Skip to content

[SPARK-16750] [Follow-up] [ML] Add transformSchema for StringIndexer/VectorAssembler and fix failed tests. #14455

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
yanboliang wants to merge 1 commit into from
Closed

[SPARK-16750] [Follow-up] [ML] Add transformSchema for StringIndexer/VectorAssembler and fix failed tests. #14455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,7 @@ class StringIndexer @Since("1.4.0") (

@Since("2.0.0")
override def fit(dataset: Dataset[_]): StringIndexerModel = {
transformSchema(dataset.schema, logging = true)
val counts = dataset.select(col($(inputCol)).cast(StringType))
.rdd
.map(_.getString(0))
Expand Down Expand Up @@ -160,7 +161,7 @@ class StringIndexerModel (
"Skip StringIndexerModel.")
return dataset.toDF
}
validateAndTransformSchema(dataset.schema)
transformSchema(dataset.schema, logging = true)

val indexer = udf { label: String =>
if (labelToIndex.contains(label)) {
Expand Down Expand Up @@ -305,6 +306,7 @@ class IndexToString private[ml] (@Since("1.5.0") override val uid: String)

@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
transformSchema(dataset.schema, logging = true)
val inputColSchema = dataset.schema($(inputCol))
// If the labels array is empty use column metadata
val values = if (!isDefined(labels) || $(labels).isEmpty) {
Expand Down
1 change: 1 addition & 0 deletions mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@ class VectorAssembler @Since("1.4.0") (@Since("1.4.0") override val uid: String)

@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
transformSchema(dataset.schema, logging = true)
// Schema transformation.
val schema = dataset.schema
lazy val first = dataset.toDF.first()
Expand Down
12 changes: 10 additions & 2 deletions mllib/src/test/scala/org/apache/spark/ml/feature/StringIndexerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,12 +120,20 @@ class StringIndexerSuite

test("StringIndexerModel can't overwrite output column") {
val df = spark.createDataFrame(Seq((1, 2), (3, 4))).toDF("input", "output")
intercept[IllegalArgumentException] {
new StringIndexer()
.setInputCol("input")
.setOutputCol("output")
.fit(df)
}

val indexer = new StringIndexer()
.setInputCol("input")
.setOutputCol("output")
.setOutputCol("indexedInput")
.fit(df)

intercept[IllegalArgumentException] {
indexer.transform(df)
indexer.setOutputCol("output").transform(df)
}
}

Expand Down
4 changes: 2 additions & 2 deletions mllib/src/test/scala/org/apache/spark/ml/feature/VectorAssemblerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,10 +74,10 @@ class VectorAssemblerSuite
val assembler = new VectorAssembler()
.setInputCols(Array("a", "b", "c"))
.setOutputCol("features")
val thrown = intercept[SparkException] {
val thrown = intercept[IllegalArgumentException] {
assembler.transform(df)
}
assert(thrown.getMessage contains "VectorAssembler does not support the StringType type")
assert(thrown.getMessage contains "Data type StringType is not supported")
}

test("ML attributes") {
Expand Down