Github user hhbyyh commented on a diff in the pull request:
https://github.com/apache/spark/pull/19588#discussion_r148440930
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala ---
@@ -37,7 +38,25 @@ import org.apache.spark.sql.types.{StructField,
StructType}
import org.apache.spark.util.collection.OpenHashSet
/** Private trait for params for VectorIndexer and VectorIndexerModel */
-private[ml] trait VectorIndexerParams extends Params with HasInputCol with
HasOutputCol {
+private[ml] trait VectorIndexerParams extends Params with HasInputCol with
HasOutputCol
+ with HasHandleInvalid {
+
+ /**
+ * Param for how to handle invalid data (unseen labels or NULL values).
+ * Options are 'skip' (filter out rows with invalid data),
+ * 'error' (throw an error), or 'keep' (put invalid data in a special
additional
+ * bucket, at index numLabels).
+ * Default: "error"
+ * @group param
+ */
+ @Since("2.3.0")
+ override val handleInvalid: Param[String] = new Param[String](this,
"handleInvalid",
+ "How to handle invalid data (unseen labels or NULL values). " +
+ "Options are 'skip' (filter out rows with invalid data), error (throw
an error), " +
+ "or 'keep' (put invalid data in a special additional bucket, at index
numLabels).",
+ ParamValidators.inArray(StringIndexer.supportedHandleInvalids))
+
+ setDefault(handleInvalid, StringIndexer.ERROR_INVALID)
--- End diff --
ditto
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
