c53016fc65847646f600eff853593e5  \n",
       "555  90e642c0e1ef6bc9f2bc43089798de00  \n",
       "\n",
       "[556 rows x 6 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pricing_formulas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46aad10f-8530-410e-872b-bb253c553a46",
   "metadata": {},
   "source": [
    "# jointure entre les bases"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4c3edd1-6d58-4c57-b3e4-0ef3529f6b8c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#dic_prod_princing=['type_of_pricing_formulas','products_groups','pricing_formulas','product_packs','products']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "eac537e1-bbad-45bc-a85c-12b675da1088",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Merge1 entre products et pricing_formulas\n",
    "base1=products.merge(pricing_formulas, how='outer', left_on= 'pricing_formula_id', right_on= 'id',  suffixes = (\"_products\", \"_pricing_formula\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7dd0bdae-c1c5-44ba-a446-42b28def2343",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "75be3a30-3114-432d-87d6-697533c3c871",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Merge2 entre products et pricing_formulas\n",
    "base2=base1.merge(products_groups, how='outer', left_on= 'pricing_formula_id', right_on= 'id',  suffixes = (\"_merge2\", \"_product_group\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "13f4e606-3678-476c-8b8f-9d3f1123e563",
   "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>id_products</th>\n",
       "      <th>amount</th>\n",
       "      <th>is_full_price</th>\n",
       "      <th>representation_id_merge2</th>\n",
       "      <th>pricing_formula_id_merge2</th>\n",
       "      <th>created_at_products</th>\n",
       "      <th>updated_at_products</th>\n",
       "      <th>category_id_merge2</th>\n",
       "      <th>apply_price</th>\n",
       "      <th>products_group_id</th>\n",
       "      <th>...</th>\n",
       "      <th>identifier_pricing_formula</th>\n",
       "      <th>id</th>\n",
       "      <th>percent_price</th>\n",
       "      <th>max_price</th>\n",
       "      <th>min_price</th>\n",
       "      <th>category_id_product_group</th>\n",
       "      <th>pricing_formula_id_product_group</th>\n",
       "      <th>representation_id_product_group</th>\n",
       "      <th>created_at</th>\n",
       "      <th>updated_at</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10682.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>914.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>2020-09-03 14:09:43.119798+02:00</td>\n",
       "      <td>2020-09-03 14:09:43.119798+02:00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10655.0</td>\n",
       "      <td>...</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "      <td>114.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>23519.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>866.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>2020-09-03 15:01:05.950869+02:00</td>\n",
       "      <td>2020-09-03 15:01:05.950869+02:00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>23460.0</td>\n",
       "      <td>...</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "      <td>114.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3703.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>1949.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>2020-09-03 13:44:01.666354+02:00</td>\n",
       "      <td>2020-09-03 13:44:01.666354+02:00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3690.0</td>\n",
       "      <td>...</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "      <td>114.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23527.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>5573.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>2020-09-03 15:01:05.958931+02:00</td>\n",
       "      <td>2020-09-03 15:01:05.958931+02:00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>23468.0</td>\n",
       "      <td>...</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "      <td>114.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3712.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>509.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>2020-09-03 13:44:01.675588+02:00</td>\n",
       "      <td>2020-09-03 13:44:01.675588+02:00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3699.0</td>\n",
       "      <td>...</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "      <td>114.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "      <td>2020-09-03 13:21:21.456941+02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187391</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>404833.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>188494.0</td>\n",
       "      <td>2023-10-31 06:06:49.074426+01:00</td>\n",
       "      <td>2023-10-31 06:06:49.074426+01:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187392</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>404834.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2799.0</td>\n",
