ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
20fa01647a
BDC-team-1/code_valeur manquante.ipynb
frodrigue-ensae 1f0892434f Valeur_manquante
2024-02-20 01:27:57 +00:00

2881 lines
106 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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": 28,
"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": 28,
"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": 7,
"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": 3,
"id": "f6d0b27c-0ecd-406b-b042-6c3802dd68fd",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_425/1008972637.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": 4,
"id": "2a6b5e22-3370-457f-83b7-dd1e13663229",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'bdc2324-data/1/1type_ofs.csv'"
]
},
"execution_count": 4,
"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": null,
"id": "83a6a48d-effe-4537-b4bb-d5a540b610f1",
"metadata": {},
"outputs": [],
"source": [
"#variable retenu:[[\"id\",\"type_of_id\",\"pricing_formula_id\"]]"
]
},
{
"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": null,
"id": "e0518684-c83c-4f0a-89ea-d7dcfd60051d",
"metadata": {},
"outputs": [],
"source": [
"#variable retenu:[[\"id\",\"percent_price\",\"max_price\",\"min_price\",\"category_id\",\"pricing_formula_id\",\"representation_id\"]]"
]
},
{
"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": null,
"id": "9f2909c1-bc6a-443f-a077-84f6ce6b7ab5",
"metadata": {},
"outputs": [],
"source": [
"#variable retenu: [[\"id\",\"name\"]]"
]
},
{
"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": null,
"id": "e0887a01-51ea-4034-84fe-dc4dbf2ad949",
"metadata": {},
"outputs": [],
"source": [
"#variable retenu:[[\"id\",\"name\"]]"
]
},
{
"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": 74,
"id": "eac537e1-bbad-45bc-a85c-12b675da1088",
"metadata": {},
"outputs": [],
"source": [
"#Merge1 entre products et pricing_formulas\n",
"base1=products.merge(pricing_formulas, how='left', left_on= 'pricing_formula_id', right_on= 'id', suffixes = (\"_products\", \"_pricing_formula\"))"
]
},
{
"cell_type": "code",
"execution_count": 78,
"id": "75be3a30-3114-432d-87d6-697533c3c871",
"metadata": {},
"outputs": [],
"source": [
"#Merge2 entre base1 et products_groups\n",
"base2=base1.merge(products_groups, how='left', left_on= 'id_pricing_formula', right_on= 'id', suffixes = (\"_merge2\", \"_product_group\"))"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "34a169c6-07a8-4ac3-a9e1-d7e7461f7310",
"metadata": {},
"outputs": [],
"source": [
"#Merge3 entre base2 et type_of_pricing_formulas\n",
"base3=base2.merge(type_of_pricing_formulas, how='left', left_on= 'id_pricing_formula', right_on= 'pricing_formula_id', suffixes = (\"_merge3\", \"_type_of_pricing_f\"))"
]
},
{
"cell_type": "code",
"execution_count": 89,
"id": "f44f40d2-5304-4931-b7e6-fcc06b2657b6",
"metadata": {},
"outputs": [],
"source": [
"#Merge4 entre base3 et type_of_pricing_formulas\n",
"df_product_pricing=base3.merge(product_packs, how='left', left_on= 'product_pack_id', right_on= 'id', suffixes = (\"_merge4\", \"_product_pack\"))"
]
},
{
"cell_type": "code",
"execution_count": 90,
"id": "a28772c3-7bc1-46b4-acc8-1388dc60ec98",
"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>pricing_formula_id</th>\n",
" <th>created_at_type_of_pricing_f</th>\n",
" <th>updated_at_type_of_pricing_f</th>\n",
" <th>identifier_merge4</th>\n",
" <th>id</th>\n",
" <th>name_product_pack</th>\n",
" <th>type_of</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>identifier_product_pack</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>...</td>\n",
" <td>114.0</td>\n",
" <td>2021-02-15 17:02:27.395376+01:00</td>\n",
" <td>2021-02-15 17:02:27.395376+01:00</td>\n",
" <td>3706121eb9f43b635bef1433c06f679c</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>a764b4bf13a360c7ac2a35ec4ca96c95</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>...</td>\n",
" <td>131.0</td>\n",
" <td>2021-02-05 11:52:05.923905+01:00</td>\n",
" <td>2021-02-05 11:52:05.923905+01:00</td>\n",
" <td>0aceb248607671792298436004b95275</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>a764b4bf13a360c7ac2a35ec4ca96c95</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>...</td>\n",
" <td>137.0</td>\n",
" <td>2021-02-05 11:52:05.939898+01:00</td>\n",
" <td>2021-02-05 11:52:05.939898+01:00</td>\n",
" <td>93002d4637331edd81ffc28b6e8e89c0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>a764b4bf13a360c7ac2a35ec4ca96c95</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>...</td>\n",
" <td>9.0</td>\n",
" <td>2021-02-05 11:52:06.107939+01:00</td>\n",
" <td>2021-02-05 11:52:06.107939+01:00</td>\n",
