mengxr commented on a change in pull request #28279:
URL: https://github.com/apache/spark/pull/28279#discussion_r412331433
##########
File path: python/pyspark/ml/tests/test_tuning.py
##########
@@ -310,6 +311,48 @@ def test_save_load_nested_estimator(self):
loadedModel = CrossValidatorModel.load(cvModelPath)
self.assertEqual(loadedModel.bestModel.uid, cvModel.bestModel.uid)
+ def test_save_load_pipeline_estimator(self):
+ temp_path = tempfile.mkdtemp()
+ training = self.spark.createDataFrame([
+ (0, "a b c d e spark", 1.0),
+ (1, "b d", 0.0),
+ (2, "spark f g h", 1.0),
+ (3, "hadoop mapreduce", 0.0),
+ (4, "b spark who", 1.0),
+ (5, "g d a y", 0.0),
+ (6, "spark fly", 1.0),
+ (7, "was mapreduce", 0.0),
+ ], ["id", "text", "label"])
+
+ # Configure an ML pipeline, which consists of tree stages: tokenizer,
hashingTF, and lr.
+ tokenizer = Tokenizer(inputCol="text", outputCol="words")
+ hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(),
outputCol="features")
+
+ ova = OneVsRest(classifier=LogisticRegression())
+ lr1 = LogisticRegression().setMaxIter(5)
+ lr2 = LogisticRegression().setMaxIter(10)
+
+ pipeline = Pipeline(stages=[tokenizer, hashingTF, ova])
Review comment:
Could you add a test that contains nested pipelines?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
