ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
d3e13f4c56
BDC-team-1/Sport/Modelization/segment_analysis_sport_0_6.ipynb

2384 lines
1.2 MiB
Plaintext
Raw Normal View History

completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
{
"cells": [
{
"cell_type": "markdown",
"id": "c488134e-680f-44e4-8c43-40c246140519",
"metadata": {},
"source": [
"# Analysis of segments and marketing personae associated"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 82,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "9a8b8c3a-8e74-49f3-91d1-cccfc057fdcd",
"metadata": {},
"outputs": [],
"source": [
"# importations\n",
"import pandas as pd\n",
"import numpy as np\n",
"import os\n",
"import io\n",
"import s3fs\n",
"import re\n",
"import pickle\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"import warnings\n",
"import matplotlib.pyplot as plt"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 83,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "d553c868-695f-4d57-96d6-d5c6629cefb2",
"metadata": {},
"outputs": [],
"source": [
"def load_model(type_of_activity, model):\n",
" BUCKET = f\"projet-bdc2324-team1/Output_model/{type_of_activity}/{model}/\"\n",
" filename = model + '.pkl'\n",
" file_path = BUCKET + filename\n",
" with fs.open(file_path, mode=\"rb\") as f:\n",
" model_bytes = f.read()\n",
"\n",
" model = pickle.loads(model_bytes)\n",
" return model\n",
"\n",
"\n",
"def load_test_file(type_of_activity):\n",
" file_path_test = f\"projet-bdc2324-team1/Generalization/{type_of_activity}/Test_set.csv\"\n",
" with fs.open(file_path_test, mode=\"rb\") as file_in:\n",
" dataset_test = pd.read_csv(file_in, sep=\",\")\n",
" return dataset_test"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 84,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "3af80fea-a937-4ea8-bece-cfeaa89d1055",
"metadata": {},
"outputs": [],
"source": [
"# exec(open('utils_segmentation.py').read())\n",
"warnings.filterwarnings('ignore')\n",
"\n",
"# Create filesystem object\n",
"S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})\n",
"\n",
"# choose the type of companies for which you want to run the pipeline\n",
"type_of_activity = \"sport\""
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 85,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "cc6af7fa-33b2-4d58-ada4-e2ee7262bab9",
"metadata": {},
"outputs": [],
"source": [
"# load test set\n",
"dataset_test = load_test_file(type_of_activity)\n",
"\n",
"# Load Model \n",
"model = load_model(type_of_activity, 'LogisticRegression_Benchmark')"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 86,
"id": "8238ee71-47ec-4621-9813-4b5d2fd03efd",
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</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>...</th>\n",
" <th>country</th>\n",
" <th>gender_label</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>time_to_open</th>\n",
" <th>y_has_purchased</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5_476624</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>100.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.177187</td>\n",
" <td>5.177187</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5_183496</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>55.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>426.265613</td>\n",
" <td>426.265613</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5_248456</td>\n",
" <td>17.0</td>\n",
" <td>1.0</td>\n",
" <td>80.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>436.033437</td>\n",
" <td>436.033437</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5_474758</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>120.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.196412</td>\n",
" <td>5.196412</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5_192421</td>\n",
" <td>34.0</td>\n",
" <td>2.0</td>\n",
" <td>416.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>478.693148</td>\n",
" <td>115.631470</td>\n",
" <td>363.061678</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</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",
" <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>96091</th>\n",
" <td>9_761001</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>67.31</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>278.442257</td>\n",
" <td>278.442257</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>ch</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>15.0</td>\n",
" <td>5.0</td>\n",
" <td>0 days 00:35:22.600000</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96092</th>\n",
" <td>9_951910</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>61.41</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>189.207373</td>\n",
" <td>189.207373</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>ch</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>12.0</td>\n",
" <td>9.0</td>\n",
" <td>0 days 10:39:13.333333333</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96093</th>\n",
" <td>9_54095</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>ch</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>29.0</td>\n",
" <td>3.0</td>\n",
" <td>0 days 13:44:43.333333333</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96094</th>\n",
" <td>9_755241</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>79.43</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>279.312905</td>\n",
" <td>279.312905</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>fr</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>20.0</td>\n",
" <td>4.0</td>\n",
" <td>0 days 01:12:12.500000</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96095</th>\n",
" <td>9_2712</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>31.0</td>\n",
" <td>4.0</td>\n",
" <td>2 days 01:39:12.750000</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>96096 rows × 40 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 5_476624 4.0 1.0 100.00 1.0 \n",
"1 5_183496 1.0 1.0 55.00 1.0 \n",
"2 5_248456 17.0 1.0 80.00 1.0 \n",
"3 5_474758 4.0 1.0 120.00 1.0 \n",
"4 5_192421 34.0 2.0 416.00 1.0 \n",
"... ... ... ... ... ... \n",
"96091 9_761001 1.0 1.0 67.31 1.0 \n",
"96092 9_951910 1.0 1.0 61.41 1.0 \n",
"96093 9_54095 0.0 0.0 0.00 0.0 \n",
"96094 9_755241 1.0 1.0 79.43 1.0 \n",
"96095 9_2712 0.0 0.0 0.00 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 5.177187 5.177187 \n",
"1 0.0 426.265613 426.265613 \n",
"2 0.0 436.033437 436.033437 \n",
"3 0.0 5.196412 5.196412 \n",
"4 0.0 478.693148 115.631470 \n",
"... ... ... ... \n",
"96091 1.0 278.442257 278.442257 \n",
"96092 1.0 189.207373 189.207373 \n",
"96093 0.0 550.000000 550.000000 \n",
"96094 1.0 279.312905 279.312905 \n",
"96095 0.0 550.000000 550.000000 \n",
"\n",
" time_between_purchase nb_tickets_internet ... country gender_label \\\n",
"0 0.000000 0.0 ... fr female \n",
"1 0.000000 0.0 ... fr male \n",
"2 0.000000 0.0 ... fr female \n",
"3 0.000000 0.0 ... fr female \n",
"4 363.061678 0.0 ... fr female \n",
"... ... ... ... ... ... \n",
"96091 0.000000 1.0 ... ch male \n",
"96092 0.000000 1.0 ... ch male \n",
"96093 -1.000000 0.0 ... ch female \n",
"96094 0.000000 1.0 ... fr male \n",
"96095 -1.000000 0.0 ... NaN male \n",
"\n",
" gender_female gender_male gender_other country_fr nb_campaigns \\\n",
"0 1 0 0 1.0 0.0 \n",
"1 0 1 0 1.0 0.0 \n",
"2 1 0 0 1.0 0.0 \n",
"3 1 0 0 1.0 0.0 \n",
"4 1 0 0 1.0 0.0 \n",
"... ... ... ... ... ... \n",
"96091 0 1 0 0.0 15.0 \n",
"96092 0 1 0 0.0 12.0 \n",
"96093 1 0 0 0.0 29.0 \n",
"96094 0 1 0 1.0 20.0 \n",
"96095 0 1 0 NaN 31.0 \n",
"\n",
" nb_campaigns_opened time_to_open y_has_purchased \n",
"0 0.0 NaN 0.0 \n",
"1 0.0 NaN 1.0 \n",
"2 0.0 NaN 0.0 \n",
"3 0.0 NaN 0.0 \n",
"4 0.0 NaN 1.0 \n",
"... ... ... ... \n",
"96091 5.0 0 days 00:35:22.600000 1.0 \n",
"96092 9.0 0 days 10:39:13.333333333 0.0 \n",
"96093 3.0 0 days 13:44:43.333333333 0.0 \n",
"96094 4.0 0 days 01:12:12.500000 0.0 \n",
"96095 4.0 2 days 01:39:12.750000 0.0 \n",
"\n",
"[96096 rows x 40 columns]"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset_test"
