ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
events_theme
BDC-team-1/Notebook_AR.ipynb
arevelle-ensae 715fccc5af run k-means
2024-02-12 10:49:33 +00:00

8899 lines
351 KiB
Plaintext
Raw Permalink 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": "455cc769-1b3b-4fef-b395-e74a988ceed3",
"metadata": {},
"source": [
"## Notebook Alexis"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "20eeb149-6618-4ef2-9cfd-ff062950f36c",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os\n",
"import s3fs"
]
},
{
"cell_type": "code",
"execution_count": 275,
"id": "30494c5e-9649-4fff-8708-617544188b20",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['bdc2324-data/1',\n",
" 'bdc2324-data/10',\n",
" 'bdc2324-data/101',\n",
" 'bdc2324-data/11',\n",
" 'bdc2324-data/12',\n",
" 'bdc2324-data/13',\n",
" 'bdc2324-data/14',\n",
" 'bdc2324-data/2',\n",
" 'bdc2324-data/3',\n",
" 'bdc2324-data/4',\n",
" 'bdc2324-data/5',\n",
" 'bdc2324-data/6',\n",
" 'bdc2324-data/7',\n",
" 'bdc2324-data/8',\n",
" 'bdc2324-data/9']"
]
},
"execution_count": 275,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 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\"\n",
"fs.ls(BUCKET)"
]
},
{
"cell_type": "markdown",
"id": "2feffee9-9f23-4caa-8a01-9e4a93abbf5d",
"metadata": {},
"source": [
"### I. Analyse fichier 8"
]
},
{
"cell_type": "markdown",
"id": "f54ba449-2051-4acd-939d-d30abd5452fe",
"metadata": {},
"source": [
"This section describes the databases associated with company 8. "
]
},
{
"cell_type": "code",
"execution_count": 276,
"id": "f1cce705-46e1-42de-8e93-2ee15312d288",
"metadata": {},
"outputs": [],
"source": [
"directory_path = '8'"
]
},
{
"cell_type": "code",
"execution_count": 277,
"id": "82d4db0e-0cd5-49af-a4d3-f17f54b1c03c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8campaign_stats.csv\n",
"bdc2324-data/8/8campaigns.csv\n",
"bdc2324-data/8/8categories.csv\n",
"bdc2324-data/8/8countries.csv\n",
"bdc2324-data/8/8currencies.csv\n",
"bdc2324-data/8/8customer_target_mappings.csv\n",
"bdc2324-data/8/8customersplus.csv\n",
"bdc2324-data/8/8event_types.csv\n",
"bdc2324-data/8/8events.csv\n",
"bdc2324-data/8/8facilities.csv\n",
"bdc2324-data/8/8link_stats.csv\n",
"bdc2324-data/8/8pricing_formulas.csv\n",
"bdc2324-data/8/8product_packs.csv\n",
"bdc2324-data/8/8products.csv\n",
"bdc2324-data/8/8products_groups.csv\n",
"bdc2324-data/8/8purchases.csv\n",
"bdc2324-data/8/8representation_category_capacities.csv\n",
"bdc2324-data/8/8representations.csv\n",
"bdc2324-data/8/8seasons.csv\n",
"bdc2324-data/8/8suppliers.csv\n",
"bdc2324-data/8/8target_types.csv\n",
"bdc2324-data/8/8targets.csv\n",
"bdc2324-data/8/8tickets.csv\n",
"bdc2324-data/8/8type_of_categories.csv\n",
"bdc2324-data/8/8type_of_pricing_formulas.csv\n",
"bdc2324-data/8/8type_ofs.csv\n"
]
}
],
"source": [
"# check the files in the directory\n",
"\n",
"objects = fs.ls(f'{BUCKET}/{directory_path}')\n",
"\n",
"for file in objects:\n",
" print(file)"
]
},
{
"cell_type": "code",
"execution_count": 278,
"id": "65cb38ad-52ae-4266-85d8-c47d81b00283",
"metadata": {},
"outputs": [],
"source": [
"def display_databases(file_name):\n",
" \"\"\"\n",
" This function returns the file from s3 storage\n",
" \"\"\"\n",
" file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
" print(\"File path : \", file_path)\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" df = pd.read_csv(file_in, sep=\",\")\n",
" \n",
" print(\"Shape : \", df.shape)\n",
" return df\n",
" "
]
},
{
"cell_type": "markdown",
"id": "ddd545ef-7e9f-4696-962a-115294991641",
"metadata": {},
"source": [
"#### Lookt at campaigns files"
]
},
{
"cell_type": "code",
"execution_count": 279,
"id": "0214d30d-5f83-498f-867f-e67b5793b731",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8campaigns.csv\n",
"Shape : (1689, 11)\n"
]
},
{
"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>service_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>process_id</th>\n",
" <th>report_url</th>\n",
" <th>category</th>\n",
" <th>to_be_synced</th>\n",
" <th>identifier</th>\n",
" <th>sent_at</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>#LOUSFP RELANCE P'TITS LOU</td>\n",
" <td>1436</td>\n",
" <td>2022-02-01 15:22:53.564432+01:00</td>\n",
" <td>2022-02-01 15:22:53.564432+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>eaa32c96f620053cf442ad32258076b9</td>\n",
" <td>2022-01-31 00:00:00+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>#LOUSFP BRASSERIE ACHETEURS</td>\n",
" <td>1435</td>\n",
" <td>2022-02-01 15:22:53.572592+01:00</td>\n",
" <td>2022-02-01 15:22:53.572592+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>1f3202d820180a39f736f20fce790de8</td>\n",
" <td>2022-01-31 00:00:00+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>PRESSE. LOU/SF Paris - RDV et protocole</td>\n",
" <td>1433</td>\n",
" <td>2022-02-01 15:22:53.578426+01:00</td>\n",
" <td>2022-02-01 15:22:53.578426+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>b069b3415151fa7217e870017374de7c</td>\n",
" <td>2022-01-31 00:00:00+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>#LOUSFP ÉTUDIANTS</td>\n",
" <td>1432</td>\n",
" <td>2022-02-01 15:22:53.584235+01:00</td>\n",
" <td>2022-02-01 15:22:53.584235+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>56468d5607a5aaf1604ff5e15593b003</td>\n",
" <td>2022-01-27 00:00:00+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>#LOUSFP P'TITS LOU</td>\n",
" <td>1431</td>\n",
" <td>2022-02-01 15:22:53.590187+01:00</td>\n",
" <td>2022-02-01 15:22:53.590187+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>e11943a6031a0e6114ae69c257617980</td>\n",
" <td>2022-01-27 00:00:00+01:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name service_id \\\n",
"0 1 #LOUSFP RELANCE P'TITS LOU 1436 \n",
"1 2 #LOUSFP BRASSERIE ACHETEURS 1435 \n",
"2 3 PRESSE. LOU/SF Paris - RDV et protocole 1433 \n",
"3 4 #LOUSFP ÉTUDIANTS 1432 \n",
"4 5 #LOUSFP P'TITS LOU 1431 \n",
"\n",
" created_at updated_at \\\n",
"0 2022-02-01 15:22:53.564432+01:00 2022-02-01 15:22:53.564432+01:00 \n",
"1 2022-02-01 15:22:53.572592+01:00 2022-02-01 15:22:53.572592+01:00 \n",
"2 2022-02-01 15:22:53.578426+01:00 2022-02-01 15:22:53.578426+01:00 \n",
"3 2022-02-01 15:22:53.584235+01:00 2022-02-01 15:22:53.584235+01:00 \n",
"4 2022-02-01 15:22:53.590187+01:00 2022-02-01 15:22:53.590187+01:00 \n",
"\n",
" process_id report_url category to_be_synced \\\n",
"0 NaN NaN 0 False \n",
"1 NaN NaN 0 False \n",
"2 NaN NaN 0 False \n",
"3 NaN NaN 0 False \n",
"4 NaN NaN 0 False \n",
"\n",
" identifier sent_at \n",
"0 eaa32c96f620053cf442ad32258076b9 2022-01-31 00:00:00+01:00 \n",
"1 1f3202d820180a39f736f20fce790de8 2022-01-31 00:00:00+01:00 \n",
"2 b069b3415151fa7217e870017374de7c 2022-01-31 00:00:00+01:00 \n",
"3 56468d5607a5aaf1604ff5e15593b003 2022-01-27 00:00:00+01:00 \n",
"4 e11943a6031a0e6114ae69c257617980 2022-01-27 00:00:00+01:00 "
]
},
"execution_count": 279,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"campaigns = display_databases(\"8campaigns.csv\")\n",
"campaigns.head()"
]
},
{
"cell_type": "code",
"execution_count": 280,
"id": "e7982be4-2c42-4a91-be5a-329a999644cc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8campaign_stats.csv\n",
"Shape : (2527083, 8)\n"
]
},
{
"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>campaign_id</th>\n",
" <th>customer_id</th>\n",
" <th>opened_at</th>\n",
" <th>sent_at</th>\n",
" <th>delivered_at</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>1</td>\n",
" <td>5</td>\n",
" <td>161410</td>\n",
" <td>2022-02-02 18:16:07+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2022-02-02 17:16:08.616899+01:00</td>\n",
" <td>2022-02-02 17:16:08.623098+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>54228</td>\n",
" <td>2022-02-02 18:18:11+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2022-02-02 17:18:12.030260+01:00</td>\n",
" <td>2022-02-02 17:18:12.036606+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>6</td>\n",
" <td>120794</td>\n",
" <td>2022-02-02 18:18:58+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2022-02-02 17:19:00.129697+01:00</td>\n",
" <td>2022-02-02 17:19:00.134704+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>467025</td>\n",
" <td>2022-02-02 18:19:33+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2022-02-02 17:19:34.023492+01:00</td>\n",
" <td>2022-02-02 17:19:34.027570+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>142106</td>\n",
" <td>2022-02-02 18:19:35+01:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2022-02-02 17:19:36.553321+01:00</td>\n",
" <td>2022-02-02 17:19:36.557473+01:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id campaign_id customer_id opened_at sent_at \\\n",
"0 1 5 161410 2022-02-02 18:16:07+01:00 NaN \n",
"1 2 1 54228 2022-02-02 18:18:11+01:00 NaN \n",
"2 3 6 120794 2022-02-02 18:18:58+01:00 NaN \n",
"3 4 3 467025 2022-02-02 18:19:33+01:00 NaN \n",
"4 5 2 142106 2022-02-02 18:19:35+01:00 NaN \n",
"\n",
" delivered_at created_at \\\n",
"0 NaN 2022-02-02 17:16:08.616899+01:00 \n",
"1 NaN 2022-02-02 17:18:12.030260+01:00 \n",
"2 NaN 2022-02-02 17:19:00.129697+01:00 \n",
"3 NaN 2022-02-02 17:19:34.023492+01:00 \n",
"4 NaN 2022-02-02 17:19:36.553321+01:00 \n",
"\n",
" updated_at \n",
"0 2022-02-02 17:16:08.623098+01:00 \n",
"1 2022-02-02 17:18:12.036606+01:00 \n",
"2 2022-02-02 17:19:00.134704+01:00 \n",
"3 2022-02-02 17:19:34.027570+01:00 \n",
"4 2022-02-02 17:19:36.557473+01:00 "
]
},
"execution_count": 280,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"campaign_stats = display_databases(\"8campaign_stats.csv\")\n",
"campaign_stats.head()"
]
},
{
"cell_type": "markdown",
"id": "e6512bc9-91f5-4fe4-a637-a4e84dc497a9",
"metadata": {},
"source": [
"#### Look at links files"
]
},
{
"cell_type": "markdown",
"id": "28e7c1fe-470f-4d84-87b8-a711a973500b",
"metadata": {},
"source": [
"There is no links file for these company. Only the link_stats file"
]
},
{
"cell_type": "code",
"execution_count": 281,
"id": "e973575b-4ed6-4b23-8024-f383ac82e87c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8link_stats.csv\n",
"Shape : (108461, 6)\n"
]
},
{
"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>clicked_at</th>\n",
" <th>link_id</th>\n",
" <th>customer_id</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>1</td>\n",
" <td>2022-02-02 18:33:17+01:00</td>\n",
" <td>1</td>\n",
" <td>62137</td>\n",
" <td>2022-02-02 17:33:19.237759+01:00</td>\n",
" <td>2022-02-02 17:33:19.237759+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2022-02-02 18:33:26+01:00</td>\n",
" <td>1</td>\n",
" <td>556048</td>\n",
" <td>2022-02-02 17:33:28.101943+01:00</td>\n",
" <td>2022-02-02 17:33:28.101943+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>2022-02-02 18:33:49+01:00</td>\n",
" <td>2</td>\n",
" <td>194456</td>\n",
" <td>2022-02-02 17:33:50.595125+01:00</td>\n",
" <td>2022-02-02 17:33:50.595125+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>2022-02-02 18:34:19+01:00</td>\n",
" <td>1</td>\n",
" <td>194456</td>\n",
" <td>2022-02-02 17:34:20.493986+01:00</td>\n",
" <td>2022-02-02 17:34:20.493986+01:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>2022-02-02 18:34:21+01:00</td>\n",
" <td>2</td>\n",
" <td>21571</td>\n",
" <td>2022-02-02 17:34:22.300427+01:00</td>\n",
" <td>2022-02-02 17:34:22.300427+01:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id clicked_at link_id customer_id \\\n",
"0 1 2022-02-02 18:33:17+01:00 1 62137 \n",
"1 2 2022-02-02 18:33:26+01:00 1 556048 \n",
"2 3 2022-02-02 18:33:49+01:00 2 194456 \n",
"3 4 2022-02-02 18:34:19+01:00 1 194456 \n",
"4 5 2022-02-02 18:34:21+01:00 2 21571 \n",
"\n",
" created_at updated_at \n",
"0 2022-02-02 17:33:19.237759+01:00 2022-02-02 17:33:19.237759+01:00 \n",
"1 2022-02-02 17:33:28.101943+01:00 2022-02-02 17:33:28.101943+01:00 \n",
"2 2022-02-02 17:33:50.595125+01:00 2022-02-02 17:33:50.595125+01:00 \n",
"3 2022-02-02 17:34:20.493986+01:00 2022-02-02 17:34:20.493986+01:00 \n",
"4 2022-02-02 17:34:22.300427+01:00 2022-02-02 17:34:22.300427+01:00 "
]
},
"execution_count": 281,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"links_stats = display_databases(\"8link_stats.csv\")\n",
"links_stats.head()"
]
},
{
"cell_type": "markdown",
"id": "8dfcca1f-1323-413f-aa8d-3ee5ce2610a8",
"metadata": {},
"source": [
"#### Analyse Customersplus file"
]
},
{
"cell_type": "code",
"execution_count": 282,
"id": "3b523575-c779-451c-a12e-a36fb4ad232c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8customersplus.csv\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_548/2210053343.py:5: DtypeWarning: Columns (20) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" customersplus = pd.read_csv(file_in, sep=\",\")\n"
]
},
{
"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>lastname</th>\n",
" <th>firstname</th>\n",
" <th>birthdate</th>\n",
" <th>email</th>\n",
" <th>street_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>civility</th>\n",
" <th>is_partner</th>\n",
" <th>...</th>\n",
" <th>preferred_category</th>\n",
" <th>preferred_supplier</th>\n",
" <th>preferred_formula</th>\n",
" <th>purchase_count</th>\n",
" <th>first_buying_date</th>\n",
" <th>last_visiting_date</th>\n",
" <th>zipcode</th>\n",
" <th>country</th>\n",
" <th>age</th>\n",
" <th>tenant_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1411166</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>email1411166</td>\n",
" <td>1</td>\n",
" <td>2022-12-19 15:03:39.419371+01:00</td>\n",
" <td>2022-12-19 15:03:39.419371+01:00</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>478498</td>\n",
" <td>lastname478498</td>\n",
" <td>firstname478498</td>\n",
" <td>NaN</td>\n",
" <td>email478498</td>\n",
" <td>339167</td>\n",
" <td>2021-09-17 18:58:30.259053+02:00</td>\n",
" <td>2023-06-28 15:25:24.146689+02:00</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>473678</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>email473678</td>\n",
" <td>339167</td>\n",
" <td>2021-09-17 18:44:04.119713+02:00</td>\n",
" <td>2021-09-17 18:44:04.124204+02:00</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>475026</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>email475026</td>\n",
" <td>339167</td>\n",
" <td>2021-09-17 18:47:28.789618+02:00</td>\n",
" <td>2021-09-17 18:47:28.793958+02:00</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>487146</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>email487146</td>\n",
" <td>339167</td>\n",
" <td>2021-09-17 19:10:24.070460+02:00</td>\n",
" <td>2021-09-17 19:10:24.076033+02:00</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1594</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 43 columns</p>\n",
"</div>"
],
"text/plain": [
" id lastname firstname birthdate email \\\n",
"0 1411166 NaN NaN NaN email1411166 \n",
"1 478498 lastname478498 firstname478498 NaN email478498 \n",
"2 473678 NaN NaN NaN email473678 \n",
"3 475026 NaN NaN NaN email475026 \n",
"4 487146 NaN NaN NaN email487146 \n",
"\n",
" street_id created_at \\\n",
"0 1 2022-12-19 15:03:39.419371+01:00 \n",
"1 339167 2021-09-17 18:58:30.259053+02:00 \n",
"2 339167 2021-09-17 18:44:04.119713+02:00 \n",
"3 339167 2021-09-17 18:47:28.789618+02:00 \n",
"4 339167 2021-09-17 19:10:24.070460+02:00 \n",
"\n",
" updated_at civility is_partner ... \\\n",
"0 2022-12-19 15:03:39.419371+01:00 NaN False ... \n",
"1 2023-06-28 15:25:24.146689+02:00 NaN False ... \n",
"2 2021-09-17 18:44:04.124204+02:00 NaN False ... \n",
"3 2021-09-17 18:47:28.793958+02:00 NaN False ... \n",
"4 2021-09-17 19:10:24.076033+02:00 NaN False ... \n",
"\n",
" preferred_category preferred_supplier preferred_formula purchase_count \\\n",
"0 NaN NaN NaN 0 \n",
"1 NaN NaN NaN 0 \n",
"2 NaN NaN NaN 0 \n",
"3 NaN NaN NaN 0 \n",
"4 NaN NaN NaN 0 \n",
"\n",
" first_buying_date last_visiting_date zipcode country age tenant_id \n",
"0 NaN NaN NaN fr NaN 1594 \n",
"1 NaN NaN NaN NaN NaN 1594 \n",
"2 NaN NaN NaN NaN NaN 1594 \n",
"3 NaN NaN NaN NaN NaN 1594 \n",
"4 NaN NaN NaN NaN NaN 1594 \n",
"\n",
"[5 rows x 43 columns]"
]
},
"execution_count": 282,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file_name = \"8customersplus.csv\"\n",
"file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
"print(file_path)\n",
"with fs.open(file_path, mode=\"rb\") as file_in:\n",
" customersplus = pd.read_csv(file_in, sep=\",\")\n",
"\n",
"customersplus.head()"
]
},
{
"cell_type": "markdown",
"id": "fe56785a-ed3c-4322-aafa-a630f97b836f",
"metadata": {},
"source": [
"#### Analyse Structures files"
]
},
{
"cell_type": "code",
"execution_count": 283,
"id": "87d801fc-d19a-4c45-9b21-9b6d7a8451fd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8structures.csv\n",
"No structures database\n"
]
}
],
"source": [
"file_name = \"8structures.csv\"\n",
"file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
"print(file_path)\n",
"try:\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" structures = pd.read_csv(file_in, sep=\",\")\n",
"except:\n",
" print(\"No structures database\")"
]
},
{
"cell_type": "markdown",
"id": "b8452558-2d32-459b-91e7-f6042345e465",
"metadata": {},
"source": [
"For Stade Français, there is no structures, tags and structure_tag_mapping databases"
]
},
{
"cell_type": "markdown",
"id": "285b1422-9ca9-4afd-b752-777a54aaa677",
"metadata": {},
"source": [
"#### Analyze Target databases"
]
},
{
"cell_type": "code",
"execution_count": 284,
"id": "b6e4c3ea-5ccf-4aec-bd2d-79a5a1194178",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8customer_target_mappings.csv\n",
"Shape : (1449147, 7)\n"
]
},
{
"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>customer_id</th>\n",
" <th>target_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>name</th>\n",
" <th>extra_field</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>460062</td>\n",
" <td>68</td>\n",
" <td>2021-09-17 20:20:24.562734+02:00</td>\n",
" <td>2021-09-17 20:20:24.562734+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>460056</td>\n",
" <td>68</td>\n",
" <td>2021-09-17 20:20:24.610139+02:00</td>\n",
" <td>2021-09-17 20:20:24.610139+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>460051</td>\n",
" <td>65</td>\n",
" <td>2021-09-17 20:20:24.641381+02:00</td>\n",
" <td>2021-09-17 20:20:24.641381+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>460051</td>\n",
" <td>66</td>\n",
" <td>2021-09-17 20:20:24.672238+02:00</td>\n",
" <td>2021-09-17 20:20:24.672238+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>460049</td>\n",
" <td>71</td>\n",
" <td>2021-09-17 20:20:24.703110+02:00</td>\n",
" <td>2021-09-17 20:20:24.703110+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id customer_id target_id created_at \\\n",
"0 1 460062 68 2021-09-17 20:20:24.562734+02:00 \n",
"1 2 460056 68 2021-09-17 20:20:24.610139+02:00 \n",
"2 3 460051 65 2021-09-17 20:20:24.641381+02:00 \n",
"3 4 460051 66 2021-09-17 20:20:24.672238+02:00 \n",
"4 5 460049 71 2021-09-17 20:20:24.703110+02:00 \n",
"\n",
" updated_at name extra_field \n",
"0 2021-09-17 20:20:24.562734+02:00 NaN NaN \n",
"1 2021-09-17 20:20:24.610139+02:00 NaN NaN \n",
"2 2021-09-17 20:20:24.641381+02:00 NaN NaN \n",
"3 2021-09-17 20:20:24.672238+02:00 NaN NaN \n",
"4 2021-09-17 20:20:24.703110+02:00 NaN NaN "
]
},
"execution_count": 284,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file_name = \"8customer_target_mappings.csv\"\n",
"file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
"print(file_path)\n",
"try:\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" customer_targets = pd.read_csv(file_in, sep=\",\")\n",
" \n",
"except:\n",
" print(\"No such database in s3\")\n",
"\n",
"print(\"Shape : \", customer_targets.shape)\n",
"customer_targets.head()"
]
},
{
"cell_type": "code",
"execution_count": 285,
"id": "6e81a35c-3c6f-403d-9ebd-e8399ecd4263",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8targets.csv\n",
"Shape : (331, 5)\n"
]
},
{
"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>target_type_id</th>\n",
" <th>name</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>1</td>\n",
" <td>1</td>\n",
" <td>ÉTUDIANTS (OPÉ PANIERS) 21-22</td>\n",
" <td>2021-09-17 18:10:40.879995+02:00</td>\n",
" <td>2021-09-17 18:10:40.879995+02:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>EFFECTIF + STAFF 21-22</td>\n",
" <td>2021-09-17 18:10:40.894758+02:00</td>\n",
" <td>2021-09-17 18:10:40.894758+02:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>Acheteurs LOU / USAP</td>\n",
" <td>2021-09-17 18:10:40.911969+02:00</td>\n",
" <td>2021-09-17 18:10:40.911969+02:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>Liste Compensation 21-22</td>\n",
" <td>2021-09-17 18:10:40.928796+02:00</td>\n",
" <td>2021-09-17 18:10:40.928796+02:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>Partenaires 21-22</td>\n",
" <td>2021-09-17 18:10:40.945476+02:00</td>\n",
" <td>2021-09-17 18:10:40.945476+02:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id target_type_id name \\\n",
"0 1 1 ÉTUDIANTS (OPÉ PANIERS) 21-22 \n",
