Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1520#discussion_r15389618 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala --- @@ -0,0 +1,422 @@ +/* + * 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.mllib.random + +import org.apache.spark.SparkContext +import org.apache.spark.mllib.linalg.Vector +import org.apache.spark.mllib.rdd.{RandomVectorRDD, RandomRDD} +import org.apache.spark.rdd.RDD +import org.apache.spark.util.Utils + +/** + * Generator methods for creating RDDs comprised of i.i.d samples from some distribution. + * + * TODO Generate RDD[Vector] from multivariate distributions. + */ +object RandomRDDGenerators { + + /** + * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0]. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @param seed Seed for the RNG that generates the seed for the generator in each partition. + * @return RDD[Double] comprised of i.i.d. samples ~ U[0.0, 1.0]. + */ + def uniformRDD(sc: SparkContext, size: Long, numPartitions: Int, seed: Long): RDD[Double] = { + val uniform = new UniformGenerator() + randomRDD(sc, uniform, size, numPartitions, seed) + } + + /** + * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0]. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ U[0.0, 1.0]. + */ + def uniformRDD(sc: SparkContext, size: Long, numPartitions: Int): RDD[Double] = { + uniformRDD(sc, size, numPartitions, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0]. + * sc.defaultParallelism used for the number of partitions in the RDD. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ U[0.0, 1.0]. + */ + def uniformRDD(sc: SparkContext, size: Long): RDD[Double] = { + uniformRDD(sc, size, sc.defaultParallelism, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples from the standard normal distribution. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @param seed Seed for the RNG that generates the seed for the generator in each partition. + * @return RDD[Double] comprised of i.i.d. samples ~ N(0.0, 1.0). + */ + def normalRDD(sc: SparkContext, size: Long, numPartitions: Int, seed: Long): RDD[Double] = { + val normal = new StandardNormalGenerator() + randomRDD(sc, normal, size, numPartitions, seed) + } + + /** + * Generates an RDD comprised of i.i.d samples from the standard normal distribution. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ N(0.0, 1.0). + */ + def normalRDD(sc: SparkContext, size: Long, numPartitions: Int): RDD[Double] = { + normalRDD(sc, size, numPartitions, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples from the standard normal distribution. + * sc.defaultParallelism used for the number of partitions in the RDD. + * + * @param sc SparkContext used to create the RDD. + * @param size Size of the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ N(0.0, 1.0). + */ + def normalRDD(sc: SparkContext, size: Long): RDD[Double] = { + normalRDD(sc, size, sc.defaultParallelism, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean. + * + * @param sc SparkContext used to create the RDD. + * @param mean Mean, or lambda, for the Poisson distribution. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @param seed Seed for the RNG that generates the seed for the generator in each partition. + * @return RDD[Double] comprised of i.i.d. samples ~ Pois(mean). + */ + def poissonRDD(sc: SparkContext, + mean: Double, + size: Long, + numPartitions: Int, + seed: Long): RDD[Double] = { + val poisson = new PoissonGenerator(mean) + randomRDD(sc, poisson, size, numPartitions, seed) + } + + /** + * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean. + * + * @param sc SparkContext used to create the RDD. + * @param mean Mean, or lambda, for the Poisson distribution. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ Pois(mean). + */ + def poissonRDD(sc: SparkContext, mean: Double, size: Long, numPartitions: Int): RDD[Double] = { + poissonRDD(sc, mean, size, numPartitions, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean. + * sc.defaultParallelism used for the number of partitions in the RDD. + * + * @param sc SparkContext used to create the RDD. + * @param mean Mean, or lambda, for the Poisson distribution. + * @param size Size of the RDD. + * @return RDD[Double] comprised of i.i.d. samples ~ Pois(mean). + */ + def poissonRDD(sc: SparkContext, mean: Double, size: Long): RDD[Double] = { + poissonRDD(sc, mean, size, sc.defaultParallelism, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator. + * + * @param sc SparkContext used to create the RDD. + * @param generator DistributionGenerator used to populate the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @param seed Seed for the RNG that generates the seed for the generator in each partition. + * @return RDD[Double] comprised of i.i.d. samples produced by generator. + */ + def randomRDD(sc: SparkContext, + generator: DistributionGenerator, + size: Long, + numPartitions: Int, + seed: Long): RDD[Double] = { + new RandomRDD(sc, size, numPartitions, generator, seed) + } + + /** + * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator. + * + * @param sc SparkContext used to create the RDD. + * @param generator DistributionGenerator used to populate the RDD. + * @param size Size of the RDD. + * @param numPartitions Number of partitions in the RDD. + * @return RDD[Double] comprised of i.i.d. samples produced by generator. + */ + def randomRDD(sc: SparkContext, + generator: DistributionGenerator, + size: Long, + numPartitions: Int): RDD[Double] = { + randomRDD(sc, generator, size, numPartitions, Utils.random.nextLong) + } + + /** + * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator. + * sc.defaultParallelism used for the number of partitions in the RDD. + * + * @param sc SparkContext used to create the RDD. + * @param generator DistributionGenerator used to populate the RDD. + * @param size Size of the RDD. + * @return RDD[Double] comprised of i.i.d. samples produced by generator. + */ + def randomRDD(sc: SparkContext, + generator: DistributionGenerator, + size: Long): RDD[Double] = { + randomRDD(sc, generator, size, sc.defaultParallelism, Utils.random.nextLong) + } + + /** + * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the + * uniform distribution on [0.0 1.0]. + * + * @param sc SparkContext used to create the RDD. + * @param numRows Number of Vectors in the RDD. + * @param numColumns Number of elements in each Vector. + * @param numPartitions Number of partitions in the RDD. + * @param seed Seed for the RNG that generates the seed for the generator in each partition. + * @return RDD[Vector] with vectors containing i.i.d samples ~ U[0.0, 1.0]. + */ + def uniformVectorRDD(sc: SparkContext, + numRows: Long, + numColumns: Int, --- End diff -- Do you mind changing it to `numCols` to match the naming in distributed matrices?
--- 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. ---