edu.stanford.nlp.sentiment

Class Evaluate

java.lang.Object

edu.stanford.nlp.sentiment.AbstractEvaluate

edu.stanford.nlp.sentiment.Evaluate

public class Evaluate
extends AbstractEvaluate

Author:

John Bauer

Field Summary

Fields

Modifier and Type	Field and Description
protected java.text.DecimalFormat	format

Fields inherited from class edu.stanford.nlp.sentiment.AbstractEvaluate

NF

Constructor Summary

Constructors

Constructor and Description
Evaluate(SentimentModel model)

Method Summary

Modifier and Type	Method and Description
protected void	countUnks(Tree tree) Keep track of how many trees have at least one unknown, and how many of those have the top level annotation correct.
void	eval(Tree tree)
static void	main(java.lang.String[] args) Expected arguments are -model model -treebank treebank For example java edu.stanford.nlp.sentiment.Evaluate -model edu/stanford/nlp/models/sentiment/sentiment.ser.gz -treebank /u/nlp/data/sentiment/sentiment-treebank/fiveclass/dev.txt Other arguments are available, for example -numClasses.
void	populatePredictedLabels(java.util.List<Tree> trees) Sets the predicted sentiment label for all trees given.
void	printSummary()
void	reset()

Methods inherited from class edu.stanford.nlp.sentiment.AbstractEvaluate

approxAccuracy, approxCombinedAccuracy, countLengthAccuracy, countRoot, countTree, eval, exactNodeAccuracy, exactRootAccuracy, lengthAccuracies, printConfusionMatrix, printLengthAccuracies

Methods inherited from class java.lang.Object

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

Field Detail

format

protected java.text.DecimalFormat format

Constructor Detail

Evaluate

public Evaluate(SentimentModel model)

Method Detail

reset

public void reset()

Overrides:

reset in class AbstractEvaluate

eval

public void eval(Tree tree)

Overrides:

eval in class AbstractEvaluate

countUnks

protected void countUnks(Tree tree)

Keep track of how many trees have at least one unknown, and how many of those have the top level annotation correct.

printSummary

public void printSummary()

Overrides:

printSummary in class AbstractEvaluate

populatePredictedLabels

public void populatePredictedLabels(java.util.List<Tree> trees)

Description copied from class: AbstractEvaluate

Sets the predicted sentiment label for all trees given. This method sets the RNNCoreAnnotations.PredictedClass annotation for all nodes in all trees.

Specified by:

populatePredictedLabels in class AbstractEvaluate

Parameters:

trees - List of Trees to be annotated

main

public static void main(java.lang.String[] args)

Expected arguments are -model model -treebank treebank
For example
java edu.stanford.nlp.sentiment.Evaluate -model edu/stanford/nlp/models/sentiment/sentiment.ser.gz -treebank /u/nlp/data/sentiment/sentiment-treebank/fiveclass/dev.txt Other arguments are available, for example -numClasses. See RNNOptions.java, RNNTestOptions.java and RNNTrainOptions.java for more arguments. The configuration is usually derived from the RNN model file, which is not available here as the predictions are external. It is the caller's responsibility to provide a configuration matching the settings of the external predictor. Flags of interest include -equivalenceClasses .