TASK-11.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Fetch the Boston housing dataset from the original source
data_url = "http://lib.stat.cmu.edu/datasets/boston"
raw_df = pd.read_csv(data_url, sep=r"\s+", skiprows=22, header=None)
data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
target = raw_df.values[1::2, 2]

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=42)

# Create and train the linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions on the training and testing sets
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)

# Calculate the mean squared error for training and testing sets
train_mse = mean_squared_error(y_train, y_train_pred)
test_mse = mean_squared_error(y_test, y_test_pred)

print("Train MSE:", train_mse)
print("Test MSE:", test_mse)

# Plot residuals
plt.scatter(y_train_pred, y_train_pred - y_train, c='blue', marker='o', label='Training data')
plt.scatter(y_test_pred, y_test_pred - y_test, c='green', marker='s', label='Test data')
plt.xlabel('Predicted values')
plt.ylabel('Residuals')
plt.legend(loc='upper left')
plt.hlines(y=0, xmin=min(y_train_pred.min(), y_test_pred.min()), xmax=max(y_train_pred.max(), y_test_pred.max()), color='red')
plt.title('Residuals plot')
plt.show()