"1 2 1 EFFECTIF + STAFF 21-22 \n",
"2 3 1 Acheteurs LOU / USAP \n",
"3 4 1 Liste Compensation 21-22 \n",
"4 5 1 Partenaires 21-22 \n",
"\n",
" created_at updated_at \n",
"0 2021-09-17 18:10:40.879995+02:00 2021-09-17 18:10:40.879995+02:00 \n",
"1 2021-09-17 18:10:40.894758+02:00 2021-09-17 18:10:40.894758+02:00 \n",
"2 2021-09-17 18:10:40.911969+02:00 2021-09-17 18:10:40.911969+02:00 \n",
"3 2021-09-17 18:10:40.928796+02:00 2021-09-17 18:10:40.928796+02:00 \n",
"4 2021-09-17 18:10:40.945476+02:00 2021-09-17 18:10:40.945476+02:00 "
]
},
"execution_count": 285,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file_name = \"8targets.csv\"\n",
"file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
"print(file_path)\n",
"try:\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" targets = pd.read_csv(file_in, sep=\",\")\n",
" \n",
"except:\n",
" print(\"No such database in s3\")\n",
"\n",
"print(\"Shape : \", targets.shape)\n",
"targets.head()"
]
},
{
"cell_type": "code",
"execution_count": 286,
"id": "85696d74-3b2f-4368-9045-44db5322b60d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"bdc2324-data/8/8target_types.csv\n",
"Shape : (4, 6)\n"
]
},
{
"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>is_import</th>\n",
" <th>name</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>NaN</td>\n",
" <td>manual_static_filter</td>\n",
" <td>2021-09-17 18:10:40.864320+02:00</td>\n",
" <td>2021-09-17 18:10:40.864320+02:00</td>\n",
" <td>e34e3aa838a6eb4c41df6ed4444b796a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>manual_dynamic_filter</td>\n",
" <td>2022-03-09 14:41:45.695407+01:00</td>\n",
" <td>2022-03-09 14:41:45.695407+01:00</td>\n",
" <td>e0f4b8693184850fefd6d2a38f10584e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>False</td>\n",
" <td>manual_static_filter</td>\n",
" <td>2022-04-01 17:02:49.588910+02:00</td>\n",
" <td>2022-04-01 17:02:49.588910+02:00</td>\n",
" <td>fb27e81baa4debc6a4e1a8639c20e808</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>True</td>\n",
" <td>manual_import</td>\n",
" <td>2022-05-06 14:26:01.923160+02:00</td>\n",
" <td>2022-05-06 14:26:01.923160+02:00</td>\n",
" <td>12213df2ce68a624e4c0070521437bac</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id is_import name created_at \\\n",
"0 1 NaN manual_static_filter 2021-09-17 18:10:40.864320+02:00 \n",
"1 2 False manual_dynamic_filter 2022-03-09 14:41:45.695407+01:00 \n",
"2 3 False manual_static_filter 2022-04-01 17:02:49.588910+02:00 \n",
"3 4 True manual_import 2022-05-06 14:26:01.923160+02:00 \n",
"\n",
" updated_at identifier \n",
"0 2021-09-17 18:10:40.864320+02:00 e34e3aa838a6eb4c41df6ed4444b796a \n",
"1 2022-03-09 14:41:45.695407+01:00 e0f4b8693184850fefd6d2a38f10584e \n",
"2 2022-04-01 17:02:49.588910+02:00 fb27e81baa4debc6a4e1a8639c20e808 \n",
"3 2022-05-06 14:26:01.923160+02:00 12213df2ce68a624e4c0070521437bac "
]
},
"execution_count": 286,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file_name = \"8target_types.csv\"\n",
"file_path = BUCKET + \"/\" + directory_path + \"/\" + file_name\n",
"print(file_path)\n",
"try:\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" target_types = pd.read_csv(file_in, sep=\",\")\n",
" \n",
"except:\n",
" print(\"No such database in s3\")\n",
"\n",
"print(\"Shape : \", target_types.shape)\n",
"target_types.head()"
]
},
{
"cell_type": "markdown",
"id": "cdc6416b-3deb-446c-8957-435745b93533",
"metadata": {},
"source": [
"#### Analyze consumption files"
]
},
{
"cell_type": "markdown",
"id": "f8622bd5-a5ab-403f-ab01-758aec879ee4",
"metadata": {},
"source": [
"Meaning consumptions.csv, suppliers.csv, tickets.csv and purchases.csv\n",
"\n",
"However, there is no consumptions.csv file"
]
},
{
"cell_type": "code",
"execution_count": 287,
"id": "7c57529b-2ffb-4039-9795-b27c6fbd54a4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8purchases.csv\n",
"Shape : (975703, 7)\n"
]
},
{
"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>purchase_date</th>\n",
" <th>customer_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>number</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>119609</td>\n",
" <td>2017-09-09 15:39:45.913000+02:00</td>\n",
" <td>1149</td>\n",
" <td>2021-06-29 21:52:21.816195+02:00</td>\n",
" <td>2021-06-29 21:52:21.816195+02:00</td>\n",
" <td>193416</td>\n",
" <td>f2956e2d53321317e7c15c1cb992156c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>119610</td>\n",
" <td>2017-09-09 15:39:46.033000+02:00</td>\n",
" <td>1149</td>\n",
" <td>2021-06-29 21:52:21.817846+02:00</td>\n",
" <td>2021-06-29 21:52:21.817846+02:00</td>\n",
" <td>193416</td>\n",
" <td>faabab441b2668a85bb484490b2166c3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5464</td>\n",
" <td>2017-07-24 19:44:11.923000+02:00</td>\n",
" <td>1251</td>\n",
" <td>2021-06-29 21:33:45.604224+02:00</td>\n",
" <td>2021-06-29 21:33:45.604224+02:00</td>\n",
" <td>184354</td>\n",
" <td>f63c69fa585ce4f91681f0d9ebeb770f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>119613</td>\n",
" <td>2017-09-10 11:25:45.820000+02:00</td>\n",
" <td>12558</td>\n",
" <td>2021-06-29 21:52:21.822033+02:00</td>\n",
" <td>2021-06-29 21:52:21.822033+02:00</td>\n",
" <td>193462</td>\n",
" <td>ffce5fd8d2348eb6885d0ee9c7bd017c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1422860</td>\n",
" <td>2018-10-08 10:30:42.980000+02:00</td>\n",
" <td>17935</td>\n",
" <td>2021-07-16 04:20:55.347369+02:00</td>\n",
" <td>2021-07-16 04:20:55.347369+02:00</td>\n",
" <td>247459</td>\n",
" <td>193e41eae8ee078537107a569c0426ef</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id purchase_date customer_id \\\n",
"0 119609 2017-09-09 15:39:45.913000+02:00 1149 \n",
"1 119610 2017-09-09 15:39:46.033000+02:00 1149 \n",
"2 5464 2017-07-24 19:44:11.923000+02:00 1251 \n",
"3 119613 2017-09-10 11:25:45.820000+02:00 12558 \n",
"4 1422860 2018-10-08 10:30:42.980000+02:00 17935 \n",
"\n",
" created_at updated_at number \\\n",
"0 2021-06-29 21:52:21.816195+02:00 2021-06-29 21:52:21.816195+02:00 193416 \n",
"1 2021-06-29 21:52:21.817846+02:00 2021-06-29 21:52:21.817846+02:00 193416 \n",
"2 2021-06-29 21:33:45.604224+02:00 2021-06-29 21:33:45.604224+02:00 184354 \n",
"3 2021-06-29 21:52:21.822033+02:00 2021-06-29 21:52:21.822033+02:00 193462 \n",
"4 2021-07-16 04:20:55.347369+02:00 2021-07-16 04:20:55.347369+02:00 247459 \n",
"\n",
" identifier \n",
"0 f2956e2d53321317e7c15c1cb992156c \n",
"1 faabab441b2668a85bb484490b2166c3 \n",
"2 f63c69fa585ce4f91681f0d9ebeb770f \n",
"3 ffce5fd8d2348eb6885d0ee9c7bd017c \n",
"4 193e41eae8ee078537107a569c0426ef "
]
},
"execution_count": 287,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"purchases = display_databases(\"8purchases.csv\")\n",
"purchases.head()"
]
},
{
"cell_type": "code",
"execution_count": 288,
"id": "903321fb-99f8-475d-b4a6-c70ec2efe190",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8tickets.csv\n",
"Shape : (2370152, 11)\n"
]
},
{
"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>number</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>purchase_id</th>\n",
" <th>product_id</th>\n",
" <th>is_from_subscription</th>\n",
" <th>type_of</th>\n",
" <th>supplier_id</th>\n",
" <th>barcode</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>254164</td>\n",
" <td>193416_763837_650_688_326212</td>\n",
" <td>2021-06-29 21:53:14.951871+02:00</td>\n",
" <td>2021-06-29 21:53:14.951871+02:00</td>\n",
" <td>119609</td>\n",
" <td>3334</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>9ec3b5617fc54512acf131aa5fa26870</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>254165</td>\n",
" <td>193416_763838_650_688_326236</td>\n",
" <td>2021-06-29 21:53:14.953717+02:00</td>\n",
" <td>2021-06-29 21:53:14.953717+02:00</td>\n",
" <td>119610</td>\n",
" <td>3334</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>b227c664e2574a919672683f5cc4c98e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>254168</td>\n",
" <td>193462_763921_649_687_305676</td>\n",
" <td>2021-06-29 21:53:14.958207+02:00</td>\n",
" <td>2021-06-29 21:53:14.958207+02:00</td>\n",
" <td>119613</td>\n",
" <td>3432</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>28ac507ad84a30993bdfc0996fd2476b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>254169</td>\n",
" <td>193462_763922_649_687_305653</td>\n",
" <td>2021-06-29 21:53:14.959681+02:00</td>\n",
" <td>2021-06-29 21:53:14.959681+02:00</td>\n",
" <td>119614</td>\n",
" <td>3268</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>131dbaeef23f5ac2271bf0266ce35476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>254170</td>\n",
" <td>193462_763923_649_687_305630</td>\n",
" <td>2021-06-29 21:53:14.961157+02:00</td>\n",
" <td>2021-06-29 21:53:14.961157+02:00</td>\n",
" <td>119615</td>\n",
" <td>3268</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>1a6342ad2c213b626aa55e5374cd661a</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id number created_at \\\n",
"0 254164 193416_763837_650_688_326212 2021-06-29 21:53:14.951871+02:00 \n",
"1 254165 193416_763838_650_688_326236 2021-06-29 21:53:14.953717+02:00 \n",
"2 254168 193462_763921_649_687_305676 2021-06-29 21:53:14.958207+02:00 \n",
"3 254169 193462_763922_649_687_305653 2021-06-29 21:53:14.959681+02:00 \n",
"4 254170 193462_763923_649_687_305630 2021-06-29 21:53:14.961157+02:00 \n",
"\n",
" updated_at purchase_id product_id \\\n",
"0 2021-06-29 21:53:14.951871+02:00 119609 3334 \n",
"1 2021-06-29 21:53:14.953717+02:00 119610 3334 \n",
"2 2021-06-29 21:53:14.958207+02:00 119613 3432 \n",
"3 2021-06-29 21:53:14.959681+02:00 119614 3268 \n",
"4 2021-06-29 21:53:14.961157+02:00 119615 3268 \n",
"\n",
" is_from_subscription type_of supplier_id barcode \\\n",
"0 False 1 2 NaN \n",
"1 False 1 2 NaN \n",
"2 False 1 2 NaN \n",
"3 False 1 2 NaN \n",
"4 False 1 2 NaN \n",
"\n",
" identifier \n",
"0 9ec3b5617fc54512acf131aa5fa26870 \n",
"1 b227c664e2574a919672683f5cc4c98e \n",
"2 28ac507ad84a30993bdfc0996fd2476b \n",
"3 131dbaeef23f5ac2271bf0266ce35476 \n",
"4 1a6342ad2c213b626aa55e5374cd661a "
]
},
"execution_count": 288,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tickets = display_databases(\"8tickets.csv\")\n",
"tickets.head()"
]
},
{
"cell_type": "code",
"execution_count": 289,
"id": "243e6942-0233-4cd5-b32b-e005457131d2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8suppliers.csv\n",
"Shape : (16, 9)\n"
]
},
{
"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>manually_added</th>\n",
" <th>label</th>\n",
" <th>itr</th>\n",
" <th>updated_at</th>\n",
" <th>created_at</th>\n",
" <th>commission</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>152</td>\n",
" <td>plateformeceweb</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2021-07-16 00:02:17.805193+02:00</td>\n",
" <td>2021-07-16 00:02:17.805193+02:00</td>\n",
" <td>NaN</td>\n",
" <td>0fc934f49bfa9f1f4e6ab7e2593b6839</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6</td>\n",
" <td>accreditation annuelle</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2021-06-29 21:33:14.138349+02:00</td>\n",
" <td>2021-06-29 21:33:14.138349+02:00</td>\n",
" <td>NaN</td>\n",
" <td>fe13238540e0ff293ec8aad29aeae6c3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>68</td>\n",
" <td>abonnement parking</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2021-06-29 22:10:31.167367+02:00</td>\n",
" <td>2021-06-29 22:10:31.167367+02:00</td>\n",
" <td>NaN</td>\n",
" <td>0f7defc52a97cdca533af74f4e6e5b1e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>9</td>\n",
" <td>accreditation match</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2021-06-29 21:33:14.142084+02:00</td>\n",
" <td>2021-06-29 21:33:14.142084+02:00</td>\n",
" <td>NaN</td>\n",
" <td>40e19a7c4824eaad298e0107ed7e3691</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>154</td>\n",
" <td>web lnr-lou</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2021-07-16 00:02:17.806521+02:00</td>\n",
" <td>2021-07-16 00:02:17.806521+02:00</td>\n",
" <td>NaN</td>\n",
" <td>b144dd617807b02e0d9002fac6c61768</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name manually_added label itr \\\n",
"0 152 plateformeceweb False NaN NaN \n",
"1 6 accreditation annuelle False NaN NaN \n",
"2 68 abonnement parking False NaN NaN \n",
"3 9 accreditation match False NaN NaN \n",
"4 154 web lnr-lou False NaN NaN \n",
"\n",
" updated_at created_at \\\n",
"0 2021-07-16 00:02:17.805193+02:00 2021-07-16 00:02:17.805193+02:00 \n",
"1 2021-06-29 21:33:14.138349+02:00 2021-06-29 21:33:14.138349+02:00 \n",
"2 2021-06-29 22:10:31.167367+02:00 2021-06-29 22:10:31.167367+02:00 \n",
"3 2021-06-29 21:33:14.142084+02:00 2021-06-29 21:33:14.142084+02:00 \n",
"4 2021-07-16 00:02:17.806521+02:00 2021-07-16 00:02:17.806521+02:00 \n",
"\n",
" commission identifier \n",
"0 NaN 0fc934f49bfa9f1f4e6ab7e2593b6839 \n",
"1 NaN fe13238540e0ff293ec8aad29aeae6c3 \n",
"2 NaN 0f7defc52a97cdca533af74f4e6e5b1e \n",
"3 NaN 40e19a7c4824eaad298e0107ed7e3691 \n",
"4 NaN b144dd617807b02e0d9002fac6c61768 "
]
},
"execution_count": 289,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"suppliers = display_databases(\"8suppliers.csv\")\n",
"suppliers.head()"
]
},
{
"cell_type": "markdown",
"id": "fd8c876a-f0c5-4123-a422-c267af5f29b1",
"metadata": {},
"source": [
"#### Analyse product file"
]
},
{
"cell_type": "code",
"execution_count": 290,
"id": "6b82efce-1dee-4d89-8585-28c4ad477eef",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8products.csv\n",
"Shape : (45411, 14)\n"
]
},
{
"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>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</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</th>\n",
" <th>amount_consumption</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>90013</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>1961</td>\n",
" <td>912</td>\n",
" <td>2021-07-16 04:56:05.797551+02:00</td>\n",
" <td>2021-07-16 04:56:05.797551+02:00</td>\n",
" <td>34</td>\n",
" <td>0.0</td>\n",
" <td>87917</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>476e111175b1660688b7c13dade2b57e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>662</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>11</td>\n",
" <td>29</td>\n",
" <td>2021-06-29 21:33:17.389201+02:00</td>\n",
" <td>2021-06-29 21:33:17.389201+02:00</td>\n",
" <td>16</td>\n",
" <td>0.0</td>\n",
" <td>640</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2c765698e9bedd48e8a3fd27dc8dbc97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>646</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>46</td>\n",
" <td>10</td>\n",
" <td>2021-06-29 21:33:17.366742+02:00</td>\n",
" <td>2021-06-29 21:33:17.366742+02:00</td>\n",
" <td>15</td>\n",
" <td>0.0</td>\n",
" <td>624</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4e719148651fd7f175e3fb51bdb5d31b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5703</td>\n",
" <td>5.0</td>\n",
" <td>False</td>\n",
" <td>7</td>\n",
" <td>188</td>\n",
" <td>2021-06-29 21:52:09.374365+02:00</td>\n",
" <td>2021-06-29 21:52:09.374365+02:00</td>\n",
" <td>4</td>\n",
" <td>0.0</td>\n",
" <td>5540</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>e4d7beeb0a631e2e51e61951623ba9b1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>648</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>49</td>\n",
" <td>10</td>\n",
" <td>2021-06-29 21:33:17.369471+02:00</td>\n",
" <td>2021-06-29 21:33:17.369471+02:00</td>\n",
" <td>15</td>\n",
" <td>0.0</td>\n",
" <td>626</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>07a5dd9e125345b9458651ab73605255</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id amount is_full_price representation_id pricing_formula_id \\\n",
"0 90013 0.0 False 1961 912 \n",
"1 662 0.0 False 11 29 \n",
"2 646 0.0 False 46 10 \n",
"3 5703 5.0 False 7 188 \n",
"4 648 0.0 False 49 10 \n",
"\n",
" created_at updated_at \\\n",
"0 2021-07-16 04:56:05.797551+02:00 2021-07-16 04:56:05.797551+02:00 \n",
"1 2021-06-29 21:33:17.389201+02:00 2021-06-29 21:33:17.389201+02:00 \n",
"2 2021-06-29 21:33:17.366742+02:00 2021-06-29 21:33:17.366742+02:00 \n",
"3 2021-06-29 21:52:09.374365+02:00 2021-06-29 21:52:09.374365+02:00 \n",
"4 2021-06-29 21:33:17.369471+02:00 2021-06-29 21:33:17.369471+02:00 \n",
"\n",
" category_id apply_price products_group_id product_pack_id extra_field \\\n",
"0 34 0.0 87917 1 NaN \n",
"1 16 0.0 640 1 NaN \n",
"2 15 0.0 624 1 NaN \n",
"3 4 0.0 5540 1 NaN \n",
"4 15 0.0 626 1 NaN \n",
"\n",
" amount_consumption identifier \n",
"0 NaN 476e111175b1660688b7c13dade2b57e \n",
"1 NaN 2c765698e9bedd48e8a3fd27dc8dbc97 \n",
"2 NaN 4e719148651fd7f175e3fb51bdb5d31b \n",
"3 NaN e4d7beeb0a631e2e51e61951623ba9b1 \n",
"4 NaN 07a5dd9e125345b9458651ab73605255 "
]
},
"execution_count": 290,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products = display_databases(\"8products.csv\")\n",
"products.head()"
]
},
{
"cell_type": "markdown",
"id": "8ad143b2-2869-4bd2-982e-688498b98727",
"metadata": {},
"source": [
"#### Analyze pricing files"
]
},
{
"cell_type": "markdown",
"id": "9a54e9a5-801d-4000-9e76-e792edbf7e41",
"metadata": {},
"source": [
"Meaning pricing_formulas.csv and type_of_pricing_formulas"
]
},
{
"cell_type": "code",
"execution_count": 291,
"id": "daf37bff-a26d-4ff5-ad50-c90f917164bd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8pricing_formulas.csv\n",
"Shape : (516, 6)\n"
]
},
{
"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>7</td>\n",
" <td>visite stade enfant</td>\n",
" <td>2021-06-29 21:33:14.160728+02:00</td>\n",
" <td>2021-06-29 21:33:14.160728+02:00</td>\n",
" <td>NaN</td>\n",
" <td>bbc80e5761a0ea325f6f6a5411752659</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3229</td>\n",
" <td>tarif bloc etudiants</td>\n",
" <td>2021-07-16 04:20:46.684601+02:00</td>\n",
" <td>2021-09-03 16:44:46.096785+02:00</td>\n",
" <td>NaN</td>\n",
" <td>205122cc7e96d559330972b0ec0cf35a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>42</td>\n",
" <td>invitation eiffage</td>\n",
" <td>2021-06-29 21:33:14.204483+02:00</td>\n",
" <td>2021-06-29 21:33:14.204483+02:00</td>\n",
" <td>NaN</td>\n",
" <td>e4e6365c02e2a7b01ebe2ce8ace624f2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4379</td>\n",
" <td>invitation offre speciale</td>\n",
" <td>2021-07-16 05:21:44.984893+02:00</td>\n",
" <td>2021-07-16 05:21:44.984893+02:00</td>\n",
" <td>NaN</td>\n",
" <td>307817b6205535a35915a64027ee161e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2641</td>\n",
" <td>prevente reabo enfant</td>\n",
" <td>2021-07-16 03:47:40.896805+02:00</td>\n",
" <td>2021-09-03 16:08:35.304298+02:00</td>\n",
" <td>NaN</td>\n",
" <td>478eb63c71ba35d8d3d64c8637dafdee</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 7 visite stade enfant 2021-06-29 21:33:14.160728+02:00 \n",
"1 3229 tarif bloc etudiants 2021-07-16 04:20:46.684601+02:00 \n",
"2 42 invitation eiffage 2021-06-29 21:33:14.204483+02:00 \n",
"3 4379 invitation offre speciale 2021-07-16 05:21:44.984893+02:00 \n",
"4 2641 prevente reabo enfant 2021-07-16 03:47:40.896805+02:00 \n",
"\n",
" updated_at extra_field \\\n",
"0 2021-06-29 21:33:14.160728+02:00 NaN \n",
"1 2021-09-03 16:44:46.096785+02:00 NaN \n",
"2 2021-06-29 21:33:14.204483+02:00 NaN \n",
"3 2021-07-16 05:21:44.984893+02:00 NaN \n",
"4 2021-09-03 16:08:35.304298+02:00 NaN \n",
"\n",
" identifier \n",
"0 bbc80e5761a0ea325f6f6a5411752659 \n",
"1 205122cc7e96d559330972b0ec0cf35a \n",
"2 e4e6365c02e2a7b01ebe2ce8ace624f2 \n",
"3 307817b6205535a35915a64027ee161e \n",
"4 478eb63c71ba35d8d3d64c8637dafdee "
]
},
"execution_count": 291,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pricing_formulas = display_databases(\"8pricing_formulas.csv\")\n",
"pricing_formulas.head()"
]
},
{
"cell_type": "code",
"execution_count": 292,
"id": "cdb14488-b093-4b39-84fa-1c2b4576208f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8type_of_pricing_formulas.csv\n",
"Shape : (103, 6)\n"
]
},
{
"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>7</td>\n",
" <td>1021</td>\n",
" <td>2021-09-03 14:17:19.816110+02:00</td>\n",
" <td>2021-09-03 14:17:19.816110+02:00</td>\n",
" <td>41047fbeb7cd3e1cb2713c608d2f786d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>7</td>\n",
" <td>4305</td>\n",
" <td>2021-09-03 14:17:19.848088+02:00</td>\n",
" <td>2021-09-03 14:17:19.848088+02:00</td>\n",
" <td>a62a4dad7d62738129244bbb5ede0747</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>7</td>\n",
" <td>4306</td>\n",
" <td>2021-09-03 14:17:19.864067+02:00</td>\n",
" <td>2021-09-03 14:17:19.864067+02:00</td>\n",
" <td>c3770373e09f55412068c447736d9da3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>7</td>\n",
" <td>29</td>\n",
" <td>2021-09-03 14:17:19.880078+02:00</td>\n",
" <td>2021-09-03 14:17:19.880078+02:00</td>\n",
" <td>7b7b1242ae7a8c9eb66d35d8a4348ccd</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>10</td>\n",
" <td>2021-09-03 14:18:03.616081+02:00</td>\n",
" <td>2021-09-03 14:18:03.616081+02:00</td>\n",
