Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/19433#discussion_r150309552 --- Diff: mllib/src/main/scala/org/apache/spark/ml/tree/impl/SplitUtils.scala --- @@ -0,0 +1,215 @@ +/* + * 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. + */ + +package org.apache.spark.ml.tree.impl + +import org.apache.spark.ml.tree.{CategoricalSplit, Split} +import org.apache.spark.mllib.tree.impurity.ImpurityCalculator +import org.apache.spark.mllib.tree.model.ImpurityStats + +/** Utility methods for choosing splits during local & distributed tree training. */ +private[impl] object SplitUtils { + + /** Sorts ordered feature categories by label centroid, returning an ordered list of categories */ + private def sortByCentroid( + binAggregates: DTStatsAggregator, + featureIndex: Int, + featureIndexIdx: Int): List[Int] = { + /* Each bin is one category (feature value). + * The bins are ordered based on centroidForCategories, and this ordering determines which + * splits are considered. (With K categories, we consider K - 1 possible splits.) + * + * centroidForCategories is a list: (category, centroid) + */ + val numCategories = binAggregates.metadata.numBins(featureIndex) + val nodeFeatureOffset = binAggregates.getFeatureOffset(featureIndexIdx) + + val centroidForCategories = Range(0, numCategories).map { featureValue => + val categoryStats = + binAggregates.getImpurityCalculator(nodeFeatureOffset, featureValue) + val centroid = ImpurityUtils.getCentroid(binAggregates.metadata, categoryStats) + (featureValue, centroid) + } + // TODO(smurching): How to handle logging statements like these? --- End diff -- What's the issue? You should be able to call logDebug if this object inherits from org.apache.spark.internal.Logging
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org