       "      <td>188494.0</td>\n",
       "      <td>2023-10-31 06:06:49.075541+01:00</td>\n",
       "      <td>2023-10-31 06:06:49.075541+01:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187393</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>404835.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5676.0</td>\n",
       "      <td>188494.0</td>\n",
       "      <td>2023-10-31 06:06:49.077170+01:00</td>\n",
       "      <td>2023-10-31 06:06:49.077170+01:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187394</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>404836.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>189434.0</td>\n",
       "      <td>2023-10-31 06:06:49.079215+01:00</td>\n",
       "      <td>2023-10-31 06:06:49.079215+01:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187395</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>404837.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6656.0</td>\n",
       "      <td>189434.0</td>\n",
       "      <td>2023-10-31 06:06:49.081039+01:00</td>\n",
       "      <td>2023-10-31 06:06:49.081039+01:00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>187396 rows × 29 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id_products  amount is_full_price  representation_id_merge2  \\\n",
       "0           10682.0     9.0         False                     914.0   \n",
       "1           23519.0     9.0         False                     866.0   \n",
       "2            3703.0     9.0         False                    1949.0   \n",
       "3           23527.0     9.0         False                    5573.0   \n",
       "4            3712.0     9.0         False                     509.0   \n",
       "...             ...     ...           ...                       ...   \n",
       "187391          NaN     NaN           NaN                       NaN   \n",
       "187392          NaN     NaN           NaN                       NaN   \n",
       "187393          NaN     NaN           NaN                       NaN   \n",
       "187394          NaN     NaN           NaN                       NaN   \n",
       "187395          NaN     NaN           NaN                       NaN   \n",
       "\n",
       "        pricing_formula_id_merge2               created_at_products  \\\n",
       "0                           114.0  2020-09-03 14:09:43.119798+02:00   \n",
       "1                           114.0  2020-09-03 15:01:05.950869+02:00   \n",
       "2                           114.0  2020-09-03 13:44:01.666354+02:00   \n",
       "3                           114.0  2020-09-03 15:01:05.958931+02:00   \n",
       "4                           114.0  2020-09-03 13:44:01.675588+02:00   \n",
       "...                           ...                               ...   \n",
       "187391                        NaN                               NaN   \n",
       "187392                        NaN                               NaN   \n",
       "187393                        NaN                               NaN   \n",
       "187394                        NaN                               NaN   \n",
       "187395                        NaN                               NaN   \n",
       "\n",
       "                     updated_at_products  category_id_merge2  apply_price  \\\n",
       "0       2020-09-03 14:09:43.119798+02:00                41.0          0.0   \n",
       "1       2020-09-03 15:01:05.950869+02:00                41.0          0.0   \n",
       "2       2020-09-03 13:44:01.666354+02:00                41.0          0.0   \n",
       "3       2020-09-03 15:01:05.958931+02:00                41.0          0.0   \n",
       "4       2020-09-03 13:44:01.675588+02:00                41.0          0.0   \n",
       "...                                  ...                 ...          ...   \n",
       "187391                               NaN                 NaN          NaN   \n",
       "187392                               NaN                 NaN          NaN   \n",
       "187393                               NaN                 NaN          NaN   \n",
       "187394                               NaN                 NaN          NaN   \n",
       "187395                               NaN                 NaN          NaN   \n",
       "\n",
       "        products_group_id  ...        identifier_pricing_formula        id  \\\n",
       "0                 10655.0  ...  039003ae0b0cd2df183786804b713470     114.0   \n",
       "1                 23460.0  ...  039003ae0b0cd2df183786804b713470     114.0   \n",
       "2                  3690.0  ...  039003ae0b0cd2df183786804b713470     114.0   \n",
       "3                 23468.0  ...  039003ae0b0cd2df183786804b713470     114.0   \n",
       "4                  3699.0  ...  039003ae0b0cd2df183786804b713470     114.0   \n",
       "...                   ...  ...                               ...       ...   \n",
