Repository: spark Updated Branches: refs/heads/master ae226283e -> 639df046a
[SPARK-16831][PYTHON] Fixed bug in CrossValidator.avgMetrics ## What changes were proposed in this pull request? avgMetrics was summed, not averaged, across folds Author: =^_^= <maxmo...@gmail.com> Closes #14456 from pkch/pkch-patch-1. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/639df046 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/639df046 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/639df046 Branch: refs/heads/master Commit: 639df046a250873c26446a037cb832ab28cb5272 Parents: ae22628 Author: =^_^= <maxmo...@gmail.com> Authored: Wed Aug 3 04:18:28 2016 -0700 Committer: Sean Owen <so...@cloudera.com> Committed: Wed Aug 3 04:18:28 2016 -0700 ---------------------------------------------------------------------- python/pyspark/ml/tuning.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/639df046/python/pyspark/ml/tuning.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/tuning.py b/python/pyspark/ml/tuning.py index 7f967e5..2dcc99c 100644 --- a/python/pyspark/ml/tuning.py +++ b/python/pyspark/ml/tuning.py @@ -166,6 +166,8 @@ class CrossValidator(Estimator, ValidatorParams): >>> evaluator = BinaryClassificationEvaluator() >>> cv = CrossValidator(estimator=lr, estimatorParamMaps=grid, evaluator=evaluator) >>> cvModel = cv.fit(dataset) + >>> cvModel.avgMetrics[0] + 0.5 >>> evaluator.evaluate(cvModel.transform(dataset)) 0.8333... @@ -234,7 +236,7 @@ class CrossValidator(Estimator, ValidatorParams): model = est.fit(train, epm[j]) # TODO: duplicate evaluator to take extra params from input metric = eva.evaluate(model.transform(validation, epm[j])) - metrics[j] += metric + metrics[j] += metric/nFolds if eva.isLargerBetter(): bestIndex = np.argmax(metrics) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org