public class ChiFeatureSelector extends AbstractFeatureSelector implements Serializable
CHI Feature Selector which uses the statistics CHI to select top features
*Please refer the paper below for details of the algorithm.
Yang, Y. and Pedersen, J.O., A comparative study on feature selection in text categorization,
In Proceedings of International Conference on Machine Learning, 1997, pp. 412-420.
Copyright: Copyright (c) 2005
Company: IST, Drexel University
featureMap, selectedFeatureNum| Constructor and Description |
|---|
ChiFeatureSelector(double topPercentage,
boolean avgMode) |
| Modifier and Type | Method and Description |
|---|---|
protected int[] |
getSelectedFeatures(IndexReader indexReader,
DocClassSet trainingSet) |
protected int[] |
getSelectedFeatures(SparseMatrix doctermMatrix,
DocClassSet trainingSet) |
getClassPrior, getSelectedFeatureNum, getTermDistribution, getTermDistribution, getTermDocFrequency, isSelected, map, setSelectedFeatures, train, trainpublic ChiFeatureSelector(double topPercentage,
boolean avgMode)
protected int[] getSelectedFeatures(IndexReader indexReader, DocClassSet trainingSet)
getSelectedFeatures in class AbstractFeatureSelectorprotected int[] getSelectedFeatures(SparseMatrix doctermMatrix, DocClassSet trainingSet)
getSelectedFeatures in class AbstractFeatureSelectorCopyright © 2018 JULIE Lab, Germany. All rights reserved.