Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/6756#discussion_r34096419 --- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala --- @@ -0,0 +1,202 @@ +/* + * 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 +import org.apache.spark.ml.param.{Param, Params, IntParam, DoubleParam, ParamMap} +import org.apache.spark.ml.param.shared.{HasFeaturesCol, HasMaxIter, HasPredictionCol, HasSeed} +import org.apache.spark.ml.util.{Identifiable, SchemaUtils} +import org.apache.spark.ml.{Estimator, Model} +import org.apache.spark.mllib.clustering.{KMeans => MLlibKMeans, KMeansModel => MLlibKMeansModel} +import org.apache.spark.mllib.linalg.{Vector, VectorUDT} +import org.apache.spark.sql.functions.{col, udf} +import org.apache.spark.sql.types.{IntegerType, StructType} +import org.apache.spark.sql.{DataFrame, Row} +import org.apache.spark.util.Utils + + +/** + * Common params for KMeans and KMeansModel + */ +private[clustering] trait KMeansParams + extends Params with HasMaxIter with HasFeaturesCol with HasSeed with HasPredictionCol { + + /** + * Set the number of clusters to create (k). Default: 2. + * @group param + */ + final val k = new IntParam(this, "k", "number of clusters to create", (x: Int) => x > 1) + + /** @group getParam */ + def getK: Int = $(k) + + /** + * Param the number of runs of the algorithm to execute in parallel. We initialize the algorithm + * this many times with random starting conditions (configured by the initialization mode), then + * return the best clustering found over any run. Default: 1. + * @group param + */ + final val runs = new IntParam(this, "runs", + "number of runs of the algorithm to execute in parallel", (value: Int) => value >= 1) + + /** @group getParam */ + def getRuns: Int = $(runs) + + /** + * Param the distance threshold within which we've consider centers to have converged. + * If all centers move less than this Euclidean distance, we stop iterating one run. + * @group param + */ + final val epsilon = new DoubleParam(this, "epsilon", "distance threshold") + + /** @group getParam */ + def getEpsilon: Double = $(epsilon) + + /** + * Param for the initialization algorithm. This can be either "random" to choose random points as + * initial cluster centers, or "k-means||" to use a parallel variant of k-means++ + * (Bahmani et al., Scalable K-Means++, VLDB 2012). Default: k-means||. + * @group param + */ + final val initMode = new Param[String](this, "initMode", "initialization algorithm", + (value: String) => MLlibKMeans.validateInitializationMode(value)) + + /** @group getParam */ + def getInitializationMode: String = $(initMode) + + /** + * Param for the number of steps for the k-means|| initialization mode. This is an advanced + * setting -- the default of 5 is almost always enough. Default: 5. + * @group param + */ + final val initSteps = new IntParam(this, "initSteps", "number of steps for k-means||", + (value: Int) => value > 0) + + /** @group getParam */ + def getInitializationSteps: Int = $(initSteps) + + /** + * Validates and transforms the input schema. + * @param schema input schema + * @return output schema + */ + protected def validateAndTransformSchema(schema: StructType): StructType = { + SchemaUtils.checkColumnType(schema, $(featuresCol), new VectorUDT) + SchemaUtils.appendColumn(schema, $(predictionCol), IntegerType) + } +} + +/** + * :: Experimental :: + * Model fitted by KMeans. + * + * @param parentModel a model trained by spark.mllib.clustering.KMeans. + */ +@Experimental +class KMeansModel private[ml] ( + override val uid: String, + private val parentModel: MLlibKMeansModel) extends Model[KMeansModel] with KMeansParams { + + override def copy(extra: ParamMap): KMeansModel = { + val copied = new KMeansModel(uid, parentModel) + copyValues(copied, extra) + } + + override def transform(dataset: DataFrame): DataFrame = { + val predictUDF = udf((vector: Vector) => predict(vector)) + dataset.withColumn($(predictionCol), predictUDF(col($(featuresCol)))) + } + + override def transformSchema(schema: StructType): StructType = { + validateAndTransformSchema(schema) + } + + private[clustering] + def predict(features: Vector): Int = parentModel.predict(features) + + def clusterCenters: Array[Vector] = parentModel.clusterCenters +} + +/** + * :: Experimental :: + * KMeans API for spark.ml Pipeline. + */ +@Experimental +class KMeans(override val uid: String) extends Estimator[KMeansModel] with KMeansParams { + + setDefault( --- End diff -- Please put this in KMeansParams. It's hard to say whether the model needs the default values, but that's the pattern we've used so far. Users could want to get a model and know what the default values are.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org