Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/10976#discussion_r52840380
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
---
@@ -62,28 +65,54 @@ final class Binarizer(override val uid: String)
def setOutputCol(value: String): this.type = set(outputCol, value)
override def transform(dataset: DataFrame): DataFrame = {
- transformSchema(dataset.schema, logging = true)
+ val outputSchema = transformSchema(dataset.schema, logging = true)
+ val schema = dataset.schema
+ val inputType = schema($(inputCol)).dataType
val td = $(threshold)
- val binarizer = udf { in: Double => if (in > td) 1.0 else 0.0 }
- val outputColName = $(outputCol)
- val metadata =
BinaryAttribute.defaultAttr.withName(outputColName).toMetadata()
- dataset.select(col("*"),
- binarizer(col($(inputCol))).as(outputColName, metadata))
+
+ val binarizerDouble = udf { in: Double => if (in > td) 1.0 else 0.0 }
+ val binarizerVector = udf { (data: Vector) =>
+ val indices = ArrayBuilder.make[Int]
+ val values = ArrayBuilder.make[Double]
+
+ data.foreachActive { (index, value) =>
+ if (value > td) {
+ indices += index
+ values += 1.0
+ }
+ }
+
+ Vectors.sparse(data.size, indices.result(),
values.result()).compressed
+ }
+
+ val metadata = outputSchema($(outputCol)).metadata
+
+ inputType match {
+ case DoubleType =>
+ dataset.select(col("*"),
binarizerDouble(col($(inputCol))).as($(outputCol), metadata))
+ case _: VectorUDT =>
+ dataset.select(col("*"),
binarizerVector(col($(inputCol))).as($(outputCol), metadata))
+ }
}
override def transformSchema(schema: StructType): StructType = {
- validateParams()
- SchemaUtils.checkColumnType(schema, $(inputCol), DoubleType)
-
- val inputFields = schema.fields
+ val inputType = schema($(inputCol)).dataType
val outputColName = $(outputCol)
-
- require(inputFields.forall(_.name != outputColName),
- s"Output column $outputColName already exists.")
-
- val attr = BinaryAttribute.defaultAttr.withName(outputColName)
- val outputFields = inputFields :+ attr.toStructField()
- StructType(outputFields)
+ var outCol: StructField = null
--- End diff --
nit: we can use `val` here like:
val outCol: StructField = inputType match {
case DoubleType =>
BinaryAttribute.defaultAttr.withName(outputColName).toStructField()
case _: VectorUDT =>
new StructField(outputColName, new VectorUDT, true)
case other =>
throw new IllegalArgumentException(s"Data type $other is not
supported.")
}
---
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
