Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/18281#discussion_r127553451
--- Diff: python/pyspark/ml/tests.py ---
@@ -1229,11 +1229,30 @@ def test_output_columns(self):
(2.0, Vectors.dense(0.5, 0.5))],
["label", "features"])
lr = LogisticRegression(maxIter=5, regParam=0.01)
- ovr = OneVsRest(classifier=lr)
+ ovr = OneVsRest(classifier=lr, parallelism=1)
model = ovr.fit(df)
output = model.transform(df)
self.assertEqual(output.columns, ["label", "features",
"prediction"])
+ def test_parallelism_doesnt_change_output(self):
+ df = self.spark.createDataFrame([(0.0, Vectors.dense(1.0, 0.8)),
+ (1.0, Vectors.sparse(2, [], [])),
+ (2.0, Vectors.dense(0.5, 0.5))],
+ ["label", "features"])
+ ovrPar1 = OneVsRest(classifier=LogisticRegression(maxIter=5,
regParam=.01), parallelism=1)
+ modelPar1 = ovrPar1.fit(df)
+ ovrPar2 = OneVsRest(classifier=LogisticRegression(maxIter=5,
regParam=.01), parallelism=2)
+ modelPar2 = ovrPar2.fit(df)
+ self.assertEqual(modelPar1.getPredictionCol(),
modelPar2.getPredictionCol())
+ for model in modelPar1.models:
+ foundCloseCoeffs = False
+ for model2 in modelPar2.models:
--- End diff --
As in Scala, this seems like a roundabout way to compare the models. Can
you just zip the two arrays of models together and compare the pairs?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
