hw_comparison.py

# Import necessary libraries
from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import time

# Load a larger dataset (MNIST dataset with 70,000 samples)
mnist = fetch_openml("mnist_784", version=1)
X, y = mnist.data, mnist.target  # Features and labels

# Split the dataset into training and testing sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# Initialize a Random Forest Classifier with more estimators for longer training time
clf = RandomForestClassifier(n_estimators=100, random_state=42)

# Measure the start time
start_time = time.time()

# Train the model on the training data
clf.fit(X_train, y_train)

# Measure the end time and calculate training duration
end_time = time.time()
training_time = end_time - start_time
print(f"Training time: {training_time:.2f} seconds")

# Make predictions on the test data
y_pred = clf.predict(X_test)

# Evaluate the model's accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy of the Random Forest Classifier: {accuracy * 100:.2f}%")