# Suppress warnings for clean output
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Data setup (Telecom Customer Churn Dataset)
import pandas as pd
url = 'https://raw.githubusercontent.com/IBM/telco-customer-churn-on-icp4d/master/data/Telco-Customer-Churn.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# Take a quick look at how many customers churned
df['Churn'].value_counts()

# Check for missing data
df.isnull().sum().sort_values(ascending=False).head(5)

# See column data types
df.dtypes.head(8)

# Clean up TotalCharges  convert to numeric, fill missing values with median
df['TotalCharges'] = pd.to_numeric(df['TotalCharges'], errors='coerce')
df['TotalCharges'].fillna(df['TotalCharges'].median(), inplace=True)

# Quick stats for numeric columns
df.describe()

# Convert categorical columns to numbers
df['Churn'] = df['Churn'].map({'Yes': 1, 'No': 0})
df['gender'] = df['gender'].map({'Male': 1, 'Female': 0})

# Pick features for our model
features = ['tenure', 'MonthlyCharges', 'TotalCharges', 'gender']
X = df[features]
y = df['Churn']

# Split data into training and test sets
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create and train Logistic Regression model
from sklearn.linear_model import LogisticRegression
model = LogisticRegression(max_iter=200, solver='liblinear')
model.fit(X_train, y_train)

# Predict churn on the test set
y_pred = model.predict(X_test)
print(y_pred[:10])

# Evaluate accuracy
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# See model probabilities
y_proba = model.predict_proba(X_test)
print(y_proba[:5])

# Visualize results: plot confusion matrix
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay
fig, ax = plt.subplots(figsize=(5, 5))
ConfusionMatrixDisplay.from_estimator(model, X_test, y_test, ax=ax)
plt.title('Churn Prediction: Confusion Matrix')
plt.show()

# Input your own example and predict
print("Enter tenure (months): ")
tenure = int(input())
print("Enter monthly charges: ")
monthly = float(input())
print("Enter total charges: ")
total = float(input())
print("Enter gender (1 for male, 0 for female): ")
gender = int(input())
sample = [[tenure, monthly, total, gender]]
prediction = model.predict(sample)
print("Predicted churn (1=Yes, 0=No): ", prediction[0])