" <td>0a2b941c46b31258c03b316aa064e86a</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id type_of_id pricing_formula_id created_at \\\n",
"0 1 7 1021 2021-09-03 14:17:19.816110+02:00 \n",
"1 2 7 4305 2021-09-03 14:17:19.848088+02:00 \n",
"2 3 7 4306 2021-09-03 14:17:19.864067+02:00 \n",
"3 4 7 29 2021-09-03 14:17:19.880078+02:00 \n",
"4 5 8 10 2021-09-03 14:18:03.616081+02:00 \n",
"\n",
" updated_at identifier \n",
"0 2021-09-03 14:17:19.816110+02:00 41047fbeb7cd3e1cb2713c608d2f786d \n",
"1 2021-09-03 14:17:19.848088+02:00 a62a4dad7d62738129244bbb5ede0747 \n",
"2 2021-09-03 14:17:19.864067+02:00 c3770373e09f55412068c447736d9da3 \n",
"3 2021-09-03 14:17:19.880078+02:00 7b7b1242ae7a8c9eb66d35d8a4348ccd \n",
"4 2021-09-03 14:18:03.616081+02:00 0a2b941c46b31258c03b316aa064e86a "
]
},
"execution_count": 292,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type_pricing_formulas = display_databases(\"8type_of_pricing_formulas.csv\")\n",
"type_pricing_formulas.head()"
]
},
{
"cell_type": "markdown",
"id": "a084297a-4fd7-4cda-b513-7704f4244a5c",
"metadata": {},
"source": [
"#### Analyze type of products"
]
},
{
"cell_type": "markdown",
"id": "76a67ea7-8720-441e-8973-23e5d105370e",
"metadata": {},
"source": [
"Meaning categories.csv, type_of_categories.csv"
]
},
{
"cell_type": "code",
"execution_count": 293,
"id": "6582694d-5339-4f33-a943-c73033121a90",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8categories.csv\n",
"Shape : (148, 7)\n"
]
},
{
"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>quota</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>653</td>\n",
" <td>acces village implid</td>\n",
" <td>2021-07-16 00:04:37.181331+02:00</td>\n",
" <td>2021-07-16 00:04:37.181331+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>c447d053646a6503d3cd84d4798bf5b7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>805</td>\n",
" <td>parking organisation</td>\n",
" <td>2021-07-16 01:54:15.822407+02:00</td>\n",
" <td>2021-07-16 01:54:15.822407+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>02bf9871964345f505ad305080daec36</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>809</td>\n",
" <td>rose rouge orange</td>\n",
" <td>2021-07-16 01:54:15.825345+02:00</td>\n",
" <td>2021-07-16 01:54:15.825345+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>31fb5b57bc1a2bcd5c155fb0d9e7c0dd</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2183</td>\n",
" <td>2eme catégorie j.b. centrale</td>\n",
" <td>2021-07-16 04:37:25.446835+02:00</td>\n",
" <td>2021-07-16 04:37:25.446835+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>c9eb6651caaed42b809b3f4407a847c9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>621</td>\n",
" <td>acces brasserie</td>\n",
" <td>2021-07-16 00:02:17.249701+02:00</td>\n",
" <td>2021-07-16 00:02:17.249701+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>349e6a59585d78d80d46acbc6a520c50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 653 acces village implid 2021-07-16 00:04:37.181331+02:00 \n",
"1 805 parking organisation 2021-07-16 01:54:15.822407+02:00 \n",
"2 809 rose rouge orange 2021-07-16 01:54:15.825345+02:00 \n",
"3 2183 2eme catégorie j.b. centrale 2021-07-16 04:37:25.446835+02:00 \n",
"4 621 acces brasserie 2021-07-16 00:02:17.249701+02:00 \n",
"\n",
" updated_at extra_field quota \\\n",
"0 2021-07-16 00:04:37.181331+02:00 NaN NaN \n",
"1 2021-07-16 01:54:15.822407+02:00 NaN NaN \n",
"2 2021-07-16 01:54:15.825345+02:00 NaN NaN \n",
"3 2021-07-16 04:37:25.446835+02:00 NaN NaN \n",
"4 2021-07-16 00:02:17.249701+02:00 NaN NaN \n",
"\n",
" identifier \n",
"0 c447d053646a6503d3cd84d4798bf5b7 \n",
"1 02bf9871964345f505ad305080daec36 \n",
"2 31fb5b57bc1a2bcd5c155fb0d9e7c0dd \n",
"3 c9eb6651caaed42b809b3f4407a847c9 \n",
"4 349e6a59585d78d80d46acbc6a520c50 "
]
},
"execution_count": 293,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"categories = display_databases(\"8categories.csv\")\n",
"categories.head()"
]
},
{
"cell_type": "code",
"execution_count": 294,
"id": "589076df-1958-42de-9941-1aff9fa8536f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8type_of_categories.csv\n",
"Shape : (6, 6)\n"
]
},
{
"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>category_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>2</td>\n",
" <td>2021-08-20 15:22:05.558209+02:00</td>\n",
" <td>2021-08-20 15:22:05.558209+02:00</td>\n",
" <td>af8fa6d57f6b19a7600a69e7771c7c3a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2021-09-02 17:29:32.582002+02:00</td>\n",
" <td>2021-09-02 17:29:32.582002+02:00</td>\n",
" <td>63718e7ad306912427758ddf988ad34f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>2021-09-02 17:32:38.299733+02:00</td>\n",
" <td>2021-09-02 17:32:38.299733+02:00</td>\n",
" <td>5e147d4d90888df14c4584f5c6887c96</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>2021-09-02 17:35:04.748993+02:00</td>\n",
" <td>2021-09-02 17:35:04.748993+02:00</td>\n",
" <td>a9dfdc3f40b41e3018933c6167fc38a5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>17</td>\n",
" <td>2021-09-02 17:35:37.396740+02:00</td>\n",
" <td>2021-09-02 17:35:37.396740+02:00</td>\n",
" <td>c05b0061d2a875adbc35d3dfa6a50a12</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id type_of_id category_id created_at \\\n",
"0 1 1 2 2021-08-20 15:22:05.558209+02:00 \n",
"1 2 2 1 2021-09-02 17:29:32.582002+02:00 \n",
"2 3 3 3 2021-09-02 17:32:38.299733+02:00 \n",
"3 4 4 4 2021-09-02 17:35:04.748993+02:00 \n",
"4 5 5 17 2021-09-02 17:35:37.396740+02:00 \n",
"\n",
" updated_at identifier \n",
"0 2021-08-20 15:22:05.558209+02:00 af8fa6d57f6b19a7600a69e7771c7c3a \n",
"1 2021-09-02 17:29:32.582002+02:00 63718e7ad306912427758ddf988ad34f \n",
"2 2021-09-02 17:32:38.299733+02:00 5e147d4d90888df14c4584f5c6887c96 \n",
"3 2021-09-02 17:35:04.748993+02:00 a9dfdc3f40b41e3018933c6167fc38a5 \n",
"4 2021-09-02 17:35:37.396740+02:00 c05b0061d2a875adbc35d3dfa6a50a12 "
]
},
"execution_count": 294,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type_categories = display_databases(\"8type_of_categories.csv\")\n",
"type_categories.head()"
]
},
{
"cell_type": "markdown",
"id": "3427b681-4c05-4e4e-9c2b-867ee789f98c",
"metadata": {},
"source": [
"#### Analyze type of representations"
]
},
{
"cell_type": "markdown",
"id": "9381e36b-090a-44c5-a29d-3ac4c9a4431e",
"metadata": {},
"source": [
"Meaning representation_category_capacities.csv, representations.csv, representations_types.csv\n",
"\n",
"however there is no representation_types database"
]
},
{
"cell_type": "code",
"execution_count": 295,
"id": "6f06d72a-5725-4eee-8e4c-e9ef5820f346",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8representation_category_capacities.csv\n",
"Shape : (7378, 7)\n"
]
},
{
"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>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>representation_id</th>\n",
" <th>category_id</th>\n",
" <th>expected_filling</th>\n",
" <th>max_filling</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>561</td>\n",
" <td>2021-06-29 21:33:14.096827+02:00</td>\n",
" <td>2021-06-29 21:33:14.096827+02:00</td>\n",
" <td>17</td>\n",
" <td>37</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>571</td>\n",
" <td>2021-06-29 21:33:14.110047+02:00</td>\n",
" <td>2021-06-29 21:33:14.110047+02:00</td>\n",
" <td>14</td>\n",
" <td>39</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>9665</td>\n",
" <td>2021-07-16 00:02:17.736387+02:00</td>\n",
" <td>2021-07-16 00:02:17.736387+02:00</td>\n",
" <td>1887</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>383906</td>\n",
" <td>2023-03-04 02:55:01.585418+01:00</td>\n",
" <td>2023-03-04 02:55:01.585418+01:00</td>\n",
" <td>52729</td>\n",
" <td>476</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>393</td>\n",
" <td>2021-06-29 21:33:13.876766+02:00</td>\n",
" <td>2021-06-29 21:33:13.876766+02:00</td>\n",
" <td>9</td>\n",
" <td>23</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id created_at updated_at \\\n",
"0 561 2021-06-29 21:33:14.096827+02:00 2021-06-29 21:33:14.096827+02:00 \n",
"1 571 2021-06-29 21:33:14.110047+02:00 2021-06-29 21:33:14.110047+02:00 \n",
"2 9665 2021-07-16 00:02:17.736387+02:00 2021-07-16 00:02:17.736387+02:00 \n",
"3 383906 2023-03-04 02:55:01.585418+01:00 2023-03-04 02:55:01.585418+01:00 \n",
"4 393 2021-06-29 21:33:13.876766+02:00 2021-06-29 21:33:13.876766+02:00 \n",
"\n",
" representation_id category_id expected_filling max_filling \n",
"0 17 37 NaN NaN \n",
"1 14 39 NaN NaN \n",
"2 1887 8 NaN NaN \n",
"3 52729 476 NaN NaN \n",
"4 9 23 NaN NaN "
]
},
"execution_count": 295,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"representation_category_capacities = display_databases(\"8representation_category_capacities.csv\")\n",
"representation_category_capacities.head()"
]
},
{
"cell_type": "code",
"execution_count": 296,
"id": "bd405913-033d-4f15-a5b9-103d577baaff",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8representations.csv\n",
"Shape : (1015, 16)\n"
]
},
{
"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>serial</th>\n",
" <th>event_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>start_date_time</th>\n",
" <th>open</th>\n",
" <th>satisfaction</th>\n",
" <th>end_date_time</th>\n",
" <th>name</th>\n",
" <th>is_display</th>\n",
" <th>representation_type_id</th>\n",
" <th>expected_filling</th>\n",
" <th>max_filling</th>\n",
" <th>extra_field</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5903</td>\n",
" <td>NaN</td>\n",
" <td>5836</td>\n",
" <td>2021-07-16 05:16:57.419565+02:00</td>\n",
" <td>2021-07-16 05:16:57.419565+02:00</td>\n",
" <td>2019-08-24 18:00:00+02:00</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>1901-01-01 00:09:21+00:09</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8009c34cae4e79e3781f16f3ceeab244</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>67133</td>\n",
" <td>NaN</td>\n",
" <td>65652</td>\n",
" <td>2023-09-27 02:21:36.573001+02:00</td>\n",
" <td>2023-09-27 02:21:36.573001+02:00</td>\n",
" <td>2023-10-04 10:30:00+02:00</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>1901-01-01 00:09:21+00:09</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4e9d3fc8d1f7bf563dc586548fe6390e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1874</td>\n",
" <td>NaN</td>\n",
" <td>1826</td>\n",
" <td>2021-07-16 00:02:17.390274+02:00</td>\n",
" <td>2021-07-16 00:02:17.390274+02:00</td>\n",
" <td>2019-09-14 18:00:00+02:00</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>1901-01-01 00:09:21+00:09</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>19f666370c1fc781dff638c20ae04c8a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5904</td>\n",
" <td>NaN</td>\n",
" <td>5837</td>\n",
" <td>2021-07-16 05:16:57.420302+02:00</td>\n",
" <td>2021-07-16 05:16:57.420302+02:00</td>\n",
" <td>2019-09-01 17:05:00+02:00</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>1901-01-01 00:09:21+00:09</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4221acd3f49179f5d0b292c15d1ab8e4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4165</td>\n",
" <td>NaN</td>\n",
" <td>4106</td>\n",
" <td>2021-07-16 03:53:05.929713+02:00</td>\n",
" <td>2021-07-16 03:53:05.929713+02:00</td>\n",
" <td>2018-10-14 14:00:00+02:00</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>1901-01-01 00:09:21+00:09</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>733104286519c0614b2d45470eb180a1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id serial event_id created_at \\\n",
"0 5903 NaN 5836 2021-07-16 05:16:57.419565+02:00 \n",
"1 67133 NaN 65652 2023-09-27 02:21:36.573001+02:00 \n",
"2 1874 NaN 1826 2021-07-16 00:02:17.390274+02:00 \n",
"3 5904 NaN 5837 2021-07-16 05:16:57.420302+02:00 \n",
"4 4165 NaN 4106 2021-07-16 03:53:05.929713+02:00 \n",
"\n",
" updated_at start_date_time open \\\n",
"0 2021-07-16 05:16:57.419565+02:00 2019-08-24 18:00:00+02:00 True \n",
"1 2023-09-27 02:21:36.573001+02:00 2023-10-04 10:30:00+02:00 True \n",
"2 2021-07-16 00:02:17.390274+02:00 2019-09-14 18:00:00+02:00 True \n",
"3 2021-07-16 05:16:57.420302+02:00 2019-09-01 17:05:00+02:00 True \n",
"4 2021-07-16 03:53:05.929713+02:00 2018-10-14 14:00:00+02:00 True \n",
"\n",
" satisfaction end_date_time name is_display \\\n",
"0 NaN 1901-01-01 00:09:21+00:09 NaN True \n",
"1 NaN 1901-01-01 00:09:21+00:09 NaN True \n",
"2 NaN 1901-01-01 00:09:21+00:09 NaN True \n",
"3 NaN 1901-01-01 00:09:21+00:09 NaN True \n",
"4 NaN 1901-01-01 00:09:21+00:09 NaN True \n",
"\n",
" representation_type_id expected_filling max_filling extra_field \\\n",
"0 NaN NaN NaN NaN \n",
"1 NaN NaN NaN NaN \n",
"2 NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN \n",
"\n",
" identifier \n",
"0 8009c34cae4e79e3781f16f3ceeab244 \n",
"1 4e9d3fc8d1f7bf563dc586548fe6390e \n",
"2 19f666370c1fc781dff638c20ae04c8a \n",
"3 4221acd3f49179f5d0b292c15d1ab8e4 \n",
"4 733104286519c0614b2d45470eb180a1 "
]
},
"execution_count": 296,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"representations = display_databases(\"8representations.csv\")\n",
"representations.head()"
]
},
{
"cell_type": "code",
"execution_count": 297,
"id": "0f2c7ea3-6964-48fd-9411-17547b2c3a3f",
"metadata": {},
"outputs": [],
"source": [
"#representation_type = display_databases(\"8representation_types.csv\")"
]
},
{
"cell_type": "markdown",
"id": "a9b02406-2a69-4431-8d49-3c6bd6a5e1c7",
"metadata": {},
"source": [
"#### Analyze type of events"
]
},
{
"cell_type": "markdown",
"id": "1d554266-282c-4f64-9a0f-ddcf591ec912",
"metadata": {},
"source": [
"Meaning events.csv, event_types.csv, seasons.csv and facilities.csv"
]
},
{
"cell_type": "code",
"execution_count": 298,
"id": "cba22ee2-338d-4ce1-a1e8-829a11a94bcf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8events.csv\n",
"Shape : (922, 12)\n"
]
},
{
"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>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>name</th>\n",
" <th>event_type_id</th>\n",
" <th>manual_added</th>\n",
" <th>is_display</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>41542</td>\n",
" <td>2022-10-29 02:54:32.756920+02:00</td>\n",
" <td>2022-10-29 02:57:35.511792+02:00</td>\n",
" <td>52</td>\n",
" <td>1</td>\n",
" <td>match lou feminin - lons</td>\n",
" <td>5588</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>5588</td>\n",
" <td>1</td>\n",
" <td>40cc5a346b1af4ee7108ac28b144fb77</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>21068</td>\n",
" <td>2021-12-17 03:43:53.166446+01:00</td>\n",
" <td>2021-12-17 03:46:40.346096+01:00</td>\n",
" <td>51</td>\n",
" <td>1</td>\n",
" <td>repas brasserie lou-racing</td>\n",
" <td>2310</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>2310</td>\n",
" <td>1</td>\n",
" <td>500b670b79aa592ecb06f4957800a752</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>59812</td>\n",
" <td>2023-05-26 01:45:54.321665+02:00</td>\n",
" <td>2023-05-26 01:46:01.571397+02:00</td>\n",
" <td>1501</td>\n",
" <td>2</td>\n",
" <td>parking match 2</td>\n",
" <td>10185</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>10185</td>\n",
" <td>2</td>\n",
" <td>d5f62ed879867b8b51ed7b85f1fc3ab0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3424</td>\n",
" <td>2021-07-16 03:13:06.988358+02:00</td>\n",
" <td>2021-07-16 05:33:31.321933+02:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>rugby + hockey sur glace</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>822b47176c355a647aa2dbdf8dfbc594</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>21379</td>\n",
" <td>2021-12-23 02:37:22.948114+01:00</td>\n",
" <td>2021-12-23 02:38:20.726329+01:00</td>\n",
" <td>51</td>\n",
" <td>1</td>\n",
" <td>bloc des etudiants lou-racing</td>\n",
" <td>2562</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>2562</td>\n",
" <td>1</td>\n",
" <td>17b91f19c71ff6287ffc1f44af952576</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id created_at updated_at \\\n",
"0 41542 2022-10-29 02:54:32.756920+02:00 2022-10-29 02:57:35.511792+02:00 \n",
"1 21068 2021-12-17 03:43:53.166446+01:00 2021-12-17 03:46:40.346096+01:00 \n",
"2 59812 2023-05-26 01:45:54.321665+02:00 2023-05-26 01:46:01.571397+02:00 \n",
"3 3424 2021-07-16 03:13:06.988358+02:00 2021-07-16 05:33:31.321933+02:00 \n",
"4 21379 2021-12-23 02:37:22.948114+01:00 2021-12-23 02:38:20.726329+01:00 \n",
"\n",
" season_id facility_id name event_type_id \\\n",
"0 52 1 match lou feminin - lons 5588 \n",
"1 51 1 repas brasserie lou-racing 2310 \n",
"2 1501 2 parking match 2 10185 \n",
"3 1 1 rugby + hockey sur glace 5 \n",
"4 51 1 bloc des etudiants lou-racing 2562 \n",
"\n",
" manual_added is_display event_type_key_id facility_key_id \\\n",
"0 False True 5588 1 \n",
"1 False True 2310 1 \n",
"2 False True 10185 2 \n",
"3 False True 5 1 \n",
"4 False True 2562 1 \n",
"\n",
" identifier \n",
"0 40cc5a346b1af4ee7108ac28b144fb77 \n",
"1 500b670b79aa592ecb06f4957800a752 \n",
"2 d5f62ed879867b8b51ed7b85f1fc3ab0 \n",
"3 822b47176c355a647aa2dbdf8dfbc594 \n",
"4 17b91f19c71ff6287ffc1f44af952576 "
]
},
"execution_count": 298,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"events = display_databases(\"8events.csv\")\n",
"events.head()"
]
},
{
"cell_type": "code",
"execution_count": 299,
"id": "3db00b9d-2187-4cb6-980d-8ac6ab9eb460",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8event_types.csv\n",
"Shape : (73, 6)\n"
]
},
{
"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>1</td>\n",
" <td>standard</td>\n",
" <td>2021-06-29 13:52:10.434850+02:00</td>\n",
" <td>2021-06-29 13:52:10.434850+02:00</td>\n",
" <td>36</td>\n",
" <td>c00f0c4675b91fb8b918e4079a0b1bac</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>11</td>\n",
" <td>ptit lou</td>\n",
" <td>2021-06-29 21:33:13.000743+02:00</td>\n",
" <td>2021-06-29 21:33:13.000743+02:00</td>\n",
" <td>36</td>\n",
" <td>dedd3579bc13b3ed7a90277247d9944b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>274</td>\n",
" <td>parking 19-20</td>\n",
" <td>2021-07-16 00:02:17.225410+02:00</td>\n",
" <td>2021-07-16 00:02:17.225410+02:00</td>\n",
" <td>36</td>\n",
" <td>0d348caeec0b66f9d4987dfbe30e1e8b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>129</td>\n",
" <td>events 2018-2019</td>\n",
" <td>2021-06-30 01:35:18.110429+02:00</td>\n",
" <td>2021-06-30 01:35:18.110429+02:00</td>\n",
" <td>36</td>\n",
" <td>65eb39ddf8f79d28d93c2f2c53118f50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>10</td>\n",
" <td>accreditations 2017-2018</td>\n",
" <td>2021-06-29 21:33:12.999510+02:00</td>\n",
" <td>2021-06-29 21:33:12.999510+02:00</td>\n",
" <td>36</td>\n",
" <td>732cfdcf2065fa0005faf42793ddd76c</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 1 standard 2021-06-29 13:52:10.434850+02:00 \n",
"1 11 ptit lou 2021-06-29 21:33:13.000743+02:00 \n",
"2 274 parking 19-20 2021-07-16 00:02:17.225410+02:00 \n",
"3 129 events 2018-2019 2021-06-30 01:35:18.110429+02:00 \n",
"4 10 accreditations 2017-2018 2021-06-29 21:33:12.999510+02:00 \n",
"\n",
" updated_at fidelity_delay \\\n",
"0 2021-06-29 13:52:10.434850+02:00 36 \n",
"1 2021-06-29 21:33:13.000743+02:00 36 \n",
"2 2021-07-16 00:02:17.225410+02:00 36 \n",
"3 2021-06-30 01:35:18.110429+02:00 36 \n",
"4 2021-06-29 21:33:12.999510+02:00 36 \n",
"\n",
" identifier \n",
"0 c00f0c4675b91fb8b918e4079a0b1bac \n",
"1 dedd3579bc13b3ed7a90277247d9944b \n",
"2 0d348caeec0b66f9d4987dfbe30e1e8b \n",
"3 65eb39ddf8f79d28d93c2f2c53118f50 \n",
"4 732cfdcf2065fa0005faf42793ddd76c "
]
},
"execution_count": 299,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"event_types = display_databases(\"8event_types.csv\")\n",
"event_types.head()"
]
},
{
"cell_type": "code",
"execution_count": 300,
"id": "cba0ee58-6280-45fe-99b3-0be09db5922b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8seasons.csv\n",
"Shape : (16, 6)\n"
]
},
{
"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>start_date_time</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1501</td>\n",
" <td>saison 2023-2024</td>\n",
" <td>2022-06-25 03:07:31.209270+02:00</td>\n",
" <td>2022-06-25 03:07:31.209270+02:00</td>\n",
" <td>NaN</td>\n",
" <td>71f5c069ce45c5e933dcc37c22507fbf</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1194</td>\n",
" <td>saison 2049-2050</td>\n",
" <td>2022-02-17 03:24:23.942691+01:00</td>\n",
" <td>2022-02-17 03:24:23.942691+01:00</td>\n",
" <td>NaN</td>\n",
" <td>44e20620bbc5926db2e295d38b606afd</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>saison 2016-2017</td>\n",
" <td>2021-06-29 21:33:00.702563+02:00</td>\n",
" <td>2021-06-29 21:33:00.702563+02:00</td>\n",
" <td>NaN</td>\n",
" <td>f9cf989d4f49300220df67ef93aa2294</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>47</td>\n",
" <td>saison 2018-2019</td>\n",
" <td>2021-06-30 01:35:15.156097+02:00</td>\n",
" <td>2021-06-30 01:35:15.156097+02:00</td>\n",
" <td>NaN</td>\n",
" <td>eec50c35fbf8593b364ced287335d90c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100</td>\n",
" <td>saison 2010-2011</td>\n",
