From 354f8f11bd4b20fa99bd67a98da3525fd3d75c81 Mon Sep 17 00:00:00 2001
From: "wm624@hotmail.com" <wm624@hotmail.com>
Date: Sat, 14 May 2016 09:45:56 +0100
Subject: [PATCH] [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.
---
.../apache/spark/ml/classification/LogisticRegression.scala | 2 +-
.../spark/ml/classification/LogisticRegressionSuite.scala | 4 ++++
2 files changed, 5 insertions(+), 1 deletion(-)
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] = {
diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
index f127aa217c..69650ebb36 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
@@ -256,6 +256,10 @@ class LogisticRegressionSuite
assert(summarizer4.countInvalid === 2)
assert(summarizer4.numClasses === 4)
+ val summarizer5 = new MultiClassSummarizer
+ assert(summarizer5.histogram.isEmpty)
+ assert(summarizer5.numClasses === 0)
+
// small map merges large one
val summarizerA = summarizer1.merge(summarizer2)
assert(summarizerA.hashCode() === summarizer2.hashCode())
--
GitLab