tclass.java~

用于multivariate时间序列分类

/**
 *  Single classifier solution. That is to say, we cluster all the instances
 *  using the same clustering algorithms. 
 * 
 * 
 * @author Waleed Kadous
 * @version $Id: TClass.java,v 1.1.1.1 2002/06/28 07:36:16 waleed Exp $
 */

package tclass;  

import java.util.StringTokenizer;

import tclass.clusteralg.GClust;
import tclass.util.Debug;
import weka.attributeSelection.BestFirst;
import weka.attributeSelection.CfsSubsetEval;
import weka.classifiers.Classifier;
import weka.core.Instances;
import weka.core.Utils;
import weka.filters.AttributeFilter;

public class TClass {
    // Ok. What we are going to do is to separate the learning task in 
    // an interesting way. 
    // First of all, though, the standard stuff
    
    String domDescFile = "tclass.tdd"; 
    String trainDataFile = "tclass.tsl"; 
    String testDataFile = "tclass.ttl"; 
    String settingsFile = "tclass.tal"; 
    String learnerStuff = "weka.classifiers.j48.J48"; 
    boolean featureSel = false; 
    boolean makeDesc = false; 
    boolean trainResults = false; 
    void parseArgs(String[] args){
        for(int i=0; i < args.length; i++){
            if(args[i].equals("-tr")){
                trainDataFile = args[++i]; 
            }
            if(args[i].equals("-dd")){
                domDescFile = args[++i]; 
            }
            if(args[i].equals("-te")){
                testDataFile = args[++i];
            }
            if(args[i].equals("-s")){
                settingsFile = args[++i]; 
            }
            if(args[i].equals("-fs")){
                featureSel = true; 
            }
            if(args[i].equals("-md")){
                makeDesc = true; 
            }
            if(args[i].equals("-trainres")){
                trainResults = true; 
            }
            if(args[i].equals("-l")){
                learnerStuff = args[++i]; 
                learnerStuff = learnerStuff.replace(':', ' '); 
                System.err.println("Learner String is: " + learnerStuff); 
            }
        }
    }

    // Alright. This is downright funky hacky stuff. 
    
    public static void main(String[] args) throws Exception {
        Debug.setDebugLevel(Debug.PROGRESS); 
        TClass thisExp = new TClass(); 
        thisExp.parseArgs(args); 
        DomDesc domDesc = new DomDesc(thisExp.domDescFile); 
        ClassStreamVecI trainStreamData = new
            ClassStreamVec(thisExp.trainDataFile, domDesc); 
        ClassStreamVecI testStreamData = new
            ClassStreamVec(thisExp.testDataFile, domDesc); 

        Debug.dp(Debug.PROGRESS, "PROGRESS: Data read in");  
        Settings settings = new Settings(thisExp.settingsFile, domDesc); 
        

        EventExtractor evExtractor = settings.getEventExtractor(); 
        // Global data is likely to be included in every model; so we
        // might as well calculated now
        GlobalCalc globalCalc = settings.getGlobalCalc(); 

        ClassStreamAttValVecI trainGlobalData =
            globalCalc.applyGlobals(trainStreamData);
        ClassStreamAttValVecI testGlobalData =
            globalCalc.applyGlobals(testStreamData);
        // And we might as well extract the events. 

        Debug.dp(Debug.PROGRESS, "PROGRESS: Globals calculated.");  
        Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size() +
                 " Test: " + testGlobalData.size());  


        ClassStreamEventsVecI trainEventData =
            evExtractor.extractEvents(trainStreamData); 
        ClassStreamEventsVecI testEventData =
            evExtractor.extractEvents(testStreamData); 

        Debug.dp(Debug.PROGRESS, "PROGRESS: Events extracted");  
        // System.out.println(trainEventData.toString()); 


        // Now we want the clustering algorithms only to cluster
        // instances of each class. Make an array of clusterers, 
        // one per class. 

        int numTestStreams = testEventData.size(); 

        int numClasses = domDesc.getClassDescVec().size(); 
        EventDescVecI eventDescVec = evExtractor.getDescription(); 
        EventClusterer eventClusterer = settings.getEventClusterer(); 
        Debug.dp(Debug.PROGRESS, "PROGRESS: Data rearranged.");  


        //And now load it up. 
        StreamEventsVecI trainEventSEV =
            trainEventData.getStreamEventsVec(); 
        ClassificationVecI trainEventCV = trainEventData.getClassVec();
        int numTrainStreams = trainEventCV.size(); 
        ClusterVecI clusters = eventClusterer.clusterEvents(trainEventData); 
        Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete"); 
        Debug.dp(Debug.PROGRESS, "Clusters are:"); 
        Debug.dp(Debug.PROGRESS, "\n" + eventClusterer.getMapping()); 
        Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete. ");  

        // But wait! There's more! There is always more. 
        // The first thing was only useful for clustering. 
        // Now attribution. We want to attribute all the data. So we are going 
        // to have one dataset for each learner. 
        // First set up the attributors. 

        Attributor attribs = new Attributor(domDesc, clusters, 
                                            eventClusterer.getDescription()); 
        Debug.dp(Debug.PROGRESS, "PROGRESS: AttributorMkr complete."); 
        

        ClassStreamAttValVecI trainEventAtts =attribs.attribute(trainStreamData, trainEventData); 
        ClassStreamAttValVecI testEventAtts = attribs.attribute(testStreamData,
                                                    testEventData); 
        Debug.dp(Debug.PROGRESS, "PROGRESS: Attribution complete."); 


        // Combine all data sources. For now, globals go in every
        // one. 

        Combiner c = new Combiner(); 
        ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData,
                                            trainEventAtts); 

        ClassStreamAttValVecI testAtts = c.combine(testGlobalData,
                                           testEventAtts); 

        trainStreamData = null; 
        testStreamData = null; 
        trainEventSEV = null; 
        trainEventCV = null; 
        if(!thisExp.makeDesc){
            clusters = null; 
            eventClusterer = null; 
        }
        attribs = null; 

        System.gc(); 


        // So now we have the raw data in the correct form for each
        // attributor. 
        // And now, we can construct a learner for each case. 
        // Well, for now, I'm going to do something completely crazy. 
        // Let's run each classifier nonetheless over the whole data
        // ... and see what the hell happens. Maybe some voting scheme 
        // is possible!! This is a strange form of ensemble
        // classifier. 
        // Each naive bayes algorithm only gets one