       "187391                NaN  ...                               NaN  404833.0   \n",
       "187392                NaN  ...                               NaN  404834.0   \n",
       "187393                NaN  ...                               NaN  404835.0   \n",
       "187394                NaN  ...                               NaN  404836.0   \n",
       "187395                NaN  ...                               NaN  404837.0   \n",
       "\n",
       "        percent_price max_price  min_price category_id_product_group  \\\n",
       "0               100.0       0.0        0.0                      16.0   \n",
       "1               100.0       0.0        0.0                      16.0   \n",
       "2               100.0       0.0        0.0                      16.0   \n",
       "3               100.0       0.0        0.0                      16.0   \n",
       "4               100.0       0.0        0.0                      16.0   \n",
       "...               ...       ...        ...                       ...   \n",
       "187391          100.0       0.0        0.0                       2.0   \n",
       "187392          100.0       0.0        0.0                       5.0   \n",
       "187393          100.0       0.0        0.0                       5.0   \n",
       "187394          100.0       0.0        0.0                       5.0   \n",
       "187395          100.0       0.0        0.0                       1.0   \n",
       "\n",
       "       pricing_formula_id_product_group representation_id_product_group  \\\n",
       "0                                  79.0                            38.0   \n",
       "1                                  79.0                            38.0   \n",
       "2                                  79.0                            38.0   \n",
       "3                                  79.0                            38.0   \n",
       "4                                  79.0                            38.0   \n",
       "...                                 ...                             ...   \n",
       "187391                              4.0                        188494.0   \n",
       "187392                           2799.0                        188494.0   \n",
       "187393                           5676.0                        188494.0   \n",
       "187394                             32.0                        189434.0   \n",
       "187395                           6656.0                        189434.0   \n",
       "\n",
       "                              created_at                        updated_at  \n",
       "0       2020-09-03 13:21:21.456941+02:00  2020-09-03 13:21:21.456941+02:00  \n",
       "1       2020-09-03 13:21:21.456941+02:00  2020-09-03 13:21:21.456941+02:00  \n",
       "2       2020-09-03 13:21:21.456941+02:00  2020-09-03 13:21:21.456941+02:00  \n",
       "3       2020-09-03 13:21:21.456941+02:00  2020-09-03 13:21:21.456941+02:00  \n",
       "4       2020-09-03 13:21:21.456941+02:00  2020-09-03 13:21:21.456941+02:00  \n",
       "...                                  ...                               ...  \n",
       "187391  2023-10-31 06:06:49.074426+01:00  2023-10-31 06:06:49.074426+01:00  \n",
       "187392  2023-10-31 06:06:49.075541+01:00  2023-10-31 06:06:49.075541+01:00  \n",
       "187393  2023-10-31 06:06:49.077170+01:00  2023-10-31 06:06:49.077170+01:00  \n",
       "187394  2023-10-31 06:06:49.079215+01:00  2023-10-31 06:06:49.079215+01:00  \n",
       "187395  2023-10-31 06:06:49.081039+01:00  2023-10-31 06:06:49.081039+01:00  \n",
       "\n",
       "[187396 rows x 29 columns]"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "base2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "053a4829-b0e7-4c8f-80b2-e57e99cdcedc",
   "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>id_products</th>\n",
       "      <th>amount</th>\n",
       "      <th>is_full_price</th>\n",
       "      <th>representation_id</th>\n",
       "      <th>pricing_formula_id</th>\n",
       "      <th>created_at_products</th>\n",
       "      <th>updated_at_products</th>\n",
       "      <th>category_id</th>\n",
       "      <th>apply_price</th>\n",
       "      <th>products_group_id</th>\n",
       "      <th>product_pack_id</th>\n",
       "      <th>extra_field_products</th>\n",
       "      <th>amount_consumption</th>\n",
       "      <th>identifier_products</th>\n",
       "      <th>id_pricing_formula</th>\n",
       "      <th>name</th>\n",
       "      <th>created_at_pricing_formula</th>\n",
       "      <th>updated_at_pricing_formula</th>\n",
       "      <th>extra_field_pricing_formula</th>\n",
       "      <th>identifier_pricing_formula</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10682</td>\n",
       "      <td>9.0</td>\n",
       "      <td>False</td>\n",
       "      <td>914</td>\n",
       "      <td>114</td>\n",
       "      <td>2020-09-03 14:09:43.119798+02:00</td>\n",
