How do I implement K-Fold cross-validation in Scikit-Learn?

How do I implement K-Fold cross-validation in Scikit-Learn?

You can use the KFold class from sklearn.model_selection. First, import it and then create an instance with your desired number of splits.

Can you show me a code example?

Sure! Here's a simple example:

from sklearn.model_selection import KFold
import numpy as np

# Sample data
X = np.array([[1], [2], [3], [4], [5], [6]])
y = np.array([1, 2, 3, 4, 5, 6])

kf = KFold(n_splits=3)
for train_index, test_index in kf.split(X):
    print("TRAIN indices:", train_index, "TEST indices:", test_index)

What if I want to use Stratified K-Fold instead?

You can use StratifiedKFold from the same module. It ensures that each fold has the same proportion of classes as the entire dataset. Here's how:

from sklearn.model_selection import StratifiedKFold

skf = StratifiedKFold(n_splits=3)
for train_index, test_index in skf.split(X, y):
    print("TRAIN indices:", train_index, "TEST indices:", test_index)

Are there any other cross-validation techniques I should know about?

Yes, there are several techniques like Leave-One-Out (LOO), Group K-Fold, and Time Series Split, each suited for different scenarios.