org.apache.spark.mllib.stat.correlation

Class PearsonCorrelation

Object

org.apache.spark.mllib.stat.correlation.PearsonCorrelation

All Implemented Interfaces:

Logging, Correlation

public class PearsonCorrelation
extends Object
implements Correlation, Logging

Compute Pearson correlation for two RDDs of the type RDD[Double] or the correlation matrix for an RDD of the type RDD[Vector].

Definition of Pearson correlation can be found at http://en.wikipedia.org/wiki/Pearson_product-moment_correlation_coefficient

Constructor Summary

Constructors

Constructor and Description
PearsonCorrelation()

Method Summary

Methods

Modifier and Type	Method and Description
static double	computeCorrelation(RDD<Object> x, RDD<Object> y) Compute the Pearson correlation for two datasets.
static Matrix	computeCorrelationMatrix(RDD<Vector> X) Compute the Pearson correlation matrix S, for the input matrix, where S(i, j) is the correlation between column i and j.
static Matrix	computeCorrelationMatrixFromCovariance(Matrix covarianceMatrix) Compute the Pearson correlation matrix from the covariance matrix.

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.apache.spark.mllib.stat.correlation.Correlation

computeCorrelation, computeCorrelationMatrix, computeCorrelationWithMatrixImpl

Methods inherited from interface org.apache.spark.Logging

initializeIfNecessary, initializeLogging, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

PearsonCorrelation

public PearsonCorrelation()

Method Detail

computeCorrelation

public static double computeCorrelation(RDD<Object> x,
                        RDD<Object> y)

Compute the Pearson correlation for two datasets. NaN if either vector has 0 variance.

computeCorrelationMatrix

public static Matrix computeCorrelationMatrix(RDD<Vector> X)

Compute the Pearson correlation matrix S, for the input matrix, where S(i, j) is the correlation between column i and j. 0 covariance results in a correlation value of Double.NaN.

computeCorrelationMatrixFromCovariance

public static Matrix computeCorrelationMatrixFromCovariance(Matrix covarianceMatrix)

Compute the Pearson correlation matrix from the covariance matrix. 0 covariance results in a correlation value of Double.NaN.