       "      <td>2020-09-03 14:09:43.119798+02:00</td>\n",
       "      <td>41</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10655</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35c88f2db8a63d7474e46eb8ca9260e7</td>\n",
       "      <td>114</td>\n",
       "      <td>visite guidée indiv tr</td>\n",
       "      <td>2020-09-03 13:21:21.397923+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>039003ae0b0cd2df183786804b713470</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>478</td>\n",
       "      <td>9.5</td>\n",
       "      <td>False</td>\n",
       "      <td>273</td>\n",
       "      <td>131</td>\n",
       "      <td>2020-09-03 13:21:22.711773+02:00</td>\n",
       "      <td>2020-09-03 13:21:22.711773+02:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>471</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8a179671ab198e570e6a104c4451379f</td>\n",
       "      <td>131</td>\n",
       "      <td>billet mucem tp - picasso</td>\n",
       "      <td>2020-09-03 13:21:21.410521+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>916c92362b8e7767715bc966de43e32b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20873</td>\n",
       "      <td>11.5</td>\n",
       "      <td>False</td>\n",
       "      <td>275</td>\n",
       "      <td>137</td>\n",
       "      <td>2020-09-03 14:46:33.589030+02:00</td>\n",
       "      <td>2020-09-03 14:46:33.589030+02:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>20825</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ee83779ce29e67ad251e40234b426d6a</td>\n",
       "      <td>137</td>\n",
       "      <td>billet mucem tp - pic. + guide</td>\n",
       "      <td>2020-09-03 13:21:21.414922+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>91dd2ee46f5f2d78af989019ebd60a60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>157142</td>\n",
       "      <td>8.0</td>\n",
       "      <td>False</td>\n",
       "      <td>82519</td>\n",
       "      <td>9</td>\n",
       "      <td>2022-01-28 19:29:23.525722+01:00</td>\n",
       "      <td>2022-01-28 19:29:23.525722+01:00</td>\n",
       "      <td>5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>156773</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d865383579314b791aa4bcf3fb418f17</td>\n",
       "      <td>9</td>\n",
       "      <td>billet mucem ts</td>\n",
       "      <td>2020-09-03 13:11:23.997074+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>37532348a1f1ef1cb916c55ebaf8345c</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1341</td>\n",
       "      <td>8.5</td>\n",
       "      <td>False</td>\n",
       "      <td>9</td>\n",
       "      <td>93</td>\n",
       "      <td>2020-09-03 13:29:30.773089+02:00</td>\n",
       "      <td>2020-09-03 13:29:30.773089+02:00</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1175</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>f1c4689bc47dee6f60b56d74b593dd46</td>\n",
       "      <td>93</td>\n",
       "      <td>billet mucem tr + guide</td>\n",
       "      <td>2020-09-03 13:21:21.382586+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>722a8610e4391c27f2ec6f1224b42b3d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94798</th>\n",
       "      <td>388554</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>181331</td>\n",
       "      <td>3153</td>\n",
       "      <td>2023-04-05 03:34:01.850415+02:00</td>\n",
       "      <td>2023-04-05 03:34:01.850415+02:00</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>387862</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>64147cc47279f4b1b76814b9f7f20619</td>\n",
       "      <td>3153</td>\n",
       "      <td>nb pers visite scolaire rep</td>\n",
       "      <td>2020-09-03 16:32:37.068864+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3cf21731c25eee650d5b232ee4780563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94799</th>\n",
       "      <td>388555</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>181331</td>\n",
       "      <td>20441</td>\n",
       "      <td>2023-04-05 03:34:01.853121+02:00</td>\n",
       "      <td>2023-04-05 03:34:01.853121+02:00</td>\n",
       "      <td>17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>387863</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>93ec10028cfa7557a8788dd2fb4f6a17</td>\n",
       "      <td>20441</td>\n",
       "      <td>visite scolaire rep1h30</td>\n",
       "      <td>2021-12-17 05:15:30.142593+01:00</td>\n",
       "      <td>2022-02-18 15:55:03.576236+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6844d69dcb1178aa9e04567bce71df1f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94800</th>\n",
       "      <td>388556</td>\n",
       "      <td>70.0</td>\n",
       "      <td>False</td>\n",
       "      <td>181332</td>\n",
       "      <td>17798</td>\n",
       "      <td>2023-04-05 03:34:01.855466+02:00</td>\n",
       "      <td>2023-04-05 03:34:01.855466+02:00</td>\n",