" <td>7d0b25bdfff9f366da8be820608c8191</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>a764b4bf13a360c7ac2a35ec4ca96c95</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>...</td>\n",
" <td>93.0</td>\n",
" <td>2021-02-05 11:52:06.004162+01:00</td>\n",
" <td>2021-02-05 11:52:06.004162+01:00</td>\n",
" <td>1dbb0795e8f47cb75ba7cdb08c06be5f</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>2020-09-03 13:11:24.501197+02:00</td>\n",
" <td>a764b4bf13a360c7ac2a35ec4ca96c95</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 41 columns</p>\n",
"</div>"
],
"text/plain": [
" id_products amount is_full_price representation_id_merge2 \\\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",
" pricing_formula_id_merge2 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",
" updated_at_products category_id_merge2 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",
" products_group_id ... pricing_formula_id \\\n",
"0 10655 ... 114.0 \n",
"1 471 ... 131.0 \n",
"2 20825 ... 137.0 \n",
"3 156773 ... 9.0 \n",
"4 1175 ... 93.0 \n",
"\n",
" created_at_type_of_pricing_f updated_at_type_of_pricing_f \\\n",
"0 2021-02-15 17:02:27.395376+01:00 2021-02-15 17:02:27.395376+01:00 \n",
"1 2021-02-05 11:52:05.923905+01:00 2021-02-05 11:52:05.923905+01:00 \n",
"2 2021-02-05 11:52:05.939898+01:00 2021-02-05 11:52:05.939898+01:00 \n",
"3 2021-02-05 11:52:06.107939+01:00 2021-02-05 11:52:06.107939+01:00 \n",
"4 2021-02-05 11:52:06.004162+01:00 2021-02-05 11:52:06.004162+01:00 \n",
"\n",
" identifier_merge4 id name_product_pack type_of \\\n",
"0 3706121eb9f43b635bef1433c06f679c 1 NaN 0 \n",
"1 0aceb248607671792298436004b95275 1 NaN 0 \n",
"2 93002d4637331edd81ffc28b6e8e89c0 1 NaN 0 \n",
"3 7d0b25bdfff9f366da8be820608c8191 1 NaN 0 \n",
"4 1dbb0795e8f47cb75ba7cdb08c06be5f 1 NaN 0 \n",
"\n",
" created_at updated_at \\\n",
"0 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n",
"1 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n",
"2 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n",
"3 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n",
"4 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n",
"\n",
" identifier_product_pack \n",
"0 a764b4bf13a360c7ac2a35ec4ca96c95 \n",
"1 a764b4bf13a360c7ac2a35ec4ca96c95 \n",
"2 a764b4bf13a360c7ac2a35ec4ca96c95 \n",
"3 a764b4bf13a360c7ac2a35ec4ca96c95 \n",
"4 a764b4bf13a360c7ac2a35ec4ca96c95 \n",
"\n",
"[5 rows x 41 columns]"
]
},
"execution_count": 90,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_product_pricing.head(5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "03442997-806f-4285-a139-3bad46bb4522",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 5,
"id": "d22a0d75-53c5-4b54-9060-c9e7c307fb13",
"metadata": {},
"outputs": [],
"source": [
"BUCKET = \"bdc2324-data\"\n",
"directory_path = '2'"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7c229dad-6ebd-4f43-99f1-fb330dc29466",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['bdc2324-data/2/2campaign_stats.csv',\n",
" 'bdc2324-data/2/2campaigns.csv',\n",
" 'bdc2324-data/2/2categories.csv',\n",
" 'bdc2324-data/2/2contribution_sites.csv',\n",
" 'bdc2324-data/2/2contributions.csv',\n",
" 'bdc2324-data/2/2countries.csv',\n",
" 'bdc2324-data/2/2currencies.csv',\n",
" 'bdc2324-data/2/2customer_target_mappings.csv',\n",
" 'bdc2324-data/2/2customersplus.csv',\n",
" 'bdc2324-data/2/2event_types.csv',\n",
" 'bdc2324-data/2/2events.csv',\n",
" 'bdc2324-data/2/2facilities.csv',\n",
" 'bdc2324-data/2/2link_stats.csv',\n",
" 'bdc2324-data/2/2pricing_formulas.csv',\n",
" 'bdc2324-data/2/2product_packs.csv',\n",
" 'bdc2324-data/2/2products.csv',\n",
" 'bdc2324-data/2/2products_groups.csv',\n",
" 'bdc2324-data/2/2purchases.csv',\n",
" 'bdc2324-data/2/2representation_category_capacities.csv',\n",
" 'bdc2324-data/2/2representations.csv',\n",
" 'bdc2324-data/2/2seasons.csv',\n",
" 'bdc2324-data/2/2structure_tag_mappings.csv',\n",
" 'bdc2324-data/2/2suppliers.csv',\n",
" 'bdc2324-data/2/2tags.csv',\n",
" 'bdc2324-data/2/2target_types.csv',\n",
" 'bdc2324-data/2/2targets.csv',\n",
" 'bdc2324-data/2/2tickets.csv']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"BUCKET = \"bdc2324-data/2\"\n",
"fs.ls(BUCKET)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "df3d3548-3d76-4f07-afa1-e240932bc1c7",
"metadata": {},
"outputs": [],
"source": [
"dic_base_ent2=['campaign_stats','campaigns','categories','contribution_sites','contributions','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']"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "90f8d5fc-43f3-4f36-b8cc-89a41785f032",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_425/673681459.py:5: DtypeWarning: Columns (20) 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_ent2=['campaign_stats','campaigns','categories','contribution_sites','contributions','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']\n",
