Repository: spark Updated Branches: refs/heads/master 11ed2b180 -> 2a6590e51
[SPARK-9981] [ML] Made labels public for StringIndexerModel Also added unit test for integration between StringIndexerModel and IndexToString CC: holdenk We realized we should have left in your unit test (to catch the issue with removing the inverse() method), so this adds it back. mengxr Author: Joseph K. Bradley <jos...@databricks.com> Closes #8211 from jkbradley/stridx-labels. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2a6590e5 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2a6590e5 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2a6590e5 Branch: refs/heads/master Commit: 2a6590e510aba3bfc6603d280023128b3f5ac702 Parents: 11ed2b1 Author: Joseph K. Bradley <jos...@databricks.com> Authored: Fri Aug 14 14:05:03 2015 -0700 Committer: Xiangrui Meng <m...@databricks.com> Committed: Fri Aug 14 14:05:03 2015 -0700 ---------------------------------------------------------------------- .../apache/spark/ml/feature/StringIndexer.scala | 5 ++++- .../spark/ml/feature/StringIndexerSuite.scala | 18 ++++++++++++++++++ 2 files changed, 22 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/2a6590e5/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala index 6347578..24250e4 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala @@ -97,14 +97,17 @@ class StringIndexer(override val uid: String) extends Estimator[StringIndexerMod /** * :: Experimental :: * Model fitted by [[StringIndexer]]. + * * NOTE: During transformation, if the input column does not exist, * [[StringIndexerModel.transform]] would return the input dataset unmodified. * This is a temporary fix for the case when target labels do not exist during prediction. + * + * @param labels Ordered list of labels, corresponding to indices to be assigned */ @Experimental class StringIndexerModel ( override val uid: String, - labels: Array[String]) extends Model[StringIndexerModel] with StringIndexerBase { + val labels: Array[String]) extends Model[StringIndexerModel] with StringIndexerBase { def this(labels: Array[String]) = this(Identifiable.randomUID("strIdx"), labels) http://git-wip-us.apache.org/repos/asf/spark/blob/2a6590e5/mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala ---------------------------------------------------------------------- diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala index 0b4c8ba..05e05bd 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala @@ -147,4 +147,22 @@ class StringIndexerSuite extends SparkFunSuite with MLlibTestSparkContext { assert(actual === expected) } } + + test("StringIndexer, IndexToString are inverses") { + val data = sc.parallelize(Seq((0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")), 2) + val df = sqlContext.createDataFrame(data).toDF("id", "label") + val indexer = new StringIndexer() + .setInputCol("label") + .setOutputCol("labelIndex") + .fit(df) + val transformed = indexer.transform(df) + val idx2str = new IndexToString() + .setInputCol("labelIndex") + .setOutputCol("sameLabel") + .setLabels(indexer.labels) + idx2str.transform(transformed).select("label", "sameLabel").collect().foreach { + case Row(a: String, b: String) => + assert(a === b) + } + } } --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