]
},
{
"cell_type": "code",
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 180,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "e4287c1a-eab6-4897-91d6-d21804518dc4",
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</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>is_email_true</th>\n",
" <th>...</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>country_fr</th>\n",
" <th>has_purchased</th>\n",
" <th>has_purchased_estim</th>\n",
" <th>score</th>\n",
" <th>segment</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>100.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.177187</td>\n",
" <td>5.177187</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.700113</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>55.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>426.265613</td>\n",
" <td>426.265613</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.223569</td>\n",
" <td>1</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>17.0</td>\n",
" <td>1.0</td>\n",
" <td>80.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>436.033437</td>\n",
" <td>436.033437</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.246124</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>120.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.196412</td>\n",
" <td>5.196412</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.700106</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>34.0</td>\n",
" <td>2.0</td>\n",
" <td>416.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>478.693148</td>\n",
" <td>115.631470</td>\n",
" <td>363.061678</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.922115</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96091</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>67.31</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>278.442257</td>\n",
" <td>278.442257</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>15.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.571135</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96092</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>61.41</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>189.207373</td>\n",
" <td>189.207373</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>12.0</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.630924</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96093</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>29.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.123418</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96094</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>79.43</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>279.312905</td>\n",
" <td>279.312905</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>20.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.578971</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96095</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>550.000000</td>\n",
" <td>550.000000</td>\n",
" <td>-1.000000</td>\n",
" <td>0.0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>31.0</td>\n",
" <td>4.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.295349</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>96096 rows × 21 columns</p>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 4.0 1.0 100.00 1.0 \n",
"1 1.0 1.0 55.00 1.0 \n",
"2 17.0 1.0 80.00 1.0 \n",
"3 4.0 1.0 120.00 1.0 \n",
"4 34.0 2.0 416.00 1.0 \n",
"... ... ... ... ... \n",
"96091 1.0 1.0 67.31 1.0 \n",
"96092 1.0 1.0 61.41 1.0 \n",
"96093 0.0 0.0 0.00 0.0 \n",
"96094 1.0 1.0 79.43 1.0 \n",
"96095 0.0 0.0 0.00 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 5.177187 5.177187 \n",
"1 0.0 426.265613 426.265613 \n",
"2 0.0 436.033437 436.033437 \n",
"3 0.0 5.196412 5.196412 \n",
"4 0.0 478.693148 115.631470 \n",
"... ... ... ... \n",
"96091 1.0 278.442257 278.442257 \n",
"96092 1.0 189.207373 189.207373 \n",
"96093 0.0 550.000000 550.000000 \n",
"96094 1.0 279.312905 279.312905 \n",
"96095 0.0 550.000000 550.000000 \n",
"\n",
" time_between_purchase nb_tickets_internet is_email_true ... \\\n",
"0 0.000000 0.0 True ... \n",
"1 0.000000 0.0 True ... \n",
"2 0.000000 0.0 True ... \n",
"3 0.000000 0.0 True ... \n",
"4 363.061678 0.0 True ... \n",
"... ... ... ... ... \n",
"96091 0.000000 1.0 True ... \n",
"96092 0.000000 1.0 True ... \n",
"96093 -1.000000 0.0 True ... \n",
"96094 0.000000 1.0 True ... \n",
"96095 -1.000000 0.0 True ... \n",
"\n",
" gender_female gender_male gender_other nb_campaigns \\\n",
"0 1 0 0 0.0 \n",
"1 0 1 0 0.0 \n",
"2 1 0 0 0.0 \n",
"3 1 0 0 0.0 \n",
"4 1 0 0 0.0 \n",
"... ... ... ... ... \n",
"96091 0 1 0 15.0 \n",
"96092 0 1 0 12.0 \n",
"96093 1 0 0 29.0 \n",
"96094 0 1 0 20.0 \n",
"96095 0 1 0 31.0 \n",
"\n",
" nb_campaigns_opened country_fr has_purchased has_purchased_estim \\\n",
"0 0.0 1.0 0.0 1.0 \n",
"1 0.0 1.0 1.0 0.0 \n",
"2 0.0 1.0 0.0 0.0 \n",
"3 0.0 1.0 0.0 1.0 \n",
"4 0.0 1.0 1.0 1.0 \n",
"... ... ... ... ... \n",
"96091 5.0 0.0 1.0 1.0 \n",
"96092 9.0 0.0 0.0 1.0 \n",
"96093 3.0 0.0 0.0 0.0 \n",
"96094 4.0 1.0 0.0 1.0 \n",
"96095 4.0 NaN 0.0 0.0 \n",
"\n",
" score segment \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 0.700113 3 \n",
"1 0.223569 1 \n",
"2 0.246124 1 \n",
"3 0.700106 3 \n",
"4 0.922115 4 \n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"... ... ... \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"96091 0.571135 3 \n",
"96092 0.630924 3 \n",
"96093 0.123418 1 \n",
"96094 0.578971 3 \n",
"96095 0.295349 2 \n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
"[96096 rows x 21 columns]"
]
},
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 180,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Processing\n",
"X_test = dataset_test[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', \n",
" 'time_between_purchase', 'nb_tickets_internet', 'is_email_true', 'opt_in', #'is_partner',\n",
minor change
2024-03-27 16:06:31 +01:00
" 'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened', 'country_fr']]\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
"y_test = dataset_test[['y_has_purchased']]\n",
"\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"X_test_segment = X_test\n",
"\n",
minor change
2024-03-27 16:06:31 +01:00
"# X_test_segment.insert(X_test.shape[1], \"country_fr\", dataset_test[\"country_fr\"])\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
"# add y_has_purchased to X_test\n",
"X_test_segment[\"has_purchased\"] = y_test\n",
"\n",
"# Add prediction and probability to dataset_test\n",
"y_pred = model.predict(X_test)\n",
"X_test_segment[\"has_purchased_estim\"] = y_pred\n",
"\n",
"y_pred_prob = model.predict_proba(X_test)[:, 1]\n",
"X_test_segment['score'] = y_pred_prob\n",
"\n",
"X_test_segment[\"segment\"] = np.where(X_test_segment['score']<0.25, '1',\n",
" np.where(X_test_segment['score']<0.5, '2',\n",
" np.where(X_test_segment['score']<0.75, '3', '4')))\n",
"\n",
"X_test_segment"
]
},
{
"cell_type": "markdown",
"id": "9058c3b2-8fa2-4322-a57b-395da4033eaf",
"metadata": {},
"source": [
"## 1. Business KPIs"
]
},
{
"cell_type": "code",
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 181,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "3067d919-50c9-49e9-b0a6-b676a5dbae56",
"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>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>vente_internet_max</th>\n",
" <th>nb_tickets_internet</th>\n",
" </tr>\n",
" <tr>\n",
" <th>segment</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>4324.0</td>\n",
" <td>1446.0</td>\n",
" <td>8.973214e+04</td>\n",
" <td>346.0</td>\n",
" <td>870.0</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>36094.0</td>\n",
" <td>15451.0</td>\n",
" <td>1.138007e+06</td>\n",
" <td>8046.0</td>\n",
" <td>19591.0</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>65817.0</td>\n",
" <td>30677.0</td>\n",
" <td>2.209794e+06</td>\n",
" <td>14407.0</td>\n",
" <td>37260.0</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>392936.0</td>\n",
" <td>102142.0</td>\n",
