def test_transform(): km = KMeans(n_clusters=n_clusters) km.fit(X) X_new = km.transform(km.cluster_centers_) for c in range(n_clusters): assert_equal(X_new[c, c], 0) for c2 in range(n_clusters): if c != c2: assert_greater(X_new[c, c2], 0)
def test_predict(): km = KMeans(n_clusters=n_clusters, random_state=42) km.fit(X) # sanity check: predict centroid labels pred = km.predict(km.cluster_centers_) assert_array_equal(pred, np.arange(n_clusters)) # sanity check: re-predict labeling for training set samples pred = km.predict(X) assert_array_equal(pred, km.labels_) # re-predict labels for training set using fit_predict pred = km.fit_predict(X) assert_array_equal(pred, km.labels_)
def test_k_means_random_init(): km = KMeans(n_clusters=n_clusters, random_state=42) km.fit(X) _check_fitted_model(km)
def test_score(): km1 = KMeans(n_clusters=n_clusters, n_init=1, max_iter=1, random_state=42) s1 = km1.fit(X).score(X) km2 = KMeans(n_clusters=n_clusters, max_iter=10, random_state=42) s2 = km2.fit(X).score(X) assert_greater(s2 + 1, s1)
def test_score(): km1 = KMeans(n_clusters=n_clusters, n_init=1, max_iter=1, random_state=42) s1 = km1.fit(X).score(X) km2 = KMeans(n_clusters=n_clusters, max_iter=10, random_state=42) s2 = km2.fit(X).score(X) assert_greater(s2, s1)