Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/12604#discussion_r61016854 --- Diff: python/pyspark/ml/tests.py --- @@ -746,6 +797,70 @@ def test_nested_pipeline_persistence(self): except OSError: pass + # TODO: Add OneVsRest as part of nested meta-algorithms. + def test_nested_meta_algorithms_persistence(self): + sqlContext = SQLContext(self.sc) + temp_path = tempfile.mkdtemp() + try: + df = sqlContext.createDataFrame([ + Row(label=0.0, features=Vectors.dense(1.0, 0.8)), + Row(label=0.0, features=Vectors.dense(0.8, 0.8)), + Row(label=0.0, features=Vectors.dense(1.0, 1.2)), + Row(label=1.0, features=Vectors.sparse(2, [], [])), + Row(label=1.0, features=Vectors.sparse(2, [0], [0.1])), + Row(label=1.0, features=Vectors.sparse(2, [1], [0.1]))]) + + lr = LogisticRegression() + + # Check the estimator of CrossValidator(TrainValidationSplit(LogisticRegression)) + tvs_grid = ParamGridBuilder().addGrid(lr.maxIter, [5, 10]).build() --- End diff -- Use maxIter = 1,2 to make it faster. Same elsewhere.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org