" <td>1.650005e+07</td>\n",
" <td>6659.0</td>\n",
" <td>112518.0</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount vente_internet_max \\\n",
"segment \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"1 4324.0 1446.0 8.973214e+04 346.0 \n",
"2 36094.0 15451.0 1.138007e+06 8046.0 \n",
"3 65817.0 30677.0 2.209794e+06 14407.0 \n",
"4 392936.0 102142.0 1.650005e+07 6659.0 \n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
" nb_tickets_internet \n",
"segment \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"1 870.0 \n",
"2 19591.0 \n",
"3 37260.0 \n",
"4 112518.0 "
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 181,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# business figures\n",
"X_test_segment.groupby(\"segment\")[[\"nb_tickets\", \"nb_purchases\", \"total_amount\", \"vente_internet_max\", \n",
" \"nb_tickets_internet\"]].sum()"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 171,
"id": "5b1acd28-b346-45b1-8da2-b79ca7f4fa96",
"metadata": {},
"outputs": [],
"source": [
"def df_business_fig(df, segment, list_var) :\n",
" df_business_kpi = df.groupby(segment)[list_var].sum().reset_index()\n",
" df_business_kpi.insert(1, \"size\", df.groupby(segment).size().values)\n",
" all_var = [\"size\"] + list_var\n",
" df_business_kpi[all_var] = 100 * df_business_kpi[all_var] / df_business_kpi[all_var].sum()\n",
"\n",
" return df_business_kpi"
]
},
{
"cell_type": "code",
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 182,
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"id": "bd63d787-3ef8-4f23-9069-e9b16b4a0de8",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"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>segment</th>\n",
" <th>size</th>\n",
" <th>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_campaigns</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>48.776224</td>\n",
" <td>0.866236</td>\n",
" <td>0.965829</td>\n",
" <td>0.450065</td>\n",
" <td>41.498188</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>19.887404</td>\n",
" <td>7.230789</td>\n",
" <td>10.320206</td>\n",
" <td>5.707847</td>\n",
" <td>24.826893</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>21.990509</td>\n",
" <td>13.185261</td>\n",
" <td>20.490128</td>\n",
" <td>11.083558</td>\n",
" <td>17.737544</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>9.345862</td>\n",
" <td>78.717714</td>\n",
" <td>68.223837</td>\n",
" <td>82.758529</td>\n",
" <td>15.937376</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment size nb_tickets nb_purchases total_amount nb_campaigns\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 1 48.776224 0.866236 0.965829 0.450065 41.498188\n",
"1 2 19.887404 7.230789 10.320206 5.707847 24.826893\n",
"2 3 21.990509 13.185261 20.490128 11.083558 17.737544\n",
"3 4 9.345862 78.717714 68.223837 82.758529 15.937376"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 182,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"business_var = [\"nb_tickets\", \"nb_purchases\", \"total_amount\", \"nb_campaigns\"]\n",
"X_test_business_fig = df_business_fig(X_test_segment, \"segment\",\n",
" business_var)\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"X_test_business_fig"
]
},
{
"cell_type": "code",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"execution_count": 57,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "d2f618b6-c984-4790-bd8f-29c7d01c6707",
"metadata": {},
"outputs": [],
"source": [
"def hist_segment_business_KPIs(df, segment, size, nb_tickets, nb_purchases, total_amount, nb_campaigns) :\n",
" \n",
" plt.figure()\n",
"\n",
" df_plot = df[[segment, size, nb_tickets, nb_purchases, total_amount, nb_campaigns]]\n",
" \n",
" x = [\"number of\\ncustomers\", \"number of\\ntickets\", \"number of\\npurchases\", \"total\\namount\", \n",
" \"number of\\ncampaigns\"]\n",
"\n",
" # liste_var = [size, nb_tickets, nb_purchases, total_amount]\n",
" \n",
" bottom = np.zeros(5)\n",
" \n",
" # Définir une palette de couleurs\n",
" colors = plt.cm.Blues(np.linspace(0.1, 0.9, 4))\n",
" \n",
" for i in range(4) :\n",
" # print(str(df_plot[segment][i]))\n",
" # segment = df_plot[segment][i]\n",
" height = list(df_plot.loc[i,size:].values)\n",
" \n",
" plt.bar(x=x, height=height, label = str(df_plot[segment][i]), bottom=bottom, color=colors[i]#, width=0.1\n",
" )\n",
" \n",
" bottom+=height\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"\n",
" # Ajuster les marges\n",
" plt.subplots_adjust(left = 0.125, right = 0.8,\n",
" bottom = 0.1, top = 0.9\n",
" )\n",
"\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" \n",
" plt.legend(title = \"segment\", loc = \"upper right\", bbox_to_anchor=(1.2, 1))\n",
" plt.ylabel(\"Fraction represented by the segment (%)\")\n",
" plt.title(\"Relative weight of each segment regarding business KPIs\")\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
" # plt.show()\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" "
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 146,
"id": "14b6ae5c-d704-4f5d-9f9b-5646e29ea470",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"outputs": [
{
"data": {
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"image/png": "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
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"hist_segment_business_KPIs(X_test_business_fig, \"segment\", \"size\", *business_var)"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "code",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"execution_count": 13,
"id": "f358fba3-f778-4414-bf55-c830be647ddd",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"'projet-bdc2324-team1/Output_marketing_personae_analysis/sport/segments_business_KPIs_sport.csv'"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"execution_count": 13,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"source": [
"activity = \"sport\"\n",
"PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{activity}/\"\n",
"\n",
"file_name = \"segments_business_KPIs_\" + activity\n",
"FILE_PATH_OUT_S3 = PATH + file_name + \".csv\"\n",
"\n",
"FILE_PATH_OUT_S3"
]
},
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
{
"cell_type": "code",
"execution_count": 178,
"id": "3eee7b59-f658-402d-95b2-fa051188fd10",
"metadata": {},
"outputs": [],
"source": [
"def save_file_s3_mp(File_name, type_of_activity):\n",
" image_buffer = io.BytesIO()\n",
" plt.savefig(image_buffer, format='png')\n",
" image_buffer.seek(0)\n",
" PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{type_of_activity}/\"\n",
" FILE_PATH_OUT_S3 = PATH + File_name + type_of_activity + '.png'\n",
" with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
" plt.close()"
]
},
added options to save plots in S3
2024-03-26 16:00:39 +01:00
{
"cell_type": "code",
"execution_count": 59,
"id": "1790cb81-3304-41f1-a371-d8c926d32906",
"metadata": {},
"outputs": [],
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"source": [
"# save to Minio\n",
"\n",
"activity = \"sport\"\n",
"PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{activity}/\"\n",
"\n",
"file_name = \"segments_business_KPIs_\" + activity\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"FILE_PATH_OUT_S3 = PATH + file_name + \".png\"\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
"hist_segment_business_KPIs(X_test_business_fig, \"segment\", \"size\", \"nb_tickets\", \n",
" \"nb_purchases\", \"total_amount\", \"nb_campaigns\")\n",
"\n",
"image_buffer = io.BytesIO()\n",
"plt.savefig(image_buffer, format='png')\n",
"image_buffer.seek(0)\n",
"\n",
"with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"plt.close()\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 179,
"id": "7a42523d-f80f-488b-ad8f-39dd793cddd6",
"metadata": {},
"outputs": [
{
"ename": "ClientError",
