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

# Data setup
import pandas as pd
url = 'https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# Check for missing values
df.isnull().sum()

# Show column names and types
df.info()

# Quick summary statistics
df.describe()

# Plot the target variable
import matplotlib.pyplot as plt
plt.figure(figsize=(8, 4))
plt.hist(df['medv'], bins=30, color='skyblue', edgecolor='black')
plt.title('Distribution of Median House Value (medv)')
plt.xlabel('Median Value (in $1000s)')
plt.ylabel('Frequency')
plt.show()

# Select features and target
X = df.drop('medv', axis=1)
y = df['medv']

# Split data into training and testing
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('Training size:', X_train.shape)
print('Testing size:', X_test.shape)

# Build and train the linear regression model
from sklearn.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(X_train, y_train)

# Make predictions on the test set
y_pred = lr.predict(X_test)
print(y_pred[:5])

# Evaluate with mean squared error and R2 score
from sklearn.metrics import mean_squared_error, r2_score
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print(f'Mean Squared Error: {mse:.2f}')
print(f'R2 Score: {r2:.2f}')

# Visualize the predictions vs. the true values
plt.figure(figsize=(6, 6))
plt.scatter(y_test, y_pred, c='purple', alpha=0.6)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)
plt.xlabel('Actual MEDV')
plt.ylabel('Predicted MEDV')
plt.title('Actual vs. Predicted Median Value')
plt.show()

# Try your own prediction: Type values for rooms, crime rate, age, and more
# Here is a beginner interactive example
print("Let us predict a house price based on your custom inputs!")
rooms = float(input("How many rooms does the house have? "))
crime = float(input("What is the crime rate? (as a number, like 0.03) "))
age = float(input("What is the age of the house? (in years) "))
inputs = df.mean().copy()
inputs['rm'] = rooms
inputs['crim'] = crime
inputs['age'] = age
your_pred = lr.predict([inputs.drop('medv').values])[0]
print(f'Estimated median price (in $1000s): {your_pred:.2f}')

# Show coefficients to interpret what influences price
feature_importance = pd.Series(lr.coef_, index=X.columns)
feature_importance = feature_importance.sort_values(ascending=False)
print(feature_importance)

# Plot the most important features
feature_importance.head(5).plot(kind='bar', color='green')
plt.title('Top 5 Positive Feature Influences')
plt.ylabel('Coefficient Value')
plt.xlabel('Feature Name')
plt.show()