" <td>2021-07-16 00:23:27.607648+02:00</td>\n",
" <td>2021-07-16 00:23:27.607648+02:00</td>\n",
" <td>NaN</td>\n",
" <td>7ccc51049a85e0df9b80662e45b6ddb8</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 1501 saison 2023-2024 2022-06-25 03:07:31.209270+02:00 \n",
"1 1194 saison 2049-2050 2022-02-17 03:24:23.942691+01:00 \n",
"2 2 saison 2016-2017 2021-06-29 21:33:00.702563+02:00 \n",
"3 47 saison 2018-2019 2021-06-30 01:35:15.156097+02:00 \n",
"4 100 saison 2010-2011 2021-07-16 00:23:27.607648+02:00 \n",
"\n",
" updated_at start_date_time \\\n",
"0 2022-06-25 03:07:31.209270+02:00 NaN \n",
"1 2022-02-17 03:24:23.942691+01:00 NaN \n",
"2 2021-06-29 21:33:00.702563+02:00 NaN \n",
"3 2021-06-30 01:35:15.156097+02:00 NaN \n",
"4 2021-07-16 00:23:27.607648+02:00 NaN \n",
"\n",
" identifier \n",
"0 71f5c069ce45c5e933dcc37c22507fbf \n",
"1 44e20620bbc5926db2e295d38b606afd \n",
"2 f9cf989d4f49300220df67ef93aa2294 \n",
"3 eec50c35fbf8593b364ced287335d90c \n",
"4 7ccc51049a85e0df9b80662e45b6ddb8 "
]
},
"execution_count": 300,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"seasons = display_databases(\"8seasons.csv\")\n",
"seasons.head()"
]
},
{
"cell_type": "code",
"execution_count": 301,
"id": "6fa82fd7-d6d3-4857-af24-ea573b1129d0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/8/8facilities.csv\n",
"Shape : (5, 7)\n"
]
},
{
"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>street_id</th>\n",
" <th>fixed_capacity</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>74</td>\n",
" <td>plan pour campagne d'abo 2011/2012</td>\n",
" <td>2021-07-16 00:23:30.337698+02:00</td>\n",
" <td>2021-07-16 00:23:30.337698+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>2e1d25d5f7e46e23c734fe0e4951390e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>accreditation</td>\n",
" <td>2021-06-29 21:33:13.018552+02:00</td>\n",
" <td>2021-06-29 21:33:13.018552+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>da37a04e592cbd344142730ce05a6887</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>organisation match exterieur</td>\n",
" <td>2021-06-29 21:33:13.019878+02:00</td>\n",
" <td>2021-06-29 21:33:13.019878+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>8f9ee8c2e954585f7c68096d7f1cf4f1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>parking matmut stadium</td>\n",
" <td>2021-06-29 21:33:13.017165+02:00</td>\n",
" <td>2021-06-29 21:33:13.017165+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>aeab282982ea738674dbf5c3763a0be0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>matmut stadium</td>\n",
" <td>2021-06-29 21:33:13.004560+02:00</td>\n",
" <td>2021-06-29 21:33:13.004560+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>89feffd283ebdabdc3b81fb62ea4f6f0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 74 plan pour campagne d'abo 2011/2012 2021-07-16 00:23:30.337698+02:00 \n",
"1 3 accreditation 2021-06-29 21:33:13.018552+02:00 \n",
"2 4 organisation match exterieur 2021-06-29 21:33:13.019878+02:00 \n",
"3 2 parking matmut stadium 2021-06-29 21:33:13.017165+02:00 \n",
"4 1 matmut stadium 2021-06-29 21:33:13.004560+02:00 \n",
"\n",
" updated_at street_id fixed_capacity \\\n",
"0 2021-07-16 00:23:30.337698+02:00 1 NaN \n",
"1 2021-06-29 21:33:13.018552+02:00 1 NaN \n",
"2 2021-06-29 21:33:13.019878+02:00 1 NaN \n",
"3 2021-06-29 21:33:13.017165+02:00 1 NaN \n",
"4 2021-06-29 21:33:13.004560+02:00 1 NaN \n",
"\n",
" identifier \n",
"0 2e1d25d5f7e46e23c734fe0e4951390e \n",
"1 da37a04e592cbd344142730ce05a6887 \n",
"2 8f9ee8c2e954585f7c68096d7f1cf4f1 \n",
"3 aeab282982ea738674dbf5c3763a0be0 \n",
"4 89feffd283ebdabdc3b81fb62ea4f6f0 "
]
},
"execution_count": 301,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"facilities = display_databases(\"8facilities.csv\")\n",
"facilities.head()"
]
},
{
"cell_type": "markdown",
"id": "c7467d41-0ded-465d-bb08-15be914a166b",
"metadata": {},
"source": [
"#### Analyze annexe databases"
]
},
{
"cell_type": "markdown",
"id": "17e9e334-0ae4-48d8-bed5-b50b4af49d5b",
"metadata": {},
"source": [
"Meaning contributions.csv, contribution_sites.csv, currencies.csv, countries.csv and type_ofs.csc"
]
},
{
"cell_type": "markdown",
"id": "d3ec1040-48b2-40bb-8947-920ddb4589f3",
"metadata": {},
"source": [
"## II. Identify Commons Datasets"
]
},
{
"cell_type": "markdown",
"id": "ec528a8a-df38-48e2-a1be-4a1459a80a1e",
"metadata": {},
"source": [
"From the analyze of the 8th company, we notice that some databases does not exist. Therefore, in order to construct a uniform database for all companies, we should first identify the common databases between all companies"
]
},
{
"cell_type": "code",
"execution_count": 302,
"id": "c240b811-48a6-4501-9e70-bc51d69e3ac4",
"metadata": {},
"outputs": [],
"source": [
"## We first construct a dictionary reporting all the datasets for each companies\n",
"\n",
"companies = fs.ls(BUCKET)\n",
"companies_database = {}\n",
"\n",
"for company in companies:\n",
" companies_database[company.split('/')[-1]] = [file.split('/')[-1].replace(company.split('/')[-1], '') for file in fs.ls(company)] \n"
]
},
{
"cell_type": "code",
"execution_count": 303,
"id": "54057367-9df9-42f4-aa07-bf524bb76462",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of databases : 30\n"
]
}
],
"source": [
"# Then we create a list of all database\n",
"\n",
"all_database = companies_database[max(companies_database, key=lambda x: len(companies_database[x]))]\n",
"print(\"Number of databases : \",len(all_database))"
]
},
{
"cell_type": "code",
"execution_count": 304,
"id": "63914e20-9efc-4088-877b-edab5f225d00",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"30\n",
"23\n"
]
}
],
"source": [
"## We then create a set of database in common for all companies\n",
"\n",
"data_in_common = set(all_database)\n",
"\n",
"print(len(data_in_common))\n",
"\n",
"for key in companies_database:\n",
" diff_database = data_in_common.symmetric_difference(companies_database[key])\n",
" data_in_common = data_in_common - diff_database\n",
"\n",
"print(len(data_in_common))\n",
" "
]
},
{
"cell_type": "markdown",
"id": "676d8536-7d8c-4075-a357-b8d06e501ca8",
"metadata": {},
"source": [
"## Create Universal database"
]
},
{
"cell_type": "markdown",
"id": "7e460fbe-5067-4998-a1a8-9e3d07401750",
"metadata": {},
"source": [
"We will first create a procedure to clean the datasets of a company and then merge them. Hence, we will be able to replicate this procedure for all companies and create a universal database.\n",
"\n",
"Let's first create our procedure for the company 1 and the datasets belongings to the theme producst"
]
},
{
"cell_type": "code",
"execution_count": 305,
"id": "590a132a-4f57-4ea3-a282-2ef913e4b753",
"metadata": {},
"outputs": [],
"source": [
"directory_path = '1'"
]
},
{
"cell_type": "code",
"execution_count": 306,
"id": "0fbebfb7-a827-46b1-890b-86c9def7cdbb",
"metadata": {},
"outputs": [],
"source": [
"theme_products = [\"products.csv\" ,\"categories.csv\", \"type_of_categories.csv\"]"
]
},
{
"cell_type": "code",
"execution_count": 307,
"id": "b8aa5f8f-845e-4ee5-b80d-38b7061a94a2",
"metadata": {},
"outputs": [],
"source": [
"def remove_horodates(df):\n",
" \"\"\"\n",
" this function remove horodate columns like created_at and updated_at\n",
" \"\"\"\n",
" df = df.drop(columns = [\"created_at\", \"updated_at\"])\n",
" return df"
]
},
{
"cell_type": "code",
"execution_count": 308,
"id": "2c478213-09ae-44ef-8c7c-125bcb571642",
"metadata": {},
"outputs": [],
"source": [
"def order_columns_id(df):\n",
" \"\"\"\n",
" this function puts all id columns at the beginning in order to read the dataset easier\n",
" \"\"\"\n",
" substring = 'id'\n",
" id_columns = [col for col in df.columns if substring in col]\n",
" remaining_col = [col for col in df.columns if substring not in col]\n",
" new_order = id_columns + remaining_col\n",
" return df[new_order]"
]
},
{
"cell_type": "code",
"execution_count": 309,
"id": "327e44b0-eb99-4022-b4ca-79548072f0f0",
"metadata": {},
"outputs": [],
"source": [
"def percent_na(df):\n",
" \"\"\"\n",
" this function returns the percentage of na for each column\n",
" \"\"\"\n",
" percent_missing = df.isna().sum() * 100 / len(df)\n",
" return percent_missing"
]
},
{
"cell_type": "code",
"execution_count": 310,
"id": "10926def-267f-4e86-b2c9-72e27ff9a9df",
"metadata": {},
"outputs": [],
"source": [
"def process_df(df):\n",
" df = remove_horodates(df)\n",
" print(\"Number of columns : \", len(df.columns))\n",
" df = order_columns_id(df)\n",
" print(\"Columns : \", df.columns)\n",
" print(\"Percent of NA for each column : \", percent_na(df))\n",
" return df"
]
},
{
"cell_type": "markdown",
"id": "98ac02cb-5295-47ca-99c6-99e622c5f388",
"metadata": {},
"source": [
"#### Deep analysis of products.csv"
]
},
{
"cell_type": "code",
"execution_count": 311,
"id": "862a7658-0602-4d94-bb58-d23774c00d32",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1products.csv\n",
"Shape : (94803, 14)\n",
"Number of columns : 14\n"
]
},
{
"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>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</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</th>\n",
" <th>amount_consumption</th>\n",
" <th>identifier</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",
" </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",
" </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",
" </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",
" </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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id amount is_full_price representation_id pricing_formula_id \\\n",
"0 10682 9.0 False 914 114 \n",
"1 478 9.5 False 273 131 \n",
"2 20873 11.5 False 275 137 \n",
"3 157142 8.0 False 82519 9 \n",
"4 1341 8.5 False 9 93 \n",
"\n",
" created_at updated_at \\\n",
"0 2020-09-03 14:09:43.119798+02:00 2020-09-03 14:09:43.119798+02:00 \n",
"1 2020-09-03 13:21:22.711773+02:00 2020-09-03 13:21:22.711773+02:00 \n",
"2 2020-09-03 14:46:33.589030+02:00 2020-09-03 14:46:33.589030+02:00 \n",
"3 2022-01-28 19:29:23.525722+01:00 2022-01-28 19:29:23.525722+01:00 \n",
"4 2020-09-03 13:29:30.773089+02:00 2020-09-03 13:29:30.773089+02:00 \n",
"\n",
" category_id apply_price products_group_id product_pack_id extra_field \\\n",
"0 41 0.0 10655 1 NaN \n",
"1 1 0.0 471 1 NaN \n",
"2 1 0.0 20825 1 NaN \n",
"3 5 0.0 156773 1 NaN \n",
"4 1 0.0 1175 1 NaN \n",
"\n",
" amount_consumption identifier \n",
"0 NaN 35c88f2db8a63d7474e46eb8ca9260e7 \n",
"1 NaN 8a179671ab198e570e6a104c4451379f \n",
"2 NaN ee83779ce29e67ad251e40234b426d6a \n",
"3 NaN d865383579314b791aa4bcf3fb418f17 \n",
"4 NaN f1c4689bc47dee6f60b56d74b593dd46 "
]
},
"execution_count": 311,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products = display_databases(\"1products.csv\")\n",
"print(\"Number of columns : \", len(products.columns))\n",
"products.head()"
]
},
{
"cell_type": "code",
"execution_count": 312,
"id": "f0db8c51-2792-4d49-9b1a-d98ce0d9ea28",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 12\n",
"Columns : Index(['id', 'representation_id', 'pricing_formula_id', 'category_id',\n",
" 'products_group_id', 'product_pack_id', 'identifier', 'amount',\n",
" 'is_full_price', 'apply_price', 'extra_field', 'amount_consumption'],\n",
" dtype='object')\n"
]
},
{
"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>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>category_id</th>\n",
" <th>products_group_id</th>\n",
" <th>product_pack_id</th>\n",
" <th>identifier</th>\n",
" <th>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>apply_price</th>\n",
" <th>extra_field</th>\n",
" <th>amount_consumption</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10682</td>\n",
" <td>914</td>\n",
" <td>114</td>\n",
" <td>41</td>\n",
" <td>10655</td>\n",
" <td>1</td>\n",
" <td>35c88f2db8a63d7474e46eb8ca9260e7</td>\n",
" <td>9.0</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>478</td>\n",
" <td>273</td>\n",
" <td>131</td>\n",
" <td>1</td>\n",
" <td>471</td>\n",
" <td>1</td>\n",
" <td>8a179671ab198e570e6a104c4451379f</td>\n",
" <td>9.5</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20873</td>\n",
" <td>275</td>\n",
" <td>137</td>\n",
" <td>1</td>\n",
" <td>20825</td>\n",
" <td>1</td>\n",
" <td>ee83779ce29e67ad251e40234b426d6a</td>\n",
" <td>11.5</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>157142</td>\n",
" <td>82519</td>\n",
" <td>9</td>\n",
" <td>5</td>\n",
" <td>156773</td>\n",
" <td>1</td>\n",
" <td>d865383579314b791aa4bcf3fb418f17</td>\n",
" <td>8.0</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1341</td>\n",
" <td>9</td>\n",
" <td>93</td>\n",
" <td>1</td>\n",
" <td>1175</td>\n",
" <td>1</td>\n",
" <td>f1c4689bc47dee6f60b56d74b593dd46</td>\n",
" <td>8.5</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id representation_id pricing_formula_id category_id \\\n",
"0 10682 914 114 41 \n",
"1 478 273 131 1 \n",
"2 20873 275 137 1 \n",
"3 157142 82519 9 5 \n",
"4 1341 9 93 1 \n",
"\n",
" products_group_id product_pack_id identifier \\\n",
"0 10655 1 35c88f2db8a63d7474e46eb8ca9260e7 \n",
"1 471 1 8a179671ab198e570e6a104c4451379f \n",
"2 20825 1 ee83779ce29e67ad251e40234b426d6a \n",
"3 156773 1 d865383579314b791aa4bcf3fb418f17 \n",
"4 1175 1 f1c4689bc47dee6f60b56d74b593dd46 \n",
"\n",
" amount is_full_price apply_price extra_field amount_consumption \n",
"0 9.0 False 0.0 NaN NaN \n",
"1 9.5 False 0.0 NaN NaN \n",
"2 11.5 False 0.0 NaN NaN \n",
"3 8.0 False 0.0 NaN NaN \n",
"4 8.5 False 0.0 NaN NaN "
]
},
"execution_count": 312,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products = remove_horodates(products)\n",
"print(\"Number of columns : \", len(products.columns))\n",
"products = order_columns_id(products)\n",
"print(\"Columns : \", products.columns)\n",
"products.head()"
]
},
{
"cell_type": "code",
"execution_count": 313,
"id": "a383474f-7da9-422c-bb69-3f0cc0b7053f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"id int64\n",
"representation_id int64\n",
"pricing_formula_id int64\n",
"category_id int64\n",
"products_group_id int64\n",
"product_pack_id int64\n",
"identifier object\n",
"amount float64\n",
"is_full_price bool\n",
"apply_price float64\n",
"extra_field float64\n",
"amount_consumption float64\n",
"dtype: object\n"
]
}
],
"source": [
"print(products.dtypes)"
]
},
{
"cell_type": "code",
"execution_count": 314,
"id": "460749ac-aa26-4216-8667-518546f72f72",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"id 0.0\n",
"representation_id 0.0\n",
"pricing_formula_id 0.0\n",
"category_id 0.0\n",
"products_group_id 0.0\n",
"product_pack_id 0.0\n",
"identifier 0.0\n",
"amount 0.0\n",
"is_full_price 0.0\n",
"apply_price 0.0\n",
"extra_field 100.0\n",
"amount_consumption 100.0\n",
"dtype: float64\n"
]
}
],
"source": [
"percent_missing = products.isna().sum() * 100 / len(products)\n",
"print(percent_missing)"
]
},
{
"cell_type": "markdown",
"id": "ebcb48ab-adad-42e5-b5d7-7275771cd200",
"metadata": {},
"source": [
"#### Deep analysis of categories.csv"
]
},
{
"cell_type": "code",
"execution_count": 315,
"id": "3efce2b6-2d2f-4da9-98ed-1aae17da624c",
"metadata": {},
"outputs": [],
"source": [
"name_dataset = '1categories.csv'"
]
},
{
"cell_type": "code",
"execution_count": 316,
"id": "38aa39fd-58af-4fb8-98f2-4269dbaf35de",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1categories.csv\n",
"Shape : (27, 7)\n",
"Number of columns : 7\n"
]
},
{
"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>quota</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>30</td>\n",
" <td>en nb entrées gr</td>\n",
" <td>2020-09-03 13:21:20.019202+02:00</td>\n",
" <td>2020-09-03 13:21:20.019202+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>849ab2791a14f5fc2bb4d87ab2b78bf6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>16</td>\n",
" <td>indiv activité enfant</td>\n",
" <td>2020-09-03 13:11:23.306968+02:00</td>\n",
" <td>2020-09-03 13:11:23.306968+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>425fd2f01984cc4ba030c1be98f42c33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>39</td>\n",
" <td>indiv activité gr</td>\n",
" <td>2020-09-03 13:21:20.029901+02:00</td>\n",
" <td>2020-09-03 13:21:20.029901+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>9244dd3738788db0d22a5d0afe687b69</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1108</td>\n",
" <td>groupe forfait adulte</td>\n",
" <td>2020-09-19 02:06:43.145697+02:00</td>\n",
" <td>2020-09-19 02:06:43.145697+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3edda20c877a93b5ff883827238eb711</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6</td>\n",
" <td>groupe forfait entrées tr</td>\n",
" <td>2020-09-03 13:11:23.264997+02:00</td>\n",
" <td>2020-09-03 13:11:23.264997+02:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>ff48df4b2dd5a14116bf4d280b31621e</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 30 en nb entrées gr 2020-09-03 13:21:20.019202+02:00 \n",
"1 16 indiv activité enfant 2020-09-03 13:11:23.306968+02:00 \n",
"2 39 indiv activité gr 2020-09-03 13:21:20.029901+02:00 \n",
"3 1108 groupe forfait adulte 2020-09-19 02:06:43.145697+02:00 \n",
"4 6 groupe forfait entrées tr 2020-09-03 13:11:23.264997+02:00 \n",
"\n",
" updated_at extra_field quota \\\n",
"0 2020-09-03 13:21:20.019202+02:00 NaN NaN \n",
"1 2020-09-03 13:11:23.306968+02:00 NaN NaN \n",
"2 2020-09-03 13:21:20.029901+02:00 NaN NaN \n",
"3 2020-09-19 02:06:43.145697+02:00 NaN NaN \n",
"4 2020-09-03 13:11:23.264997+02:00 NaN NaN \n",
"\n",
" identifier \n",
"0 849ab2791a14f5fc2bb4d87ab2b78bf6 \n",
"1 425fd2f01984cc4ba030c1be98f42c33 \n",
"2 9244dd3738788db0d22a5d0afe687b69 \n",
"3 3edda20c877a93b5ff883827238eb711 \n",
"4 ff48df4b2dd5a14116bf4d280b31621e "
]
},
"execution_count": 316,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = display_databases(name_dataset)\n",
"print(\"Number of columns : \", len(df.columns))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 317,
"id": "99eb6d14-8b4b-4d55-8fc7-ddf2726096f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 5\n",
"Columns : Index(['id', 'identifier', 'name', 'extra_field', 'quota'], dtype='object')\n",
"Percent of NA for each column : id 0.000000\n",
"identifier 0.000000\n",
"name 3.703704\n",
"extra_field 100.000000\n",
"quota 100.000000\n",
"dtype: float64\n"
]
},
{
"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>identifier</th>\n",
" <th>name</th>\n",
" <th>extra_field</th>\n",
" <th>quota</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>30</td>\n",
" <td>849ab2791a14f5fc2bb4d87ab2b78bf6</td>\n",
" <td>en nb entrées gr</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>16</td>\n",
" <td>425fd2f01984cc4ba030c1be98f42c33</td>\n",
" <td>indiv activité enfant</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>39</td>\n",
" <td>9244dd3738788db0d22a5d0afe687b69</td>\n",
" <td>indiv activité gr</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1108</td>\n",
" <td>3edda20c877a93b5ff883827238eb711</td>\n",
" <td>groupe forfait adulte</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6</td>\n",
" <td>ff48df4b2dd5a14116bf4d280b31621e</td>\n",
" <td>groupe forfait entrées tr</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id identifier name \\\n",
"0 30 849ab2791a14f5fc2bb4d87ab2b78bf6 en nb entrées gr \n",
"1 16 425fd2f01984cc4ba030c1be98f42c33 indiv activité enfant \n",
"2 39 9244dd3738788db0d22a5d0afe687b69 indiv activité gr \n",
"3 1108 3edda20c877a93b5ff883827238eb711 groupe forfait adulte \n",
"4 6 ff48df4b2dd5a14116bf4d280b31621e groupe forfait entrées tr \n",
"\n",
" extra_field quota \n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN "
]
},
"execution_count": 317,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = process_df(df)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 318,
"id": "c5f39cc9-dff8-452c-9a3e-9f7df81a8a19",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id int64\n",
"identifier object\n",
"name object\n",
"extra_field float64\n",
"quota float64\n",
"dtype: object"
]
},
"execution_count": 318,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "markdown",
"id": "c4cb0b37-2262-45c0-97be-b12c503016e3",
"metadata": {},
"source": [
"#### Deep analysis of type_of_categories.csv"
]
},
{
"cell_type": "markdown",
"id": "3b4a3af9-ed12-43ec-b17e-fd425b238265",
"metadata": {},
"source": [
"#### Deep analysis of representation_category_capacities.csv"
]
},
{
"cell_type": "markdown",
"id": "135966fb-aab1-48d7-bb4c-39a53ee643ca",
"metadata": {},
"source": [
"#### Deep analysis of representations.csv"
]
},
{
"cell_type": "markdown",
"id": "b480f39f-d5c7-4ded-8f64-ea8ac31f5db5",
"metadata": {},
"source": [
"#### Deep analysis of events.csv"
]
},
{
"cell_type": "code",
"execution_count": 319,
"id": "2d52d6da-cca5-4abd-be05-2f00fd3eca8e",
"metadata": {},
"outputs": [],
"source": [
"name_dataset = '1events.csv'"
]
},
{
"cell_type": "code",
"execution_count": 320,
