#!/usr/bin/env python
import scipy
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
from sklearn.metrics import completeness_score

rng = np.random.RandomState(0)
X, y = make_blobs(random_state=rng)
X = scipy.sparse.csr_matrix(X)
X_train, X_test, _, y_test = train_test_split(X, y, random_state=rng)
kmeans = KMeans(algorithm='elkan').fit(X_train)
print(completeness_score(kmeans.predict(X_test), y_test))