"evalue": "An error occurred (InvalidAccessKeyId) when calling the PutObject operation: The Access Key Id you provided does not exist in our records.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mClientError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[179], line 8\u001b[0m\n\u001b[1;32m 3\u001b[0m activity \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msport\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 5\u001b[0m hist_segment_business_KPIs(X_test_business_fig, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msegment\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnb_tickets\u001b[39m\u001b[38;5;124m\"\u001b[39m, \n\u001b[1;32m 6\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnb_purchases\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtotal_amount\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnb_campaigns\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 8\u001b[0m \u001b[43msave_file_s3_mp\u001b[49m\u001b[43m(\u001b[49m\u001b[43mFile_name\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msegments_business_KPIs_\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtype_of_activity\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mactivity\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[0;32mIn[178], line 7\u001b[0m, in \u001b[0;36msave_file_s3_mp\u001b[0;34m(File_name, type_of_activity)\u001b[0m\n\u001b[1;32m 5\u001b[0m PATH \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprojet-bdc2324-team1/Output_marketing_personae_analysis/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtype_of_activity\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 6\u001b[0m FILE_PATH_OUT_S3 \u001b[38;5;241m=\u001b[39m PATH \u001b[38;5;241m+\u001b[39m File_name \u001b[38;5;241m+\u001b[39m type_of_activity \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.png\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 7\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mwith\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mFILE_PATH_OUT_S3\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mwb\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mas\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ms3_file\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43ms3_file\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwrite\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimage_buffer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 9\u001b[0m plt\u001b[38;5;241m.\u001b[39mclose()\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1963\u001b[0m, in \u001b[0;36mAbstractBufferedFile.__exit__\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m 1962\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__exit__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs):\n\u001b[0;32m-> 1963\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclose\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1930\u001b[0m, in \u001b[0;36mAbstractBufferedFile.close\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1928\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1929\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mforced:\n\u001b[0;32m-> 1930\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mflush\u001b[49m\u001b[43m(\u001b[49m\u001b[43mforce\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 1932\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfs \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 1933\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfs\u001b[38;5;241m.\u001b[39minvalidate_cache(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1801\u001b[0m, in \u001b[0;36mAbstractBufferedFile.flush\u001b[0;34m(self, force)\u001b[0m\n\u001b[1;32m 1798\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclosed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 1799\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m\n\u001b[0;32m-> 1801\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_upload_chunk\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfinal\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m:\n\u001b[1;32m 1802\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moffset \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuffer\u001b[38;5;241m.\u001b[39mseek(\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m2\u001b[39m)\n\u001b[1;32m 1803\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuffer \u001b[38;5;241m=\u001b[39m io\u001b[38;5;241m.\u001b[39mBytesIO()\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:1252\u001b[0m, in \u001b[0;36mS3File._upload_chunk\u001b[0;34m(self, final)\u001b[0m\n\u001b[1;32m 1249\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparts\u001b[38;5;241m.\u001b[39mappend({\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPartNumber\u001b[39m\u001b[38;5;124m'\u001b[39m: part, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mETag\u001b[39m\u001b[38;5;124m'\u001b[39m: out[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mETag\u001b[39m\u001b[38;5;124m'\u001b[39m]})\n\u001b[1;32m 1251\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mautocommit \u001b[38;5;129;01mand\u001b[39;00m final:\n\u001b[0;32m-> 1252\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcommit\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1253\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m final\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:1267\u001b[0m, in \u001b[0;36mS3File.commit\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1265\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuffer\u001b[38;5;241m.\u001b[39mseek(\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m 1266\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuffer\u001b[38;5;241m.\u001b[39mread()\n\u001b[0;32m-> 1267\u001b[0m write_result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_s3\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1268\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43ms3\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mput_object\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1269\u001b[0m \u001b[43m \u001b[49m\u001b[43mKey\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[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mBucket\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[43mbucket\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mBody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;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[43mkwargs\u001b[49m\n\u001b[1;32m 1270\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfs\u001b[38;5;241m.\u001b[39mversion_aware:\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mversion_id \u001b[38;5;241m=\u001b[39m write_result\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mVersionId\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:1130\u001b[0m, in \u001b[0;36mS3File._call_s3\u001b[0;34m(self, method, *kwarglist, **kwargs)\u001b[0m\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call_s3\u001b[39m(\u001b[38;5;28mself\u001b[39m, method, \u001b[38;5;241m*\u001b[39mkwarglist, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_s3\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43ms3_additional_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwarglist\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:200\u001b[0m, in \u001b[0;36mS3FileSystem._call_s3\u001b[0;34m(self, method, *akwarglist, **kwargs)\u001b[0m\n\u001b[1;32m 197\u001b[0m logger\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCALL: \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m - \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m - \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m (method\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, akwarglist, kw2))\n\u001b[1;32m 198\u001b[0m additional_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_s3_method_kwargs(method, \u001b[38;5;241m*\u001b[39makwarglist,\n\u001b[1;32m 199\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 200\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmethod\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43madditional_kwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:553\u001b[0m, in \u001b[0;36mClientCreator._create_api_method.