org.deeplearning4j.models.rntn

Class RNTNEval

java.lang.Object

org.deeplearning4j.models.rntn.RNTNEval

public class RNTNEval
extends Object

Recursive counter for an RNTN

Author:

Adam Gibson

Constructor Summary

Constructors

Constructor and Description
RNTNEval()

Method Summary

Modifier and Type	Method and Description
void	eval(RNTN rntn, List<Tree> trees) Eval the RNTN
double	f1() TP: true positive FP: False Positive FN: False Negative F1 score: 2 * TP / (2TP + FP + FN)
double	f1(int i) Calculate f1 score for a given class
void	incrementFalseNegatives(int clazz, int i)
void	incrementFalsePositives(int clazz, int i)
void	incrementTruePositives(int clazz, int i)
double	precision() Total precision based on guesses so far
double	precision(int i) Returns the precision for a given label
double	recall() Returns the recall for the outcomes
double	recall(int i)
String	stats() Print the summary of the rntnresults

Methods inherited from class java.lang.Object

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

Constructor Detail

RNTNEval

public RNTNEval()

Method Detail

eval

public void eval(RNTN rntn,
                 List<Tree> trees)

Eval the RNTN

Parameters:

rntn -

trees -

incrementTruePositives

public void incrementTruePositives(int clazz,
                                   int i)

incrementFalsePositives

public void incrementFalsePositives(int clazz,
                                    int i)

incrementFalseNegatives

public void incrementFalseNegatives(int clazz,
                                    int i)

stats

public String stats()

Print the summary of the rntnresults

Returns:

the summary of the rntn

precision

public double precision()

Total precision based on guesses so far

Returns:

the total precision based on guesses so far

precision

public double precision(int i)

Returns the precision for a given label

Parameters:

i - the label

Returns:

the precision for the label

recall

public double recall()

Returns the recall for the outcomes

Returns:

the recall for the outcomes

recall

public double recall(int i)

f1

public double f1()

TP: true positive FP: False Positive FN: False Negative F1 score: 2 * TP / (2TP + FP + FN)

Returns:

the f1 score or harmonic mean based on current guesses

f1

public double f1(int i)

Calculate f1 score for a given class

Parameters:

i - the label to calculate f1 for

Returns:

the f1 score for the given label