Closed
Description
We might a have a test which somehow flaky:
[00:11:40] ================================== FAILURES ===================================
[00:11:40] __________________________ test_weighted_vs_repeated __________________________
[00:11:40]
[00:11:40] def test_weighted_vs_repeated():
[00:11:40] # a sample weight of N should yield the same result as an N-fold
[00:11:40] # repetition of the sample
[00:11:40] sample_weight = np.random.randint(1, 5, size=n_samples)
[00:11:40] X_repeat = np.repeat(X, sample_weight, axis=0)
[00:11:40] estimators = [KMeans(init="k-means++", n_clusters=n_clusters,
[00:11:40] random_state=42),
[00:11:40] KMeans(init="random", n_clusters=n_clusters,
[00:11:40] random_state=42),
[00:11:40] KMeans(init=centers.copy(), n_clusters=n_clusters,
[00:11:40] random_state=42),
[00:11:40] MiniBatchKMeans(n_clusters=n_clusters, batch_size=10,
[00:11:40] random_state=42)]
[00:11:40] for estimator in estimators:
[00:11:40] est_weighted = clone(estimator).fit(X, sample_weight=sample_weight)
[00:11:40] est_repeated = clone(estimator).fit(X_repeat)
[00:11:40] repeated_labels = np.repeat(est_weighted.labels_, sample_weight)
[00:11:40] assert_almost_equal(v_measure_score(est_repeated.labels_,
[00:11:40] > repeated_labels), 1.0)
[00:11:40] E AssertionError:
[00:11:40] E Arrays are not almost equal to 7 decimals
[00:11:40] E ACTUAL: 0.95443625305609903
[00:11:40] E DESIRED: 1.0
[00:11:40]
[00:11:40] X_repeat = array([[ 0.1777796 , 0.24368721, 0.24496657, 4.49305682, 0.52896169],
[00:11:40] [ 0.41278093, 5.82206016, 1.8967929...367, -0.56629773, 0.09965137, -0.50347565],
[00:11:40] [ 2.19045563, 4.00946367, -0.56629773, 0.09965137, -0.50347565]])
[00:11:40] est_repeated = MiniBatchKMeans(batch_size=10, compute_labels=True, init='k-means++',
[00:11:40] init_size=None, max_iter=100, max_no_improvement=10, n_clusters=3,
[00:11:40] n_init=3, random_state=42, reassignment_ratio=0.01, tol=0.0,
[00:11:40] verbose=0)
[00:11:40] est_weighted = MiniBatchKMeans(batch_size=10, compute_labels=True, init='k-means++',
[00:11:40] init_size=None, max_iter=100, max_no_improvement=10, n_clusters=3,
[00:11:40] n_init=3, random_state=42, reassignment_ratio=0.01, tol=0.0,
[00:11:40] verbose=0)
[00:11:40] estimator = MiniBatchKMeans(batch_size=10, compute_labels=True, init='k-means++',
[00:11:40] init_size=None, max_iter=100, max_no_improvement=10, n_clusters=3,
[00:11:40] n_init=3, random_state=42, reassignment_ratio=0.01, tol=0.0,
[00:11:40] verbose=0)
[00:11:40] estimators = [KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,
[00:11:40] n_clusters=3, n_init=10, n_jobs=1, precompu..._improvement=10, n_clusters=3,
[00:11:40] n_init=3, random_state=42, reassignment_ratio=0.01, tol=0.0,
[00:11:40] verbose=0)]
[00:11:40] repeated_labels = array([1, 2, 0, 0, 0, 0, 2, 2, 0, 0, 0, 0, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1,
[00:11:40] 1, 0, 0, 0, 0, 2, 1, 1, 0, 2, 2, 2,...1, 2, 2, 2, 2, 2,
[00:11:40] 2, 0, 0, 0, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1,
[00:11:40] 0, 0, 2, 2, 2, 2])
[00:11:40] sample_weight = array([1, 1, 4, 1, 1, 2, 2, 2, 2, 4, 4, 4, 1, 2, 1, 4, 3, 4, 1, 1, 4, 2, 3,
[00:11:40] 3, 1, 4, 3, 1, 2, 4, 1, 4, 2, 4, 4,...3, 4, 4, 3,
[00:11:40] 4, 2, 1, 4, 2, 4, 4, 2, 2, 3, 3, 1, 4, 1, 3, 1, 2, 2, 3, 2, 2, 4, 3,
[00:11:40] 3, 3, 4, 3, 2, 4, 2, 4])
[00:11:40]
[00:11:40] c:\python36\lib\site-packages\sklearn\cluster\tests\test_k_means.py:935: AssertionError
This is the second time that I got a CI failing on this one. I could not find any other issue related to that.