BDC-team-1/Descriptive_statistics/debug.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "718d4e6d-b90a-4955-90ee-c1518246c07c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Choisissez le type de compagnie : sport ? musique ? musee ? sport\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "File path :  projet-bdc2324-team1/0_Input/Company_5/customerplus_cleaned.csv\n",
      "File path :  projet-bdc2324-team1/0_Input/Company_5/campaigns_information.csv\n",
      "File path :  projet-bdc2324-team1/0_Input/Company_5/products_purchased_reduced.csv\n",
      "File path :  projet-bdc2324-team1/0_Input/Company_5/target_information.csv\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os\n",
    "import s3fs\n",
    "import re\n",
    "import warnings\n",
    "\n",
    "# Ignore warning\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "exec(open('../0_KPI_functions.py').read())\n",
    "exec(open('plot.py').read())\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",
    "companies = {'musee' : ['1', '2', '3', '4'], # , '101'\n",
    "            'sport': ['5'],\n",
    "            'musique' : ['10', '11', '12', '13', '14']}\n",
    "\n",
    "\n",
    "type_of_activity = input('Choisissez le type de compagnie : sport ? musique ? musee ?')\n",
    "list_of_comp = companies[type_of_activity] \n",
    "\n",
    "# Load files\n",
    "customer, campaigns_kpi, campaigns_brut, tickets, products = load_files(list_of_comp)\n",
    "\n",
    "# Identify anonymous customer for each company and remove them from our datasets\n",
    "outlier_list = outlier_detection(tickets, list_of_comp)\n",
    "\n",
    "# Identify valid customer (customer who bought tickets after starting date or received mails after starting date)\n",
    "customer_valid_list = valid_customer_detection(products, campaigns_brut)\n",
    "\n",
    "databases = [customer, campaigns_kpi, campaigns_brut, tickets, products]\n",
    "\n",
    "for dataset in databases:\n",
    "    dataset['customer_id'] = dataset['customer_id'].apply(lambda x: remove_elements(x, outlier_list))# remove outlier\n",
    "    dataset = dataset[dataset['customer_id'].isin(customer_valid_list)] # keep only valid customer\n",
    "    #print(f'shape of {dataset} : ', dataset.shape)\n",
    "\n",
    "# Identify customer who bought during the period of y\n",
    "customer_target_period = identify_purchase_during_target_periode(products)\n",
    "customer['has_purchased_target_period'] = np.where(customer['customer_id'].isin(customer_target_period), 1, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "97d1ceba-0ff9-4e36-87ab-7ebca2857798",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lazy_customer_plot(campaigns_kpi, type_of_activity)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "5113b91e-2b2e-4d96-822f-bbb590f4b62d",
   "metadata": {},
   "outputs": [],
   "source": [
    "exec(open('plot.py').read())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "28def014-5186-4df6-b222-0b260539f838",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sale_dynamics(products, campaigns_brut, type_of_activity)"
   ]
  }
 ],
 "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
}