• Wyciek danych: dane spoza zbioru treningowego są używane do trenowania modelu

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier


X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)

knn = KNeighborsClassifier()
scaler = StandardScaler()

X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)


knn.fit(X_train_scaled, y_train)

knn.score(X_test_scaled, y_test)