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 3e8040d3e9cddc73d1b20176be14044c2ac48c28..ffd03e55b5bb2324aad0cd807e5aa55495782348 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 f127aa217c94d60917fd8384e7d7107190db36c9..69650ebb3690a710f3233aadef8586087aeb7e46 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())