       "      <td>17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>387864</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a0cc8e58412502e24e38dfeded032485</td>\n",
       "      <td>17798</td>\n",
       "      <td>visite scolaire 1h30</td>\n",
       "      <td>2021-09-30 08:15:49.172362+02:00</td>\n",
       "      <td>2022-02-18 15:55:03.576236+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>cfa6ba42e14f2a170a0fc566a183fe94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94801</th>\n",
       "      <td>388557</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>181332</td>\n",
       "      <td>3126</td>\n",
       "      <td>2023-04-05 03:34:01.857441+02:00</td>\n",
       "      <td>2023-04-05 03:34:01.857441+02:00</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>387865</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>94532a14d98637ac9ee2b7d9aedad188</td>\n",
       "      <td>3126</td>\n",
       "      <td>nb pers visite scolaire</td>\n",
       "      <td>2020-09-03 16:31:39.822413+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ab5dbcde8e5e1fce29737070bce06799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94802</th>\n",
       "      <td>388526</td>\n",
       "      <td>5.0</td>\n",
       "      <td>False</td>\n",
       "      <td>181318</td>\n",
       "      <td>96</td>\n",
       "      <td>2023-04-04 06:06:31.784073+02:00</td>\n",
       "      <td>2023-04-04 06:06:31.784073+02:00</td>\n",
       "      <td>39</td>\n",
       "      <td>0.0</td>\n",
       "      <td>387834</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4c1ee03106e34585d57d96da5e7c5f50</td>\n",
       "      <td>96</td>\n",
       "      <td>visite guidée indiv tu</td>\n",
       "      <td>2020-09-03 13:21:21.384812+02:00</td>\n",
       "      <td>2022-02-18 15:57:55.792581+01:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>62fd9a5b40c116e45eda51222d135dfd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>94803 rows × 20 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id_products  amount  is_full_price  representation_id  \\\n",
       "0            10682     9.0          False                914   \n",
       "1              478     9.5          False                273   \n",
       "2            20873    11.5          False                275   \n",
       "3           157142     8.0          False              82519   \n",
       "4             1341     8.5          False                  9   \n",
       "...            ...     ...            ...                ...   \n",
       "94798       388554     0.0          False             181331   \n",
       "94799       388555     0.0          False             181331   \n",
       "94800       388556    70.0          False             181332   \n",
       "94801       388557     0.0          False             181332   \n",
       "94802       388526     5.0          False             181318   \n",
       "\n",
       "       pricing_formula_id               created_at_products  \\\n",
       "0                     114  2020-09-03 14:09:43.119798+02:00   \n",
       "1                     131  2020-09-03 13:21:22.711773+02:00   \n",
       "2                     137  2020-09-03 14:46:33.589030+02:00   \n",
       "3                       9  2022-01-28 19:29:23.525722+01:00   \n",
       "4                      93  2020-09-03 13:29:30.773089+02:00   \n",
       "...                   ...                               ...   \n",
       "94798                3153  2023-04-05 03:34:01.850415+02:00   \n",
       "94799               20441  2023-04-05 03:34:01.853121+02:00   \n",
       "94800               17798  2023-04-05 03:34:01.855466+02:00   \n",
       "94801                3126  2023-04-05 03:34:01.857441+02:00   \n",
       "94802                  96  2023-04-04 06:06:31.784073+02:00   \n",
       "\n",
       "                    updated_at_products  category_id  apply_price  \\\n",
       "0      2020-09-03 14:09:43.119798+02:00           41          0.0   \n",
       "1      2020-09-03 13:21:22.711773+02:00            1          0.0   \n",
       "2      2020-09-03 14:46:33.589030+02:00            1          0.0   \n",
       "3      2022-01-28 19:29:23.525722+01:00            5          0.0   \n",
       "4      2020-09-03 13:29:30.773089+02:00            1          0.0   \n",
       "...                                 ...          ...          ...   \n",
       "94798  2023-04-05 03:34:01.850415+02:00            9          0.0   \n",
       "94799  2023-04-05 03:34:01.853121+02:00           17          0.0   \n",
       "94800  2023-04-05 03:34:01.855466+02:00           17          0.0   \n",
       "94801  2023-04-05 03:34:01.857441+02:00            9          0.0   \n",
       "94802  2023-04-04 06:06:31.784073+02:00           39          0.0   \n",
       "\n",
       "       products_group_id  product_pack_id  extra_field_products  \\\n",
       "0                  10655                1                   NaN   \n",
       "1                    471                1                   NaN   \n",
