customer_churn.py

# -*- coding: utf-8 -*-
"""
Created on Mon Aug 21 11:46:58 2023

@author: Aditya King
"""

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix

# Loading the dataset 
data = pd.read_csv(r'H:\CODESOFT\Customer Churn Prediction\customer_churn_dataset\Churn_Modelling.csv')

# Excluded non-numeric columns like 'Surname'
numeric_columns = ['CreditScore', 'Age', 'Tenure', 'Balance', 'NumOfProducts', 'HasCrCard', 'IsActiveMember', 'EstimatedSalary']
X = data[numeric_columns]

# Splitting data in target label 
y = data['Exited']

# Splitting data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Feature scaling
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Building and train of model (Random Forest)
model = RandomForestClassifier()
model.fit(X_train, y_train)

# Predicting
y_pred = model.predict(X_test)

# Evaluating the model
report = classification_report(y_test, y_pred)
conf_matrix = confusion_matrix(y_test, y_pred)
print("Classification Report:\n", report)
print("Confusion Matrix:\n", conf_matrix)