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. Would you like a code example?

Yes, please provide 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]])
y = np.array([1, 2, 3, 4, 5])

kf = KFold(n_splits=3)
for train_index, test_index in kf.split(X):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    print("TRAIN:", train_index, "TEST:", test_index)

What does n_splits do in KFold?

n_splits determines how many folds the dataset will be split into. For example, if n_splits=3, the data will be divided into 3 parts.

Can I use K-Fold with a pipeline?

Yes, you can use K-Fold with a pipeline! You can integrate it with cross_val_score to evaluate your model.