org.apache.spark.mllib.tree.loss

Class LogLoss

java.lang.Object

org.apache.spark.mllib.tree.loss.LogLoss

public class LogLoss
extends java.lang.Object

:: DeveloperApi :: Class for log loss calculation (for classification). This uses twice the binomial negative log likelihood, called "deviance" in Friedman (1999).

The log loss is defined as: 2 log(1 + exp(-2 y F(x))) where y is a label in {-1, 1} and F(x) is the model prediction for features x.

Constructor Summary

Constructors

Constructor and Description
LogLoss()

Method Summary

Methods

Modifier and Type	Method and Description
static double	gradient(double prediction, double label) Method to calculate the loss gradients for the gradient boosting calculation for binary classification The gradient with respect to F(x) is: - 4 y / (1 + exp(2 y F(x)))

Methods inherited from class java.lang.Object

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

Constructor Detail

LogLoss

public LogLoss()

Method Detail

gradient

public static double gradient(double prediction,
              double label)

Method to calculate the loss gradients for the gradient boosting calculation for binary classification The gradient with respect to F(x) is: - 4 y / (1 + exp(2 y F(x)))

Parameters:

prediction - Predicted label.

label - True label.

Returns:

Loss gradient