"for nom_base in dic_base_ent2:\n",
" FILE_PATH_S3_fanta = 'bdc2324-data/2/2' + 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": 9,
"id": "3e39a584-e02b-41b2-831c-33b920e298e9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"27"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(dic_base_ent2)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "2b6c6f65",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"def calculer_proportion_valeurs_manquantes_et_exporter(databases, fichier_sortie='proportion_valeurs_manquantes.xlsx'):\n",
" \"\"\"\n",
" Calculer la proportion de valeurs manquantes pour chaque variable dans chaque base de données et exporter les résultats dans un fichier Excel.\n",
"\n",
" Paramètres:\n",
" - databases (dict): Un dictionnaire où les clés sont les noms des bases de données et les valeurs sont les DataFrames pandas.\n",
" - fichier_sortie (str): Le chemin du fichier Excel de sortie.\n",
"\n",
" Retourne:\n",
" - Un fichier Excel où chaque onglet représente une base de données différente avec la proportion de valeurs manquantes pour chaque variable.\n",
" \"\"\"\n",
" with pd.ExcelWriter(fichier_sortie) as writer:\n",
" for nom_db, df in databases.items():\n",
" # Calculer la proportion de valeurs manquantes pour chaque colonne\n",
" proportion_manquantes = df.isnull().mean()\n",
" # Convertir en DataFrame pour un meilleur affichage\n",
" resultats_df = pd.DataFrame(proportion_manquantes, columns=['ProportionValeursManquantes'])\n",
" resultats_df['ProportionValeursManquantes'] = resultats_df['ProportionValeursManquantes'].map(lambda x: f\"{x:.2%}\")\n",
" # Écrire le DataFrame dans un onglet du fichier Excel\n",
" resultats_df.to_excel(writer, sheet_name=nom_db)\n",
"\n",
" print(f\"Les résultats ont été exportés dans le fichier '{fichier_sortie}'.\")\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "06759646-9419-4841-b12f-bbfceb417f3a",
"metadata": {},
"outputs": [],
"source": [
"#fonction calcul la proportion de valeur manquante\n",
"\n",
"import pandas as pd\n",
"\n",
"def calculer_proportion_valeurs_manquantes(databases):\n",
" \"\"\"\n",
" Calculer la proportion de valeurs manquantes pour chaque variable dans chaque base de données.\n",
"\n",
" Paramètres:\n",
" - databases (dict): Un dictionnaire où les clés sont les noms des bases de données et les valeurs sont les DataFrames pandas.\n",
"\n",
" Retourne:\n",
" - Un dictionnaire où les clés sont les noms des bases de données et les valeurs sont des DataFrames avec la proportion de valeurs manquantes pour chaque variable.\n",
" \"\"\"\n",
" resultats = {}\n",
" for nom_db, df in databases.items():\n",
" # Calculer la proportion de valeurs manquantes pour chaque colonne\n",
" proportion_manquantes = df.isnull().mean()\n",
" # Convertir en DataFrame pour un meilleur affichage\n",
" resultats_df = pd.DataFrame(proportion_manquantes, columns=['ProportionValeursManquantes'])\n",
" resultats_df['ProportionValeursManquantes'] = resultats_df['ProportionValeursManquantes'].map(lambda x: f\"{x:.2%}\")\n",
" # Ajouter le résultat au dictionnaire\n",
" resultats[nom_db] = resultats_df\n",
" return resultats"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "0960daa8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Base de données: Base1\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"campaign_id 0.00%\n",
"customer_id 0.00%\n",
"opened_at 68.67%\n",
"sent_at 0.00%\n",
"delivered_at 1.61%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: Base2\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"service_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"process_id 100.00%\n",
"report_url 100.00%\n",
"category 0.00%\n",
"to_be_synced 0.00%\n",
"identifier 0.00%\n",
"sent_at 0.00%\n",
"\n"
]
}
],
"source": [
"# Exemple d'utilisation\n",
"\n",
"databases = {'Base1': campaign_stats, 'Base2': campaigns}\n",
"\n",
"resultats = calculer_proportion_valeurs_manquantes(databases)\n",
"\n",
"for nom_db, resultat in resultats.items():\n",
" print(f\"Base de données: {nom_db}\")\n",
" print(resultat)\n",
" print()\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "77dc02bb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Base de données: campaign_stats\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"campaign_id 0.00%\n",
"customer_id 0.00%\n",
"opened_at 68.67%\n",
"sent_at 0.00%\n",
"delivered_at 1.61%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: campaigns\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"service_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"process_id 100.00%\n",
"report_url 100.00%\n",
"category 0.00%\n",
"to_be_synced 0.00%\n",
"identifier 0.00%\n",
"sent_at 0.00%\n",
"\n",
