diff options
author | Grzegorz Chilkiewicz <grzegorz.chilkiewicz@codilime.com> | 2016-02-02 11:16:24 -0800 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2016-02-02 11:16:24 -0800 |
commit | b1835d727234fdff42aa8cadd17ddcf43b0bed15 (patch) | |
tree | 9cd6c3ed62a9212c15bee65e48c5f228ff6e3bdf /mllib | |
parent | 358300c795025735c3b2f96c5447b1b227d4abc1 (diff) | |
download | spark-b1835d727234fdff42aa8cadd17ddcf43b0bed15.tar.gz spark-b1835d727234fdff42aa8cadd17ddcf43b0bed15.tar.bz2 spark-b1835d727234fdff42aa8cadd17ddcf43b0bed15.zip |
[SPARK-12711][ML] ML StopWordsRemover does not protect itself from column name duplication
Fixes problem and verifies fix by test suite.
Also - adds optional parameter: nullable (Boolean) to: SchemaUtils.appendColumn
and deduplicates SchemaUtils.appendColumn functions.
Author: Grzegorz Chilkiewicz <grzegorz.chilkiewicz@codilime.com>
Closes #10741 from grzegorz-chilkiewicz/master.
Diffstat (limited to 'mllib')
3 files changed, 19 insertions, 8 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala index b93c9ed382..e53ef300f6 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala @@ -149,9 +149,7 @@ class StopWordsRemover(override val uid: String) val inputType = schema($(inputCol)).dataType require(inputType.sameType(ArrayType(StringType)), s"Input type must be ArrayType(StringType) but got $inputType.") - val outputFields = schema.fields :+ - StructField($(outputCol), inputType, schema($(inputCol)).nullable) - StructType(outputFields) + SchemaUtils.appendColumn(schema, $(outputCol), inputType, schema($(inputCol)).nullable) } override def copy(extra: ParamMap): StopWordsRemover = defaultCopy(extra) diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala index e71dd9eee0..76021ad8f4 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala @@ -71,12 +71,10 @@ private[spark] object SchemaUtils { def appendColumn( schema: StructType, colName: String, - dataType: DataType): StructType = { + dataType: DataType, + nullable: Boolean = false): StructType = { if (colName.isEmpty) return schema - val fieldNames = schema.fieldNames - require(!fieldNames.contains(colName), s"Column $colName already exists.") - val outputFields = schema.fields :+ StructField(colName, dataType, nullable = false) - StructType(outputFields) + appendColumn(schema, StructField(colName, dataType, nullable)) } /** diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/StopWordsRemoverSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/StopWordsRemoverSuite.scala index fb217e0c1d..a5b24c1856 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/feature/StopWordsRemoverSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/feature/StopWordsRemoverSuite.scala @@ -89,4 +89,19 @@ class StopWordsRemoverSuite .setCaseSensitive(true) testDefaultReadWrite(t) } + + test("StopWordsRemover output column already exists") { + val outputCol = "expected" + val remover = new StopWordsRemover() + .setInputCol("raw") + .setOutputCol(outputCol) + val dataSet = sqlContext.createDataFrame(Seq( + (Seq("The", "the", "swift"), Seq("swift")) + )).toDF("raw", outputCol) + + val thrown = intercept[IllegalArgumentException] { + testStopWordsRemover(remover, dataSet) + } + assert(thrown.getMessage == s"requirement failed: Column $outputCol already exists.") + } } |