customer-churn-prediction-simple-ann.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2964171c",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.182998Z",
     "iopub.status.busy": "2023-06-19T11:55:54.182193Z",
     "iopub.status.idle": "2023-06-19T11:55:54.201090Z",
     "shell.execute_reply": "2023-06-19T11:55:54.199846Z"
    },
    "papermill": {
     "duration": 0.028252,
     "end_time": "2023-06-19T11:55:54.204244",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.175992",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/kaggle/input/credit-card-customer-churn-prediction/Churn_Modelling.csv\n"
     ]
    }
   ],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "236d379f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.215614Z",
     "iopub.status.busy": "2023-06-19T11:55:54.214864Z",
     "iopub.status.idle": "2023-06-19T11:55:54.272622Z",
     "shell.execute_reply": "2023-06-19T11:55:54.271361Z"
    },
    "papermill": {
     "duration": 0.066241,
     "end_time": "2023-06-19T11:55:54.275581",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.209340",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('/kaggle/input/credit-card-customer-churn-prediction/Churn_Modelling.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "54b2aac6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.284887Z",
     "iopub.status.busy": "2023-06-19T11:55:54.284472Z",
     "iopub.status.idle": "2023-06-19T11:55:54.322478Z",
     "shell.execute_reply": "2023-06-19T11:55:54.321339Z"
    },
    "papermill": {
     "duration": 0.046017,
     "end_time": "2023-06-19T11:55:54.325340",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.279323",
     "status": "completed"
    },
    "tags": []
   },
   "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>RowNumber</th>\n",
       "      <th>CustomerId</th>\n",
       "      <th>Surname</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>Geography</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Tenure</th>\n",
       "      <th>Balance</th>\n",
       "      <th>NumOfProducts</th>\n",
       "      <th>HasCrCard</th>\n",
       "      <th>IsActiveMember</th>\n",
       "      <th>EstimatedSalary</th>\n",
       "      <th>Exited</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>15634602</td>\n",
       "      <td>Hargrave</td>\n",
       "      <td>619</td>\n",
       "      <td>France</td>\n",
       "      <td>Female</td>\n",
       "      <td>42</td>\n",
       "      <td>2</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>101348.88</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>15647311</td>\n",
       "      <td>Hill</td>\n",
       "      <td>608</td>\n",
       "      <td>Spain</td>\n",
       "      <td>Female</td>\n",
       "      <td>41</td>\n",
       "      <td>1</td>\n",
       "      <td>83807.86</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>112542.58</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>15619304</td>\n",
       "      <td>Onio</td>\n",
       "      <td>502</td>\n",
       "      <td>France</td>\n",
       "      <td>Female</td>\n",
       "      <td>42</td>\n",
       "      <td>8</td>\n",
       "      <td>159660.80</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113931.57</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>15701354</td>\n",
       "      <td>Boni</td>\n",
       "      <td>699</td>\n",
       "      <td>France</td>\n",
       "      <td>Female</td>\n",
       "      <td>39</td>\n",
       "      <td>1</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>93826.63</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>15737888</td>\n",
       "      <td>Mitchell</td>\n",
       "      <td>850</td>\n",
       "      <td>Spain</td>\n",
       "      <td>Female</td>\n",
       "      <td>43</td>\n",
       "      <td>2</td>\n",
       "      <td>125510.82</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>79084.10</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   RowNumber  CustomerId   Surname  CreditScore Geography  Gender  Age  \\\n",
       "0          1    15634602  Hargrave          619    France  Female   42   \n",
       "1          2    15647311      Hill          608     Spain  Female   41   \n",
       "2          3    15619304      Onio          502    France  Female   42   \n",
       "3          4    15701354      Boni          699    France  Female   39   \n",
       "4          5    15737888  Mitchell          850     Spain  Female   43   \n",
       "\n",
       "   Tenure    Balance  NumOfProducts  HasCrCard  IsActiveMember  \\\n",
       "0       2       0.00              1          1               1   \n",
       "1       1   83807.86              1          0               1   \n",
       "2       8  159660.80              3          1               0   \n",
       "3       1       0.00              2          0               0   \n",
       "4       2  125510.82              1          1               1   \n",
       "\n",
       "   EstimatedSalary  Exited  \n",
       "0        101348.88       1  \n",
       "1        112542.58       0  \n",
       "2        113931.57       1  \n",
       "3         93826.63       0  \n",
       "4         79084.10       0  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d969f4dc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.335362Z",
     "iopub.status.busy": "2023-06-19T11:55:54.334747Z",
     "iopub.status.idle": "2023-06-19T11:55:54.341854Z",
     "shell.execute_reply": "2023-06-19T11:55:54.340715Z"
    },
    "papermill": {
     "duration": 0.014942,
     "end_time": "2023-06-19T11:55:54.344355",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.329413",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10000, 14)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1094e290",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.354886Z",
     "iopub.status.busy": "2023-06-19T11:55:54.354056Z",
     "iopub.status.idle": "2023-06-19T11:55:54.392625Z",
     "shell.execute_reply": "2023-06-19T11:55:54.391467Z"
    },
    "papermill": {
     "duration": 0.047076,
     "end_time": "2023-06-19T11:55:54.395660",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.348584",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 10000 entries, 0 to 9999\n",
      "Data columns (total 14 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   RowNumber        10000 non-null  int64  \n",
      " 1   CustomerId       10000 non-null  int64  \n",
      " 2   Surname          10000 non-null  object \n",
      " 3   CreditScore      10000 non-null  int64  \n",
      " 4   Geography        10000 non-null  object \n",
      " 5   Gender           10000 non-null  object \n",
      " 6   Age              10000 non-null  int64  \n",
      " 7   Tenure           10000 non-null  int64  \n",
      " 8   Balance          10000 non-null  float64\n",
      " 9   NumOfProducts    10000 non-null  int64  \n",
      " 10  HasCrCard        10000 non-null  int64  \n",
      " 11  IsActiveMember   10000 non-null  int64  \n",
      " 12  EstimatedSalary  10000 non-null  float64\n",
      " 13  Exited           10000 non-null  int64  \n",
      "dtypes: float64(2), int64(9), object(3)\n",
      "memory usage: 1.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4f9055ca",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.406008Z",
     "iopub.status.busy": "2023-06-19T11:55:54.405637Z",
     "iopub.status.idle": "2023-06-19T11:55:54.428695Z",
     "shell.execute_reply": "2023-06-19T11:55:54.427341Z"
    },
    "papermill": {
     "duration": 0.032159,
     "end_time": "2023-06-19T11:55:54.432155",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.399996",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2805098e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-19T11:55:54.443153Z",
     "iopub.status.busy": "2023-06-19T11:55:54.442743Z",
     "iopub.status.idle": "2023-06-19T11:55:54.452211Z",
     "shell.execute_reply": "2023-06-19T11:55:54.451031Z"
    },
    "papermill": {
     "duration": 0.017862,
     "end_time": "2023-06-19T11:55:54.454649",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.436787",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    7963\n",
       "1    2037\n",
       "Name: Exited, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Exited'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "09e33c35",
   "metadata": {
    "papermill": {
     "duration": 0.004303,
     "end_time": "2023-06-19T11:55:54.463553",
     "exception": false,
     "start_time": "2023-06-19T11:55:54.459250",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.10"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 14.105129,
   "end_time": "2023-06-19T11:55:55.390742",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2023-06-19T11:55:41.285613",
   "version": "2.4.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}