"Base de données: categories\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 100.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"extra_field 100.00%\n",
"quota 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: contribution_sites\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"identifier 0.00%\n",
"facility_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: contributions\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"sent_at 0.00%\n",
"software 100.00%\n",
"satisfaction 39.65%\n",
"extra_field 100.00%\n",
"customer_id 0.00%\n",
"contribution_site_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: countries\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 1.63%\n",
"code 0.41%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: currencies\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: customer_target_mappings\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"customer_id 0.00%\n",
"target_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"name 100.00%\n",
"extra_field 100.00%\n",
"\n",
"Base de données: customersplus\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"lastname 0.02%\n",
"firstname 0.01%\n",
"birthdate 96.75%\n",
"email 1.05%\n",
"street_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"civility 100.00%\n",
"is_partner 0.00%\n",
"extra 100.00%\n",
"deleted_at 100.00%\n",
"reference 100.00%\n",
"gender 0.00%\n",
"is_email_true 0.00%\n",
"extra_field 100.00%\n",
"identifier 0.00%\n",
"opt_in 0.00%\n",
"structure_id 97.57%\n",
"note 97.84%\n",
"profession 100.00%\n",
"language 46.16%\n",
"mcp_contact_id 100.00%\n",
"need_reload 0.00%\n",
"last_buying_date 12.58%\n",
"max_price 12.58%\n",
"ticket_sum 0.00%\n",
"average_price 12.58%\n",
"fidelity 0.00%\n",
"average_purchase_delay 12.58%\n",
"average_price_basket 12.58%\n",
"average_ticket_basket 12.58%\n",
"total_price 0.00%\n",
"preferred_category 100.00%\n",
"preferred_supplier 100.00%\n",
"preferred_formula 100.00%\n",
"purchase_count 0.00%\n",
"first_buying_date 12.58%\n",
"last_visiting_date 100.00%\n",
"zipcode 98.80%\n",
"country 97.64%\n",
"age 96.75%\n",
"tenant_id 0.00%\n",
"\n",
"Base de données: event_types\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"fidelity_delay 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: events\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"season_id 0.00%\n",
"facility_id 0.00%\n",
"name 0.00%\n",
"event_type_id 0.00%\n",
"manual_added 0.00%\n",
"is_display 0.00%\n",
"event_type_key_id 0.00%\n",
"facility_key_id 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: facilities\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 50.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"street_id 0.00%\n",
"fixed_capacity 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: link_stats\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"clicked_at 0.00%\n",
"link_id 0.00%\n",
"customer_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: pricing_formulas\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"extra_field 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: product_packs\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 100.00%\n",
"type_of 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: products\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"amount 0.00%\n",
"is_full_price 0.00%\n",
"representation_id 0.00%\n",
"pricing_formula_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"category_id 0.00%\n",
"apply_price 0.00%\n",
"products_group_id 0.00%\n",
"product_pack_id 0.00%\n",
"extra_field 100.00%\n",
"amount_consumption 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: products_groups\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"percent_price 0.00%\n",
"max_price 0.00%\n",
"min_price 0.00%\n",
"category_id 0.00%\n",
"pricing_formula_id 0.00%\n",
"representation_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: purchases\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"purchase_date 0.00%\n",
"customer_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"number 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: representation_category_capacities\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"representation_id 0.00%\n",
"category_id 0.00%\n",
"expected_filling 100.00%\n",
"max_filling 100.00%\n",
"\n",
"Base de données: representations\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"serial 100.00%\n",
"event_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"start_date_time 0.00%\n",
"open 0.00%\n",
"satisfaction 100.00%\n",
"end_date_time 0.00%\n",
"name 100.00%\n",
"is_display 0.00%\n",
"representation_type_id 100.00%\n",
"expected_filling 100.00%\n",
"max_filling 100.00%\n",
