1

上学期我有一个项目，当给定一组汽车数据时，我必须建立一个模型并使用该模型从用户输入的数据中进行预测（它涉及 GUI 等）。教授介绍了 Weka，但只是以它的 GUI 形式。我正在重新创建项目，但这次是使用 Weka 库。这是有问题的课程：

public class TreeModel {
private J48 model = new J48();
private String[] options = new String[1];
private DataSource source;
private Instances data;
private Evaluation eval;

// Constructor
public TreeModel(String file) throws Exception {
     source = new DataSource(file);
     // By default, the options are set to produce unpruned tree '-U'
     options[0] = "-U";
     data = source.getDataSet();         
     model.setOptions(options);
}

// Overloaded constructor allowing you to choose options for the model
public TreeModel(String file, String[] options) throws Exception {
     DataSource source = new DataSource(file);
     data = source.getDataSet();
     model.setOptions(options);
}

// Builds the decision tree
public void buildDecisionTree() throws Exception {
     data.setClassIndex(data.numAttributes() - 1);
     model.buildClassifier(data);
}

/*
 * Uses cross validation technique to calculate the accuracy.
 * Gives a more respected accuracy that is more likely to hold 
 * with instances not in the dataset.
 */
public void crossValidatedEvaluation(int folds) throws Exception {
    eval = new Evaluation(data);
    eval.crossValidateModel(model, data, folds, new Random());
    System.out.println("The model predicted "+eval.pctCorrect()+" percent of the data correctly.");
}

/*
 * Evaluates the accuracy of a decision tree when using all available data
 * This should be looked at with skepticism (less interpretable)
 */
public void evaluateModel() throws Exception {
     eval = new Evaluation(data);
     eval.evaluateModel(model, data);
     System.out.println("The model predicted "+eval.pctCorrect()+" percent of the data correctly.");
}


/*
 *  Returns a prediction for a particular instance. Will take in an instance 
 *  as a parameter.
 */
public String getPrediction() throws Exception {
    DataSource predFile = new DataSource("./predict.arff");
    Instances pred = predFile.getDataSet();

    Instance predic = pred.get(0);
    pred.setClassIndex(pred.numAttributes() - 1);

    double classify = model.classifyInstance(predic);

    pred.instance(0).setClassValue(classify);
    return pred.instance(0).stringValue(6);
}

// Returns source code version of the model (warning: messy code)
public String getModelSourceCode() throws Exception {
     return model.toSource("DecisionTree");
}   
}

在我的 getPrediction() 方法中，我有一个简单的示例，用于获取 ARFF 文件中实例的预测。问题是我无法弄清楚如何初始化单个 Instance 对象，然后将我想要进行预测的数据放入“in”该实例中。我查看了 Instance 类的文档，但乍一看什么也没看到。有没有办法手动将数据放入实例中，或者我需要将我的预测数据转换为 ARFF 文件？

4

1 回答 1

1

此代码片段应该可以帮助您在没有 ARFF 文件的情况下构建自己的一组实例。下面我展示了从具有两个属性的数组创建一组新实例；纬度和经度。

import weka.core.Attribute;
import weka.core.DenseInstance;
import weka.core.FastVector;
import weka.core.Instances;

public class AttTest {

    public static void main(String[] args) throws Exception
    {
        double[] one={0,1,2,3};
        double[] two={3,2,1,0};
        double[][] both=new double[2][4];
        both[0]=one;
        both[1]=two;

        Instances to_use=AttTest.buildArff(both);
        System.out.println(to_use.toString());
    }

  public static Instances buildArff(double[][] array) throws Exception
  {
         FastVector      atts = new FastVector();
         atts.addElement(new Attribute("lat")); //latitude
         atts.addElement(new Attribute("lon")); //longitude

         // 2. create Instances object
         Instances test = new Instances("location", atts, 0);

         // 3. fill with data
         for(int s1=0; s1 < array[0].length; s1=s1+1)
         {
             double vals[] = new double[test.numAttributes()];
             vals[0] = array[0][s1];
             vals[1] = array[1][s1];
             test.add(new DenseInstance(1.0, vals));
         }

         return(test);
  }
}
于 2019-03-03T11:21:17.273 回答