import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Load the dataset
df = pd.read_csv('Telco-Customer-Churn.csv')
display(df.head())

# 4. Feature Engineering: Remove irrelevant columns
df.drop('customerID', axis=1, inplace=True)

# Convert TotalCharges to numeric, coerce errors to NaN
df['TotalCharges'] = pd.to_numeric(df['TotalCharges'], errors='coerce')

# 2. Data Preprocessing: Handle missing values
df['TotalCharges'].fillna(df['TotalCharges'].median(), inplace=True)

# 4. Feature Engineering: Create Average Monthly Spend (already have MonthlyCharges, but let's demonstrate)
df['Avg_Monthly_Spend'] = np.where(df['tenure'] > 0, df['TotalCharges'] / df['tenure'], df['MonthlyCharges'])

# 4. Feature Engineering: Contract type grouping (Month-to-month vs Long-term)
df['Is_Long_Term_Contract'] = df['Contract'].apply(lambda x: 1 if x in ['One year', 'Two year'] else 0)

# 2. Data Preprocessing: Encode categorical variables
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()

for col in df.select_dtypes(include=['object']).columns:
    df[col] = le.fit_transform(df[col])

display(df.head())

C:\Users\hari shanker s.t\AppData\Local\Temp\ipykernel_8316\2032627952.py:8: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.
The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.

For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.


  df['TotalCharges'].fillna(df['TotalCharges'].median(), inplace=True)

plt.figure(figsize=(6,4))
sns.countplot(data=df, x='Churn')
plt.title('Churn Distribution (0: No, 1: Yes)')
plt.show()

plt.figure(figsize=(6,4))
sns.boxplot(x='Churn', y='MonthlyCharges', data=df)
plt.title('Monthly Charges vs Churn')
plt.show()

plt.figure(figsize=(6,4))
sns.boxplot(x='Churn', y='tenure', data=df)
plt.title('Tenure vs Churn')
plt.show()

plt.figure(figsize=(12,8))
sns.heatmap(df.corr(), annot=False, cmap='coolwarm')
plt.title('Correlation Heatmap')
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, ConfusionMatrixDisplay
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier

# Prepare data
X = df.drop('Churn', axis=1)
y = df['Churn']

# Train-test split
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_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Initialize models
models = {
    'Logistic Regression': LogisticRegression(),
    'Decision Tree': DecisionTreeClassifier(random_state=42),
    'Random Forest': RandomForestClassifier(random_state=42),
    'KNN': KNeighborsClassifier()
}

# Train and evaluate models
results = []
for name, model in models.items():
    model.fit(X_train_scaled, y_train)
    y_pred = model.predict(X_test_scaled)
    
    acc = accuracy_score(y_test, y_pred)
    prec = precision_score(y_test, y_pred)
    rec = recall_score(y_test, y_pred)
    f1 = f1_score(y_test, y_pred)
    cm = confusion_matrix(y_test, y_pred)
    
    results.append({
        'Model': name,
        'Accuracy': acc,
        'Precision': prec,
        'Recall': rec,
        'F1 Score': f1
    })
    
    print(f"\n{name} Confusion Matrix:")
    disp = ConfusionMatrixDisplay(confusion_matrix=cm)
    disp.plot(cmap='Blues')
    plt.title(f'{name} Confusion Matrix')
    plt.show()

# Display evaluation metrics
results_df = pd.DataFrame(results)
display(results_df)

Logistic Regression Confusion Matrix:

Decision Tree Confusion Matrix:

Random Forest Confusion Matrix:

KNN Confusion Matrix:

	gender	Partner	tenure	PhoneService	MultipleLines	InternetService	OnlineSecurity	OnlineBackup	...	Contract	PaperlessBilling	PaymentMethod	MonthlyCharges	TotalCharges	Churn	Avg_Monthly_Spend	Is_Long_Term_Contract
0	0	1	1	0	1	0	0	2	...	0	1	2	29.85	29.85	0	29.850000	0
1	1	0	34	1	0	0	2	0	...	1	0	3	56.95	1889.50	0	55.573529	1
2	1	0	2	1	0	0	2	2	...	0	1	3	53.85	108.15	1	54.075000	0
3	1	0	45	0	1	0	2	0	...	1	0	0	42.30	1840.75	0	40.905556	1
4	0	0	2	1	0	1	0	0	...	0	1	2	70.70	151.65	1	75.825000	0

	Model	Accuracy	Precision	Recall	F1 Score
0	Logistic Regression	0.815472	0.677116	0.579088	0.624277
1	Decision Tree	0.731725	0.493473	0.506702	0.500000
2	Random Forest	0.804826	0.681481	0.493298	0.572317
3	KNN	0.765791	0.560907	0.530831	0.545455

Task 4 — Customer Churn Prediction System¶

1. Data Collection¶

2. Data Preprocessing & 4. Feature Engineering¶

3. Exploratory Data Analysis (EDA)¶

5. Model Building & 6. Model Evaluation¶

	customerID	gender	Partner	Dependents	tenure	PhoneService	MultipleLines	InternetService	OnlineSecurity	...	DeviceProtection	TechSupport	StreamingTV	StreamingMovies	Contract	PaperlessBilling	PaymentMethod	MonthlyCharges	TotalCharges	Churn
0	7590-VHVEG	Female	Yes	No	1	No	No phone service	DSL	No	...	No	No	No	No	Month-to-month	Yes	Electronic check	29.85	29.85	No
1	5575-GNVDE	Male	No	No	34	Yes	No	DSL	Yes	...	Yes	No	No	No	One year	No	Mailed check	56.95	1889.5	No
2	3668-QPYBK	Male	No	No	2	Yes	No	DSL	Yes	...	No	No	No	No	Month-to-month	Yes	Mailed check	53.85	108.15	Yes
3	7795-CFOCW	Male	No	No	45	No	No phone service	DSL	Yes	...	Yes	Yes	No	No	One year	No	Bank transfer (automatic)	42.30	1840.75	No
4	9237-HQITU	Female	No	No	2	Yes	No	Fiber optic	No	...	No	No	No	No	Month-to-month	Yes	Electronic check	70.70	151.65	Yes