org.apache.spark.mllib.tree.impurity

Class Gini

Object

org.apache.spark.mllib.tree.impurity.Gini

public class Gini
extends Object

Class for calculating the Gini impurity (http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity) during multiclass classification.

Constructor Summary

Constructors

Constructor and Description
Gini()

Method Summary

Modifier and Type	Method and Description
static double	calculate(double[] counts, double totalCount) information calculation for multiclass classification
static double	calculate(double count, double sum, double sumSquares) variance calculation
static org.apache.spark.mllib.tree.impurity.Gini$	instance() Get this impurity instance.

Methods inherited from class Object

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

Constructor Detail

Gini

public Gini()

Method Detail

calculate

public static double calculate(double[] counts,
                               double totalCount)

information calculation for multiclass classification

Parameters:

counts - Array[Double] with counts for each label

totalCount - sum of counts for all labels

Returns:

information value, or 0 if totalCount = 0

calculate

public static double calculate(double count,
                               double sum,
                               double sumSquares)

variance calculation

Parameters:

count - number of instances

sum - sum of labels

sumSquares - summation of squares of the labels

Returns:

information value, or 0 if count = 0

instance

public static org.apache.spark.mllib.tree.impurity.Gini$ instance()

Get this impurity instance. This is useful for passing impurity parameters to a Strategy in Java.

Returns:

(undocumented)