Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/20446#discussion_r165362568 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala --- @@ -0,0 +1,60 @@ +/* + * 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.linalg.{Vector, Vectors} +import org.apache.spark.ml.stat.Summarizer +// $example off$ +import org.apache.spark.sql.SparkSession + +object SummarizerExample { + def main(args: Array[String]): Unit = { + val spark = SparkSession + .builder + .appName("SummarizerExample") + .getOrCreate() + + import spark.implicits._ + import Summarizer._ + + // $example on$ + val data = Seq( + (Vectors.dense(2.0, 3.0, 5.0), 1.0), + (Vectors.dense(4.0, 6.0, 7.0), 2.0) + ) + + val df = data.toDF("features", "weight") + + val Tuple1((meanVal, varianceVal)) = df.select(metrics("mean", "variance") + .summary($"features", $"weight")) + .as[Tuple1[(Vector, Vector)]].first() + + println(s"with weight: mean = ${meanVal}, variance = ${varianceVal}") + + val (meanVal2, varianceVal2) = df.select(mean($"features"), variance($"features")) + .as[(Vector, Vector)].first() + + println(s"without weight: mean = ${meanVal2}, sum = ${varianceVal2}") --- End diff -- Same applies here, why not just `df.select(...).show()`?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org