"extra_field 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: seasons\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"start_date_time 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: structure_tag_mappings\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"structure_id 0.00%\n",
"tag_id 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: suppliers\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 20.00%\n",
"manually_added 0.00%\n",
"label 100.00%\n",
"itr 100.00%\n",
"updated_at 0.00%\n",
"created_at 0.00%\n",
"commission 100.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: tags\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"name 50.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: target_types\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"is_import 25.00%\n",
"name 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"identifier 0.00%\n",
"\n",
"Base de données: targets\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"target_type_id 0.00%\n",
"name 5.26%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"\n",
"Base de données: tickets\n",
" ProportionValeursManquantes\n",
"id 0.00%\n",
"number 0.00%\n",
"created_at 0.00%\n",
"updated_at 0.00%\n",
"purchase_id 0.00%\n",
"product_id 0.00%\n",
"is_from_subscription 0.00%\n",
"type_of 0.00%\n",
"supplier_id 0.00%\n",
"barcode 100.00%\n",
"identifier 0.00%\n",
"\n"
]
}
],
"source": [
"# Exemple d'utilisation\n",
"dict={'campaign_stats': campaign_stats,\n",
" 'campaigns': campaigns,\n",
" 'categories': categories,\n",
" 'contribution_sites': contribution_sites,\n",
" 'contributions': contributions,\n",
" 'countries': countries,\n",
" 'currencies': currencies,\n",
" 'customer_target_mappings': customer_target_mappings,\n",
" 'customersplus': customersplus,\n",
" 'event_types': event_types,\n",
" 'events': events,\n",
" 'facilities': facilities,\n",
" 'link_stats': link_stats,\n",
" 'pricing_formulas': pricing_formulas,\n",
" 'product_packs': product_packs,\n",
" 'products': products,\n",
" 'products_groups': products_groups,\n",
" 'purchases': purchases,\n",
" 'representation_category_capacities': representation_category_capacities,\n",
" 'representations': representations,\n",
" 'seasons': seasons,\n",
" 'structure_tag_mappings': structure_tag_mappings,\n",
" 'suppliers': suppliers,\n",
" 'tags': tags,\n",
" 'target_types': target_types,\n",
" 'targets': targets,\n",
" 'tickets': tickets}\n",
"\n",
"resultats = calculer_proportion_valeurs_manquantes(dict)\n",
"\n",
"for nom_db, resultat in resultats.items():\n",
" print(f\"Base de données: {nom_db}\")\n",
" print(resultat)\n",
" print()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "60be9271",
"metadata": {},
"outputs": [],
"source": [
"#MEME CODE mais avec l'exportation de result a en format excel"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "955fe358",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"def calculer_proportion_valeurs_manquantes_et_exporter(databases, fichier_sortie='proportion_valeurs_manquantes.xlsx'):\n",
" \"\"\"\n",
" Calculer la proportion de valeurs manquantes pour chaque variable dans chaque base de données et exporter les résultats dans un fichier Excel.\n",
"\n",
" Paramètres:\n",
" - databases (dict): Un dictionnaire où les clés sont les noms des bases de données et les valeurs sont les DataFrames pandas.\n",
" - fichier_sortie (str): Le chemin du fichier Excel de sortie.\n",
"\n",
" Retourne:\n",
" - Un fichier Excel où chaque onglet représente une base de données différente avec la proportion de valeurs manquantes pour chaque variable.\n",
" \"\"\"\n",
" with pd.ExcelWriter(fichier_sortie) as writer:\n",
" for nom_db, df in databases.items():\n",
" # Calculer la proportion de valeurs manquantes pour chaque colonne\n",
" proportion_manquantes = df.isnull().mean()\n",
" # Convertir en DataFrame pour un meilleur affichage\n",
" resultats_df = pd.DataFrame(proportion_manquantes, columns=['ProportionValeursManquantes'])\n",
" resultats_df['ProportionValeursManquantes'] = resultats_df['ProportionValeursManquantes'].map(lambda x: f\"{x:.2%}\")\n",
" # Écrire le DataFrame dans un onglet du fichier Excel\n",
" resultats_df.to_excel(writer, sheet_name=nom_db)\n",
"\n",
" print(f\"Les résultats ont été exportés dans le fichier '{fichier_sortie}'.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7897b689",
"metadata": {},
"outputs": [],
"source": [
"# Exemple d'utilisation\n",
"dict={'campaign_stats': campaign_stats,\n",
" 'campaigns': campaigns,\n",
" 'categories': categories,\n",
" 'contribution_sites': contribution_sites,\n",
" 'contributions': contributions,\n",
" 'countries': countries,\n",
" 'currencies': currencies,\n",
" 'customer_target_mappings': customer_target_mappings,\n",