<locals>._api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 549\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[1;32m 550\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpy_operation_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m() only accepts keyword arguments.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 551\u001b[0m )\n\u001b[1;32m 552\u001b[0m \u001b[38;5;66;03m# The \"self\" in this scope is referring to the BaseClient.\u001b[39;00m\n\u001b[0;32m--> 553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_api_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43moperation_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:1009\u001b[0m, in \u001b[0;36mBaseClient._make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m 1005\u001b[0m error_code \u001b[38;5;241m=\u001b[39m error_info\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mQueryErrorCode\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m error_info\u001b[38;5;241m.\u001b[39mget(\n\u001b[1;32m 1006\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCode\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1007\u001b[0m )\n\u001b[1;32m 1008\u001b[0m error_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexceptions\u001b[38;5;241m.\u001b[39mfrom_code(error_code)\n\u001b[0;32m-> 1009\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error_class(parsed_response, operation_name)\n\u001b[1;32m 1010\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1011\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parsed_response\n",
"\u001b[0;31mClientError\u001b[0m: An error occurred (InvalidAccessKeyId) when calling the PutObject operation: The Access Key Id you provided does not exist in our records."
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# with function\n",
"\n",
"activity = \"sport\"\n",
"\n",
"hist_segment_business_KPIs(X_test_business_fig, \"segment\", \"size\", \"nb_tickets\", \n",
" \"nb_purchases\", \"total_amount\", \"nb_campaigns\")\n",
"\n",
"save_file_s3_mp(File_name = \"segments_business_KPIs_\", type_of_activity = activity)"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "markdown",
"id": "53d24165-6b98-4b66-9ad8-7514564689d8",
"metadata": {},
"source": [
"## 2. Spider plot summarizing sociodemographic characteristics and purchasing behaviour"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 165,
"id": "beb31e4b-a01b-4312-879a-fe5757ea061f",
"metadata": {},
"outputs": [],
"source": [
"def df_segment_mp(df, segment, gender_female, gender_male, gender_other, country_fr) :\n",
" df_mp = df.groupby(segment)[[gender_female, gender_male, gender_other, country_fr]].mean().reset_index()\n",
" df_mp.insert(3, \"share_known_gender\", X_test_segment_mp[gender_female]+X_test_segment_mp[gender_male])\n",
" df_mp.insert(4, \"share_of_women\", X_test_segment_mp[gender_female]/(X_test_segment_mp[\"share_known_gender\"]))\n",
" return df_mp"
]
},
{
"cell_type": "code",
"execution_count": 159,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "267ebaee-eaef-4720-8ca9-e40c0cf125df",
"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>segment</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>share_known_gender</th>\n",
" <th>share_of_women</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.222670</td>\n",
" <td>0.419974</td>\n",
" <td>0.642644</td>\n",
" <td>0.346491</td>\n",
" <td>0.357356</td>\n",
" <td>0.477963</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.274449</td>\n",
" <td>0.556486</td>\n",
" <td>0.830935</td>\n",
" <td>0.330290</td>\n",
" <td>0.169065</td>\n",
" <td>0.763818</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.272998</td>\n",
" <td>0.541312</td>\n",
" <td>0.814310</td>\n",
" <td>0.335251</td>\n",
" <td>0.185690</td>\n",
" <td>0.661414</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.206547</td>\n",
" <td>0.622871</td>\n",
" <td>0.829418</td>\n",
" <td>0.249027</td>\n",
" <td>0.170582</td>\n",
" <td>0.657373</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment gender_female gender_male share_known_gender share_of_women \\\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 1 0.222670 0.419974 0.642644 0.346491 \n",
"1 2 0.274449 0.556486 0.830935 0.330290 \n",
"2 3 0.272998 0.541312 0.814310 0.335251 \n",
"3 4 0.206547 0.622871 0.829418 0.249027 \n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
" gender_other country_fr \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 0.357356 0.477963 \n",
"1 0.169065 0.763818 \n",
"2 0.185690 0.661414 \n",
"3 0.170582 0.657373 "
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 159,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# description of marketing personae\n",
"\n",
"X_test_segment_mp = X_test_segment.groupby(\"segment\")[['gender_female', 'gender_male', 'gender_other', 'country_fr']].mean().reset_index()\n",
"X_test_segment_mp.insert(3, \"share_known_gender\", X_test_segment_mp[\"gender_female\"]+X_test_segment_mp[\"gender_male\"])\n",
"X_test_segment_mp.insert(4, \"share_of_women\", X_test_segment_mp[\"gender_female\"]/(X_test_segment_mp[\"share_known_gender\"]))\n",
"X_test_segment_mp"
]
},
{
"cell_type": "code",
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 183,
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"id": "5f908232-b0fe-4707-a8c5-5cadb7d8653f",
"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>segment</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>share_known_gender</th>\n",
" <th>share_of_women</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.222670</td>\n",
" <td>0.419974</td>\n",
" <td>0.642644</td>\n",
" <td>0.346491</td>\n",
" <td>0.357356</td>\n",
" <td>0.477963</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.274449</td>\n",
" <td>0.556486</td>\n",
" <td>0.830935</td>\n",
" <td>0.330290</td>\n",
" <td>0.169065</td>\n",
" <td>0.763818</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.272998</td>\n",
" <td>0.541312</td>\n",
" <td>0.814310</td>\n",
" <td>0.335251</td>\n",
" <td>0.185690</td>\n",
" <td>0.661414</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.206547</td>\n",
" <td>0.622871</td>\n",
" <td>0.829418</td>\n",
" <td>0.249027</td>\n",
" <td>0.170582</td>\n",
" <td>0.657373</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment gender_female gender_male share_known_gender share_of_women \\\n",
"0 1 0.222670 0.419974 0.642644 0.346491 \n",
"1 2 0.274449 0.556486 0.830935 0.330290 \n",
"2 3 0.272998 0.541312 0.814310 0.335251 \n",
"3 4 0.206547 0.622871 0.829418 0.249027 \n",
"\n",
" gender_other country_fr \n",
"0 0.357356 0.477963 \n",
"1 0.169065 0.763818 \n",
"2 0.185690 0.661414 \n",
"3 0.170582 0.657373 "
]
},
minor change
2024-03-27 16:06:31 +01:00
"execution_count": 183,
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment_mp = df_segment_mp(X_test_segment, \"segment\", \"gender_female\", \n",
" \"gender_male\", \"gender_other\", \"country_fr\")\n",
"X_test_segment_mp"
]
},
{
"cell_type": "code",
"execution_count": 150,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "910876fe-e6df-4f8d-9978-5d6fdd893ac0",
"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>segment</th>\n",
" <th>share_tickets_internet</th>\n",
" <th>share_campaigns_opened</th>\n",
" <th>opt_in</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.247851</td>\n",
" <td>0.136462</td>\n",
" <td>0.595110</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.630889</td>\n",
" <td>0.233739</td>\n",
" <td>0.411281</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.679076</td>\n",
" <td>0.297721</td>\n",
" <td>0.045523</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.588024</td>\n",
" <td>0.366443</td>\n",
" <td>0.134395</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment share_tickets_internet share_campaigns_opened opt_in\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 1 0.247851 0.136462 0.595110\n",
"1 2 0.630889 0.233739 0.411281\n",
"2 3 0.679076 0.297721 0.045523\n",
"3 4 0.588024 0.366443 0.134395"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 150,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# purchasing behaviour\n",