"id": "6cab507d-8b11-404d-9286-5cc205228af9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1events.csv\n",
"Shape : (1232, 12)\n",
"Number of columns : 12\n"
]
},
{
"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>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>name</th>\n",
" <th>event_type_id</th>\n",
" <th>manual_added</th>\n",
" <th>is_display</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>192</td>\n",
" <td>2020-09-03 13:36:42.216991+02:00</td>\n",
" <td>2021-11-02 15:06:40.663219+01:00</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>frontières</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>c1cecd093146068fd57896e254e98170</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>30329</td>\n",
" <td>2023-11-04 02:50:34.602462+01:00</td>\n",
" <td>2023-11-04 02:52:26.138154+01:00</td>\n",
" <td>2767</td>\n",
" <td>1</td>\n",
" <td>visite guidée une autre histoire du monde (1h00)</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>f510a6710878d7aca36e71c54abab525</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>161</td>\n",
" <td>2020-09-03 13:29:27.944002+02:00</td>\n",
" <td>2021-11-02 15:06:40.652026+01:00</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>visite contée les chercheurs d'or indiv</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>21177fa9acad1ae2b1f595690fb853d3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5957</td>\n",
" <td>2021-07-31 11:16:42.575583+02:00</td>\n",
" <td>2021-11-02 15:06:40.663219+01:00</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>we dreamt of utopia and we woke up screaming.</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>962601f1eb153d45d49437f8fe839f7f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>8337</td>\n",
" <td>2021-08-17 13:40:34.111923+02:00</td>\n",
" <td>2021-11-02 15:06:40.663219+01:00</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>jeff koons épisodes 4</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>bfa22f5a2364a2dacfc45cca1c8d3215</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id created_at updated_at \\\n",
"0 192 2020-09-03 13:36:42.216991+02:00 2021-11-02 15:06:40.663219+01:00 \n",
"1 30329 2023-11-04 02:50:34.602462+01:00 2023-11-04 02:52:26.138154+01:00 \n",
"2 161 2020-09-03 13:29:27.944002+02:00 2021-11-02 15:06:40.652026+01:00 \n",
"3 5957 2021-07-31 11:16:42.575583+02:00 2021-11-02 15:06:40.663219+01:00 \n",
"4 8337 2021-08-17 13:40:34.111923+02:00 2021-11-02 15:06:40.663219+01:00 \n",
"\n",
" season_id facility_id name \\\n",
"0 16 1 frontières \n",
"1 2767 1 visite guidée une autre histoire du monde (1h00) \n",
"2 16 1 visite contée les chercheurs d'or indiv \n",
"3 582 1 we dreamt of utopia and we woke up screaming. \n",
"4 582 1 jeff koons épisodes 4 \n",
"\n",
" event_type_id manual_added is_display event_type_key_id \\\n",
"0 4 False True 4 \n",
"1 5 False True 5 \n",
"2 2 False True 2 \n",
"3 4 False True 4 \n",
"4 4 False True 4 \n",
"\n",
" facility_key_id identifier \n",
"0 1 c1cecd093146068fd57896e254e98170 \n",
"1 1 f510a6710878d7aca36e71c54abab525 \n",
"2 1 21177fa9acad1ae2b1f595690fb853d3 \n",
"3 1 962601f1eb153d45d49437f8fe839f7f \n",
"4 1 bfa22f5a2364a2dacfc45cca1c8d3215 "
]
},
"execution_count": 320,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = display_databases(name_dataset)\n",
"print(\"Number of columns : \", len(df.columns))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 321,
"id": "9fe57873-8108-44c9-b8a5-f58d3cbb6d17",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 10\n",
"Columns : Index(['id', 'season_id', 'facility_id', 'event_type_id', 'event_type_key_id',\n",
" 'facility_key_id', 'identifier', 'name', 'manual_added', 'is_display'],\n",
" dtype='object')\n",
"Percent of NA for each column : id 0.000000\n",
"season_id 0.000000\n",
"facility_id 0.000000\n",
"event_type_id 0.000000\n",
"event_type_key_id 0.000000\n",
"facility_key_id 0.000000\n",
"identifier 0.000000\n",
"name 0.974026\n",
"manual_added 0.000000\n",
"is_display 0.000000\n",
"dtype: float64\n"
]
},
{
"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>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>event_type_id</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>identifier</th>\n",
" <th>name</th>\n",
" <th>manual_added</th>\n",
" <th>is_display</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>192</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>c1cecd093146068fd57896e254e98170</td>\n",
" <td>frontières</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>30329</td>\n",
" <td>2767</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>f510a6710878d7aca36e71c54abab525</td>\n",
" <td>visite guidée une autre histoire du monde (1h00)</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>161</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>21177fa9acad1ae2b1f595690fb853d3</td>\n",
" <td>visite contée les chercheurs d'or indiv</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5957</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>962601f1eb153d45d49437f8fe839f7f</td>\n",
" <td>we dreamt of utopia and we woke up screaming.</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>8337</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>bfa22f5a2364a2dacfc45cca1c8d3215</td>\n",
" <td>jeff koons épisodes 4</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id season_id facility_id event_type_id event_type_key_id \\\n",
"0 192 16 1 4 4 \n",
"1 30329 2767 1 5 5 \n",
"2 161 16 1 2 2 \n",
"3 5957 582 1 4 4 \n",
"4 8337 582 1 4 4 \n",
"\n",
" facility_key_id identifier \\\n",
"0 1 c1cecd093146068fd57896e254e98170 \n",
"1 1 f510a6710878d7aca36e71c54abab525 \n",
"2 1 21177fa9acad1ae2b1f595690fb853d3 \n",
"3 1 962601f1eb153d45d49437f8fe839f7f \n",
"4 1 bfa22f5a2364a2dacfc45cca1c8d3215 \n",
"\n",
" name manual_added is_display \n",
"0 frontières False True \n",
"1 visite guidée une autre histoire du monde (1h00) False True \n",
"2 visite contée les chercheurs d'or indiv False True \n",
"3 we dreamt of utopia and we woke up screaming. False True \n",
"4 jeff koons épisodes 4 False True "
]
},
"execution_count": 321,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = process_df(df)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 322,
"id": "7fd9e5bd-baac-4b3b-9ffb-5a9baa18399b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id int64\n",
"season_id int64\n",
"facility_id int64\n",
"event_type_id int64\n",
"event_type_key_id int64\n",
"facility_key_id int64\n",
"identifier object\n",
"name object\n",
"manual_added bool\n",
"is_display bool\n",
"dtype: object"
]
},
"execution_count": 322,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "markdown",
"id": "24186efa-5908-4b03-bf52-96415fc8bd54",
"metadata": {},
"source": [
"#### Deep analysis of event_types.csv"
]
},
{
"cell_type": "code",
"execution_count": 323,
"id": "90ab62d4-a086-4469-961c-67eefb375388",
"metadata": {},
"outputs": [],
"source": [
"name_dataset = '1event_types.csv'"
]
},
{
"cell_type": "code",
"execution_count": 324,
"id": "58db1751-fd56-4c28-b49e-bc8235bb0dc8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1event_types.csv\n",
"Shape : (9, 6)\n",
"Number of columns : 6\n"
]
},
{
"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>1</td>\n",
" <td>standard</td>\n",
" <td>2020-09-03 12:24:22.574262+02:00</td>\n",
" <td>2020-09-03 12:24:22.574262+02:00</td>\n",
" <td>36</td>\n",
" <td>c00f0c4675b91fb8b918e4079a0b1bac</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>66</td>\n",
" <td>package</td>\n",
" <td>2020-09-03 14:05:04.648137+02:00</td>\n",
" <td>2020-09-03 14:05:04.648137+02:00</td>\n",
" <td>36</td>\n",
" <td>efe90a8e604a7c840e88d03a67f6b7d8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>83</td>\n",
" <td>guide multimédias</td>\n",
" <td>2020-09-03 14:15:17.252539+02:00</td>\n",
" <td>2020-09-03 14:15:17.252539+02:00</td>\n",
" <td>36</td>\n",
" <td>ee14c62b3b9f6c7dd5401685a18e4460</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>non défini</td>\n",
" <td>2020-09-03 13:11:23.117024+02:00</td>\n",
" <td>2020-09-03 13:11:23.117024+02:00</td>\n",
" <td>36</td>\n",
" <td>52ff3466787b4d538407372e5f7afe0f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2723</td>\n",
" <td>NaN</td>\n",
" <td>2021-12-22 09:45:47.715105+01:00</td>\n",
" <td>2021-12-22 09:45:47.715105+01:00</td>\n",
" <td>36</td>\n",
" <td>d41d8cd98f00b204e9800998ecf8427e</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 1 standard 2020-09-03 12:24:22.574262+02:00 \n",
"1 66 package 2020-09-03 14:05:04.648137+02:00 \n",
"2 83 guide multimédias 2020-09-03 14:15:17.252539+02:00 \n",
"3 3 non défini 2020-09-03 13:11:23.117024+02:00 \n",
"4 2723 NaN 2021-12-22 09:45:47.715105+01:00 \n",
"\n",
" updated_at fidelity_delay \\\n",
"0 2020-09-03 12:24:22.574262+02:00 36 \n",
"1 2020-09-03 14:05:04.648137+02:00 36 \n",
"2 2020-09-03 14:15:17.252539+02:00 36 \n",
"3 2020-09-03 13:11:23.117024+02:00 36 \n",
"4 2021-12-22 09:45:47.715105+01:00 36 \n",
"\n",
" identifier \n",
"0 c00f0c4675b91fb8b918e4079a0b1bac \n",
"1 efe90a8e604a7c840e88d03a67f6b7d8 \n",
"2 ee14c62b3b9f6c7dd5401685a18e4460 \n",
"3 52ff3466787b4d538407372e5f7afe0f \n",
"4 d41d8cd98f00b204e9800998ecf8427e "
]
},
"execution_count": 324,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = display_databases(name_dataset)\n",
"print(\"Number of columns : \", len(df.columns))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 325,
"id": "ac93382c-0b5f-462d-8021-0dd1e7201b8c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 4\n",
"Columns : Index(['id', 'fidelity_delay', 'identifier', 'name'], dtype='object')\n",
"Percent of NA for each column : id 0.000000\n",
"fidelity_delay 0.000000\n",
"identifier 0.000000\n",
"name 11.111111\n",
"dtype: float64\n"
]
},
{
"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>fidelity_delay</th>\n",
" <th>identifier</th>\n",
" <th>name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>36</td>\n",
" <td>c00f0c4675b91fb8b918e4079a0b1bac</td>\n",
" <td>standard</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>66</td>\n",
" <td>36</td>\n",
" <td>efe90a8e604a7c840e88d03a67f6b7d8</td>\n",
" <td>package</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>83</td>\n",
" <td>36</td>\n",
" <td>ee14c62b3b9f6c7dd5401685a18e4460</td>\n",
" <td>guide multimédias</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>36</td>\n",
" <td>52ff3466787b4d538407372e5f7afe0f</td>\n",
" <td>non défini</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2723</td>\n",
" <td>36</td>\n",
" <td>d41d8cd98f00b204e9800998ecf8427e</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id fidelity_delay identifier name\n",
"0 1 36 c00f0c4675b91fb8b918e4079a0b1bac standard\n",
"1 66 36 efe90a8e604a7c840e88d03a67f6b7d8 package\n",
"2 83 36 ee14c62b3b9f6c7dd5401685a18e4460 guide multimédias\n",
"3 3 36 52ff3466787b4d538407372e5f7afe0f non défini\n",
"4 2723 36 d41d8cd98f00b204e9800998ecf8427e NaN"
]
},
"execution_count": 325,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = process_df(df)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 326,
"id": "18cbd630-3c7d-49e1-932b-9460badf3758",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id int64\n",
"fidelity_delay int64\n",
"identifier object\n",
"name object\n",
"dtype: object"
]
},
"execution_count": 326,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "markdown",
"id": "5847a441-31b9-4802-a5ae-90d8c6d6e153",
"metadata": {},
"source": [
"#### Deep analysis of seasons.csv"
]
},
{
"cell_type": "code",
"execution_count": 327,
"id": "ae544dcc-f23d-4216-bb5b-597cc1b3765e",
"metadata": {},
"outputs": [],
"source": [
"name_dataset = '1seasons.csv'"
]
},
{
"cell_type": "code",
"execution_count": 328,
"id": "1ac97963-9208-4329-be41-d71a5797487f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1seasons.csv\n",
"Shape : (13, 6)\n",
"Number of columns : 6\n"
]
},
{
"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>start_date_time</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>943</td>\n",
" <td>2013</td>\n",
" <td>2021-07-29 08:55:33.282607+02:00</td>\n",
" <td>2021-07-29 08:55:33.282607+02:00</td>\n",
" <td>NaN</td>\n",
" <td>8038da89e49ac5eabb489cfc6cea9fc1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>129</td>\n",
" <td>2014</td>\n",
" <td>2020-09-03 15:13:08.105567+02:00</td>\n",
" <td>2020-09-03 15:13:08.105567+02:00</td>\n",
" <td>NaN</td>\n",
" <td>cee8d6b7ce52554fd70354e37bbf44a2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>2015</td>\n",
" <td>2020-09-03 13:11:19.405037+02:00</td>\n",
" <td>2020-09-03 13:11:19.405037+02:00</td>\n",
" <td>NaN</td>\n",
" <td>65d2ea03425887a717c435081cfc5dbb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>2016</td>\n",
" <td>2020-09-03 13:11:19.401001+02:00</td>\n",
" <td>2020-09-03 13:11:19.401001+02:00</td>\n",
" <td>NaN</td>\n",
" <td>95192c98732387165bf8e396c0f2dad2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>2017</td>\n",
" <td>2020-09-03 13:11:19.409005+02:00</td>\n",
" <td>2020-09-03 13:11:19.409005+02:00</td>\n",
" <td>NaN</td>\n",
" <td>8d8818c8e140c64c743113f563cf750f</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 943 2013 2021-07-29 08:55:33.282607+02:00 \n",
"1 129 2014 2020-09-03 15:13:08.105567+02:00 \n",
"2 3 2015 2020-09-03 13:11:19.405037+02:00 \n",
"3 2 2016 2020-09-03 13:11:19.401001+02:00 \n",
"4 4 2017 2020-09-03 13:11:19.409005+02:00 \n",
"\n",
" updated_at start_date_time \\\n",
"0 2021-07-29 08:55:33.282607+02:00 NaN \n",
"1 2020-09-03 15:13:08.105567+02:00 NaN \n",
"2 2020-09-03 13:11:19.405037+02:00 NaN \n",
"3 2020-09-03 13:11:19.401001+02:00 NaN \n",
"4 2020-09-03 13:11:19.409005+02:00 NaN \n",
"\n",
" identifier \n",
"0 8038da89e49ac5eabb489cfc6cea9fc1 \n",
"1 cee8d6b7ce52554fd70354e37bbf44a2 \n",
"2 65d2ea03425887a717c435081cfc5dbb \n",
"3 95192c98732387165bf8e396c0f2dad2 \n",
"4 8d8818c8e140c64c743113f563cf750f "
]
},
"execution_count": 328,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = display_databases(name_dataset)\n",
"print(\"Number of columns : \", len(df.columns))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 329,
"id": "b4593d46-105c-47dd-aa71-babd8e63e65b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 4\n",
"Columns : Index(['id', 'identifier', 'name', 'start_date_time'], dtype='object')\n",
"Percent of NA for each column : id 0.000000\n",
"identifier 0.000000\n",
"name 7.692308\n",
"start_date_time 100.000000\n",
"dtype: float64\n"
]
},
{
"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>identifier</th>\n",
" <th>name</th>\n",
" <th>start_date_time</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>943</td>\n",
" <td>8038da89e49ac5eabb489cfc6cea9fc1</td>\n",
" <td>2013</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>129</td>\n",
" <td>cee8d6b7ce52554fd70354e37bbf44a2</td>\n",
" <td>2014</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>65d2ea03425887a717c435081cfc5dbb</td>\n",
" <td>2015</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>95192c98732387165bf8e396c0f2dad2</td>\n",
" <td>2016</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>8d8818c8e140c64c743113f563cf750f</td>\n",
" <td>2017</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id identifier name start_date_time\n",
"0 943 8038da89e49ac5eabb489cfc6cea9fc1 2013 NaN\n",
"1 129 cee8d6b7ce52554fd70354e37bbf44a2 2014 NaN\n",
"2 3 65d2ea03425887a717c435081cfc5dbb 2015 NaN\n",
"3 2 95192c98732387165bf8e396c0f2dad2 2016 NaN\n",
"4 4 8d8818c8e140c64c743113f563cf750f 2017 NaN"
]
},
"execution_count": 329,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = process_df(df)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 330,
"id": "5d3b096d-8e73-4514-94e5-f2dcd4d0a89c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id int64\n",
"identifier object\n",
"name object\n",
"start_date_time float64\n",
"dtype: object"
]
},
"execution_count": 330,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "markdown",
"id": "a7b00bc7-eae6-457c-ac68-a4a55a6d1c8c",
"metadata": {},
"source": [
"#### Deep Analysis of facilities.csv"
]
},
{
"cell_type": "code",
"execution_count": 331,
"id": "d95ef015-d44c-4353-8761-771b910d21c9",
"metadata": {},
"outputs": [],
"source": [
"name_dataset = '1facilities.csv'"
]
},
{
"cell_type": "code",
"execution_count": 332,
"id": "ef5fe794-8df7-4f27-8554-ecdc4074ac0b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1facilities.csv\n",
"Shape : (2, 7)\n",
"Number of columns : 7\n"
]
},
{
"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>street_id</th>\n",
" <th>fixed_capacity</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2</td>\n",
" <td>non défini</td>\n",
" <td>2020-09-03 13:16:35.293111+02:00</td>\n",
" <td>2020-09-03 13:16:35.293111+02:00</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>52ff3466787b4d538407372e5f7afe0f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>mucem</td>\n",
" <td>2020-09-03 13:11:23.133059+02:00</td>\n",
" <td>2020-09-03 13:11:23.133059+02:00</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>702bd76fe3dd5dbcf118a6965a946f54</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name created_at \\\n",
"0 2 non défini 2020-09-03 13:16:35.293111+02:00 \n",
"1 1 mucem 2020-09-03 13:11:23.133059+02:00 \n",
"\n",
" updated_at street_id fixed_capacity \\\n",
"0 2020-09-03 13:16:35.293111+02:00 2 NaN \n",
"1 2020-09-03 13:11:23.133059+02:00 1 NaN \n",
"\n",
" identifier \n",
"0 52ff3466787b4d538407372e5f7afe0f \n",
"1 702bd76fe3dd5dbcf118a6965a946f54 "
]
},
"execution_count": 332,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = display_databases(name_dataset)\n",
"print(\"Number of columns : \", len(df.columns))\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 333,
"id": "e3621201-fab9-49fd-95c1-0b9d5da76e50",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of columns : 5\n",
"Columns : Index(['id', 'street_id', 'identifier', 'name', 'fixed_capacity'], dtype='object')\n",
"Percent of NA for each column : id 0.0\n",
"street_id 0.0\n",
"identifier 0.0\n",
"name 0.0\n",
"fixed_capacity 100.0\n",
"dtype: float64\n"
]
},
{
"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>street_id</th>\n",
" <th>identifier</th>\n",
" <th>name</th>\n",
" <th>fixed_capacity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>52ff3466787b4d538407372e5f7afe0f</td>\n",
" <td>non défini</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>702bd76fe3dd5dbcf118a6965a946f54</td>\n",
" <td>mucem</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id street_id identifier name fixed_capacity\n",
"0 2 2 52ff3466787b4d538407372e5f7afe0f non défini NaN\n",
"1 1 1 702bd76fe3dd5dbcf118a6965a946f54 mucem NaN"
]
},
"execution_count": 333,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = process_df(df)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 334,
"id": "1b198b92-8654-4531-a0dd-8f2e01c2e6c1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id int64\n",
"street_id int64\n",
"identifier object\n",
"name object\n",
"fixed_capacity float64\n",
"dtype: object"
]
},
"execution_count": 334,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "markdown",
"id": "ab5c4c2d-3e04-457d-a183-e173df89b650",
"metadata": {},
"source": [
"## Merge"
]
},
{
"cell_type": "code",
"execution_count": 335,
"id": "43576244-c8cf-4ca0-b056-7aea1fbf0bc7",
"metadata": {},
"outputs": [],
"source": [
"def process_df_2(df):\n",
" df = remove_horodates(df)\n",
" print(\"Number of columns : \", len(df.columns))\n",
" df = order_columns_id(df)\n",
" print(\"Columns : \", df.columns)\n",
" return df"
]
},
{
"cell_type": "code",
"execution_count": 336,
"id": "0fad097e-474c-4af7-b1e1-7d8dda3f09ea",
"metadata": {},
"outputs": [],
"source": [
"def load_dataset(name):\n",
" df = display_databases(name)\n",
" df = process_df_2(df)\n",
" # drop na :\n",
" #df = df.dropna(axis=1, thresh=len(df))\n",
" # if identifier in table : delete it\n",
" if 'identifier' in df.columns:\n",
" df = df.drop(columns = 'identifier')\n",
" return df"
]
},
{
"cell_type": "markdown",
"id": "b60034ef-fdd6-4640-a012-cf74c17b333f",
"metadata": {},
"source": [
"### Products Table"
]
},
{
"cell_type": "code",
"execution_count": 337,
"id": "6213b1eb-c5f8-49dd-ab69-366542380e80",
"metadata": {},
"outputs": [],
"source": [
"def create_products_table():\n",
" # first merge products and categories\n",
" print(\"first merge products and categories\")\n",
" products = load_dataset(\"1products.csv\")\n",
" categories = load_dataset(\"1categories.csv\")\n",
" # Drop useless columns\n",
" products = products.drop(columns = ['apply_price', 'extra_field', 'amount_consumption'])\n",
" categories = categories.drop(columns = ['extra_field', 'quota'])\n",
"\n",
" #Merge\n",
" products_theme = products.merge(categories, how = 'left', left_on = 'category_id',\n",
" right_on = 'id', suffixes=('_products', '_categories'))\n",
" products_theme = products_theme.rename(columns = {\"name\" : \"name_categories\"})\n",
" \n",