" 'customersplus': customersplus,\n",
" 'event_types': event_types,\n",
" 'events': events,\n",
" 'facilities': facilities,\n",
" 'link_stats': link_stats,\n",
" 'pricing_formulas': pricing_formulas,\n",
" 'product_packs': product_packs,\n",
" 'products': products,\n",
" 'products_groups': products_groups,\n",
" 'purchases': purchases,\n",
" 'representation_category_capacities': representation_category_capacities,\n",
" 'representations': representations,\n",
" 'seasons': seasons,\n",
" 'structure_tag_mappings': structure_tag_mappings,\n",
" 'suppliers': suppliers,\n",
" 'tags': tags,\n",
" 'target_types': target_types,\n",
" 'targets': targets,\n",
" 'tickets': tickets}\n",
"\n",
"calculer_proportion_valeurs_manquantes_et_exporter(dict, 'proportion_valeurs_manquantes_ent1.xlsx')\n"
]
},
{
"cell_type": "markdown",
"id": "514273f4",
"metadata": {},
"source": [
"## Entreprise 3"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "69b8f59a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['bdc2324-data/3/3campaign_stats.csv',\n",
" 'bdc2324-data/3/3campaigns.csv',\n",
" 'bdc2324-data/3/3categories.csv',\n",
" 'bdc2324-data/3/3consumptions.csv',\n",
" 'bdc2324-data/3/3contribution_sites.csv',\n",
" 'bdc2324-data/3/3contributions.csv',\n",
" 'bdc2324-data/3/3countries.csv',\n",
" 'bdc2324-data/3/3currencies.csv',\n",
" 'bdc2324-data/3/3customer_target_mappings.csv',\n",
" 'bdc2324-data/3/3customersplus.csv',\n",
" 'bdc2324-data/3/3event_types.csv',\n",
" 'bdc2324-data/3/3events.csv',\n",
" 'bdc2324-data/3/3facilities.csv',\n",
" 'bdc2324-data/3/3link_stats.csv',\n",
" 'bdc2324-data/3/3pricing_formulas.csv',\n",
" 'bdc2324-data/3/3product_packs.csv',\n",
" 'bdc2324-data/3/3products.csv',\n",
" 'bdc2324-data/3/3products_groups.csv',\n",
" 'bdc2324-data/3/3purchases.csv',\n",
" 'bdc2324-data/3/3representation_category_capacities.csv',\n",
" 'bdc2324-data/3/3representations.csv',\n",
" 'bdc2324-data/3/3seasons.csv',\n",
" 'bdc2324-data/3/3structure_tag_mappings.csv',\n",
" 'bdc2324-data/3/3suppliers.csv',\n",
" 'bdc2324-data/3/3tags.csv',\n",
" 'bdc2324-data/3/3target_types.csv',\n",
" 'bdc2324-data/3/3targets.csv',\n",
" 'bdc2324-data/3/3tickets.csv']"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"BUCKET = \"bdc2324-data/3\"\n",
"fs.ls(BUCKET)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8a842d0b-f341-4752-b624-3a339ef0fe1e",
"metadata": {},
"outputs": [],
"source": [
"# Chargement des données temporaires\n",
"BUCKET = \"projet-bdc2324-team1\"\n",
"FILE_KEY_S3 = \"0_Temp/Company 1 - Purchasing behaviour.csv\"\n",
"FILE_PATH_S3 = BUCKET + \"/\" + FILE_KEY_S3\n",
"\n",
"with fs.open(FILE_PATH_S3, mode=\"rb\") as file_in:\n",
" tickets_kpi = pd.read_csv(file_in, sep=\",\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "9b4c005f",
"metadata": {},
"outputs": [],
"source": [
"dic_base_ent3=['campaign_stats','campaigns','categories','consumptions','contribution_sites','contributions','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']"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "aae542d6",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_425/4241072101.py:5: DtypeWarning: Columns (19,20) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" globals()[nom_base] = pd.read_csv(file_in, sep=\",\")\n",
"/tmp/ipykernel_425/4241072101.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_ent3=['campaign_stats','campaigns','categories','consumptions','contribution_sites','contributions','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']\n",
"for nom_base in dic_base_ent2:\n",
" FILE_PATH_S3_fanta = 'bdc2324-data/3/3' + 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": 21,
"id": "907c650c-df7e-4e5c-b3cb-6595be061e99",
"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>fidelity_delay</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>60873</td>\n",
" <td>journees des plantes</td>\n",
" <td>2022-09-13 17:42:18.040557+02:00</td>\n",
" <td>2022-09-13 17:42:18.040557+02:00</td>\n",
" <td>36</td>\n",
" <td>58568a64f69dd864539e7a682b03ef3a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>60876</td>\n",
" <td>parking</td>\n",
" <td>2022-09-13 17:42:18.043821+02:00</td>\n",
" <td>2022-09-13 17:42:18.043821+02:00</td>\n",
" <td>36</td>\n",
" <td>3ac156eead4ae6b40e9c498d532b4448</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>60997</td>\n",
" <td>pass arc</td>\n",
" <td>2022-09-13 18:04:38.812389+02:00</td>\n",
" <td>2022-09-13 18:04:38.812389+02:00</td>\n",
" <td>36</td>\n",
" <td>ddffce8b0a072d76a766097b34208482</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>61233</td>\n",
" <td>paris pass museum</td>\n",
" <td>2022-09-13 18:53:15.878739+02:00</td>\n",
" <td>2022-09-13 18:53:15.878739+02:00</td>\n",
" <td>36</td>\n",