"\n",
"X_test_segment[\"share_tickets_internet\"] = X_test_segment[\"nb_tickets_internet\"]/X_test_segment[\"nb_tickets\"]\n",
"X_test_segment[\"share_campaigns_opened\"] = X_test_segment[\"nb_campaigns_opened\"]/X_test_segment[\"nb_campaigns\"]\n",
"X_test_segment_pb = X_test_segment.groupby(\"segment\")[[\"share_tickets_internet\", \"share_campaigns_opened\", \"opt_in\"]].mean().reset_index()\n",
"X_test_segment_pb"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 168,
"id": "8d3ab073-040c-4480-bd44-33fc88626707",
"metadata": {},
"outputs": [],
"source": [
"def df_segment_pb (df, segment, nb_tickets_internet, nb_tickets, nb_campaigns_opened, nb_campaigns, opt_in) :\n",
" df_used = df\n",
" df_used[\"share_tickets_internet\"] = df_used[nb_tickets_internet]/df_used[nb_tickets]\n",
" df_used[\"share_campaigns_opened\"] = df_used[nb_campaigns_opened]/df_used[nb_campaigns]\n",
" df_pb = df_used.groupby(segment)[[\"share_tickets_internet\", \"share_campaigns_opened\", opt_in]].mean().reset_index()\n",
" return df_pb"
]
},
{
"cell_type": "code",
"execution_count": 170,
"id": "0cb8f47a-bf0f-4285-b2ff-d90de394c787",
"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>segment</th>\n",
" <th>share_tickets_internet</th>\n",
" <th>share_campaigns_opened</th>\n",
" <th>opt_in</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.247851</td>\n",
" <td>0.136462</td>\n",
" <td>0.595110</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.630889</td>\n",
" <td>0.233739</td>\n",
" <td>0.411281</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.679076</td>\n",
" <td>0.297721</td>\n",
" <td>0.045523</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.588024</td>\n",
" <td>0.366443</td>\n",
" <td>0.134395</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment share_tickets_internet share_campaigns_opened opt_in\n",
"0 1 0.247851 0.136462 0.595110\n",
"1 2 0.630889 0.233739 0.411281\n",
"2 3 0.679076 0.297721 0.045523\n",
"3 4 0.588024 0.366443 0.134395"
]
},
"execution_count": 170,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment_pb = df_segment_pb(X_test_segment, \"segment\", \"nb_tickets_internet\", \"nb_tickets\", \n",
" \"nb_campaigns_opened\", \"nb_campaigns\", \"opt_in\")\n",
"X_test_segment_pb"
]
},
{
"cell_type": "code",
"execution_count": 151,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "ba2884e3-004a-4554-ab82-6d477dcc4869",
"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>segment</th>\n",
" <th>share_tickets_internet</th>\n",
" <th>share_campaigns_opened</th>\n",
" <th>opt_in</th>\n",
" <th>share_known_gender</th>\n",
" <th>share_of_women</th>\n",
" <th>country_fr</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.247851</td>\n",
" <td>0.136462</td>\n",
" <td>0.595110</td>\n",
" <td>0.642644</td>\n",
" <td>0.346491</td>\n",
" <td>0.477963</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.630889</td>\n",
" <td>0.233739</td>\n",
" <td>0.411281</td>\n",
" <td>0.830935</td>\n",
" <td>0.330290</td>\n",
" <td>0.763818</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.679076</td>\n",
" <td>0.297721</td>\n",
" <td>0.045523</td>\n",
" <td>0.814310</td>\n",
" <td>0.335251</td>\n",
" <td>0.661414</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" <td>0.588024</td>\n",
" <td>0.366443</td>\n",
" <td>0.134395</td>\n",
" <td>0.829418</td>\n",
" <td>0.249027</td>\n",
" <td>0.657373</td>\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" segment share_tickets_internet share_campaigns_opened opt_in \\\n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 1 0.247851 0.136462 0.595110 \n",
"1 2 0.630889 0.233739 0.411281 \n",
"2 3 0.679076 0.297721 0.045523 \n",
"3 4 0.588024 0.366443 0.134395 \n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
" share_known_gender share_of_women country_fr \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"0 0.642644 0.346491 0.477963 \n",
"1 0.830935 0.330290 0.763818 \n",
"2 0.814310 0.335251 0.661414 \n",
"3 0.829418 0.249027 0.657373 "
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 151,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment_caract = pd.concat([X_test_segment_pb, X_test_segment_mp[['share_known_gender', 'share_of_women', 'country_fr']]], axis=1)\n",
"X_test_segment_caract"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 152,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "23a37e9b-bb29-4122-85cb-cc15cc344ee2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"share_tickets_internet 0.679076\n",
"share_campaigns_opened 0.366443\n",
"opt_in 0.595110\n",
"share_known_gender 0.830935\n",
"share_of_women 0.346491\n",
"country_fr 0.763818\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"dtype: float64"
]
},
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 152,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment_caract.loc[:,\"share_tickets_internet\":].max()"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 153,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "0809e2ae-3487-4b24-8f60-741c683cb9af",
"metadata": {},
"outputs": [],
"source": [
"# def d'une fonction associée - KEEP THIS !!!\n",
"\n",
"def radar_mp_plot(df, categories, index) :\n",
" categories = categories\n",
"\n",
" # true values are used to print the true value in parenthesis\n",
" tvalues = list(df.loc[index,categories]) \n",
"\n",
" max_values = df[categories].max()\n",
"\n",
" # values are true values / max among the 4 segments, allows to \n",
" # put values in relation with the values for other segments\n",
" # if the point has a maximal abscisse it means that value is maximal for the segment considered\n",
" # , event if not equal to 1\n",
" \n",
" values = list(df.loc[index,categories]/max_values)\n",
" \n",
" # values normalized are used to adjust the value around the circle\n",
" # for instance if the maximum of values is equal to 0.8, we want the point to be \n",
" # at 8/10th of the circle radius, not at the edge \n",
" values_normalized = [ max(values) * elt for elt in values]\n",
"\n",
" # Nb of categories\n",
" num_categories = len(categories)\n",
" \n",
" angles = np.linspace(0, 2 * np.pi, num_categories, endpoint=False).tolist()\n",
" \n",
" # Initialize graphic\n",
" fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))\n",
" \n",
" # we have to draw first a transparent line (alpha=0) of values to adjust the radius of the circle\n",
" # which is based on max(value)\n",
" ax.plot(angles + angles[:1], values + values[:1], color='skyblue', alpha=0, linewidth=1.5)\n",
" ax.plot(angles + angles[:1], values_normalized + values_normalized[:1], color='black', alpha = 0.5, linewidth=1.2)\n",
" \n",
" # fill the sector\n",
" ax.fill(angles, values_normalized, color='orange', alpha=0.4)\n",
" \n",
" # labels\n",
" ax.set_yticklabels([])\n",
" ax.set_xticks(angles)\n",
" ticks = [categories[i].replace(\"_\",\" \") + f\"\\n({round(100 * tvalues[i],2)}%)\" for i in range(len(categories))]\n",
" ax.set_xticklabels(ticks, color=\"black\")\n",
" \n",
" ax.spines['polar'].set_visible(False)\n",
" \n",
" plt.title(f'Characteristics of the segment {index+1}\\n')\n",
" \n",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
" # plt.show()"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 157,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "56cb026b-857f-42eb-baed-0ebdf5aee447",
"metadata": {},
"outputs": [
{
"data": {
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"image/png": "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
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"text/plain": [
"<Figure size 600x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"categories = list(X_test_segment_caract.drop(\"segment\", axis=1).columns)\n",
"#for i in range(4) :\n",
"# radar_mp_plot(df=X_test_segment_caract, categories=categories, index=i)\n",
"radar_mp_plot(df=X_test_segment_caract, categories=categories, index=3)"
]
},
{
"cell_type": "code",
"execution_count": 739,
"id": "5b3c4bac-396e-4117-a7d9-f39a3d8f95b4",
