import pandas as pd 
# Load the dataset 
df = pd.read_csv('student_scores.csv') 
# Display the first few rows and basic information 
print(df.head()) 
print(df.describe()) 
print(df.info()) 
from sklearn.model_selection import train_test_split 
# Separate features and target 
X = df.drop(columns=['Score'])  # Assuming 'Score' is the target column 
y = df['Score'] 
# Split into training and testing sets 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) 
from sklearn.preprocessing import StandardScaler 
# Initialize and fit the scaler on training data 
scaler = StandardScaler() 
X_train_scaled = scaler.fit_transform(X_train) 
X_test_scaled = scaler.transform(X_test) 
from sklearn.linear_model import LinearRegression 
from sklearn.metrics import mean_absolute_error, mean_squared_error 
import numpy as np 
# Initialize and train the model 
model = LinearRegression() 
model.fit(X_train_scaled, y_train) 
# Predict on the test set 
y_pred = model.predict(X_test_scaled) 
# Evaluate performance 
mae = mean_absolute_error(y_test, y_pred) 
rmse = np.sqrt(mean_squared_error(y_test, y_pred)) 
print("Without Dimensionality Reduction") 
print("Mean Absolute Error (MAE):", mae) 
print("Root Mean Squared Error (RMSE):", rmse) 
from sklearn.decomposition import PCA 
# Initialize PCA and fit on the scaled training data 
pca = PCA(n_components=0.95)  # Retain 95% variance 
X_train_pca = pca.fit_transform(X_train_scaled) 
X_test_pca = pca.transform(X_test_scaled) 
# Check the number of components 
print("Number of components selected:", pca.n_components_) 
# Train the regression model on PCA-reduced data 
model_pca = LinearRegression() 
model_pca.fit(X_train_pca, y_train) 
# Predict on the PCA-transformed test set 
y_pred_pca = model_pca.predict(X_test_pca) 
# Evaluate performance 
mae_pca = mean_absolute_error(y_test, y_pred_pca) 
rmse_pca = np.sqrt(mean_squared_error(y_test, y_pred_pca)) 
print("With Dimensionality Reduction (PCA)") 
print("Mean Absolute Error (MAE):", mae_pca) 
print("Root Mean Squared Error (RMSE):", rmse_pca) 
print("Comparison of Model Performance:") 
print("Without Dimensionality Reduction - MAE:", mae, ", RMSE:", rmse) 
print("With Dimensionality Reduction (PCA) - MAE:", mae_pca, ", RMSE:", rmse_pca)