java中1維數據的輕量級增量分類

Question

我有一組觀察值（類，值）。值是自然數。只有兩類。我期望在一個決策點上很容易區分類別，例如，如果值爲< 10，則類別A;如果值> = 10，則類別B是唯一的。唯一的困難是類別和值之間有一些重疊邊界。

是否有一種快速輕量級的方式來更新觀察值並對Java中的新數據點進行分類以解決此問題？理想情況是這樣的：

classifier.addObservation(observation); 
classifier.classify(value); 

一個解決方案將是一個Java包的演示和你選擇算法的理由。

Answer 1

經過一番搜索，我結束了使用Weka。特別是我使用了樸素貝葉斯分類器。他們的數據結構有點神祕，但它的工作原理很快。

package agent.agenttype.ijcai; 
import weka.classifiers.Classifier; 
import weka.classifiers.bayes.NaiveBayes; 
import weka.core.Attribute; 
import weka.core.FastVector; 
import weka.core.Instance; 
import weka.core.Instances; 
import weka.core.SparseInstance; 

public class Example { 

    public static enum ClassLabel {A, B}; 

    Instances trainingSet; 
    FastVector att = new FastVector(2); 
    FastVector cl = new FastVector(2); 

    public Example(){ 
     //Add class labels 
     cl.addElement(ClassLabel.values()[0].name()); 
     cl.addElement(ClassLabel.values()[1].name()); 
     //set the name of our value attribute 
     Attribute Attribute1 = new Attribute("Value"); 
     //set the name of our class label atrribute 
     Attribute ClassAttribute = new Attribute("Label", cl);  
     att.addElement(Attribute1); 
     att.addElement(ClassAttribute);  
     //create training set that uses our attributes to interpret instances 
     trainingSet = new Instances("TrainingSet", att, 2); 
     trainingSet.setClassIndex(1);//tell our training set that index 2 of instances is the class label 
    } 

    public void addObservationToEdge(int value, ClassLabel classLabel){ 
      Instance instance = new SparseInstance(2); 
      instance.setValue((Attribute)att.elementAt(0), value); //set value 
      instance.setValue((Attribute)att.elementAt(1), classLabel.name());//set our 
      trainingSet.add(instance); 
    } 

    public ClassLabel classifyValue(int value) throws Exception{ 

     Instance instanceForClassification = new SparseInstance(1); 
     instanceForClassification.setValue((Attribute)att.elementAt(0), value); 
     instanceForClassification.setDataset(trainingSet);//make instance inherit attribute labels from training set 

     Classifier cModel = (Classifier)new NaiveBayes();//create naive bayes classifier 
     cModel.buildClassifier(trainingSet); 

     int labelNumber = (int) cModel.classifyInstance(instanceForClassification); 
     return ClassLabel.values()[labelNumber]; 
    } 

    public static void main(String[] args){ 
     Example example = new Example(); 
     example.addObservationToEdge(1, ClassLabel.A); 
     example.addObservationToEdge(2, ClassLabel.A); 
     example.addObservationToEdge(5, ClassLabel.A); 
     example.addObservationToEdge(11, ClassLabel.A); 
     example.addObservationToEdge(9, ClassLabel.B); 
     example.addObservationToEdge(12, ClassLabel.B); 
     example.addObservationToEdge(15, ClassLabel.B); 
     example.addObservationToEdge(20, ClassLabel.B); 

     try { 
     //print classification results 
     for(int i = 0; i<20; i++){ 
      System.out.println("Value: " + i + " Class Label:" + example.classifyValue(i)); 
     } 
     } catch (Exception e) { 
     // TODO Auto-generated catch block 
     e.printStackTrace(); 
     }  
    } 

} 

OUTPUT：

Value: 0 Class Label:A 
Value: 1 Class Label:A 
Value: 2 Class Label:A 
Value: 3 Class Label:A 
Value: 4 Class Label:A 
Value: 5 Class Label:A 
Value: 6 Class Label:A 
Value: 7 Class Label:A 
Value: 8 Class Label:A 
Value: 9 Class Label:A 
Value: 10 Class Label:B 
Value: 11 Class Label:B 
Value: 12 Class Label:B 
Value: 13 Class Label:B 
Value: 14 Class Label:B 
Value: 15 Class Label:B 
Value: 16 Class Label:B 
Value: 17 Class Label:B 
Value: 18 Class Label:B 
Value: 19 Class Label:B