" # Second merge products_theme and type of categories\n",
" print(\"Second merge products_theme and type of categories\")\n",
" type_of_categories = load_dataset(\"1type_of_categories.csv\")\n",
" type_of_categories = type_of_categories.drop(columns = 'id')\n",
" products_theme = products_theme.merge(type_of_categories, how = 'left', left_on = 'category_id',\n",
" right_on = 'category_id' )\n",
"\n",
" # Index cleaning\n",
" products_theme = products_theme.drop(columns = ['id_categories'])\n",
" products_theme = order_columns_id(products_theme)\n",
"\n",
" \n",
"\n",
" return products_theme"
]
},
{
"cell_type": "code",
"execution_count": 338,
"id": "b853e020-f73d-44e8-b086-e5548ce21011",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"first merge products and categories\n",
"File path : bdc2324-data/1/1products.csv\n",
"Shape : (94803, 14)\n",
"Number of columns : 12\n",
"Columns : Index(['id', 'representation_id', 'pricing_formula_id', 'category_id',\n",
" 'products_group_id', 'product_pack_id', 'identifier', 'amount',\n",
" 'is_full_price', 'apply_price', 'extra_field', 'amount_consumption'],\n",
" dtype='object')\n",
"File path : bdc2324-data/1/1categories.csv\n",
"Shape : (27, 7)\n",
"Number of columns : 5\n",
"Columns : Index(['id', 'identifier', 'name', 'extra_field', 'quota'], dtype='object')\n",
"Second merge products_theme and type of categories\n",
"File path : bdc2324-data/1/1type_of_categories.csv\n",
"Shape : (5, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'type_of_id', 'category_id', 'identifier'], dtype='object')\n"
]
},
{
"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>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>category_id</th>\n",
" <th>products_group_id</th>\n",
" <th>product_pack_id</th>\n",
" <th>type_of_id</th>\n",
" <th>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>name_categories</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10682</td>\n",
" <td>914</td>\n",
" <td>114</td>\n",
" <td>41</td>\n",
" <td>10655</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>9.0</td>\n",
" <td>False</td>\n",
" <td>indiv activité tr</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>478</td>\n",
" <td>273</td>\n",
" <td>131</td>\n",
" <td>1</td>\n",
" <td>471</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>9.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20873</td>\n",
" <td>275</td>\n",
" <td>137</td>\n",
" <td>1</td>\n",
" <td>20825</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>11.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>157142</td>\n",
" <td>82519</td>\n",
" <td>9</td>\n",
" <td>5</td>\n",
" <td>156773</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>8.0</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tr</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1341</td>\n",
" <td>9</td>\n",
" <td>93</td>\n",
" <td>1</td>\n",
" <td>1175</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>8.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id_products representation_id pricing_formula_id category_id \\\n",
"0 10682 914 114 41 \n",
"1 478 273 131 1 \n",
"2 20873 275 137 1 \n",
"3 157142 82519 9 5 \n",
"4 1341 9 93 1 \n",
"\n",
" products_group_id product_pack_id type_of_id amount is_full_price \\\n",
"0 10655 1 NaN 9.0 False \n",
"1 471 1 12.0 9.5 False \n",
"2 20825 1 12.0 11.5 False \n",
"3 156773 1 NaN 8.0 False \n",
"4 1175 1 12.0 8.5 False \n",
"\n",
" name_categories \n",
"0 indiv activité tr \n",
"1 indiv entrées tp \n",
"2 indiv entrées tp \n",
"3 indiv entrées tr \n",
"4 indiv entrées tp "
]
},
"execution_count": 338,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_theme = create_products_table()\n",
"products_theme.head()"
]
},
{
"cell_type": "markdown",
"id": "8bd7b7ab-fd04-48d2-898b-48c5815457f3",
"metadata": {},
"source": [
"### Events Table"
]
},
{
"cell_type": "code",
"execution_count": 339,
"id": "6ed0ad20-8315-4112-9a85-10e5f04ef852",
"metadata": {},
"outputs": [],
"source": [
"def create_events_table():\n",
" # first merge events and seasons : \n",
" print(\"first merge events and seasons : \")\n",
" events = load_dataset(\"1events.csv\")\n",
" seasons = load_dataset(\"1seasons.csv\")\n",
"\n",
" # Drop useless columns\n",
" events = events.drop(columns = ['manual_added', 'is_display'])\n",
" seasons = seasons.drop(columns = ['start_date_time'])\n",
" \n",
" events_theme = events.merge(seasons, how = 'left', left_on = 'season_id', right_on = 'id', suffixes=('_events', '_seasons'))\n",
"\n",
" # Secondly merge events_theme and event_types\n",
" print(\"Secondly merge events_theme and event_types : \")\n",
" event_types = load_dataset(\"1event_types.csv\")\n",
" event_types = event_types.drop(columns = ['fidelity_delay'])\n",
" \n",
" events_theme = events_theme.merge(event_types, how = 'left', left_on = 'event_type_id', right_on = 'id', suffixes=('_events', '_event_type'))\n",
" events_theme = events_theme.rename(columns = {\"name\" : \"name_event_types\"})\n",
" events_theme = events_theme.drop(columns = 'id')\n",
"\n",
" # thirdly merge events_theme and facilities\n",
" print(\"thirdly merge events_theme and facilities : \")\n",
" facilities = load_dataset(\"1facilities.csv\")\n",
" facilities = facilities.drop(columns = ['fixed_capacity'])\n",
" \n",
" events_theme = events_theme.merge(facilities, how = 'left', left_on = 'facility_id', right_on = 'id', suffixes=('_events', '_facility'))\n",
" events_theme = events_theme.rename(columns = {\"name\" : \"name_facilities\", \"id_events\" : \"event_id\"})\n",
" events_theme = events_theme.drop(columns = 'id')\n",
"\n",
" # Index cleaning\n",
" events_theme = events_theme.drop(columns = ['id_seasons'])\n",
" events_theme = order_columns_id(events_theme)\n",
" return events_theme"
]
},
{
"cell_type": "code",
"execution_count": 340,
"id": "98ef0636-8c45-4a23-a62a-1fbe1544f8ce",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"first merge events and seasons : \n",
"File path : bdc2324-data/1/1events.csv\n",
"Shape : (1232, 12)\n",
"Number of columns : 10\n",
"Columns : Index(['id', 'season_id', 'facility_id', 'event_type_id', 'event_type_key_id',\n",
" 'facility_key_id', 'identifier', 'name', 'manual_added', 'is_display'],\n",
" dtype='object')\n",
"File path : bdc2324-data/1/1seasons.csv\n",
"Shape : (13, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'identifier', 'name', 'start_date_time'], dtype='object')\n",
"Secondly merge events_theme and event_types : \n",
"File path : bdc2324-data/1/1event_types.csv\n",
"Shape : (9, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'fidelity_delay', 'identifier', 'name'], dtype='object')\n",
"thirdly merge events_theme and facilities : \n",
"File path : bdc2324-data/1/1facilities.csv\n",
"Shape : (2, 7)\n",
"Number of columns : 5\n",
"Columns : Index(['id', 'street_id', 'identifier', 'name', 'fixed_capacity'], dtype='object')\n"
]
},
{
"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>event_id</th>\n",
" <th>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>event_type_id</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>street_id</th>\n",
" <th>name_events</th>\n",
" <th>name_seasons</th>\n",
" <th>name_event_types</th>\n",
" <th>name_facilities</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>192</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>frontières</td>\n",
" <td>2018</td>\n",
" <td>spectacle vivant</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>30329</td>\n",
" <td>2767</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>visite guidée une autre histoire du monde (1h00)</td>\n",
" <td>2023</td>\n",
" <td>offre muséale groupe</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>161</td>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>visite contée les chercheurs d'or indiv</td>\n",
" <td>2018</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5957</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>we dreamt of utopia and we woke up screaming.</td>\n",
" <td>2021</td>\n",
" <td>spectacle vivant</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>8337</td>\n",
" <td>582</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>jeff koons épisodes 4</td>\n",
" <td>2021</td>\n",
" <td>spectacle vivant</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" event_id season_id facility_id event_type_id event_type_key_id \\\n",
"0 192 16 1 4 4 \n",
"1 30329 2767 1 5 5 \n",
"2 161 16 1 2 2 \n",
"3 5957 582 1 4 4 \n",
"4 8337 582 1 4 4 \n",
"\n",
" facility_key_id street_id \\\n",
"0 1 1 \n",
"1 1 1 \n",
"2 1 1 \n",
"3 1 1 \n",
"4 1 1 \n",
"\n",
" name_events name_seasons \\\n",
"0 frontières 2018 \n",
"1 visite guidée une autre histoire du monde (1h00) 2023 \n",
"2 visite contée les chercheurs d'or indiv 2018 \n",
"3 we dreamt of utopia and we woke up screaming. 2021 \n",
"4 jeff koons épisodes 4 2021 \n",
"\n",
" name_event_types name_facilities \n",
"0 spectacle vivant mucem \n",
"1 offre muséale groupe mucem \n",
"2 offre muséale individuel mucem \n",
"3 spectacle vivant mucem \n",
"4 spectacle vivant mucem "
]
},
"execution_count": 340,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"events_theme= create_events_table()\n",
"events_theme.head()"
]
},
{
"cell_type": "markdown",
"id": "4ad5b680-bb27-4f86-a5f3-7ff4fd1be96a",
"metadata": {},
"source": [
"## Representations_Table"
]
},
{
"cell_type": "code",
"execution_count": 341,
"id": "481dddd6-80a8-4b9e-a05e-ed06fa3ed7a6",
"metadata": {},
"outputs": [],
"source": [
"def create_representations_table():\n",
" representations = load_dataset(\"1representations.csv\")\n",
" representations = representations.drop(columns = ['serial', 'open', 'satisfaction', 'is_display', 'expected_filling',\n",
" 'max_filling', 'extra_field', 'start_date_time', 'end_date_time', 'name',\n",
" 'representation_type_id'])\n",
" \n",
" representations_capacity = load_dataset(\"1representation_category_capacities.csv\")\n",
" representations_capacity = representations_capacity.drop(columns = ['expected_filling', 'max_filling'])\n",
"\n",
" representations_theme = representations.merge(representations_capacity, how='left',\n",
" left_on='id', right_on='representation_id',\n",
" suffixes=('_representation', '_representation_cap'))\n",
" # index cleaning\n",
" representations_theme = representations_theme.drop(columns = [\"id_representation\"])\n",
" representations_theme = order_columns_id(representations_theme)\n",
" return representations_theme"
]
},
{
"cell_type": "code",
"execution_count": 342,
"id": "677f4ed8-ef58-45f2-9056-ede0898c6a64",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1representations.csv\n",
"Shape : (36095, 16)\n",
"Number of columns : 14\n",
"Columns : Index(['id', 'event_id', 'representation_type_id', 'identifier', 'serial',\n",
" 'start_date_time', 'open', 'satisfaction', 'end_date_time', 'name',\n",
" 'is_display', 'expected_filling', 'max_filling', 'extra_field'],\n",
" dtype='object')\n",
"File path : bdc2324-data/1/1representation_category_capacities.csv\n",
"Shape : (65241, 7)\n",
"Number of columns : 5\n",
"Columns : Index(['id', 'representation_id', 'category_id', 'expected_filling',\n",
" 'max_filling'],\n",
" dtype='object')\n"
]
},
{
"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>event_id</th>\n",
" <th>id_representation_cap</th>\n",
" <th>representation_id</th>\n",
" <th>category_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12384</td>\n",
" <td>123058</td>\n",
" <td>84820</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>37</td>\n",
" <td>2514</td>\n",
" <td>269</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>37</td>\n",
" <td>384</td>\n",
" <td>269</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>37</td>\n",
" <td>2515</td>\n",
" <td>269</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>37</td>\n",
" <td>383</td>\n",
" <td>269</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" event_id id_representation_cap representation_id category_id\n",
"0 12384 123058 84820 2\n",
"1 37 2514 269 2\n",
"2 37 384 269 5\n",
"3 37 2515 269 10\n",
"4 37 383 269 1"
]
},
"execution_count": 342,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"representation_theme = create_representations_table()\n",
"representation_theme.head()"
]
},
{
"cell_type": "markdown",
"id": "e274e3cc-1b41-43e0-8412-1563166060cb",
"metadata": {},
"source": [
"## Price Table"
]
},
{
"cell_type": "code",
"execution_count": 343,
"id": "c52621e7-01de-48dc-b572-2974542a8be5",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1product_packs.csv\n",
"Shape : (1, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'identifier', 'name', 'type_of'], dtype='object')\n"
]
},
{
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name type_of\n",
"0 1 NaN 0"
]
},
"execution_count": 343,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"product_packs = load_dataset(\"1product_packs.csv\")\n",
"product_packs.head()"
]
},
{
"cell_type": "code",
"execution_count": 344,
"id": "9e4f60ab-9a2c-4090-b0c4-f9a1530b2d39",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1pricing_formulas.csv\n",
"Shape : (556, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'identifier', 'name', 'extra_field'], dtype='object')\n"
]
},
{
"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>extra_field</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>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>502</td>\n",
" <td>entree mucem tp( expo picasso)</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>504</td>\n",
" <td>nombre de personnes cinema</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>117</td>\n",
" <td>spectacle tarif e famille tr</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1496</td>\n",
" <td>billet nb famille mecene 1a</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name extra_field\n",
"0 41909 visite mécènes 1h30 NaN\n",
"1 502 entree mucem tp( expo picasso) NaN\n",
"2 504 nombre de personnes cinema NaN\n",
"3 117 spectacle tarif e famille tr NaN\n",
"4 1496 billet nb famille mecene 1a NaN"
]
},
"execution_count": 344,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pricing_formula = load_dataset(\"1pricing_formulas.csv\")\n",
"pricing_formula.head()"
]
},
{
"cell_type": "code",
"execution_count": 345,
"id": "247b5c45-a18a-4cfd-86b4-d3453e157bcd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1type_of_pricing_formulas.csv\n",
"Shape : (568, 6)\n",
"Number of columns : 4\n",
"Columns : Index(['id', 'type_of_id', 'pricing_formula_id', 'identifier'], dtype='object')\n"
]
},
{
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>127</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2425</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2937</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id type_of_id pricing_formula_id\n",
"0 1 1 127\n",
"1 2 1 2425\n",
"2 3 1 2937\n",
"3 4 1 48\n",
"4 5 1 7"
]
},
"execution_count": 345,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type_pricing_formula = load_dataset(\"1type_of_pricing_formulas.csv\")\n",
"type_pricing_formula.head()"
]
},
{
"cell_type": "code",
"execution_count": 346,
"id": "4b48f7b3-0f06-4ef6-9355-5016af82f49c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1products_groups.csv\n",
"Shape : (92973, 9)\n",
"Number of columns : 7\n",
"Columns : Index(['id', 'category_id', 'pricing_formula_id', 'representation_id',\n",
" 'percent_price', 'max_price', 'min_price'],\n",
" dtype='object')\n"
]
},
{
"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>category_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>representation_id</th>\n",
" <th>percent_price</th>\n",
" <th>max_price</th>\n",
" <th>min_price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2735</td>\n",
" <td>8</td>\n",
" <td>97</td>\n",
" <td>1534</td>\n",
" <td>100.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>156773</td>\n",
" <td>5</td>\n",
" <td>9</td>\n",
" <td>82519</td>\n",
" <td>100.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14387</td>\n",
" <td>16</td>\n",
" <td>79</td>\n",
" <td>8046</td>\n",
" <td>100.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2770</td>\n",
" <td>2</td>\n",
" <td>37</td>\n",
" <td>1563</td>\n",
" <td>100.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>27179</td>\n",
" <td>13</td>\n",
" <td>119</td>\n",
" <td>14192</td>\n",
" <td>100.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id category_id pricing_formula_id representation_id percent_price \\\n",
"0 2735 8 97 1534 100.0 \n",
"1 156773 5 9 82519 100.0 \n",
"2 14387 16 79 8046 100.0 \n",
"3 2770 2 37 1563 100.0 \n",
"4 27179 13 119 14192 100.0 \n",
"\n",
" max_price min_price \n",
"0 0.0 0.0 \n",
"1 0.0 0.0 \n",
"2 0.0 0.0 \n",
"3 0.0 0.0 \n",
"4 0.0 0.0 "
]
},
"execution_count": 346,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"product_groups = load_dataset(\"1products_groups.csv\")\n",
"product_groups.head()"
]
},
{
"cell_type": "markdown",
"id": "71c26a38-6818-42df-8aee-0135681a5563",
"metadata": {},
"source": [
"## Uniform Products theme database"
]
},
{
"cell_type": "code",
"execution_count": 347,
"id": "b26f4e7e-134d-4e32-a615-4b0e6bb80b25",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Products theme columns : Index(['id_products', 'representation_id', 'pricing_formula_id', 'category_id',\n",
" 'products_group_id', 'product_pack_id', 'type_of_id', 'amount',\n",
" 'is_full_price', 'name_categories'],\n",
" dtype='object')\n",
"\n",
" Representation theme columns : Index(['event_id', 'id_representation_cap', 'representation_id',\n",
" 'category_id'],\n",
" dtype='object')\n",
"\n",
" Events theme columns : Index(['event_id', 'season_id', 'facility_id', 'event_type_id',\n",
" 'event_type_key_id', 'facility_key_id', 'street_id', 'name_events',\n",
" 'name_seasons', 'name_event_types', 'name_facilities'],\n",
" dtype='object')\n"
]
}
],
"source": [
"print(\"Products theme columns : \", products_theme.columns)\n",
"print(\"\\n Representation theme columns : \", representation_theme.columns)\n",
"print(\"\\n Events theme columns : \", events_theme.columns)"
]
},
{
"cell_type": "code",
"execution_count": 348,
"id": "d40b1e3b-b1f3-4915-8ebc-6bb7856da42a",
"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>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>category_id</th>\n",
" <th>products_group_id</th>\n",
" <th>product_pack_id</th>\n",
" <th>type_of_id</th>\n",
" <th>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>name_categories</th>\n",
" <th>event_id</th>\n",
" <th>id_representation_cap</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10682</td>\n",
" <td>914</td>\n",
" <td>114</td>\n",
" <td>41</td>\n",
" <td>10655</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>9.0</td>\n",
" <td>False</td>\n",
" <td>indiv activité tr</td>\n",
" <td>132</td>\n",
" <td>8789</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>478</td>\n",
" <td>273</td>\n",
" <td>131</td>\n",
" <td>1</td>\n",
" <td>471</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>9.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>37</td>\n",
" <td>390</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20873</td>\n",
" <td>275</td>\n",
" <td>137</td>\n",
" <td>1</td>\n",
" <td>20825</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>11.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>37</td>\n",
" <td>395</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>157142</td>\n",
" <td>82519</td>\n",
" <td>9</td>\n",
" <td>5</td>\n",
" <td>156773</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>8.0</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tr</td>\n",
" <td>12365</td>\n",
" <td>120199</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1341</td>\n",
" <td>9</td>\n",
" <td>93</td>\n",
" <td>1</td>\n",
" <td>1175</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>8.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>8</td>\n",
" <td>21</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id_products representation_id pricing_formula_id category_id \\\n",
"0 10682 914 114 41 \n",
"1 478 273 131 1 \n",
"2 20873 275 137 1 \n",
"3 157142 82519 9 5 \n",
"4 1341 9 93 1 \n",
"\n",
" products_group_id product_pack_id type_of_id amount is_full_price \\\n",
"0 10655 1 NaN 9.0 False \n",
"1 471 1 12.0 9.5 False \n",
"2 20825 1 12.0 11.5 False \n",
"3 156773 1 NaN 8.0 False \n",
"4 1175 1 12.0 8.5 False \n",
"\n",
" name_categories event_id id_representation_cap \n",
"0 indiv activité tr 132 8789 \n",
"1 indiv entrées tp 37 390 \n",
"2 indiv entrées tp 37 395 \n",
"3 indiv entrées tr 12365 120199 \n",
"4 indiv entrées tp 8 21 "
]
},
"execution_count": 348,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_global = products_theme.merge(representation_theme, how='left',\n",
" on= [\"representation_id\", \"category_id\"])\n",
"\n",
"\n",
"products_global.head()"
]
},
{
"cell_type": "code",
"execution_count": 349,
"id": "78d75a08-e959-429c-847a-7d70a2804806",