"metadata": {},
"outputs": [
{
"ename": "SyntaxError",
"evalue": "invalid syntax (4005960846.py, line 6)",
"output_type": "error",
"traceback": [
"\u001b[0;36m Cell \u001b[0;32mIn[739], line 6\u001b[0;36m\u001b[0m\n\u001b[0;31m file_name = \"spider_chart_\" + activity + \"_sgt_\" str(index)\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
]
}
],
"source": [
"# export to MinIo\n",
"\n",
"activity = \"sport\"\n",
"PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{activity}/\"\n",
"\n",
"file_name = \"spider_chart_\" + activity + \"_sgt_\" + str(index)\n",
"FILE_PATH_OUT_S3 = PATH + file_name + \".csv\"\n",
"\n",
"\n",
"radar_mp_plot(df=X_test_segment_caract, categories=categories, index=3)\n",
"\n",
"image_buffer = io.BytesIO()\n",
"plt.savefig(image_buffer, format='png')\n",
"image_buffer.seek(0)\n",
"\n",
"with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
"plt.close()"
]
},
{
"cell_type": "code",
"execution_count": 740,
"id": "276de9a5-d506-4c11-a7c2-a23ebbc59fe5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'projet-bdc2324-team1/Output_marketing_personae_analysis/sport/spider_chart_sport_sgt_3.csv'"
]
},
"execution_count": 740,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"activity = \"sport\"\n",
"PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{activity}/\"\n",
"\n",
"file_name = \"spider_chart_\" + activity + \"_sgt_\" + str(index)\n",
"FILE_PATH_OUT_S3 = PATH + file_name + \".csv\"\n",
"FILE_PATH_OUT_S3"
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 154,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "80e47dbc-3efd-4857-8055-876b308cbcb5",
"metadata": {},
"outputs": [],
"source": [
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"# general function to have the 4 radars in one plot\n",
"\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"def radar_mp_plot_all(df, categories) :\n",
" \n",
" nb_segments = df.shape[0]\n",
" categories = categories\n",
"\n",
" # Initialize graphic\n",
" fig, ax = plt.subplots(2,2, figsize=(25, 20), subplot_kw=dict(polar=True))\n",
" \n",
" for index in range(nb_segments) :\n",
" row = index // 2 # Division entière pour obtenir le numéro de ligne\n",
" col = index % 2 \n",
" \n",
" df = X_test_segment_caract\n",
" \n",
" # true values are used to print the true value in parenthesis\n",
" tvalues = list(df.loc[index,categories]) \n",
" \n",
" max_values = df[categories].max()\n",
" \n",
" # values are true values / max among the 4 segments, allows to \n",
" # put values in relation with the values for other segments\n",
" # if the point has a maximal abscisse it means that value is maximal for the segment considered\n",
" # , event if not equal to 1\n",
" \n",
" values = list(df.loc[index,categories]/max_values)\n",
" \n",
" # values normalized are used to adjust the value around the circle\n",
" # for instance if the maximum of values is equal to 0.8, we want the point to be \n",
" # at 8/10th of the circle radius, not at the edge \n",
" values_normalized = [ max(values) * elt for elt in values]\n",
" \n",
" # Nb of categories\n",
" num_categories = len(categories)\n",
"\n",
" angles = np.linspace(0, 2 * np.pi, num_categories, endpoint=False).tolist()\n",
" \n",
" # we have to draw first a transparent line (alpha=0) of values to adjust the radius of the circle\n",
" # which is based on max(value)\n",
" ax[row, col].plot(angles + angles[:1], values + values[:1], color='skyblue', alpha=0, linewidth=1.5)\n",
" ax[row, col].plot(angles + angles[:1], values_normalized + values_normalized[:1], color='black', alpha = 0.5, linewidth=1.2)\n",
" \n",
" # fill the sector\n",
" ax[row, col].fill(angles, values_normalized, color='orange', alpha=0.4, label = index)\n",
" \n",
" # labels\n",
" ax[row, col].set_yticklabels([])\n",
" ax[row, col].set_xticks(angles)\n",
" ticks = [categories[i].replace(\"_\",\" \") + f\"\\n({round(100 * tvalues[i],2)}%)\" for i in range(len(categories))]\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
" ax[row, col].set_xticklabels(ticks, color=\"black\", size = 20)\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
" \n",
" ax[row, col].spines['polar'].set_visible(False)\n",
" \n",
" # plt.title(f'Characteristics of the segment {index+1}\\n')\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
" ax[row, col].set_title(f'Characteristics of the segment {index+1}\\n', size = 24)\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
" # plt.show()"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "code",
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"execution_count": 156,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "edf76688-1b7e-469e-873f-4884d551be66",
"metadata": {},
"outputs": [
{
"data": {
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"image/png": "iVBORw0KGgoAAAANSUhEUgAACDoAAAZgCAYAAACVvbXGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd3gUVf828HvTNr2QSjqhJfTQQzH0piBFKSIEUAERuwKiP0AfFcWGogj4KEUBEZDeEiAJNYQACQklgRQglVTS+3n/4M08WbK72TSSwP25rr0yu3PmnDOzM2dnvjlzRiaEECAiIiIiIiIiIiIiIiIiIiJqBrQauwJEREREREREREREREREREREmmJHByIiIiIiIiIiIiIiIiIiImo22NGBiIiIiIiIiIiIiIiIiIiImg12dCAiIiIiIiIiIiIiIiIiIqJmgx0diIiIiIiIiIiIiIiIiIiIqNlgRwciIiIiIiIiIiIiIiIiIiJqNtjRgYiIiIiIiIiIiIiIiIiIiJoNdnQgIiIiIiIiIiIiIiIiIiKiZoMdHYiIiIiIiIiIiIiIiIiIiKjZYEcHIqoXgwYNgkwmg0wmQ0BAQGNXh5qBTZs2SfvMrFmzGrs6VXCfrp2ysjL8/vvvGDFiBGxtbaGnp/fYv+emvm8REREREVHd8HqNaqqpXydyn64dxiCIiIiebjqNXQEialwPHjzAkSNH4Ofnh0uXLiE1NRVpaWnQ09ODhYUF2rdvj169emHs2LHw8vJq7OoSURNWXFyM0aNH4+TJk41dFSKqB2lpaQgJCcHFixdx8eJFhISEICkpSZrv7++PQYMGNV4FiYiIqNlhDIKI6gtjEERPjuLiYpw6dQonTpxASEgIbt68ibS0NACApaUlOnfujGHDhmH27Nlo0aJFI9eWiJoSdnQgekrl5+dj9erV+Pbbb5GZmVllfnFxMXJzc3Hv3j0cP34cK1euRLt27bBixQpMnToVMpmsEWpNj5o1axY2b94MANi4cSN7jqswaNAgBAYGAuA/5hrSd999pxBg8Pb2Rps2baCvrw8A6Nu3b43zDAgIwODBg6X8eGcL0UOVf4eFEPWef79+/XD+/Pl6z5eIiIieToxBPBkYg9AMYxCPB2MQRI9PQ8YgFi1ahN9++w1ZWVlK5yckJCAhIQFHjx7F8uXL8e2332L+/Pn1Wgciar7Y0YHoKXT37l2MHTsWV69eVfjc2dkZXbp0gbW1NcrKypCcnIywsDCkpKQAAKKiovDSSy/h3r17WLRoUWNUnYiasIqAV8X0zJkzG7E2RFQXiYmJjV0FIiIiekIwBkFEDYExCKInw/79+xU6ORgbG6N3795wcHCAnp4ebt26hfPnz6OkpAR5eXl4/fXXcefOHaxcubLxKk1ETQY7OhA9ZeLi4uDl5YXk5GQAD3tjTps2DUuXLkXHjh2rpBdCICQkBGvWrMHWrVtRXl6O/Pz8x11tegLNmjWrSd/9wV77NZOfn4/IyEgAgJ6eHl5++eVGrhER1ZWuri46deqEXr16Sa9u3bo1drWIiIioGWEMgpoKxiCeLIxBED1ZdHR0MGnSJLzyyisYPHgwdHQU/3V59+5dzJkzBydOnAAAfPXVV3jmmWcwevToxqguETUh7OhA9BQpLi7Giy++KAUY9PX1sX37dowfP17lMjKZDL169cKWLVuwaNEiTJs27THVloiak8rDz9ra2kJLS6sRa0NEdbV//360a9dOGvaViIiIqKYYgyCihsIYBNGTY+rUqZgxYwZat26tMo2zszMOHTqEgQMH4uLFiwCAzz77jB0diAg8AyB6iqxatQohISHS+82bN6sNMDyqU6dOCAoKwvDhwxugdkTUnJWUlEjTDDAQNX9dunRhJwciIiKqE8YgiKihMAZB9ORYsWKF2k4OFeRyOT799FPp/YULF5Cent6QVSOiZoBnAURPiYKCAvz000/S+4kTJ2Ly5Mk1zsfIyAj9+/fXKG1GRga+/vpr9OrVC1ZWVjAwMICbmxteeeUVREREaFzvvXv34q233sKAAQNga2sLPT09GBsbw9XVFRMnTsQff/yB4uLiavMKCAiATCaDTCbDoEGDpM8PHz6MadOmoW3btjA2NoZMJsPq1asVli0pKcGxY8ewaNEiDB48GPb29tDX14eBgQEcHR0xZswY/Pjjj8jNzdVovSpLSUnBqlWrMHz4cDg7O8PAwAAGBgZwdnbG6NGjsWrVKsTFxSks4+rqCplMpvA8wtmzZ0vrV/m1YsUKlWWXlJTgzz//xOTJk+Hm5gYTExMYGRmhVatWmDZtGvbs2QMhhNr613a7btq0SVquuuEjL168iIULF6J79+6wsLCArq4uWrRogXbt2mHAgAF47733cOzYMRQUFCgsV5F/YGCg9NngwYOVbqdNmzYpLDto0CBpnqZDSB45cgTz5s1Dp06dYGlpCV1dXZibm6N79+6YN28e9u/fj9LS0npfz7oQQmDnzp2YNm0aWrduDWNjYxgbG6N169Z46aWXsGvXLrX7QMU2atWqlfTZnTt3qmzfyvuGJlasWAGZTIbBgwdLnwUGBir97lxdXTXKc8+ePRg7diycnZ0hl8thY2ODESNG4K+//qp2P3/UjRs3sHTpUvTu3Vtql6ytrdGnTx8sW7YMiYmJNcpPEzdv3sSiRYvQt29fWFlZQU9PD2ZmZmjTpg369u2LBQsWYO/evcjOzq42r/o49itLS0vD8uXL0a1bN5iZmcHExAQeHh546623cOPGDQAPhy2u7jtTlcbf3x/Tpk2Dm5sb9PX1YWFhgREjRuDAgQNV8igrK8OePXswevRouLi4QF9fH46Ojnj55ZcRHh6u8TrV13ZS1UaePHkSU6dOldbJ0tISzzzzDH7++WeFoJ2qvCpTdlzIZLIqvx1EREREjwtjEIxBKMMYBGMQjEEwBsEYRMNupyc9BlH5nEAIgTt37jR4mUTUxAkieips2bJFAJBeZ86cqdf8vb29pbz9/f3FmTNnhIODg0KZlV/a2tpiw4YNavMMCgoSxsbGKvOo/HJ1dRWXL19Wm5+/v7+U3tvbW2RlZYkJEyYoze+HH36Qlrt7966wtLTUqB5WVlbC19dXo21WVlYmPv30U2FoaFhtvlpaWuLatWvSsi4uLhrVB4BYvny5yu3RunXrapfv27eviI+Pr/ftunHjRulzHx8fpXmXlJSIuXPnaryuH3/8scLymi4HQGzcuFFh2Uf3aXUiIiJEz549NSpnypQp9b6etRUVFSU8PT2rLa9Hjx7i9u3bSvPQtM7e3t41qtvy5cs1ztvFxUVh2Uf3raysLDFu3Di1eYwaNUrk5+dXW6/CwkIxf/58oa2trTY/AwMDsWbNmhqtc3XbQ0dHR6PtMX36dLV51dexX+HYsWPCyspKZT56enpi3bp1IjY2VuV3VuHRNKWlpWLhwoVq6/nJJ59Iy6ekpIi+ffuqTKurqyt27typ0TZvqDayqKio2uO9e/fuIjU1VW1emrxiY2M1WteaqJx/dW0jERERPb0Yg2AMQtn2YAzify/GIFS/GIP4H8YgqmIM4umKQTwqOztboczg4OAGL5OImjYdENFT4eTJk9K0s7OzxndE1EZERAQ++ugj5ObmwsbGBgMHDoSlpSUSEhJw8uRJFBQUoKysDPPnz0enTp3g5eWlNJ/MzEzp7gQbGxt07NgRjo6OMDIyQn5+Pm7fvo3g4GCUlpYiLi4O3t7euHz5Mtq0aVNtHYUQePnll3Hw4EHpGaAeHh4QQiAiIkKhp2peXp40DJaFhQU6duwIFxcXGBsbo7i4GLGxsQgKCkJhYSHS0tIwZswYBAYGol+/firLLysrw4svvog9e/ZIn+np6cHLywuurq7Q0dFBcnIyLl++jKSkJJSXlyvcMeLj44P09HScOHECN2/eBAAMHToU7u7uVcrq3bt3lc927tyJ6dOnSz129fX10bdvX7i6ukJbWxtRUVE4f/48SktLERQUBC8vL1y8eBG2trb1tl018cEHH2DDhg3SewcHB/Tu3RtWVlYQQiA9PR3Xr19HZGSk0uXfeOMNAA970Vf0bh8/fjw
