# Suppress warnings to make outputs clean
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Load the California housing dataset
import pandas as pd
url = 'https://raw.githubusercontent.com/ageron/handson-ml/master/datasets/housing/housing.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# Let us check the column names and types
print(df.dtypes)

# Summary statistics help us see data shape
print(df.describe())

# Find missing values by column
print(df.isnull().sum())

# Remove rows with missing values
df = df.dropna()
print(df.shape)

# Plot the distribution of median house values
import matplotlib.pyplot as plt
plt.figure(figsize=(8,4))
plt.hist(df['median_house_value'], bins=30, color='skyblue')
plt.title('Distribution of Median House Value')
plt.xlabel('Median House Value')
plt.ylabel('Number of Districts')
plt.show()

# Quick look at correlation with house value
corr = df.corr()
print(corr['median_house_value'].sort_values(ascending=False))

# Visualize longitude and latitude
plt.figure(figsize=(8,6))
plt.scatter(df['longitude'], df['latitude'], alpha=0.2,
            c=df['median_house_value'], cmap='viridis')
plt.colorbar(label='Median House Value')
plt.xlabel('Longitude')
plt.ylabel('Latitude')
plt.title('House Prices by Location')
plt.show()

# Select numeric features
features = [
    'median_income',
    'housing_median_age',
    'total_rooms',
    'total_bedrooms',
    'population',
    'households'
]
X = df[features]
y = df['median_house_value']
print(X.shape, y.shape)

# Split 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)
print(X_train.shape, X_test.shape)

# Train a linear regression model
from sklearn.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(X_train, y_train)

# Predict prices for test data
y_pred = lr.predict(X_test)
print(y_pred[:5])

# Measure model accuracy
from sklearn.metrics import mean_squared_error, r2_score
mse = mean_squared_error(y_test, y_pred)
rmse = mse ** 0.5
r2 = r2_score(y_test, y_pred)
print(f"Root Mean Squared Error: {rmse:.2f}")
print(f"R2 Score: {r2:.3f}")

# Plot predicted vs actual house prices
plt.figure(figsize=(6,6))
plt.scatter(y_test, y_pred, alpha=0.2, color='purple')
plt.xlabel('Actual Price')
plt.ylabel('Predicted Price')
plt.title('Predicted vs Actual House Prices')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--')
plt.show()

# Try your own prediction!
print("Enter median income to predict house price:")
user_income = float(input("Median income (for example, 3.0): "))
user_data = pd.DataFrame({
    'median_income': [user_income],
    'housing_median_age': [df['housing_median_age'].mean()],
    'total_rooms': [df['total_rooms'].mean()],
    'total_bedrooms': [df['total_bedrooms'].mean()],
    'population': [df['population'].mean()],
    'households': [df['households'].mean()]
})
prediction = lr.predict(user_data)
print(f"Predicted median house value: ${prediction[0]:,.2f}")