"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>representation_id</th>\n",
" <th>pricing_formula_id</th>\n",
" <th>category_id</th>\n",
" <th>products_group_id</th>\n",
" <th>product_pack_id</th>\n",
" <th>type_of_id</th>\n",
" <th>event_id</th>\n",
" <th>id_representation_cap</th>\n",
" <th>season_id</th>\n",
" <th>...</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>street_id</th>\n",
" <th>amount</th>\n",
" <th>is_full_price</th>\n",
" <th>name_categories</th>\n",
" <th>name_events</th>\n",
" <th>name_seasons</th>\n",
" <th>name_event_types</th>\n",
" <th>name_facilities</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10682</td>\n",
" <td>914</td>\n",
" <td>114</td>\n",
" <td>41</td>\n",
" <td>10655</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>132</td>\n",
" <td>8789</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>9.0</td>\n",
" <td>False</td>\n",
" <td>indiv activité tr</td>\n",
" <td>visite-jeu \"le classico des minots\" (1h30)</td>\n",
" <td>2017</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>478</td>\n",
" <td>273</td>\n",
" <td>131</td>\n",
" <td>1</td>\n",
" <td>471</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>37</td>\n",
" <td>390</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>9.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>billet mucem picasso</td>\n",
" <td>2016</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20873</td>\n",
" <td>275</td>\n",
" <td>137</td>\n",
" <td>1</td>\n",
" <td>20825</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>37</td>\n",
" <td>395</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>11.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>billet mucem picasso</td>\n",
" <td>2016</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>157142</td>\n",
" <td>82519</td>\n",
" <td>9</td>\n",
" <td>5</td>\n",
" <td>156773</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>12365</td>\n",
" <td>120199</td>\n",
" <td>1754</td>\n",
" <td>...</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8.0</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tr</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1341</td>\n",
" <td>9</td>\n",
" <td>93</td>\n",
" <td>1</td>\n",
" <td>1175</td>\n",
" <td>1</td>\n",
" <td>12.0</td>\n",
" <td>8</td>\n",
" <td>21</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8.5</td>\n",
" <td>False</td>\n",
" <td>indiv entrées tp</td>\n",
" <td>non défini</td>\n",
" <td>2017</td>\n",
" <td>non défini</td>\n",
" <td>mucem</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" id_products representation_id pricing_formula_id category_id \\\n",
"0 10682 914 114 41 \n",
"1 478 273 131 1 \n",
"2 20873 275 137 1 \n",
"3 157142 82519 9 5 \n",
"4 1341 9 93 1 \n",
"\n",
" products_group_id product_pack_id type_of_id event_id \\\n",
"0 10655 1 NaN 132 \n",
"1 471 1 12.0 37 \n",
"2 20825 1 12.0 37 \n",
"3 156773 1 NaN 12365 \n",
"4 1175 1 12.0 8 \n",
"\n",
" id_representation_cap season_id ... event_type_key_id facility_key_id \\\n",
"0 8789 4 ... 5 1 \n",
"1 390 2 ... 2 1 \n",
"2 395 2 ... 2 1 \n",
"3 120199 1754 ... 4 1 \n",
"4 21 4 ... 6 1 \n",
"\n",
" street_id amount is_full_price name_categories \\\n",
"0 1 9.0 False indiv activité tr \n",
"1 1 9.5 False indiv entrées tp \n",
"2 1 11.5 False indiv entrées tp \n",
"3 1 8.0 False indiv entrées tr \n",
"4 1 8.5 False indiv entrées tp \n",
"\n",
" name_events name_seasons \\\n",
"0 visite-jeu \"le classico des minots\" (1h30) 2017 \n",
"1 billet mucem picasso 2016 \n",
"2 billet mucem picasso 2016 \n",
"3 NaN NaN \n",
"4 non défini 2017 \n",
"\n",
" name_event_types name_facilities \n",
"0 offre muséale individuel mucem \n",
"1 offre muséale individuel mucem \n",
"2 offre muséale individuel mucem \n",
"3 offre muséale individuel mucem \n",
"4 non défini mucem \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 349,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_global = products_global.merge(events_theme, how='left', on='event_id',\n",
" suffixes = (\"_representation\", \"_event\"))\n",
"products_global = order_columns_id(products_global)\n",
"products_global.head()"
]
},
{
"cell_type": "code",
"execution_count": 350,
"id": "4a6950e8-4818-4df2-afa9-562e0921698c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['id_products', 'representation_id', 'pricing_formula_id', 'category_id',\n",
" 'products_group_id', 'product_pack_id', 'type_of_id', 'event_id',\n",
" 'id_representation_cap', 'season_id', 'facility_id', 'event_type_id',\n",
" 'event_type_key_id', 'facility_key_id', 'street_id', 'amount',\n",
" 'is_full_price', 'name_categories', 'name_events', 'name_seasons',\n",
" 'name_event_types', 'name_facilities'],\n",
" dtype='object')"
]
},
"execution_count": 350,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_global.columns"
]
},
{
"cell_type": "code",
"execution_count": 351,
"id": "b18f6428-90e0-4b1b-9b8d-bad995fb6c98",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(94803, 22)"
]
},
"execution_count": 351,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_global.shape"
]
},
{
"cell_type": "markdown",
"id": "c3caf2fd-178e-48e9-b95f-5798bd576f5d",
"metadata": {},
"source": [
"## Analysis of Products_global"
]
},
{
"cell_type": "code",
"execution_count": 352,
"id": "33ee07a2-d871-4436-9860-9be389bc4902",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id_products 0\n",
"representation_id 0\n",
"pricing_formula_id 0\n",
"category_id 0\n",
"products_group_id 0\n",
"product_pack_id 0\n",
"type_of_id 67589\n",
"event_id 0\n",
"id_representation_cap 0\n",
"season_id 0\n",
"facility_id 0\n",
"event_type_id 0\n",
"event_type_key_id 0\n",
"facility_key_id 0\n",
"street_id 0\n",
"amount 0\n",
"is_full_price 0\n",
"name_categories 3991\n",
"name_events 46657\n",
"name_seasons 30663\n",
"name_event_types 0\n",
"name_facilities 0\n",
"dtype: int64"
]
},
"execution_count": 352,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_global.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 353,
"id": "557fc475-4417-4d9f-8d4e-8c49bc42367f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['offre muséale individuel', 'non défini', 'spectacle vivant',\n",
" 'offre muséale groupe', 'formule adhésion'], dtype=object)"
]
},
"execution_count": 353,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many event types ?\n",
"\n",
"products_global['name_event_types'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 354,
"id": "a9b9a23c-b0de-4685-97e5-d52dd78349f5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"644"
]
},
"execution_count": 354,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many events ?\n",
"\n",
"len(products_global['name_events'].unique())"
]
},
{
"cell_type": "code",
"execution_count": 355,
"id": "fb374c72-58ca-404d-a86b-e834a2fc4a34",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['indiv activité tr', 'indiv entrées tp', 'indiv entrées tr',\n",
" 'indiv prog enfant', 'indiv activité gr', 'indiv prog gr',\n",
" 'indiv activité tp', 'indiv activité enfant', 'indiv entrées gr',\n",
" 'groupe forfait entrées tr', 'groupe autonome adulte',\n",
" 'indiv prog tp', 'indiv prog tr', 'indiv entrées fa',\n",
" 'groupe forfait scolaire', 'en nb entrées tr', 'non défini', nan,\n",
" 'en nb entrées gr', 'groupe autonome entrées gr',\n",
" 'groupe forfait entrées gr', 'groupe autonome entrées tr',\n",
" 'en nb entrées tp', 'groupe autonome gr',\n",
" 'groupe autonome entrées tp', 'groupe forfait adulte',\n",
" 'groupe forfait etudiant'], dtype=object)"
]
},
"execution_count": 355,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# how many categories ?\n",
"products_global['name_categories'].unique()\n"
]
},
{
"cell_type": "code",
"execution_count": 356,
"id": "11f89771-8d50-4ef4-b34e-53e4f6b419bb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"27"
]
},
"execution_count": 356,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(products_global['category_id'].unique())"
]
},
{
"cell_type": "code",
"execution_count": 357,
"id": "8add1ff2-b7e8-4381-90d8-d18d8660ed39",
"metadata": {},
"outputs": [],
"source": [
"def uniform_product_df():\n",
" \"\"\"\n",
" This function returns the uniform product dataset\n",
" \"\"\"\n",
" print(\"Products theme columns : \", products_theme.columns)\n",
" print(\"\\n Representation theme columns : \", representation_theme.columns)\n",
" print(\"\\n Events theme columns : \", events_theme.columns)\n",
"\n",
" products_global = products_theme.merge(representation_theme, how='left',\n",
" on= [\"representation_id\", \"category_id\"])\n",
" \n",
" products_global = products_global.merge(events_theme, how='left', on='event_id',\n",
" suffixes = (\"_representation\", \"_event\"))\n",
" \n",
" products_global = order_columns_id(products_global)\n",
"\n",
" # remove useless columns \n",
" products_global = products_global.drop(columns = ['type_of_id', 'name_events', 'name_seasons', 'name_categories'])\n",
" return products_global\n",
" "
]
},
{
"cell_type": "markdown",
"id": "b9303d35-4449-4cb6-887b-73a75f3cb868",
"metadata": {},
"source": [
"# Investigate Customer Plus"
]
},
{
"cell_type": "code",
"execution_count": 358,
"id": "1fd9dcb0-164a-4fd0-90c3-2fd9e7b44016",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : bdc2324-data/1/1customersplus.csv\n",
"Shape : (151866, 43)\n",
"Number of columns : 41\n",
"Columns : Index(['id', 'street_id', 'identifier', 'structure_id', 'mcp_contact_id',\n",
" 'fidelity', 'tenant_id', 'lastname', 'firstname', 'birthdate', 'email',\n",
" 'civility', 'is_partner', 'extra', 'deleted_at', 'reference', 'gender',\n",
" 'is_email_true', 'extra_field', 'opt_in', 'note', 'profession',\n",
" 'language', 'need_reload', 'last_buying_date', 'max_price',\n",
" 'ticket_sum', 'average_price', 'average_purchase_delay',\n",
" 'average_price_basket', 'average_ticket_basket', 'total_price',\n",
" 'preferred_category', 'preferred_supplier', 'preferred_formula',\n",
" 'purchase_count', 'first_buying_date', 'last_visiting_date', 'zipcode',\n",
" 'country', 'age'],\n",
" dtype='object')\n"
]
},
{
"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>street_id</th>\n",
" <th>structure_id</th>\n",
" <th>mcp_contact_id</th>\n",
" <th>fidelity</th>\n",
" <th>tenant_id</th>\n",
" <th>lastname</th>\n",
" <th>firstname</th>\n",
" <th>birthdate</th>\n",
" <th>email</th>\n",
" <th>...</th>\n",
" <th>total_price</th>\n",
" <th>preferred_category</th>\n",
" <th>preferred_supplier</th>\n",
" <th>preferred_formula</th>\n",
" <th>purchase_count</th>\n",
" <th>first_buying_date</th>\n",
" <th>last_visiting_date</th>\n",
" <th>zipcode</th>\n",
" <th>country</th>\n",
" <th>age</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12751</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1311</td>\n",
" <td>lastname12751</td>\n",
" <td>firstname12751</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>12825</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1311</td>\n",
" <td>lastname12825</td>\n",
" <td>firstname12825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>11261</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1311</td>\n",
" <td>lastname11261</td>\n",
" <td>firstname11261</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>13071</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1311</td>\n",
" <td>lastname13071</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>653061</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1311</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>email653061</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 40 columns</p>\n",
"</div>"
],
"text/plain": [
" id street_id structure_id mcp_contact_id fidelity tenant_id \\\n",
"0 12751 2 NaN NaN 0 1311 \n",
"1 12825 2 NaN NaN 0 1311 \n",
"2 11261 2 NaN NaN 0 1311 \n",
"3 13071 2 NaN NaN 0 1311 \n",
"4 653061 10 NaN NaN 0 1311 \n",
"\n",
" lastname firstname birthdate email ... total_price \\\n",
"0 lastname12751 firstname12751 NaN NaN ... NaN \n",
"1 lastname12825 firstname12825 NaN NaN ... NaN \n",
"2 lastname11261 firstname11261 NaN NaN ... NaN \n",
"3 lastname13071 NaN NaN NaN ... NaN \n",
"4 NaN NaN NaN email653061 ... NaN \n",
"\n",
" preferred_category preferred_supplier preferred_formula purchase_count \\\n",
"0 NaN NaN NaN 0 \n",
"1 NaN NaN NaN 0 \n",
"2 NaN NaN NaN 0 \n",
"3 NaN NaN NaN 0 \n",
"4 NaN NaN NaN 0 \n",
"\n",
" first_buying_date last_visiting_date zipcode country age \n",
"0 NaN NaN NaN fr NaN \n",
"1 NaN NaN NaN fr NaN \n",
"2 NaN NaN NaN fr NaN \n",
"3 NaN NaN NaN fr NaN \n",
"4 NaN NaN NaN NaN NaN \n",
"\n",
"[5 rows x 40 columns]"
]
},
"execution_count": 358,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer_plus = load_dataset(\"1customersplus.csv\")\n",
"customer_plus.head()"
]
},
{
"cell_type": "code",
"execution_count": 359,
"id": "e4a5f890-d5aa-40d7-a70c-8d8a254a5c9a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"id 0\n",
"street_id 0\n",
"structure_id 133752\n",
"mcp_contact_id 52965\n",
"fidelity 0\n",
"tenant_id 0\n",
"lastname 66003\n",
"firstname 68333\n",
"birthdate 146429\n",
"email 13094\n",
"civility 151866\n",
"is_partner 0\n",
"extra 151866\n",
"deleted_at 151866\n",
"reference 151866\n",
"gender 0\n",
"is_email_true 0\n",
"extra_field 151866\n",
"opt_in 0\n",
"note 150960\n",
"profession 145660\n",
"language 150774\n",
"need_reload 0\n",
"last_buying_date 78444\n",
"max_price 78444\n",
"ticket_sum 0\n",
"average_price 13120\n",
"average_purchase_delay 78444\n",
"average_price_basket 78444\n",
"average_ticket_basket 78444\n",
"total_price 65324\n",
"preferred_category 151866\n",
"preferred_supplier 151866\n",
"preferred_formula 151866\n",
"purchase_count 0\n",
"first_buying_date 78444\n",
"last_visiting_date 151866\n",
"zipcode 108093\n",
"country 8291\n",
"age 146429\n",
"dtype: int64"
]
},
"execution_count": 359,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer_plus.isna().sum()"
]
},
{
"cell_type": "markdown",
"id": "55ac8ec6-baa2-4199-b29a-d931260a6970",
"metadata": {},
"source": [
"# Analysis of Customer Products"
]
},
{
"cell_type": "code",
"execution_count": 360,
"id": "de370d66-852e-46a1-8fb4-5c1e5756f5cd",
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 361,
"id": "088a1f50-cf5d-4d1a-891d-4e9df7e1c35b",
"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>customer_id</th>\n",
" <th>birthdate</th>\n",
" <th>street_id</th>\n",
" <th>is_partner</th>\n",
" <th>gender</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>structure_id</th>\n",
" <th>profession</th>\n",
" <th>language</th>\n",
" <th>...</th>\n",
" <th>first_buying_date</th>\n",
" <th>country</th>\n",
" <th>age</th>\n",
" <th>tenant_id</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>time_to_open</th>\n",
" <th>event_type_id</th>\n",
" <th>nb_tickets</th>\n",
" <th>avg_amount</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12751</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</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",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>12825</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</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",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>11261</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</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",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>13071</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</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",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>653061</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" <td>80.0</td>\n",
" <td>2.0</td>\n",
" <td>0 days 19:53:02.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 31 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id birthdate street_id is_partner gender is_email_true \\\n",
"0 12751 NaN 2 False 1 True \n",
"1 12825 NaN 2 False 2 True \n",
"2 11261 NaN 2 False 1 True \n",
"3 13071 NaN 2 False 2 True \n",
"4 653061 NaN 10 False 2 True \n",
"\n",
" opt_in structure_id profession language ... first_buying_date country \\\n",
"0 True NaN NaN NaN ... NaN fr \n",
"1 True NaN NaN NaN ... NaN fr \n",
"2 True NaN NaN NaN ... NaN fr \n",
"3 True NaN NaN NaN ... NaN fr \n",
"4 False NaN NaN NaN ... NaN NaN \n",
"\n",
" age tenant_id nb_campaigns nb_campaigns_opened time_to_open \\\n",
"0 NaN 1311 NaN NaN NaN \n",
"1 NaN 1311 NaN NaN NaN \n",
"2 NaN 1311 NaN NaN NaN \n",
"3 NaN 1311 NaN NaN NaN \n",
"4 NaN 1311 80.0 2.0 0 days 19:53:02.500000 \n",
"\n",
" event_type_id nb_tickets avg_amount \n",
"0 NaN NaN NaN \n",
"1 NaN NaN NaN \n",
"2 NaN NaN NaN \n",
"3 NaN NaN NaN \n",
"4 NaN NaN NaN \n",
"\n",
"[5 rows x 31 columns]"
]
},
"execution_count": 361,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer_product = pd.read_csv(\"customer_product.csv\")\n",
"customer_product.head()"
]
},
{
"cell_type": "code",
"execution_count": 362,
"id": "bdd582af-0cf1-4e04-90ad-7165b8a36ac8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(156289, 31)\n",
"Index(['customer_id', 'birthdate', 'street_id', 'is_partner', 'gender',\n",
" 'is_email_true', 'opt_in', 'structure_id', 'profession', 'language',\n",
" 'mcp_contact_id', 'last_buying_date', 'max_price', 'ticket_sum',\n",
" 'average_price', 'fidelity', 'average_purchase_delay',\n",
" 'average_price_basket', 'average_ticket_basket', 'total_price',\n",
" 'purchase_count', 'first_buying_date', 'country', 'age', 'tenant_id',\n",
" 'nb_campaigns', 'nb_campaigns_opened', 'time_to_open', 'event_type_id',\n",
" 'nb_tickets', 'avg_amount'],\n",
" dtype='object')\n"
]
}
],
"source": [
"# Shape :\n",
"print(customer_product.shape)\n",
"# columns : \n",
"print(customer_product.columns)"
]
},
{
"cell_type": "code",
"execution_count": 363,
"id": "55fa2361-ebde-4472-b8d2-521a20be766d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"customer_id 0\n",
"birthdate 149375\n",
"street_id 0\n",
"is_partner 0\n",
"gender 0\n",
"is_email_true 0\n",
"opt_in 0\n",
"structure_id 136867\n",
"profession 150004\n",
"language 155184\n",
"mcp_contact_id 53519\n",
"last_buying_date 78445\n",
"max_price 78445\n",
"ticket_sum 0\n",
"average_price 13120\n",
"fidelity 0\n",
"average_purchase_delay 78445\n",
"average_price_basket 78445\n",
"average_ticket_basket 78445\n",
"total_price 65325\n",
"purchase_count 0\n",
"first_buying_date 78445\n",
"country 8304\n",
"age 149375\n",
"tenant_id 0\n",
"nb_campaigns 21623\n",
"nb_campaigns_opened 21623\n",
"time_to_open 69017\n",
"event_type_id 78355\n",
"nb_tickets 78355\n",
"avg_amount 78355\n",
"dtype: int64"
]
},
"execution_count": 363,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# check NA\n",
"\n",
"customer_product.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 364,
"id": "2e228eb6-8cc7-4fd7-8e17-2b818095cb96",
"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>customer_id</th>\n",
" <th>gender</th>\n",
" <th>is_partner</th>\n",
" <th>is_email_true</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>fidelity</th>\n",
" <th>nb_tickets</th>\n",
" <th>ticket_sum</th>\n",
" <th>average_price</th>\n",
" <th>avg_amount</th>\n",
" <th>event_type_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12751</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>12825</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>11261</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>13071</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>653061</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>80.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" customer_id gender is_partner is_email_true nb_campaigns \\\n",
"0 12751 1 False True NaN \n",
"1 12825 2 False True NaN \n",
"2 11261 1 False True NaN \n",
"3 13071 2 False True NaN \n",
"4 653061 2 False True 80.0 \n",
"\n",
" nb_campaigns_opened fidelity nb_tickets ticket_sum average_price \\\n",
"0 NaN 0 NaN 0 0.0 \n",
"1 NaN 0 NaN 0 0.0 \n",
"2 NaN 0 NaN 0 0.0 \n",
"3 NaN 0 NaN 0 0.0 \n",
"4 2.0 0 NaN 0 0.0 \n",
"\n",
" avg_amount event_type_id \n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN "
]
},
"execution_count": 364,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"## Investigate a subset of variables\n",
"\n",
"df = customer_product[[\"customer_id\", \"gender\", \"is_partner\", \"is_email_true\",\"nb_campaigns\", \"nb_campaigns_opened\", \"fidelity\",\n",
" \"nb_tickets\", \"ticket_sum\", \"average_price\", \"avg_amount\", \"event_type_id\"]]\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 368,
"id": "80120f51-f91e-4d4d-9578-1dc88cd94754",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"shape : (156289, 12)\n",
"Nombre de customer unique : 151866\n",
"Nombre de ligne où nb_tickets est non nul : 77934\n"
]
}
],
"source": [
"print(\"shape : \", df.shape)\n",
"print(\"Nombre de customer unique : \", len(df[\"customer_id\"].unique()))\n",
"print(\"Nombre de ligne où nb_tickets est non nul : \", df[\"nb_tickets\"].count())"
]
},
{
"cell_type": "code",