" <td>394a376e43e498dccf8a448004f2aa84</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>60911</td>\n",
" <td>spectacle noel</td>\n",
" <td>2022-09-13 17:48:50.549760+02:00</td>\n",
" <td>2022-09-13 17:48:50.549760+02:00</td>\n",
" <td>36</td>\n",
" <td>a2b0f7c330d4c8d0338e6edf5ce4c81a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>61007</td>\n",
" <td>domaine + spect noel</td>\n",
" <td>2022-09-13 18:07:25.121513+02:00</td>\n",
" <td>2022-09-13 18:07:25.121513+02:00</td>\n",
" <td>36</td>\n",
" <td>c65e9028b505dcfa71acef4e15f6e7be</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>62374</td>\n",
" <td>patrivia</td>\n",
" <td>2022-09-14 02:08:56.789118+02:00</td>\n",
" <td>2022-09-14 02:08:56.789118+02:00</td>\n",
" <td>36</td>\n",
" <td>8db1f5c8774a8cf07542249278d7d778</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>72615</td>\n",
" <td>NaN</td>\n",
" <td>2023-08-14 06:20:26.491399+02:00</td>\n",
" <td>2023-08-14 06:20:26.491399+02:00</td>\n",
" <td>36</td>\n",
" <td>d41d8cd98f00b204e9800998ecf8427e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>61011</td>\n",
" <td>prestation annexe</td>\n",
" <td>2022-09-13 18:07:25.126517+02:00</td>\n",
" <td>2022-09-13 18:07:25.126517+02:00</td>\n",
" <td>36</td>\n",
" <td>2588ceebb05d3329f334687b8647887e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>60877</td>\n",
" <td>minibus</td>\n",
" <td>2022-09-13 17:42:18.045141+02:00</td>\n",
" <td>2022-09-13 17:42:18.045141+02:00</td>\n",
" <td>36</td>\n",
" <td>397361c9c0dc82d911aa931223bd7a4e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>61708</td>\n",
" <td>location espace</td>\n",
" <td>2022-09-13 21:52:57.785694+02:00</td>\n",
" <td>2022-09-13 21:52:57.785694+02:00</td>\n",
" <td>36</td>\n",
" <td>3738beebf604a960e016ffad6db1df74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>60931</td>\n",
" <td>exposition</td>\n",
" <td>2022-09-13 17:52:36.164774+02:00</td>\n",
" <td>2022-09-13 17:52:36.164774+02:00</td>\n",
" <td>36</td>\n",
" <td>69033f19d53294c467d0fb7d3a4ad868</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>60871</td>\n",
" <td>domaine</td>\n",
" <td>2022-09-13 17:42:18.037831+02:00</td>\n",
" <td>2022-09-13 17:42:18.037831+02:00</td>\n",
" <td>36</td>\n",
" <td>b81285860b791e63dee94559f0a9e8e4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>60878</td>\n",
" <td>visite guidee</td>\n",
" <td>2022-09-13 17:42:18.046593+02:00</td>\n",
" <td>2022-09-13 17:42:18.046593+02:00</td>\n",
" <td>36</td>\n",
" <td>3474ed518d4fa7b86719680e70039ac2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>60875</td>\n",
" <td>parc</td>\n",
" <td>2022-09-13 17:42:18.042824+02:00</td>\n",
" <td>2022-09-13 17:42:18.042824+02:00</td>\n",
" <td>36</td>\n",
" <td>41c16554f8160b3bd2a6b3809f309e27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>60870</td>\n",
" <td>spectacle saison</td>\n",
" <td>2022-09-13 17:42:18.028836+02:00</td>\n",
" <td>2022-09-13 17:42:18.028836+02:00</td>\n",
" <td>36</td>\n",
" <td>7afdec36b66f94b67e813ac7d092ea0c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>60872</td>\n",
" <td>domaine + spect saison</td>\n",
" <td>2022-09-13 17:42:18.039515+02:00</td>\n",
" <td>2022-09-13 17:42:18.039515+02:00</td>\n",
" <td>36</td>\n",
" <td>ccd5dffaa070e9c7885ff3e9149f12f0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>60874</td>\n",
" <td>supplement spectacle</td>\n",
" <td>2022-09-13 17:42:18.041862+02:00</td>\n",
" <td>2022-09-13 17:42:18.041862+02:00</td>\n",
" <td>36</td>\n",
" <td>093d3e6b14b1ad33908a18522d02886b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>61203</td>\n",
" <td>pique nique en blanc</td>\n",
" <td>2022-09-13 18:44:16.813045+02:00</td>\n",
" <td>2022-09-13 18:44:16.813045+02:00</td>\n",
" <td>36</td>\n",
" <td>ff9a87979d4a564a1d2a1055a1aa186e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>61427</td>\n",
" <td>restauration</td>\n",
" <td>2022-09-13 19:26:41.906836+02:00</td>\n",
" <td>2022-09-13 19:26:41.906836+02:00</td>\n",
" <td>36</td>\n",
" <td>f1bcd494fa3171bf042e62c311157547</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>60879</td>\n",
" <td>animation culturelle</td>\n",
" <td>2022-09-13 17:42:18.047567+02:00</td>\n",
" <td>2022-09-13 17:42:18.047567+02:00</td>\n",
" <td>36</td>\n",
" <td>27b0b018dfa7301abffcb243a876e4c4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>61270</td>\n",
" <td>ecurie</td>\n",
" <td>2022-09-13 18:57:52.734356+02:00</td>\n",
" <td>2022-09-13 18:57:52.734356+02:00</td>\n",
" <td>36</td>\n",
" <td>a21e22a0d924104179b25069de927909</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>60929</td>\n",
" <td>domaine + spect ete</td>\n",
" <td>2022-09-13 17:52:36.162726+02:00</td>\n",
" <td>2022-09-13 17:52:36.162726+02:00</td>\n",