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"text/plain": [
"<Figure size 2500x2000 with 4 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
from notebook to .py for segment analysis
2024-03-27 15:59:33 +01:00
"categories = list(X_test_segment_caract.drop(\"segment\", axis=1).columns)\n",
"radar_mp_plot_all(df=X_test_segment_caract, categories=categories)"
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
]
},
{
"cell_type": "code",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"execution_count": 81,
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"id": "c48136d1-c980-4f74-a69f-ed4304c83188",
"metadata": {},
"outputs": [],
"source": [
"# export to MinIo\n",
"\n",
added options to save plots in S3
2024-03-26 16:00:39 +01:00
"# activity = \"sport\"\n",
"# PATH = f\"projet-bdc2324-team1/Output_marketing_personae_analysis/{activity}/\"\n",
completed segment mp analysis sport
2024-03-26 12:20:03 +01:00
"\n",
"file_name = \"spider_chart_all_\" + activity\n",
"FILE_PATH_OUT_S3 = PATH + file_name + \".png\"\n",
"\n",
"radar_mp_plot_all(df=X_test_segment_caract, categories=categories)\n",
"\n",
"image_buffer = io.BytesIO()\n",
"plt.savefig(image_buffer, format='png')\n",
"image_buffer.seek(0)\n",
"\n",
"with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
"plt.close()"
]
},
{
"cell_type": "markdown",
"id": "a2395680-69fe-4247-8deb-22f8ee15830b",
"metadata": {},
"source": [
"## --- end of the main part --- here are just some attempts --- ##"
]
},
{
"cell_type": "code",
"execution_count": 489,
"id": "7d9a2aca-d28d-43b3-9b72-5913b20c4f04",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 600x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"colors = plt.cm.Blues(np.linspace(0.1, 0.9, 4)) \n",
"colors = [\"blue\", \"green\", \"orange\", \"red\"]\n",
"\n",
"# Initialisez le graphique en étoile\n",
"fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))\n",
"\n",
"for i in range(4) :\n",
"\n",
" # Caractéristiques et valeurs associées (exemple)\n",
" categories = ['share_known_gender', 'share_of_women', 'country_fr']\n",
" values = list(X_test_segment_mp.loc[i,categories]) # Exemple de valeurs, ajustez selon vos données\n",
" \n",
" values_normalized = [ max(values) * elt for elt in values]\n",
" \n",
" # Nombre de caractéristiques\n",
" num_categories = len(categories)\n",
" \n",
" # Créer un angle pour chaque axe\n",
" angles = np.linspace(0, 2 * np.pi, num_categories, endpoint=False).tolist()\n",
" \n",
" \n",
" # Tracer uniquement le contour du polygone\n",
" ax.plot(angles + angles[:1], values + values[:1], color='skyblue', alpha=0, linewidth=1.5)\n",
" # ax.plot(angles + angles[:1], values_normalized + values_normalized[:1], color='blue', alpha = 0.3, linewidth=1.5)\n",
" \n",
" # Remplir le secteur central avec une couleur\n",
" ax.fill(angles, values_normalized, color=colors[i], alpha=0.2, label = str(i+1))\n",
"\n",
"# Étiqueter les axes\n",
"ax.set_yticklabels([])\n",
"ax.set_xticks(angles)\n",
"ax.set_xticklabels(categories)\n",
"ax.legend()\n",
"\n",
"# Titre du graphique\n",
"plt.title('Résumé des caractéristiques')\n",
"\n",
"# Afficher le graphique\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 301,
"id": "96aa9ff5-c1ed-49eb-8fb7-2319ac0c40be",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 600x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# KEEP THIS CODE !!\n",
"\n",
"# Caractéristiques et valeurs associées (exemple)\n",
"categories = ['Force', 'Vitesse', 'Agilité', 'Précision', 'Endurance']\n",
"values = [8, 7, 6, 9, 7] # Exemple de valeurs, ajustez selon vos données\n",
"\n",
"# Plage de valeurs maximales pour chaque caractéristique\n",
"max_range = [20, 20, 20, 20, 20]\n",
"\n",
"values_normalized = [2 * max(values) * x / y for x, y in zip(values, max_range)]\n",
"\n",
"# Nombre de caractéristiques\n",
"num_categories = len(categories)\n",
"\n",
"# Créer un angle pour chaque axe\n",
"angles = np.linspace(0, 2 * np.pi, num_categories, endpoint=False).tolist()\n",
"\n",
"# Initialisez le graphique en étoile\n",
"fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))\n",
"\n",
"# Tracer uniquement le contour du polygone\n",
"ax.plot(angles + angles[:1], values + values[:1], color='skyblue', alpha=0, linewidth=1.5)\n",
"ax.plot(angles + angles[:1], values_normalized + values_normalized[:1], color='blue', linewidth=1.5)\n",
"\n",
"# Remplir le secteur central avec une couleur\n",
"ax.fill(angles, values_normalized, color='skyblue', alpha=0.4)\n",
"\n",
"# Étiqueter les axes\n",
"ax.set_yticklabels([])\n",
"ax.set_xticks(angles)\n",
"ax.set_xticklabels(categories)\n",
"\n",
"# Titre du graphique\n",
"plt.title('Résumé des caractéristiques')\n",
"\n",
"# Afficher le graphique\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 149,
"id": "adb7ccb3-7dea-4347-9298-37311a2f1fb1",
"metadata": {},
"outputs": [],
"source": [
"def radar_chart(values, categories, segment) :\n",
" # Caractéristiques et valeurs associées (exemple)\n",
" categories = categories\n",
" values = values # Exemple de valeurs, ajustez selon vos données\n",
" \n",
" # Nombre de caractéristiques\n",
" num_categories = len(categories)\n",
" \n",
" # Créer un angle pour chaque axe\n",
" angles = np.linspace(0, 2 * np.pi, num_categories, endpoint=False).tolist()\n",
" \n",
" # Répéter le premier angle pour fermer la figure\n",
" values += values[:1]\n",
" angles += angles[:1]\n",
" \n",
" # Initialisez le graphique en étoile\n",
" fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))\n",
" \n",
" # Tracer les lignes radiales\n",
" ax.fill(angles, values, color='skyblue', alpha=0.4)\n",
" \n",
" # Tracer les points sur les axes radiaux\n",
" ax.plot(angles, values, color='blue', linewidth=2, linestyle='solid')\n",
"\n",
" # Afficher les valeurs associées sous les noms de variables\n",
" \"\"\"\n",
" for i, angle in enumerate(angles[:-1]):\n",
" x = angle\n",
" y = values[i] + 0.2 # Ajustez la distance des valeurs par rapport au centre\n",
" plt.text(x, y, str(values[i]), color='black', ha='center', fontsize=10)\n",
" \"\"\"\n",
" \n",
" # Remplir le secteur central avec une couleur\n",
" # ax.fill(angles, values, color='skyblue', alpha=0.4)\n",
"\n",
" \n",
" # Étiqueter les axes\n",
" ax.set_yticklabels([])\n",
" #ax.set_xticks(angles[:-1])\n",
" #ax.set_xticklabels(categories, # fontsize=12, ha='right', rotation=45\n",
" # )\n",
" # ax.set_xticklabels(categories, fontsize=10, color='black', ha='right')\n",
"\n",
" labels = [f\"{category} = {round(100 *value,2)}%\" for category, value in zip(categories, values[:-1])]\n",
" ax.set_xticks(angles[:-1])\n",
" ax.set_xticklabels(labels, fontsize=10, color='black', ha='right')\n",
" \n",
" # Titre du graphique\n",
" plt.title(f'Caracteristics of segment {segment}')\n",
" \n",
" # Afficher le graphique\n",
" plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 150,
"id": "8793fb51-812c-4500-b252-2e2d61d6ff48",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 600x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"categories= [\"share_known_gender\",\"share_of_women\",\"country_fr\"]\n",
"radar_chart(values=X_test_segment_mp.loc[0,categories].values.tolist(), categories= categories,\n",
" segment = \"1\")"
]
}
],
"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 Copy Permalink