# Select all bad parts
bad_parts = data[data['Label'] == 'Bad']

# Randomly select an equal number of good parts
good_parts = data[data['Label'] == 'Good'].sample(n=len(bad_parts), random_state=42)

# Combine both subsets to create a balanced dataset
balanced_data = pd.concat([bad_parts, good_parts])

# Shuffle the combined dataset
balanced_data = balanced_data.sample(frac=1, random_state=42).reset_index(drop=True)

# Display the number of good and bad parts in the balanced dataset
print("Number of Good and Bad Parts in the balanced dataset:")
print(balanced_data['Label'].value_counts())