Cross-Validation

Stratified K-Fold

from sklearn import datasets
from sklearn.model_selection import StratifiedKFold
from sklearn.svm import LinearSVC

iris = datasets.load_iris()
features = iris.data
labels = iris.target

skf = StratifiedKFold(n_splits=5)

fold = 1
for train_index, test_index in skf.split(features, labels):
    X_train, X_test = features[train_index], features[test_index]
    y_train, y_test = labels[train_index], labels[test_index]
    print("fold {}".format(fold), end="\t")
    print("banyak data latih {}".format(len(y_train)), end="\t")
    print("banyak data uji {}".format(len(y_test)), end="\t")
    
    #contoh hitung akurasi model linear svm
    clf = LinearSVC(C=1, max_iter=10000)
    clf.fit(X_train, y_train)
    print("akurasi {}".format(clf.score(X_test, y_test)))
    fold+=1