import warnings
import numpy as np
np.random.seed(42)
warnings.filterwarnings("ignore")

# Suppressing warning messages helps beginners focus.

# 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))

# Basic data cleaning
df = df.copy()
df = df.drop(['customerID'], axis=1)
df['TotalCharges'] = pd.to_numeric(df['TotalCharges'], errors='coerce')
missing = df.isnull().sum().sum()
print('Missing values:', missing)
df = df.dropna()
print(df.shape)

# Convert object columns to categorical numbers
for col in df.columns:
    if df[col].dtype == 'object':
        if set(df[col].unique()) == set(['Yes', 'No']):
            df[col] = df[col].map({'Yes': 1, 'No': 0})
        else:
            df[col] = pd.factorize(df[col])[0]
print(df.dtypes.head())

import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style='whitegrid')

# Boxplot: MonthlyCharges by Churn
plt.figure(figsize=(6,4))
sns.boxplot(x='Churn', y='MonthlyCharges', data=df)
plt.title('Boxplot of Monthly Charges by Churn Status')
plt.show()

# Countplot: Number of Churned customers
sns.countplot(x='Churn', data=df)
plt.title('Churn Counts')
plt.show()

# Train-test split
from sklearn.model_selection import train_test_split
target = 'Churn'
X = df.drop(target, axis=1)
y = df[target]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
print(X_train.shape, X_test.shape)

# CART Decision Tree (scikit-learn)
from sklearn.tree import DecisionTreeClassifier
tree_cart = DecisionTreeClassifier(criterion='gini', random_state=42, max_depth=4)
tree_cart.fit(X_train, y_train)
print('Train accuracy:', tree_cart.score(X_train, y_train))
print('Test accuracy:', tree_cart.score(X_test, y_test))

# Visualize the CART tree
from sklearn.tree import plot_tree
plt.figure(figsize=(18,10))
plot_tree(tree_cart, feature_names=X_train.columns, class_names=['No','Yes'], filled=True, max_depth=3)
plt.show()

# Confusion Matrix and Classification Report
from sklearn.metrics import confusion_matrix, classification_report
y_pred = tree_cart.predict(X_test)
print('Confusion Matrix:')
print(confusion_matrix(y_test, y_pred))
print('Classification Report:')
print(classification_report(y_test, y_pred))

# Try Decision Tree ID3 (entropy)
tree_id3 = DecisionTreeClassifier(criterion='entropy', random_state=42, max_depth=4)
tree_id3.fit(X_train, y_train)
print('Train accuracy (ID3):', tree_id3.score(X_train, y_train))
print('Test accuracy (ID3):', tree_id3.score(X_test, y_test))

# C4.5-style: using criterion='entropy' + pruning
tree_c45 = DecisionTreeClassifier(criterion='entropy', max_depth=4, min_samples_split=20, random_state=42)
tree_c45.fit(X_train, y_train)
print('Train accuracy (C4.5 style):', tree_c45.score(X_train, y_train))
print('Test accuracy (C4.5 style):', tree_c45.score(X_test, y_test))

# Feature importance for the tree
import numpy as np
importances = tree_cart.feature_importances_
indices = np.argsort(importances)[::-1][:5]
features = X_train.columns[indices]
print('Top 5 features for CART:')
for i in range(5):
    print(f"{features[i]}: {importances[indices[i]]:.3f}")
    

# Data setup (Titanic Dataset)
import pandas as pd
url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df2 = pd.read_csv(url)
print(df2.shape)
print(df2.head(3))

# Prepare Titanic data for decision trees
df2 = df2[['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']].copy()
df2['Age'] = df2['Age'].fillna(df2['Age'].median())
df2['Embarked'] = df2['Embarked'].fillna('S')
df2['Sex'] = df2['Sex'].map({'male': 0, 'female': 1})
df2['Embarked'] = pd.factorize(df2['Embarked'])[0]

# Fit a Titanic tree
from sklearn.model_selection import train_test_split
X2 = df2.drop('Survived', axis=1)
y2 = df2['Survived']
X2_train, X2_test, y2_train, y2_test = train_test_split(X2, y2, test_size=0.25, random_state=42)
tree_titanic = DecisionTreeClassifier(max_depth=3, random_state=42)
tree_titanic.fit(X2_train, y2_train)
print('Train accuracy:', tree_titanic.score(X2_train, y2_train))
print('Test accuracy:', tree_titanic.score(X2_test, y2_test))

# Interactive: Your prediction
pclass = int(input("Enter passenger class (1, 2, or 3): "))
sex = int(input("Enter sex (0 = male, 1 = female): "))
age = float(input("Enter age: "))
sibsp = int(input("Enter number of siblings/spouses: "))
parch = int(input("Enter number of parents/children: "))
fare = float(input("Enter fare: "))
embarked = int(input("Enter port (0 = S, 1 = C, 2 = Q): "))
sample = [[pclass, sex, age, sibsp, parch, fare, embarked]]
prediction = tree_titanic.predict(sample)[0]
print("Prediction (1 = survived, 0 = did not survive):", prediction)