cc.mallet.share.upenn.ner.LengthBins Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of jcore-mallet-2.0.9 Show documentation

MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.

The newest version!

package cc.mallet.share.upenn.ner;


import java.util.*;

import cc.mallet.pipe.*;
import cc.mallet.types.*;

/**
 * A feature approximating string length.
 */
public class LengthBins extends Pipe implements java.io.Serializable {

    String name;
    int[] bins;
    String[] binNames;

    /**
     * bins contains the maximum sizes of elements in each bin.
     * 
For example, passing in {1,3,7} would produce 4 bins, for strings
     * of lengths 1, 2-3, 4-7, and 8+.
     */
    public LengthBins (String featureName, int[] binMaxes) {
		this.name = featureName;
        this.bins = binMaxes;
        Arrays.sort(bins);
        
        int min = 1;
        binNames = new String[bins.length+1];
        for (int i=0; i