tokensequence.java

常用机器学习算法,java编写源代码,内含常用分类算法,包括说明文档

/* Copyright (C) 2002 Univ. of Massachusetts Amherst, Computer Science Dept.
   This file is part of "MALLET" (MAchine Learning for LanguagE Toolkit).
   http://www.cs.umass.edu/~mccallum/mallet
   This software is provided under the terms of the Common Public License,
   version 1.0, as published by http://www.opensource.org.  For further
   information, see the file `LICENSE' included with this distribution. */




/** 
   @author Andrew McCallum <a href="mailto:[e-mail]">[e-mail]</a>
 */

package edu.umass.cs.mallet.base.types;

import edu.umass.cs.mallet.base.types.FeatureVector;
import edu.umass.cs.mallet.base.types.FeatureSequence;
import edu.umass.cs.mallet.base.util.PropertyList;
import edu.umass.cs.mallet.base.pipe.PipeOutputAccumulator;
import edu.umass.cs.mallet.base.pipe.Pipe;
import java.util.ArrayList;
import java.util.Collection;
import java.util.HashMap;
import java.util.Iterator;

/** A representation of a piece of text, usually a single word, to
		which we can attach properties. */

public class TokenSequence implements PipeOutputAccumulator, Sequence
{
	ArrayList tokens;
	PropertyList properties = null;				// for arbitrary properties
	
	public TokenSequence (Collection tokens)
	{
		this.tokens = new ArrayList (tokens);
	}

	public TokenSequence ()
	{
		this.tokens = new ArrayList ();
	}

	public TokenSequence (int capacity)
	{
		this.tokens = new ArrayList (capacity);
	}

	public TokenSequence (Token[] tokens)
	{
		this(tokens.length);
		for (int i = 0; i < tokens.length; i++)
			this.add (tokens[i]);
	}
	
	public TokenSequence (Object[] tokens)
	{
		this(tokens.length);
		for (int i = 0; i < tokens.length; i++)
			this.add (new Token (tokens[i].toString()));
	}


	public int size ()
	{
		return this.tokens.size();
	}

	public String toString ()
	{
		StringBuffer sb = new StringBuffer ();
		sb.append ("TokenSequence "+super.toString()+"\n");
		for (int i = 0; i < tokens.size(); i++) {
			String tt = getToken(i).toString();
			sb.append ("Token#"+i+":");
			sb.append (tt);
			if (!tt.endsWith("\n"))
				sb.append ("\n");
		}
		return sb.toString();
	}

	public Token getToken (int i)
	{
		return (Token) tokens.get (i);
	}

	public Object get (int i)
	{
		return tokens.get (i);
	}

	public void add (Object o)
	{
		if (o instanceof Token)
			add ((Token)o);
		else if (o instanceof TokenSequence)
			add ((TokenSequence)o);
		else
			add (new Token (o.toString()));
	}

	public void add (Token t)
	{
		tokens.add (t);
	}

	//added by Fuchun Peng, Oct. 24, 2003
	public Object remove(int index)
	{
		return tokens.remove(index);
	}
	
	// added by Fuchun Peng, Oct. 24, 2003
	public Object removeLastToken()
	{	
		if(tokens.size() > 0){
			return tokens.remove(tokens.size()-1);
		}
		else return null;
	}

	public void addAll (TokenSequence ts)
	{
		for (int i = 0; i < ts.size(); i++)
			add (ts.getToken(i));
	}
	 
	public void addAll (Token[] tokens)
	{
		for (int i = 0; i < tokens.length; i++)
			add (tokens[i]);
	}

	public void addAll (Object[] tokens)
	{
		for (int i = 0; i < tokens.length; i++) {
			if (tokens[i] instanceof Token)
				add ((Token)tokens[i]);
			else
				add (new Token (tokens[i].toString()));
		}
	}

	public Iterator iterator ()
	{
		return tokens.iterator();
	}

	public void pipeOutputAccumulate (Instance carrier, Pipe iteratedPipe)
	{
		Object data = carrier.getData();
		if (! (data instanceof Token))
			throw new IllegalArgumentException ("TokenSequence can only accumulator Token's");
		add ((Token)data);
	}

	public PipeOutputAccumulator clonePipeOutputAccumulator ()
	{
		TokenSequence ret = new TokenSequence (tokens);
		ret.properties = this.properties;
		return ret;
	}
		
	public FeatureSequence toFeatureSequence (Alphabet dict)
	{
		FeatureSequence fs = new FeatureSequence (dict, tokens.size());
		for (int i = 0; i < tokens.size(); i++)
			fs.add (dict.lookupIndex (((Token)tokens.get(i)).getText()));
		return fs;
	}
	
	public FeatureVector toFeatureVector (Alphabet dict)
	{
		return new FeatureVector (toFeatureSequence(dict));
	}

	public void setNumericProperty (String key, double value)
	{
		properties = PropertyList.add (key, value, properties);
	}

	public void setProperty (String key, Object value)
	{
		properties = PropertyList.add (key, value, properties);
	}

	public double getNumericProperty (String key)
	{
		return properties.lookupNumber (key);
	}

	public Object getProperty (String key)
	{
		return properties.lookupObject (key);
	}

	public boolean hasProperty (String key)
	{
		return properties.hasProperty (key);
	}

	
}