diff options
| author | wm624@hotmail.com <wm624@hotmail.com> | 2016-05-14 09:45:56 +0100 |
|---|---|---|
| committer | Sean Owen <sowen@cloudera.com> | 2016-05-14 09:45:56 +0100 |
| commit | 354f8f11bd4b20fa99bd67a98da3525fd3d75c81 (patch) | |
| tree | 91811f926f3b46d39efe908f1468e4c4bc74bc28 /mllib/src/main/scala | |
| parent | 0f1f31d3a6669fbac474518cf2a871485e202bdc (diff) | |
| download | spark-354f8f11bd4b20fa99bd67a98da3525fd3d75c81.tar.gz spark-354f8f11bd4b20fa99bd67a98da3525fd3d75c81.tar.bz2 spark-354f8f11bd4b20fa99bd67a98da3525fd3d75c81.zip | |
[SPARK-15096][ML] LogisticRegression MultiClassSummarizer numClasses can fail if no valid labels are found
## What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
Throw better exception when numClasses is empty and empty.max is thrown.
## How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
Add a new unit test, which calls histogram with empty numClasses.
Author: wm624@hotmail.com <wm624@hotmail.com>
Closes #12969 from wangmiao1981/logisticR.
Diffstat (limited to 'mllib/src/main/scala')
| -rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala index 3e8040d3e9..ffd03e55b5 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala @@ -745,7 +745,7 @@ private[classification] class MultiClassSummarizer extends Serializable { def countInvalid: Long = totalInvalidCnt /** @return The number of distinct labels in the input dataset. */ - def numClasses: Int = distinctMap.keySet.max + 1 + def numClasses: Int = if (distinctMap.isEmpty) 0 else distinctMap.keySet.max + 1 /** @return The weightSum of each label in the input dataset. */ def histogram: Array[Double] = { |