       "2                  20825                1                   NaN   \n",
       "3                 156773                1                   NaN   \n",
       "4                   1175                1                   NaN   \n",
       "...                  ...              ...                   ...   \n",
       "94798             387862                1                   NaN   \n",
       "94799             387863                1                   NaN   \n",
       "94800             387864                1                   NaN   \n",
       "94801             387865                1                   NaN   \n",
       "94802             387834                1                   NaN   \n",
       "\n",
       "       amount_consumption               identifier_products  \\\n",
       "0                     NaN  35c88f2db8a63d7474e46eb8ca9260e7   \n",
       "1                     NaN  8a179671ab198e570e6a104c4451379f   \n",
       "2                     NaN  ee83779ce29e67ad251e40234b426d6a   \n",
       "3                     NaN  d865383579314b791aa4bcf3fb418f17   \n",
       "4                     NaN  f1c4689bc47dee6f60b56d74b593dd46   \n",
       "...                   ...                               ...   \n",
       "94798                 NaN  64147cc47279f4b1b76814b9f7f20619   \n",
       "94799                 NaN  93ec10028cfa7557a8788dd2fb4f6a17   \n",
       "94800                 NaN  a0cc8e58412502e24e38dfeded032485   \n",
       "94801                 NaN  94532a14d98637ac9ee2b7d9aedad188   \n",
       "94802                 NaN  4c1ee03106e34585d57d96da5e7c5f50   \n",
       "\n",
       "       id_pricing_formula                            name  \\\n",
       "0                     114          visite guidée indiv tr   \n",
       "1                     131       billet mucem tp - picasso   \n",
       "2                     137  billet mucem tp - pic. + guide   \n",
       "3                       9                 billet mucem ts   \n",
       "4                      93         billet mucem tr + guide   \n",
       "...                   ...                             ...   \n",
       "94798                3153     nb pers visite scolaire rep   \n",
       "94799               20441         visite scolaire rep1h30   \n",
       "94800               17798            visite scolaire 1h30   \n",
       "94801                3126         nb pers visite scolaire   \n",
       "94802                  96          visite guidée indiv tu   \n",
       "\n",
       "             created_at_pricing_formula        updated_at_pricing_formula  \\\n",
       "0      2020-09-03 13:21:21.397923+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "1      2020-09-03 13:21:21.410521+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "2      2020-09-03 13:21:21.414922+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "3      2020-09-03 13:11:23.997074+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "4      2020-09-03 13:21:21.382586+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "...                                 ...                               ...   \n",
       "94798  2020-09-03 16:32:37.068864+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "94799  2021-12-17 05:15:30.142593+01:00  2022-02-18 15:55:03.576236+01:00   \n",
       "94800  2021-09-30 08:15:49.172362+02:00  2022-02-18 15:55:03.576236+01:00   \n",
       "94801  2020-09-03 16:31:39.822413+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "94802  2020-09-03 13:21:21.384812+02:00  2022-02-18 15:57:55.792581+01:00   \n",
       "\n",
       "       extra_field_pricing_formula        identifier_pricing_formula  \n",
       "0                              NaN  039003ae0b0cd2df183786804b713470  \n",
       "1                              NaN  916c92362b8e7767715bc966de43e32b  \n",
       "2                              NaN  91dd2ee46f5f2d78af989019ebd60a60  \n",
       "3                              NaN  37532348a1f1ef1cb916c55ebaf8345c  \n",
       "4                              NaN  722a8610e4391c27f2ec6f1224b42b3d  \n",
       "...                            ...                               ...  \n",
       "94798                          NaN  3cf21731c25eee650d5b232ee4780563  \n",
       "94799                          NaN  6844d69dcb1178aa9e04567bce71df1f  \n",
       "94800                          NaN  cfa6ba42e14f2a170a0fc566a183fe94  \n",
       "94801                          NaN  ab5dbcde8e5e1fce29737070bce06799  \n",
       "94802                          NaN  62fd9a5b40c116e45eda51222d135dfd  \n",
       "\n",
       "[94803 rows x 20 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Merge2 entre products et pricing_formulas\n",
    "base2=base1.merge(pricing_formulas, how='left', left_on= 'id_pricing_formula', right_on= 'id',  suffixes = (\"\", \"\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bad94144-2474-49dd-9133-ab6082565ff1",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}