Customer Churn Prediction Project

1. data_loader.py

import pandas as pd

def load_data(file_path):

try:

df = pd.read_csv(file_path)

return df

except FileNotFoundError:

return None

def explore_data(df):

if df is not None:

print(df.head())

print(df.info())

print(df.describe())

print(df['Churn'].value_counts())

if __name__ == "__main__":

data_file = 'customer_churn.csv'

churn_df = load_data(data_file)

if churn_df is not None:

explore_data(churn_df)

2. data_preprocessing.py

import pandas as pd

from sklearn.model_selec�on import train_test_split

from sklearn.preprocessing import LabelEncoder, StandardScaler, OneHotEncoder

from sklearn.compose import ColumnTransformer

from sklearn.pipeline import Pipeline

df = df.copy()

df['TotalCharges'] = pd.to_numeric(df['TotalCharges'], errors='coerce')

df.dropna(subset=['TotalCharges'], inplace=True)

categorical_features = df.select_dtypes(include='object').columns.tolist()

numerical_features = df.select_dtypes(include=['int64', 'float64']).columns.tolist()

if 'customerID' in categorical_features:

categorical_features.remove('customerID')

target_variable = 'Churn'

if target_variable in categorical_features:

categorical_features.remove(target_variable)

numerical_transformer = StandardScaler()

categorical_transformer = OneHotEncoder(handle_unknown='ignore')

preprocessor = ColumnTransformer(

transformers=[

('num', numerical_transformer, numerical_features),

('cat', categorical_transformer, categorical_features)])

label_encoder = LabelEncoder()

df[target_variable] = label_encoder.fit_transform(df[target_variable])

X = df.drop(target_variable, axis=1)

y = df[target_variable]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stra�fy=y)

return preprocessor, X_train, X_test, y_train, y_test

if __name__ == "__main__":

data_file = 'customer_churn.csv'

churn_df = pd.read_csv(data_file)

if churn_df is not None:

preprocessor, X_train, X_test, y_train, y_test = preprocess_data(churn_df)

from sklearn.linear_model import Logis�cRegression

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier

from sklearn.pipeline import Pipeline

def train_logis�c_regression(preprocessor, X_train, y_train):

model = Pipeline(steps=[('preprocessor', preprocessor),

('classifier', Logis�cRegression(random_state=42))])

model.fit(X_train, y_train)

return model

def train_decision_tree(preprocessor, X_train, y_train):

model = Pipeline(steps=[('preprocessor', preprocessor),

('classifier', DecisionTreeClassifier(random_state=42))])

model.fit(X_train, y_train)

return model

def train_random_forest(preprocessor, X_train, y_train):

model = Pipeline(steps=[('preprocessor', preprocessor),

('classifier', RandomForestClassifier(random_state=42))])

model.fit(X_train, y_train)

return model

if __name__ == "__main__":

from data_loader import load_data

from data_preprocessing import preprocess_data

data_file = 'customer_churn.csv'

churn_df = load_data(data_file)

if churn_df is not None:

logis�c_model = train_logis�c_regression(preprocessor, X_train, y_train)

decision_tree_model = train_decision_tree(preprocessor, X_train, y_train)

random_forest_model = train_random_forest(preprocessor, X_train, y_train)

4. model_evalua�on.py

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score,

import matplotlib.pyplot as plt

import seaborn as sns

def evaluate_model(model, X_test, y_test, model_name):

y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)

precision = precision_score(y_test, y_pred)

recall = recall_score(y_test, y_pred)

f1 = f1_score(y_test, y_pred)

conf_matrix = confusion_matrix(y_test, y_pred)

print(f"\n--- {model_name} Evalua�on ---")

print(f"Accuracy: {accuracy:.4f}")

print(f"Precision: {precision:.4f}")

print(f"Recall: {recall:.4f}")

print(f"F1-Score: {f1:.4f}")

print("\nConfusion Matrix:")

print(conf_matrix)

plt.figure(figsize=(6, 5))

sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues',

x�cklabels=['No Churn', 'Churn'], y�cklabels=['No Churn', 'Churn'])

plt.xlabel('Predicted')

plt.ylabel('Actual')

plt.�tle(f'Confusion Matrix - {model_name}')

if __name__ == "__main__":

from data_loader import load_data

from data_preprocessing import preprocess_data

from model_training import train_logis�c_regression, train_decision_tree, train_random_forest

data_file = 'customer_churn.csv'

churn_df = load_data(data_file)

if churn_df is not None:

preprocessor, X_train, X_test, y_train, y_test = preprocess_data(churn_df)

logis�c_model = train_logis�c_regression(preprocessor, X_train, y_train)

decision_tree_model = train_decision_tree(preprocessor, X_train, y_train)

random_forest_model = train_random_forest(preprocessor, X_train, y_train)

evaluate_model(logis�c_model, X_test, y_test, "Logis�c Regression")

evaluate_model(decision_tree_model, X_test, y_test, "Decision Tree")

evaluate_model(random_forest_model, X_test, y_test, "Random Forest")

5. main.py

from data_loader import load_data

from data_preprocessing import preprocess_data

from model_training import train_logis�c_regression, train_decision_tree, train_random_forest

from model_evalua�on import evaluate_model

def main():

data_file = 'customer_churn.csv'

churn_df = load_data(data_file)

if churn_df is not None:

preprocessor, X_train, X_test, y_train, y_test = preprocess_data(churn_df)

logis�c_model = train_logis�c_regression(preprocessor, X_train, y_train)

decision_tree_model = train_decision_tree(preprocessor, X_train, y_train)

evaluate_model(logis�c_model, X_test, y_test, "Logis�c Regression")

evaluate_model(decision_tree_model, X_test, y_test, "Decision Tree")

evaluate_model(random_forest_model, X_test, y_test, "Random Forest")

if __name__ == "__main__":

main()