Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/21090#discussion_r188813735 --- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala --- @@ -0,0 +1,256 @@ +/* + * 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.clustering + +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.ml.Transformer +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.util._ +import org.apache.spark.mllib.clustering.{PowerIterationClustering => MLlibPowerIterationClustering} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{DataFrame, Dataset, Row} +import org.apache.spark.sql.functions.col +import org.apache.spark.sql.types._ + +/** + * Common params for PowerIterationClustering + */ +private[clustering] trait PowerIterationClusteringParams extends Params with HasMaxIter + with HasPredictionCol { + + /** + * The number of clusters to create (k). Must be > 1. Default: 2. + * @group param + */ + @Since("2.4.0") + final val k = new IntParam(this, "k", "The number of clusters to create. " + + "Must be > 1.", ParamValidators.gt(1)) + + /** @group getParam */ + @Since("2.4.0") + def getK: Int = $(k) + + /** + * Param for the initialization algorithm. This can be either "random" to use a random vector + * as vertex properties, or "degree" to use a normalized sum of similarities with other vertices. + * Default: random. + * @group expertParam + */ + @Since("2.4.0") + final val initMode = { + val allowedParams = ParamValidators.inArray(Array("random", "degree")) + new Param[String](this, "initMode", "The initialization algorithm. This can be either " + + "'random' to use a random vector as vertex properties, or 'degree' to use a normalized sum " + + "of similarities with other vertices. Supported options: 'random' and 'degree'.", + allowedParams) + } + + /** @group expertGetParam */ + @Since("2.4.0") + def getInitMode: String = $(initMode) + + /** + * Param for the name of the input column for vertex IDs. + * Default: "id" + * @group param + */ + @Since("2.4.0") + val idCol = new Param[String](this, "idCol", "Name of the input column for vertex IDs.", + (value: String) => value.nonEmpty) + + setDefault(idCol, "id") + + /** @group getParam */ + @Since("2.4.0") + def getIdCol: String = getOrDefault(idCol) + + /** + * Param for the name of the input column for neighbors in the adjacency list representation. + * Default: "neighbors" + * @group param + */ + @Since("2.4.0") + val neighborsCol = new Param[String](this, "neighborsCol", + "Name of the input column for neighbors in the adjacency list representation.", + (value: String) => value.nonEmpty) + + setDefault(neighborsCol, "neighbors") + + /** @group getParam */ + @Since("2.4.0") + def getNeighborsCol: String = $(neighborsCol) + + /** + * Param for the name of the input column for neighbors in the adjacency list representation. + * Default: "similarities" + * @group param + */ + @Since("2.4.0") + val similaritiesCol = new Param[String](this, "similaritiesCol", + "Name of the input column for neighbors in the adjacency list representation.", + (value: String) => value.nonEmpty) + --- End diff -- No, it's meant to be an adjacency list representation of the graph: neighborsCol has the set of neighbor vertex IDs, and similaritiesCol has the corresponding set of edge weights.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org