diff options
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala | 1 | ||||
-rw-r--r-- | mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala | 9 |
2 files changed, 10 insertions, 0 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala index 7b726da388..825f9ed1b5 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala @@ -131,6 +131,7 @@ final class OneVsRestModel private[ml] ( // output label and label metadata as prediction val labelUdf = callUDF(label, DoubleType, col(accColName)) aggregatedDataset.withColumn($(predictionCol), labelUdf.as($(predictionCol), labelMetadata)) + .drop(accColName) } } diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala index 770b56890f..1b354d077d 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala @@ -94,6 +94,15 @@ class OneVsRestSuite extends FunSuite with MLlibTestSparkContext { val datasetWithLabelMetadata = dataset.select(labelWithMetadata, features) ova.fit(datasetWithLabelMetadata) } + + test("SPARK-8049: OneVsRest shouldn't output temp columns") { + val logReg = new LogisticRegression() + .setMaxIter(1) + val ovr = new OneVsRest() + .setClassifier(logReg) + val output = ovr.fit(dataset).transform(dataset) + assert(output.schema.fieldNames.toSet === Set("label", "features", "prediction")) + } } private class MockLogisticRegression(uid: String) extends LogisticRegression(uid) { |