Github user MrBago commented on a diff in the pull request: https://github.com/apache/spark/pull/18888#discussion_r132562392 --- Diff: python/pyspark/ml/tests.py --- @@ -1142,6 +1142,35 @@ def test_nested_pipeline_persistence(self): except OSError: pass + def test_python_transformer_pipeline_persistence(self): + """ + Pipeline[MockUnaryTransformer, Binarizer] + """ + temp_path = tempfile.mkdtemp() + + try: + df = self.spark.range(0, 10).toDF('input') + tf = MockUnaryTransformer(shiftVal=2)\ + .setInputCol("input").setOutputCol("shiftedInput") + tf2 = Binarizer(threshold=6, inputCol="shiftedInput", outputCol="binarized") + pl = Pipeline(stages=[tf, tf2]) + model = pl.fit(df) + + pipeline_path = temp_path + "/pipeline" + pl.save(pipeline_path) + loaded_pipeline = Pipeline.load(pipeline_path) + self._compare_pipelines(pl, loaded_pipeline) + + model_path = temp_path + "/pipeline-model" + model.save(model_path) + loaded_model = PipelineModel.load(model_path) + self._compare_pipelines(model, loaded_model) + finally: + try: + rmtree(temp_path) --- End diff -- Why do we need this in a `try` block? I worry about silencing errors in tests because it's a good way to miss issues.
--- 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