import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.metrics import mean_squared_error, r2_score

def linear_regression_boston():
    boston = fetch_openml(name="boston", version=1, as_frame=True)
    data = boston.frame
    X = data[["RM"]] 
    y = data["MEDV"] 
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42
    )

    model = LinearRegression()
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)

    plt.scatter(X_test, y_test, color="blue", label="Actual")
    plt.plot(X_test, y_pred, color="red", label="Predicted")
    plt.xlabel("Average number of rooms (RM)")
    plt.ylabel("Median value of homes ($1000s)")
    plt.title("Linear Regression - Boston Housing Dataset")
    plt.legend()
    plt.show()

    print("Linear Regression - Boston Housing Dataset")
    print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
    print("R^2 Score:", r2_score(y_test, y_pred))

def polynomial_regression_auto_mpg():
    url = "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data"
    column_names = [
        "mpg", "cylinders", "displacement", "horsepower", "weight",
        "acceleration", "model_year", "origin"
    ]
    data = pd.read_csv(url, sep='\s+', names=column_names, na_values="?")
    data = data.dropna()

    X = data["displacement"].values.reshape(-1, 1)
    y = data["mpg"].values

    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42
    )

    poly_model = make_pipeline(
        PolynomialFeatures(degree=2),
        StandardScaler(),
        LinearRegression()
    )
    poly_model.fit(X_train, y_train)
    y_pred = poly_model.predict(X_test)

    plt.scatter(X_test, y_test, color="blue", label="Actual")
    X_sorted = np.sort(X_test, axis=0)
    y_sorted_pred = poly_model.predict(X_sorted)
    plt.plot(X_sorted, y_sorted_pred, color="red", label="Predicted Curve")
    plt.xlabel("Displacement")
    plt.ylabel("Miles per gallon (mpg)")
    plt.title("Polynomial Regression - Auto MPG Dataset")
    plt.legend()
    plt.show()

    print("Polynomial Regression - Auto MPG Dataset")
    print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
    print("R^2 Score:", r2_score(y_test, y_pred))

if __name__ == "__main__":
    print("Demonstrating Linear Regression and Polynomial Regression\n")
    linear_regression_boston()
    polynomial_regression_auto_mpg()