diff options
Diffstat (limited to 'python/pyspark/mllib/tests.py')
-rw-r--r-- | python/pyspark/mllib/tests.py | 17 |
1 files changed, 16 insertions, 1 deletions
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py index 140c22b5fd..f48e3d6dac 100644 --- a/python/pyspark/mllib/tests.py +++ b/python/pyspark/mllib/tests.py @@ -140,7 +140,7 @@ class ListTests(PySparkTestCase): as NumPy arrays. """ - def test_clustering(self): + def test_kmeans(self): from pyspark.mllib.clustering import KMeans data = [ [0, 1.1], @@ -152,6 +152,21 @@ class ListTests(PySparkTestCase): self.assertEquals(clusters.predict(data[0]), clusters.predict(data[1])) self.assertEquals(clusters.predict(data[2]), clusters.predict(data[3])) + def test_kmeans_deterministic(self): + from pyspark.mllib.clustering import KMeans + X = range(0, 100, 10) + Y = range(0, 100, 10) + data = [[x, y] for x, y in zip(X, Y)] + clusters1 = KMeans.train(self.sc.parallelize(data), + 3, initializationMode="k-means||", seed=42) + clusters2 = KMeans.train(self.sc.parallelize(data), + 3, initializationMode="k-means||", seed=42) + centers1 = clusters1.centers + centers2 = clusters2.centers + for c1, c2 in zip(centers1, centers2): + # TODO: Allow small numeric difference. + self.assertTrue(array_equal(c1, c2)) + def test_classification(self): from pyspark.mllib.classification import LogisticRegressionWithSGD, SVMWithSGD, NaiveBayes from pyspark.mllib.tree import DecisionTree |