Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/19892#discussion_r162900053 --- Diff: python/pyspark/ml/feature.py --- @@ -315,13 +315,19 @@ class BucketedRandomProjectionLSHModel(LSHModel, JavaMLReadable, JavaMLWritable) @inherit_doc -class Bucketizer(JavaTransformer, HasInputCol, HasOutputCol, HasHandleInvalid, - JavaMLReadable, JavaMLWritable): - """ - Maps a column of continuous features to a column of feature buckets. - - >>> values = [(0.1,), (0.4,), (1.2,), (1.5,), (float("nan"),), (float("nan"),)] - >>> df = spark.createDataFrame(values, ["values"]) +class Bucketizer(JavaTransformer, HasInputCol, HasOutputCol, HasInputCols, HasOutputCols, + HasHandleInvalid, JavaMLReadable, JavaMLWritable): + """ + Maps a column of continuous features to a column of feature buckets. Since 2.3.0, + :py:class:`Bucketizer` can map multiple columns at once by setting the :py:attr:`inputCols` + parameter. Note that when both the :py:attr:`inputCol` and :py:attr:`inputCols` parameters + are set, a log warning will be printed and only :py:attr:`inputCol` will take effect, while --- End diff -- @holdenk this comment will need to be changed as per #19993 - but that has not been merged yet. I think #19993 will block 2.3 though, so we could preemptively change the doc here to match the Scala side in #19993 about throwing and exception.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org