การตรวจจับค่าผิดปกติ

# Split the data into training and test set
X_train, X_test, y_train, y_test = ____(____, ____, test_size=0.3, random_state=0)

# Define K-means model 
kmeans = ____(n_clusters=____, random_state=42).fit(____)

# Obtain predictions and calculate distance from cluster centroid
X_test_clusters = ____.____(X_test)
X_test_clusters_centers = ____.____
dist = [np.linalg.norm(x-y) for x, y in zip(X_test, X_test_clusters_centers[X_test_clusters])]

# Create fraud predictions based on outliers on clusters 
km_y_pred = np.array(dist)
km_y_pred[dist >= np.percentile(dist, ____)] = 1
km_y_pred[dist < np.percentile(dist, ____)] = 0