gate.plugin.learningframework.mallet.PipeScaleMeanVarAll Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of learningframework Show documentation

A GATE plugin that provides many different machine learning algorithms for a wide range of NLP-related machine learning tasks like text classification, tagging, or chunking.

There is a newer version: 4.2

Show newest version

/*
 * Copyright (c) 2015-2016 The University Of Sheffield.
 *
 * This file is part of gateplugin-LearningFramework 
 * (see https://github.com/GateNLP/gateplugin-LearningFramework).
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as published by
 * the Free Software Foundation, either version 2.1 of the License, or
 * (at your option) any later version.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public License
 * along with this software. If not, see .
 */

package gate.plugin.learningframework.mallet;

import cc.mallet.pipe.Pipe;
import cc.mallet.types.Alphabet;
import cc.mallet.types.FeatureVector;
import cc.mallet.types.Instance;
import gate.plugin.learningframework.mbstats.FVStatsMeanVarAll;
import gate.plugin.learningframework.mbstats.PerFeatureStats;
import gate.util.GateRuntimeException;
import java.io.Serializable;
import java.util.List;

/**
 * Pipe for normalizing features so they have mean 1 and standard deviation 1.
 * 
 * If a feature only has one value the variance is 0 so it is impossible to scale
 * to variance 1. 
 *
 */
public class PipeScaleMeanVarAll extends Pipe implements Serializable {

  protected double means[];
  protected double variances[];
  protected boolean normalize[];
  
  /**
   * Constructor from alphabet and stats.
   * @param alphabet alphabet
   * @param stats feature stats
   */
  public PipeScaleMeanVarAll(Alphabet alphabet, FVStatsMeanVarAll stats) {
    super(alphabet, null);
    List pfss = stats.getStats();
    int n = pfss.size();
    means = new double[n];
    variances = new double[n];
    normalize = new boolean[n];
    for(int i=0; i-->