Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/7574#discussion_r35596332
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
---
@@ -114,25 +177,29 @@ class RFormula(override val uid: String)
}
}
- private def transformFeatures: Transformer = {
- // TODO(ekl) add support for non-numeric features and feature
interactions
- new VectorAssembler(uid)
- .setInputCols(parsedFormula.get.terms.toArray)
- .setOutputCol($(featuresCol))
- }
-
private def checkCanTransform(schema: StructType) {
- require(parsedFormula.isDefined, "Must call setFormula() first.")
val columnNames = schema.map(_.name)
require(!columnNames.contains($(featuresCol)), "Features column
already exists.")
require(
!columnNames.contains($(labelCol)) || schema($(labelCol)).dataType
== DoubleType,
"Label column already exists and is not of type DoubleType.")
}
+}
- private def hasLabelCol(schema: StructType): Boolean = {
- schema.map(_.name).contains($(labelCol))
+/**
+ * Utility transformer for removing temporary columns from a DataFrame.
+ * TODO(ekl) make this a public transformer
+ */
+private class ColumnPruner(columnsToPrune: Set[String]) extends
Transformer {
+ override val uid = Identifiable.randomUID("columnPruner")
+ override def transform(dataset: DataFrame): DataFrame = {
--- End diff --
insert an empty line between methods definitions
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
