Repository: spark Updated Branches: refs/heads/branch-2.1 4964dbedb -> 30954806f
[SPARK-20043][ML] DecisionTreeModel: ImpurityCalculator builder fails for uppercase impurity type Gini Fix bug: DecisionTreeModel can't recongnize Impurity "Gini" when loading TODO: + [x] add unit test + [x] fix the bug Author: é¢åæï¼Yan Facaiï¼ <facai....@gmail.com> Closes #17407 from facaiy/BUG/decision_tree_loader_failer_with_Gini_impurity. (cherry picked from commit 7d432af8f3c47973550ea253dae0c23cd2961bde) Signed-off-by: Joseph K. Bradley <jos...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/30954806 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/30954806 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/30954806 Branch: refs/heads/branch-2.1 Commit: 30954806f1be0dba63f0a608d824d7d811485801 Parents: 4964dbe Author: é¢åæï¼Yan Facaiï¼ <facai....@gmail.com> Authored: Tue Mar 28 16:14:01 2017 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Tue Mar 28 16:14:11 2017 -0700 ---------------------------------------------------------------------- .../apache/spark/mllib/tree/impurity/Impurity.scala | 2 +- .../classification/DecisionTreeClassifierSuite.scala | 14 ++++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/30954806/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala index a5bdc2c..98a3021 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala @@ -184,7 +184,7 @@ private[spark] object ImpurityCalculator { * the given stats. */ def getCalculator(impurity: String, stats: Array[Double]): ImpurityCalculator = { - impurity match { + impurity.toLowerCase match { case "gini" => new GiniCalculator(stats) case "entropy" => new EntropyCalculator(stats) case "variance" => new VarianceCalculator(stats) http://git-wip-us.apache.org/repos/asf/spark/blob/30954806/mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala ---------------------------------------------------------------------- diff --git a/mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala index c711e7f..692a172 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala @@ -383,6 +383,20 @@ class DecisionTreeClassifierSuite testEstimatorAndModelReadWrite(dt, continuousData, allParamSettings ++ Map("maxDepth" -> 0), checkModelData) } + + test("SPARK-20043: " + + "ImpurityCalculator builder fails for uppercase impurity type Gini in model read/write") { + val rdd = TreeTests.getTreeReadWriteData(sc) + val data: DataFrame = + TreeTests.setMetadata(rdd, Map.empty[Int, Int], numClasses = 2) + + val dt = new DecisionTreeClassifier() + .setImpurity("Gini") + .setMaxDepth(2) + val model = dt.fit(data) + + testDefaultReadWrite(model) + } } private[ml] object DecisionTreeClassifierSuite extends SparkFunSuite { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
