# Required Libraries
import numpy as np
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split, KFold, cross_val_score,
RepeatedKFold
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, r2_score
# Load dataset
boston = load_boston()
X = pd.DataFrame(boston.data, columns=boston.feature_names)
y = pd.Series(boston.target)
# Split data into training and testing sets (70% training, 30% testing)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,
random_state=42)
# Create a linear regression model
mlr_model = LinearRegression()
# Fit the model on the training data
mlr_model.fit(X_train, y_train)
# Predict the values on the test data
y_pred = mlr_model.predict(X_test)
# Repeated Holdout with multiple iterations
n_repeats = 10
holdout_results = []
for _ in range(n_repeats):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,
random_state=np.random.randint(1, 100))
mlr_model.fit(X_train, y_train)
y_pred = mlr_model.predict(X_test)
# Store the R^2 score
holdout_results.append(r2_score(y_test, y_pred))
print("Average R^2 for Repeated Holdout: ", np.mean(holdout_results))
# k-Fold Cross Validation (with k=10)
kf = KFold(n_splits=10)
cv_results = cross_val_score(mlr_model, X, y, cv=kf, scoring='r2')
print("Average R^2 for k-Fold Cross-Validation: ", np.mean(cv_results))
# SSE (Sum of Squares of Errors)
sse = np.sum((y_test - y_pred) ** 2)
# SST (Total Sum of Squares)
sst = np.sum((y_test - np.mean(y_test)) ** 2)
# SSR (Sum of Squares of Regression)
ssr = np.sum((y_pred - np.mean(y_test)) ** 2)
# R^2 (Coefficient of Determination)
r2 = r2_score(y_test, y_pred)
# Mean Absolute Error (MAE)
mae = mean_absolute_error(y_test, y_pred)
# Output the results
print(f"SSE: {sse}")
print(f"SSR: {ssr}")
print(f"SST: {sst}")
print(f"R^2: {r2}")
print(f"Mean Absolute Error: {mae}")
