org.apache.spark.mllib.feature
Class PCA

Object
  org.apache.spark.mllib.feature.PCA

public class PCA
extends Object

A feature transformer that projects vectors to a low-dimensional space using PCA.

param: k number of principal components

Constructor Summary

PCA(int k)

Method Summary

PCAModel	fit(JavaRDD<Vector> sources) Java-friendly version of fit()
PCAModel	fit(RDD<Vector> sources) Computes a PCAModel that contains the principal components of the input vectors.
int	k()

Methods inherited from class Object

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

Constructor Detail

PCA

public PCA(int k)

Method Detail

k

public int k()

fit

public PCAModel fit(RDD<Vector> sources)

Computes a PCAModel that contains the principal components of the input vectors.

Parameters:

sources - source vectors

Returns:

(undocumented)

fit

public PCAModel fit(JavaRDD<Vector> sources)

Java-friendly version of fit()