无法处理多值标称类- JAVA

Question

我试图向LinearRegression对象传递一个.arff文件，同时它给了我这个异常，不能处理多值标称类！。

实际发生的情况是，在这样做之后，我使用CFSSubsetEval计算程序执行属性选择，然后搜索为LinearRegression，将这些属性传递给LinearRegression，如下所示

LinearRegression rl=new LinearRegression(); rl.buildClassifier(data);    

data是一个实例对象，它拥有来自.arff文件的数据，以前仅使用weka将其转换为标称值。我在这里做错什么了吗？我试图在谷歌上搜索这个错误，但是找不到。

代码

package com.attribute;

import java.io.BufferedReader;
import java.io.FileReader;
import java.util.Random;

import weka.attributeSelection.AttributeSelection;
import weka.attributeSelection.CfsSubsetEval;
import weka.attributeSelection.GreedyStepwise;
import weka.classifiers.Evaluation;
import weka.classifiers.functions.LinearRegression;
import weka.classifiers.meta.AttributeSelectedClassifier;
import weka.classifiers.trees.J48;
import weka.core.Instances;
import weka.core.Utils;
import weka.filters.supervised.attribute.NominalToBinary;

/**
 * performs attribute selection using CfsSubsetEval and GreedyStepwise
 * (backwards) and trains J48 with that. Needs 3.5.5 or higher to compile.
 * 
 * @author FracPete (fracpete at waikato dot ac dot nz)
 */
public class AttributeSelectionTest2 {

    /**
     * uses the meta-classifier
     */
    protected static void useClassifier(Instances data) throws Exception {
        System.out.println("\n1. Meta-classfier");
        AttributeSelectedClassifier classifier = new AttributeSelectedClassifier();
        CfsSubsetEval eval = new CfsSubsetEval();
        GreedyStepwise search = new GreedyStepwise();
        search.setSearchBackwards(true);
        J48 base = new J48();
        classifier.setClassifier(base);
        classifier.setEvaluator(eval);
        classifier.setSearch(search);
        Evaluation evaluation = new Evaluation(data);
        evaluation.crossValidateModel(classifier, data, 10, new Random(1));
        System.out.println(evaluation.toSummaryString());
    }

    /**
     * uses the low level approach
     */
    protected static void useLowLevel(Instances data) throws Exception {
        System.out.println("\n3. Low-level");
        AttributeSelection attsel = new AttributeSelection();
        CfsSubsetEval eval = new CfsSubsetEval();
        GreedyStepwise search = new GreedyStepwise();
        search.setSearchBackwards(true);
        attsel.setEvaluator(eval);
        attsel.setSearch(search);
        attsel.SelectAttributes(data);
        int[] indices = attsel.selectedAttributes();
        System.out.println("selected attribute indices (starting with 0):\n"
                + Utils.arrayToString(indices));
        useLinearRegression(indices, data);
    }

    protected static void useLinearRegression(int[] indices, Instances data) throws Exception{
        System.out.println("\n 4. Linear-Regression on above selected attributes");

        BufferedReader reader = new BufferedReader(new FileReader(
                "C:/Entertainement/MS/Fall 2014/spdb/project 4/healthcare.arff"));
        Instances data1 = new Instances(reader);
        data.setClassIndex(data.numAttributes() - 1);
        /*NominalToBinary nb = new NominalToBinary();
        for(int i=0;i<=20; i++){
         //Still coding left here, create an Instance variable to store the data from 'data' variable for given indices
            Instances data_lr=data1.
        }*/
        LinearRegression rl=new LinearRegression(); //Creating a LinearRegression Object to pass data1
        rl.buildClassifier(data1);
    }
    /**
     * takes a dataset as first argument
     * 
     * @param args
     *            the commandline arguments
     * @throws Exception
     *             if something goes wrong
     */
    public static void main(String[] args) throws Exception {
        // load data
        System.out.println("\n0. Loading data");
        BufferedReader reader = new BufferedReader(new FileReader(
                "C:/Entertainement/MS/Fall 2014/spdb/project 4/healthcare.arff"));
        Instances data = new Instances(reader);

        if (data.classIndex() == -1)
            data.setClassIndex(data.numAttributes() - 14);

        // 1. meta-classifier
        useClassifier(data);

        // 2. filter
        //useFilter(data);

        // 3. low-level
        useLowLevel(data);
    }
}

注意到：由于我没有编写代码来构建具有“indices”属性的实例变量，所以我(为了程序运行)从同一个原始文件加载数据。

我不知道如何上传一个样本数据的文件，但是它看起来像这样。链接

Answer 1

根据您的数据，您的最后一个属性似乎是一个名义数据类型(主要包含数字，但也有一些字符串)。LinearRegression不允许对标称类进行预测。

您可能要做的事情，以确保您的给定数据集工作，运行它通过Weka资源管理器与线性回归，并看看是否产生所需的结果。在此之后，数据很有可能在代码中正确工作。

希望这能帮上忙！

Answer 2

下面是用于LinearRegression (来源)的数据集示例

@RELATION house
@ATTRIBUTE houseSize NUMERIC
@ATTRIBUTE lotSize NUMERIC
@ATTRIBUTE bedrooms NUMERIC
@ATTRIBUTE granite NUMERIC
@ATTRIBUTE bathroom NUMERIC
@ATTRIBUTE sellingPrice NUMERIC

@DATA
3529,9191,6,0,0,205000
3247,10061,5,1,1,224900
4032,10150,5,0,1,197900
2397,14156,4,1,0,189900
2200,9600,4,0,1,195000
3536,19994,6,1,1,325000
2983,9365,5,0,1,230000