"execution_count": 370,
"id": "0d56bfa9-c93c-42ee-bec2-96f0598fce2c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nombre de consommateur unique : 73511\n",
"Nombre de type d'évènement : 4\n"
]
},
{
"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>customer_id</th>\n",
" <th>gender</th>\n",
" <th>is_partner</th>\n",
" <th>is_email_true</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>fidelity</th>\n",
" <th>nb_tickets</th>\n",
" <th>ticket_sum</th>\n",
" <th>average_price</th>\n",
" <th>avg_amount</th>\n",
" <th>event_type_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>162</th>\n",
" <td>309255</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>2.0</td>\n",
" <td>0</td>\n",
" <td>0.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>195</th>\n",
" <td>7772</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>133.0</td>\n",
" <td>19.0</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" <td>5</td>\n",
" <td>2.800000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>197</th>\n",
" <td>280009</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>116.0</td>\n",
" <td>32.0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>11.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>199</th>\n",
" <td>1556</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>9.0</td>\n",
" <td>8.0</td>\n",
" <td>1</td>\n",
" <td>2.0</td>\n",
" <td>3</td>\n",
" <td>23.333333</td>\n",
" <td>6.150659</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>200</th>\n",
" <td>1556</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>9.0</td>\n",
" <td>8.0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>23.333333</td>\n",
" <td>6.439463</td>\n",
" <td>6.0</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",
" </tr>\n",
" <tr>\n",
" <th>156245</th>\n",
" <td>293753</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>94.0</td>\n",
" <td>34.0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>11.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>156246</th>\n",
" <td>293798</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>12.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>156281</th>\n",
" <td>295224</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>98.0</td>\n",
" <td>98</td>\n",
" <td>0.000000</td>\n",
" <td>6.150659</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>156287</th>\n",
" <td>295366</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>3</td>\n",
" <td>11.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>156288</th>\n",
" <td>295368</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>11.000000</td>\n",
" <td>7.762474</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>77934 rows × 12 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id gender is_partner is_email_true nb_campaigns \\\n",
"162 309255 2 False True 2.0 \n",
"195 7772 0 False True 133.0 \n",
"197 280009 0 False True 116.0 \n",
"199 1556 0 False True 9.0 \n",
"200 1556 0 False True 9.0 \n",
"... ... ... ... ... ... \n",
"156245 293753 2 False True 94.0 \n",
"156246 293798 2 False True 7.0 \n",
"156281 295224 2 False True 10.0 \n",
"156287 295366 2 False True 5.0 \n",
"156288 295368 2 False True 5.0 \n",
"\n",
" nb_campaigns_opened fidelity nb_tickets ticket_sum average_price \\\n",
"162 2.0 0 2.0 0 0.000000 \n",
"195 19.0 0 5.0 5 2.800000 \n",
"197 32.0 1 1.0 1 11.000000 \n",
"199 8.0 1 2.0 3 23.333333 \n",
"200 8.0 1 1.0 3 23.333333 \n",
"... ... ... ... ... ... \n",
"156245 34.0 1 1.0 1 11.000000 \n",
"156246 0.0 2 2.0 2 12.000000 \n",
"156281 0.0 1 98.0 98 0.000000 \n",
"156287 0.0 1 3.0 3 11.000000 \n",
"156288 0.0 1 2.0 2 11.000000 \n",
"\n",
" avg_amount event_type_id \n",
"162 7.762474 4.0 \n",
"195 7.762474 4.0 \n",
"197 7.762474 4.0 \n",
"199 6.150659 2.0 \n",
"200 6.439463 6.0 \n",
"... ... ... \n",
"156245 7.762474 4.0 \n",
"156246 7.762474 4.0 \n",
"156281 6.150659 2.0 \n",
"156287 7.762474 4.0 \n",
"156288 7.762474 4.0 \n",
"\n",
"[77934 rows x 12 columns]"
]
},
"execution_count": 370,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Filter only customer that buy tickets\n",
"\n",
"df_purchase = df.dropna(subset= [\"nb_tickets\"])\n",
"print(\"Nombre de consommateur unique : \", len(df_purchase[\"customer_id\"].unique()))\n",
"print(\"Nombre de type d'évènement : \", len(df_purchase[\"event_type_id\"].unique()))\n",
"#print(\"Nombre de type d'évènement (nom) : \", len(df_purchase[\"name_event_types\"].unique()))\n",
"df_purchase"
]
},
{
"cell_type": "code",
"execution_count": 371,
"id": "0cc96c4e-f3f3-43d2-94b5-a11719f09607",
"metadata": {},
"outputs": [
{
"ename": "KeyError",
"evalue": "'name_event_types'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[371], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m event_counts \u001b[38;5;241m=\u001b[39m \u001b[43mdf_purchase\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgroupby\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mname_event_types\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcustomer_id\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mnunique()\n\u001b[1;32m 3\u001b[0m event_counts\u001b[38;5;241m.\u001b[39mplot(kind\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbar\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 4\u001b[0m plt\u001b[38;5;241m.\u001b[39mxlabel(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mType d\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mévènement\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.10/site-packages/pandas/core/frame.py:8869\u001b[0m, in \u001b[0;36mDataFrame.groupby\u001b[0;34m(self, by, axis, level, as_index, sort, group_keys, observed, dropna)\u001b[0m\n\u001b[1;32m 8866\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m level \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m by \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 8867\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou have to supply one of \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mby\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m and \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlevel\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 8869\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDataFrameGroupBy\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 8870\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8871\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mby\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8872\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8873\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8874\u001b[0m \u001b[43m \u001b[49m\u001b[43mas_index\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mas_index\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8875\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8876\u001b[0m \u001b[43m \u001b[49m\u001b[43mgroup_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroup_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8877\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8878\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8879\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.10/site-packages/pandas/core/groupby/groupby.py:1278\u001b[0m, in \u001b[0;36mGroupBy.__init__\u001b[0;34m(self, obj, keys, axis, level, grouper, exclusions, selection, as_index, sort, group_keys, observed, dropna)\u001b[0m\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdropna \u001b[38;5;241m=\u001b[39m dropna\n\u001b[1;32m 1277\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m grouper \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1278\u001b[0m grouper, exclusions, obj \u001b[38;5;241m=\u001b[39m \u001b[43mget_grouper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1279\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1280\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1281\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1282\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1283\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1284\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mno_default\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1285\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1286\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1288\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m observed \u001b[38;5;129;01mis\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default:\n\u001b[1;32m 1289\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28many\u001b[39m(ping\u001b[38;5;241m.\u001b[39m_passed_categorical \u001b[38;5;28;01mfor\u001b[39;00m ping \u001b[38;5;129;01min\u001b[39;00m grouper\u001b[38;5;241m.\u001b[39mgroupings):\n",
"File \u001b[0;32m/opt/mamba/lib/python3.10/site-packages/pandas/core/groupby/grouper.py:1009\u001b[0m, in \u001b[0;36mget_grouper\u001b[0;34m(obj, key, axis, level, sort, observed, validate, dropna)\u001b[0m\n\u001b[1;32m 1007\u001b[0m in_axis, level, gpr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m, gpr, \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1008\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1009\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(gpr)\n\u001b[1;32m 1010\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(gpr, Grouper) \u001b[38;5;129;01mand\u001b[39;00m gpr\u001b[38;5;241m.\u001b[39mkey \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1011\u001b[0m \u001b[38;5;66;03m# Add key to exclusions\u001b[39;00m\n\u001b[1;32m 1012\u001b[0m exclusions\u001b[38;5;241m.\u001b[39madd(gpr\u001b[38;5;241m.\u001b[39mkey)\n",
"\u001b[0;31mKeyError\u001b[0m: 'name_event_types'"
]
}
],
"source": [
"event_counts = df_purchase.groupby('name_event_types')['customer_id'].nunique()\n",
"\n",
"event_counts.plot(kind='bar')\n",
"plt.xlabel(\"Type d'évènement\")\n",
"plt.ylabel('Nombre de consommateurs uniques')\n",
"plt.title(\"Nombre de consommateurs uniques par type d'évènement\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e37ad847-7ea5-4afe-9c6d-e07a668d2a27",
"metadata": {},
"outputs": [],
"source": [
"average_tickets_by_event = df_purchase.groupby('name_event_types')['nb_tickets'].mean()\n",
"\n",
"average_tickets_by_event.plot(kind='bar', figsize=(8, 5))\n",
"plt.xlabel(\"Type d'évènements\")\n",
"plt.ylabel('Nombre moyen de tickets achetés')\n",
"plt.title(\"Nombre moyen de tickets achetés par Type d'évènements\")\n",
"plt.xticks(rotation=45)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e02b260a-fcb7-418b-87a8-de2bb4e6eb0a",
"metadata": {},
"outputs": [],
"source": [
"df_purchase.isna().sum()"
]
},
{
"cell_type": "markdown",
"id": "26fa888d-dd33-4990-89bd-6a9c1391098b",
"metadata": {},
"source": [
"## Modelisation K-means"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "25346383-25e3-43e3-8ea4-fe05bd68900d",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os\n",
"import s3fs\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "453c317a-b979-4fac-a9eb-60d72bf9caa8",
"metadata": {},
"outputs": [],
"source": [
"# Create filesystem object\n",
"S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "07bb1dbc-1543-49b0-a41c-6d5f569698d0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(156289, 41)\n"
]
},
{
"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>customer_id</th>\n",
" <th>birthdate</th>\n",
" <th>street_id</th>\n",
" <th>is_partner</th>\n",
" <th>gender</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>structure_id</th>\n",
" <th>profession</th>\n",
" <th>language</th>\n",
" <th>...</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>time_between_purchase</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>name_event_types</th>\n",
" <th>avg_amount</th>\n",
" <th>nb_categories</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>time_to_open</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>1705.261192</td>\n",
" <td>1456.333715</td>\n",
" <td>248.927477</td>\n",
" <td>0.0</td>\n",
" <td>formule adhésion</td>\n",
" <td>6.439463</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>2041.274549</td>\n",
" <td>1340.308160</td>\n",
" <td>700.966389</td>\n",
" <td>0.0</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>6.150659</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>3</td>\n",
" <td>NaN</td>\n",
" <td>3</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>1511.177396</td>\n",
" <td>42.428692</td>\n",
" <td>1468.748704</td>\n",
" <td>6.0</td>\n",
" <td>spectacle vivant</td>\n",
" <td>7.762474</td>\n",
" <td>1.0</td>\n",
" <td>222.0</td>\n",
" <td>124.0</td>\n",
" <td>1 days 00:28:30.169354838</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>1511.157396</td>\n",
" <td>1511.157396</td>\n",
" <td>0.000000</td>\n",
" <td>2.0</td>\n",
" <td>formule adhésion</td>\n",
" <td>6.439463</td>\n",
" <td>1.0</td>\n",
" <td>7.0</td>\n",
" <td>7.0</td>\n",
" <td>1 days 04:31:01.428571428</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>4</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>797.033437</td>\n",
" <td>797.033437</td>\n",
" <td>0.000000</td>\n",
" <td>2.0</td>\n",
" <td>spectacle vivant</td>\n",
" <td>7.762474</td>\n",
" <td>1.0</td>\n",
" <td>7.0</td>\n",
" <td>7.0</td>\n",
" <td>1 days 04:31:01.428571428</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 41 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id birthdate street_id is_partner gender is_email_true \\\n",
"4 2 NaN 2 False 1 True \n",
"5 2 NaN 2 False 1 True \n",
"6 3 NaN 3 False 1 True \n",
"7 4 NaN 4 False 0 True \n",
"8 4 NaN 4 False 0 True \n",
"\n",
" opt_in structure_id profession language ... purchase_date_min \\\n",
"4 True NaN NaN NaN ... 1705.261192 \n",
"5 True NaN NaN NaN ... 2041.274549 \n",
"6 True NaN NaN NaN ... 1511.177396 \n",
"7 True NaN NaN NaN ... 1511.157396 \n",
"8 True NaN NaN NaN ... 797.033437 \n",
"\n",
" purchase_date_max time_between_purchase nb_tickets_internet \\\n",
"4 1456.333715 248.927477 0.0 \n",
"5 1340.308160 700.966389 0.0 \n",
"6 42.428692 1468.748704 6.0 \n",
"7 1511.157396 0.000000 2.0 \n",
"8 797.033437 0.000000 2.0 \n",
"\n",
" name_event_types avg_amount nb_categories nb_campaigns \\\n",
"4 formule adhésion 6.439463 1.0 4.0 \n",
"5 offre muséale individuel 6.150659 1.0 4.0 \n",
"6 spectacle vivant 7.762474 1.0 222.0 \n",
"7 formule adhésion 6.439463 1.0 7.0 \n",
"8 spectacle vivant 7.762474 1.0 7.0 \n",
"\n",
" nb_campaigns_opened time_to_open \n",
"4 NaN NaN \n",
"5 NaN NaN \n",
"6 124.0 1 days 00:28:30.169354838 \n",
"7 7.0 1 days 04:31:01.428571428 \n",
"8 7.0 1 days 04:31:01.428571428 \n",
"\n",
"[5 rows x 41 columns]"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Chargement des données temporaires\n",
"BUCKET = \"projet-bdc2324-team1\"\n",
"FILE_KEY_S3 = \"0_Temp/Company 1 - customer_event.csv\"\n",
"FILE_PATH_S3 = BUCKET + \"/\" + FILE_KEY_S3\n",
"\n",
"with fs.open(FILE_PATH_S3, mode=\"rb\") as file_in:\n",
" customer = pd.read_csv(file_in, sep=\",\")\n",
"\n",
"print(customer.shape)\n",
"# Remove customer 1 as outlier\n",
"\n",
"customer = customer[customer['customer_id']!=1]\n",
"customer.head()"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "d1f2608a-911c-440e-b7cd-5cd6684b0de3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['customer_id', 'birthdate', 'street_id', 'is_partner', 'gender',\n",
" 'is_email_true', 'opt_in', 'structure_id', 'profession', 'language',\n",
" 'mcp_contact_id', 'last_buying_date', 'max_price', 'ticket_sum',\n",
" 'average_price', 'fidelity', 'average_purchase_delay',\n",
" 'average_price_basket', 'average_ticket_basket', 'total_price',\n",
" 'purchase_count', 'first_buying_date', 'country', 'age', 'tenant_id',\n",
" 'event_type_id', 'nb_tickets', 'nb_purchases', 'total_amount',\n",
" 'nb_suppliers', 'vente_internet_max', 'purchase_date_min',\n",
" 'purchase_date_max', 'time_between_purchase', 'nb_tickets_internet',\n",
" 'name_event_types', 'avg_amount', 'nb_categories', 'nb_campaigns',\n",
" 'nb_campaigns_opened', 'time_to_open'],\n",
" dtype='object')"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer.columns"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "fe5557f9-b629-46bf-a606-a8db2158933c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 6., 2., 4., 5., nan])"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer['event_type_id'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "b1681828-165b-43be-8e42-04af052c132a",
"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>event_type_id</th>\n",
" <th>name_event_types</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6.0</td>\n",
" <td>formule adhésion</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2.0</td>\n",
" <td>offre muséale individuel</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.0</td>\n",
" <td>spectacle vivant</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>5.0</td>\n",
" <td>offre muséale groupe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" event_type_id name_event_types\n",
"4 6.0 formule adhésion\n",
"5 2.0 offre muséale individuel\n",
"6 4.0 spectacle vivant\n",
"16 5.0 offre muséale groupe\n",
"40 NaN NaN"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer[['event_type_id', 'name_event_types']].drop_duplicates()"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "daef46cd-f6a5-4282-ac0a-83fde277edec",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"shape : (21388, 41)\n"
]
}
],
"source": [
"customer_event1 = customer[customer['event_type_id']==2]\n",
"print(\"shape : \", customer_event1.shape)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "cd1103b4-27b5-4be1-8451-43172df2d33e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_551/3565272300.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" customer_event1[\"percent_campaign_opened\"] = 100* (customer_event1[\"nb_campaigns_opened\"] /\n"
]
}
],
"source": [
"customer_event1[\"percent_campaign_opened\"] = 100* (customer_event1[\"nb_campaigns_opened\"] /\n",
" customer_event1[\"nb_campaigns\"])"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "ec19582b-7d84-422c-8f53-9b0eb1bea21e",
"metadata": {},
"outputs": [],
"source": [
"customer_event1 = customer_event1.fillna(0)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "e34437e6-a57d-4d10-ac62-5c43cdda6892",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sklearn.cluster import KMeans\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"columns_for_clustering = [\"percent_campaign_opened\", 'nb_tickets', 'average_price', 'nb_purchases',\n",
" 'average_purchase_delay', 'average_price_basket', 'average_ticket_basket',\n",
" 'nb_categories', 'nb_suppliers']\n",
"\n",
"scaler = StandardScaler()\n",
"X = scaler.fit_transform(customer_event1[columns_for_clustering])\n",
"\n",
"inertia = []\n",
"for i in range(1, 11):\n",
" kmeans = KMeans(n_clusters=i, random_state=42)\n",
" kmeans.fit(X)\n",
" inertia.append(kmeans.inertia_)\n",
"\n",
"# Plot the elbow curve to find the optimal k\n",
"plt.figure(figsize=(8, 6))\n",
"plt.plot(range(1, 11), inertia, marker='o', linestyle='-', color='b')\n",
"plt.xlabel('Number of clusters (k)')\n",
"plt.ylabel('Inertia (Within-cluster sum of squares)')\n",
"plt.title('Elbow Method for Optimal k')\n",
"plt.grid()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "4da7d97e-9128-4e4a-a454-1451d2dfee40",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cluster 1:\n",
"percent_campaign_opened 23.552766\n",
"nb_tickets 4.831229\n",
"average_price 9.073833\n",
"nb_purchases 1.178776\n",
"average_purchase_delay -243.688956\n",
"average_price_basket 19.548741\n",
"average_ticket_basket 3.755214\n",
"nb_categories 1.123118\n",
"nb_suppliers 1.000000\n",
"Name: 0, dtype: float64\n",
"Size: 20590\n",
"\n",
"Cluster 2:\n",
"percent_campaign_opened 35.050398\n",
"nb_tickets 36.677136\n",
"average_price 13.146019\n",
"nb_purchases 4.533920\n",
"average_purchase_delay 40.550181\n",
"average_price_basket 54.766752\n",
"average_ticket_basket 9.094874\n",
"nb_categories 1.918342\n",
"nb_suppliers 2.036432\n",
"Name: 1, dtype: float64\n",
"Size: 796\n",
"\n",
"Cluster 3:\n",
"percent_campaign_opened 49.430524\n",
"nb_tickets 9085.000000\n",
"average_price 1.149821\n",
"nb_purchases 485.000000\n",
"average_purchase_delay -3.941335\n",
"average_price_basket 12.981105\n",
"average_ticket_basket 38.049343\n",
"nb_categories 13.500000\n",
"nb_suppliers 4.500000\n",
"Name: 2, dtype: float64\n",
"Size: 2\n",
"\n"
]
}
],
"source": [
"k = 3 \n",
"\n",
"kmeans = KMeans(n_clusters=k, random_state=42)\n",
"customer_event1['cluster'] = kmeans.fit_predict(X)\n",
"\n",
"cluster_means = customer_event1.groupby('cluster')[columns_for_clustering].mean()\n",
"cluster_sizes = customer_event1['cluster'].value_counts()\n",
"\n",
"for cluster in range(k):\n",
" print(f\"Cluster {cluster + 1}:\")\n",
" print(cluster_means.loc[cluster])\n",
" print(f\"Size: {cluster_sizes[cluster]}\\n\")"
]
}
],
"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