spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mengxr <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-2359][MLlib] Correlations
Date Sat, 12 Jul 2014 23:31:58 GMT
Github user mengxr commented on a diff in the pull request:

    https://github.com/apache/spark/pull/1367#discussion_r14855883
  
    --- Diff: mllib/src/main/scala/org/apache/spark/mllib/stat/correlation/SpearmansCorrelation.scala
---
    @@ -0,0 +1,102 @@
    +/*
    + * 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.stat.correlation
    +
    +import org.apache.spark.Partitioner
    +import org.apache.spark.SparkContext._
    +import org.apache.spark.mllib.linalg.{DenseVector, Matrix, Vector}
    +import org.apache.spark.rdd.{CoGroupedRDD, RDD}
    +
    +/**
    + * Compute Spearman's correlation for two RDDs of the type RDD[Double] or the correlation
matrix
    + * for an RDD of the type RDD[Vector].
    + *
    + * Definition of Spearman's correlation can be found at
    + * http://en.wikipedia.org/wiki/Spearman's_rank_correlation_coefficient
    + */
    +object SpearmansCorrelation extends Correlation {
    +
    +  /**
    +   * Compute Spearman's correlation for two datasets.
    +   */
    +  override def computeCorrelation(x: RDD[Double], y: RDD[Double]): Double = {
    +    computeCorrelationWithMatrixImpl(x, y)
    +  }
    +
    +  /**
    +   * Compute Spearman's correlation matrix S, for the input matrix, where S(i, j) is
the
    +   * correlation between column i and j.
    +   */
    +  override def computeCorrelationMatrix(X: RDD[Vector]): Matrix = {
    +    val indexed = X.zipWithIndex()
    +    // Attempt to checkpoint the RDD before splitting it into numCols RDD[Double]s to
avoid
    +    // computing the lineage prefix multiple times.
    +    // If checkpoint directory not set, cache the RDD instead.
    +    try {
    +      indexed.checkpoint()
    +    } catch {
    +      case e: Exception => indexed.cache()
    +    }
    +
    +    val numCols = X.first.size
    +    val ranks = new Array[RDD[(Long, Double)]](numCols)
    +
    +    // Note: we use a for loop here instead of a while loop with a single index variable
    +    // to avoid race condition caused by closure serialization
    +    for (k <- 0 until numCols) {
    +      val column = indexed.map {case(vector, index) => {
    +        (vector(k), index)}
    +      }
    +      ranks(k) = getRanks(column)
    +    }
    +
    +    val ranksMat: RDD[Vector] = makeRankMatrix(ranks)
    +    PearsonCorrelation.computeCorrelationMatrix(ranksMat)
    +  }
    +
    +  /**
    +   * Compute the ranks for elements in the input RDD, using the average method for ties.
    --- End diff --
    
    Add doc explaining the return type.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message