spark PartitionwiseSampledRDD 源码
spark PartitionwiseSampledRDD 代码
文件路径：/core/src/main/scala/org/apache/spark/rdd/PartitionwiseSampledRDD.scala
/*
* 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.rdd
import java.util.Random
import scala.reflect.ClassTag
import org.apache.spark.{Partition, TaskContext}
import org.apache.spark.util.Utils
import org.apache.spark.util.random.RandomSampler
private[spark]
class PartitionwiseSampledRDDPartition(val prev: Partition, val seed: Long)
extends Partition with Serializable {
override val index: Int = prev.index
}
/**
* An RDD sampled from its parent RDD partition-wise. For each partition of the parent RDD,
* a user-specified [[org.apache.spark.util.random.RandomSampler]] instance is used to obtain
* a random sample of the records in the partition. The random seeds assigned to the samplers
* are guaranteed to have different values.
*
* @param prev RDD to be sampled
* @param sampler a random sampler
* @param preservesPartitioning whether the sampler preserves the partitioner of the parent RDD
* @param seed random seed
* @tparam T input RDD item type
* @tparam U sampled RDD item type
*/
private[spark] class PartitionwiseSampledRDD[T: ClassTag, U: ClassTag](
prev: RDD[T],
sampler: RandomSampler[T, U],
preservesPartitioning: Boolean,
@transient private val seed: Long = Utils.random.nextLong)
extends RDD[U](prev) {
@transient override val partitioner = if (preservesPartitioning) prev.partitioner else None
override def getPartitions: Array[Partition] = {
val random = new Random(seed)
firstParent[T].partitions.map(x => new PartitionwiseSampledRDDPartition(x, random.nextLong()))
}
override def getPreferredLocations(split: Partition): Seq[String] =
firstParent[T].preferredLocations(split.asInstanceOf[PartitionwiseSampledRDDPartition].prev)
override def compute(splitIn: Partition, context: TaskContext): Iterator[U] = {
val split = splitIn.asInstanceOf[PartitionwiseSampledRDDPartition]
val thisSampler = sampler.clone
thisSampler.setSeed(split.seed)
thisSampler.sample(firstParent[T].iterator(split.prev, context))
}
override protected def getOutputDeterministicLevel = {
if (prev.outputDeterministicLevel == DeterministicLevel.UNORDERED) {
DeterministicLevel.INDETERMINATE
} else {
super.getOutputDeterministicLevel
}
}
}
相关信息
相关文章
0
赞
- 所属分类： 前端技术
- 本文标签：
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
6、 golang
-
7、 openharmony