" <td>36</td>\n",
" <td>8bdc1d1d5fba2317af8c4d733d8206d7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>60910</td>\n",
" <td>spectacle ete</td>\n",
" <td>2022-09-13 17:48:50.548826+02:00</td>\n",
" <td>2022-09-13 17:48:50.548826+02:00</td>\n",
" <td>36</td>\n",
" <td>44878d1fd6c7fe384274861294c59017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 60873 journees des plantes 2022-09-13 17:42:18.040557+02:00 \n",
"1 60876 parking 2022-09-13 17:42:18.043821+02:00 \n",
"2 60997 pass arc 2022-09-13 18:04:38.812389+02:00 \n",
"3 61233 paris pass museum 2022-09-13 18:53:15.878739+02:00 \n",
"4 60911 spectacle noel 2022-09-13 17:48:50.549760+02:00 \n",
"5 61007 domaine + spect noel 2022-09-13 18:07:25.121513+02:00 \n",
"6 62374 patrivia 2022-09-14 02:08:56.789118+02:00 \n",
"7 72615 NaN 2023-08-14 06:20:26.491399+02:00 \n",
"8 61011 prestation annexe 2022-09-13 18:07:25.126517+02:00 \n",
"9 60877 minibus 2022-09-13 17:42:18.045141+02:00 \n",
"10 61708 location espace 2022-09-13 21:52:57.785694+02:00 \n",
"11 60931 exposition 2022-09-13 17:52:36.164774+02:00 \n",
"12 60871 domaine 2022-09-13 17:42:18.037831+02:00 \n",
"13 60878 visite guidee 2022-09-13 17:42:18.046593+02:00 \n",
"14 60875 parc 2022-09-13 17:42:18.042824+02:00 \n",
"15 60870 spectacle saison 2022-09-13 17:42:18.028836+02:00 \n",
"16 60872 domaine + spect saison 2022-09-13 17:42:18.039515+02:00 \n",
"17 60874 supplement spectacle 2022-09-13 17:42:18.041862+02:00 \n",
"18 61203 pique nique en blanc 2022-09-13 18:44:16.813045+02:00 \n",
"19 61427 restauration 2022-09-13 19:26:41.906836+02:00 \n",
"20 60879 animation culturelle 2022-09-13 17:42:18.047567+02:00 \n",
"21 61270 ecurie 2022-09-13 18:57:52.734356+02:00 \n",
"22 60929 domaine + spect ete 2022-09-13 17:52:36.162726+02:00 \n",
"23 60910 spectacle ete 2022-09-13 17:48:50.548826+02:00 \n",
"\n",
" updated_at fidelity_delay \\\n",
"0 2022-09-13 17:42:18.040557+02:00 36 \n",
"1 2022-09-13 17:42:18.043821+02:00 36 \n",
"2 2022-09-13 18:04:38.812389+02:00 36 \n",
"3 2022-09-13 18:53:15.878739+02:00 36 \n",
"4 2022-09-13 17:48:50.549760+02:00 36 \n",
"5 2022-09-13 18:07:25.121513+02:00 36 \n",
"6 2022-09-14 02:08:56.789118+02:00 36 \n",
"7 2023-08-14 06:20:26.491399+02:00 36 \n",
"8 2022-09-13 18:07:25.126517+02:00 36 \n",
"9 2022-09-13 17:42:18.045141+02:00 36 \n",
"10 2022-09-13 21:52:57.785694+02:00 36 \n",
"11 2022-09-13 17:52:36.164774+02:00 36 \n",
"12 2022-09-13 17:42:18.037831+02:00 36 \n",
"13 2022-09-13 17:42:18.046593+02:00 36 \n",
"14 2022-09-13 17:42:18.042824+02:00 36 \n",
"15 2022-09-13 17:42:18.028836+02:00 36 \n",
"16 2022-09-13 17:42:18.039515+02:00 36 \n",
"17 2022-09-13 17:42:18.041862+02:00 36 \n",
"18 2022-09-13 18:44:16.813045+02:00 36 \n",
"19 2022-09-13 19:26:41.906836+02:00 36 \n",
"20 2022-09-13 17:42:18.047567+02:00 36 \n",
"21 2022-09-13 18:57:52.734356+02:00 36 \n",
"22 2022-09-13 17:52:36.162726+02:00 36 \n",
"23 2022-09-13 17:48:50.548826+02:00 36 \n",
"\n",
" identifier \n",
"0 58568a64f69dd864539e7a682b03ef3a \n",
"1 3ac156eead4ae6b40e9c498d532b4448 \n",
"2 ddffce8b0a072d76a766097b34208482 \n",
"3 394a376e43e498dccf8a448004f2aa84 \n",
"4 a2b0f7c330d4c8d0338e6edf5ce4c81a \n",
"5 c65e9028b505dcfa71acef4e15f6e7be \n",
"6 8db1f5c8774a8cf07542249278d7d778 \n",
"7 d41d8cd98f00b204e9800998ecf8427e \n",
"8 2588ceebb05d3329f334687b8647887e \n",
"9 397361c9c0dc82d911aa931223bd7a4e \n",
"10 3738beebf604a960e016ffad6db1df74 \n",
"11 69033f19d53294c467d0fb7d3a4ad868 \n",
"12 b81285860b791e63dee94559f0a9e8e4 \n",
"13 3474ed518d4fa7b86719680e70039ac2 \n",
"14 41c16554f8160b3bd2a6b3809f309e27 \n",
"15 7afdec36b66f94b67e813ac7d092ea0c \n",
"16 ccd5dffaa070e9c7885ff3e9149f12f0 \n",
"17 093d3e6b14b1ad33908a18522d02886b \n",
"18 ff9a87979d4a564a1d2a1055a1aa186e \n",
"19 f1bcd494fa3171bf042e62c311157547 \n",
"20 27b0b018dfa7301abffcb243a876e4c4 \n",
"21 a21e22a0d924104179b25069de927909 \n",
"22 8bdc1d1d5fba2317af8c4d733d8206d7 \n",
"23 44878d1fd6c7fe384274861294c59017 "
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"event_types"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "617f6e54-c2a4-4627-9b94-9644a4dace71",
"metadata": {},
"outputs": [],
"source": [
"entreprise_base=['bdc2324-data/1', 'bdc2324-data/2', 'bdc2324-data/3', 'bdc2324-data/4', 'bdc2324-data/5', 'bdc2324-data/6', 'bdc2324-data/7', 'bdc2324-data/8','bdc2324-data/9','bdc2324-data/10','bdc2324-data/11','bdc2324-data/12','bdc2324-data/13','bdc2324-data/14','bdc2324-data/101']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b4ce5f9e-7358-4c09-871b-45989f142e25",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "7a0b081c-e0ad-49a8-af25-78b2dc3cdcb8",
"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": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink