Github user viirya commented on a diff in the pull request: https://github.com/apache/spark/pull/20285#discussion_r162223973 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/VectorSizeHintExample.scala --- @@ -0,0 +1,63 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +// scalastyle:off println +package org.apache.spark.examples.ml + +// $example on$ +import org.apache.spark.ml.feature.{VectorAssembler, VectorSizeHint} +import org.apache.spark.ml.linalg.Vectors +// $example off$ +import org.apache.spark.sql.SparkSession + +object VectorSizeHintExample { + def main(args: Array[String]): Unit = { + val spark = SparkSession + .builder + .appName("VectorSizeHintExample") + .getOrCreate() + + // $example on$ + val dataset = spark.createDataFrame( + Seq( + (0, 18, 1.0, Vectors.dense(0.0, 10.0, 0.5), 1.0), + (0, 18, 1.0, Vectors.dense(0.0, 10.0), 0.0)) + ).toDF("id", "hour", "mobile", "userFeatures", "clicked") + + val sizeHint = new VectorSizeHint() + .setInputCol("userFeatures") + .setHandleInvalid("skip") + .setSize(3) + + val datasetWithSize = sizeHint.transform(dataset) + println("Rows where 'userFeatures' is not the right size are filtered out") + datasetWithSize.show(false) + + val assembler = new VectorAssembler() + .setInputCols(Array("hour", "mobile", "userFeatures")) + .setOutputCol("features") + + // This dataframe can be used by used by downstream transformers as before --- End diff -- ditto.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org