相關數據挖掘算法的調用

 分類算法： 

     1.調用C4.5

        分類算法我們會額外計算它的分類準確率，實現代碼如下，有註釋了，分類算法的實現很多共通之處，往後的幾個 分類算法就不指明瞭：

        必須提醒的是，設置分類屬性所在行號是必須的。

import weka.classifiers.*;
import weka.core.Instances;
import weka.core.converters.*;
import weka.classifiers.trees.J48;                                         // C45算法(1)
import java.io.File;
import java.io.IOException;

import javax.swing.*;

public class callC45
{
    public callC45()
    {}

    public void Main() throws Exception
    {
        J48 m_classifier = new J48();

        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff");   //訓練語料文件
        ArffLoader atf = new ArffLoader();
        atf.setFile(inputFile);
        Instances instancesTrain = atf.getDataSet();             //讀入訓練文件

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff"); // 測試語料文件
        atf.setFile(inputFile);
        Instances instancesTest = atf.getDataSet();    //讀入訓練文件
        instancesTest.setClassIndex(0);                                                                              //設置分類屬性所在行號（第一行爲0號），instancesTest.numAttributes()可以取得屬性總數

        double sum = instancesTest.numInstances(),right=0.0f;           //測試語料實例數
        instancesTrain.setClassIndex(0);

        m_classifier.buildClassifier(instancesTrain);
        System.out.println(m_classifier.toString());
        System.out.println("");
        for(int i = 0; i < sum ; i++)
        {
            if(m_classifier.classifyInstance(instancesTest.instance(i))==instancesTest.instance(i).classValue())  //如果預測值和答案值相等（測試語料中的分類列提供的須爲正確答案，結果纔有意義）
            {
                right++;
            }
        }
        System.out.println("J48 classification precision:"+(right/sum));
    }

//  public static void main(String[] args) throws Exception
//  {
//      callC45 a = new callC45();
//      a.Main();
//  }

}

         2.調用AdaBoost算法

          

import weka.classifiers.meta.AdaBoostM1;
import weka.classifiers.*;
import weka.core.converters.*;
import weka.core.Instances;
import java.io.*;

public class callAdaBoostM1
{
    public callAdaBoostM1()
    {

    }

    public void Main() throws Exception
    {
        AdaBoostM1 m_classifier = new AdaBoostM1();

        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff");
        ArffLoader arf = new ArffLoader();
        arf.setFile(inputFile);
        Instances instancesTrain = arf.getDataSet();

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff");
        arf.setFile(inputFile);
        Instances instancesTest = arf.getDataSet();
        instancesTest.setClassIndex(0);

        double sum = instancesTest.numInstances(),right=0.0f;
        instancesTrain.setClassIndex(0);

        m_classifier.buildClassifier(instancesTrain);
        System.out.println(m_classifier.toString());
        System.out.println("");

        for(int i = 0; i<sum ; i++)
        {
            if(m_classifier.classifyInstance(instancesTest.instance(i)) == instancesTest.instance(i).classValue())
            {
                right++;
            }
        }
        System.out.println("AdaBoostM1 classification precision:"+(right/sum));

    }

    public static void main(String[] args) throws Exception
    {
        callAdaBoostM1 a = new callAdaBoostM1();
        a.Main();
    }
}

            3.調用樸素bayes算法;

import java.io.*;
import weka.classifiers.*;
import weka.classifiers.bayes.*;
import weka.core.Instances;
import weka.core.converters.*;
import java.io.File;
import java.io.IOException;

public class callbayes
{
    public callbayes()
    {}

    public void Main() throws Exception
    {
        NaiveBayes m_classifier = new NaiveBayes();     //樸素貝葉斯的調用

        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\labor.arff");
        ArffLoader atf = new ArffLoader();
        atf.setFile(inputFile);
        Instances instancesTrain = atf.getDataSet();
        instancesTrain.setClassIndex(instancesTrain.numAttributes()-1);

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\labor.arff");
        atf.setFile(inputFile);
        Instances instancesTest = atf.getDataSet();
        instancesTest.setClassIndex(instancesTest.numAttributes()-1);

        double sum =  instancesTest.numInstances(),right = 0.0f;

        m_classifier.buildClassifier(instancesTrain);
        System.out.println(m_classifier.toString());
        System.out.println("");
        for(int i = 0; i < sum ; i++)
        {
            if(m_classifier.classifyInstance(instancesTest.instance(i)) == instancesTest.instance(i).classValue())
            {
                right++;
            }
        }

        System.out.println("Navisbayes classification precision:" + (right/sum));

    }

//  public static void main(String[] args) throws Exception
//  {
//      callbayes a = new callbayes();
    //  a.Main();
//  }

}

             4.調用KNN算法：

import weka.classifiers.*;
import weka.classifiers.lazy.IBk;
import weka.core.converters.*;
import weka.core.Instances;
import java.io.*;

public class callKNN
{
    public callKNN()
    {}

    public void Main() throws Exception
    {
        IBk m_classifier = new IBk(3);
    //  int k=3;
    //  Classifier m_classifier = new IBk(k);
        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff");
        ArffLoader arf = new ArffLoader();
        arf.setFile(inputFile);
        Instances instancesTrain = arf.getDataSet();

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.with.vendor.arff");
        arf.setFile(inputFile);
        Instances instancesTest = arf.getDataSet();
        instancesTest.setClassIndex(0);

        double sum = instancesTest.numInstances(),right=0.0f;
        instancesTrain.setClassIndex(0);

        m_classifier.buildClassifier(instancesTrain);
        System.out.println("The k is : "+m_classifier.getKNN());
        System.out.println("");
        System.out.println(m_classifier.toString());
        System.out.println("");

        for(int i = 0; i<sum ; i++)
        {
            if(m_classifier.classifyInstance(instancesTest.instance(i)) == instancesTest.instance(i).classValue())
            {
                right++;
            }
        }
        System.out.println("KNN classification precision:"+(right/sum));
    }

    public static void main(String[] args) throws Exception
    {
        callKNN a = new callKNN();
        a.Main();
    }
}

            5.調用ID3（CART） 算法

import weka.classifiers.*;
import weka.classifiers.trees.Id3;
import weka.core.Instances;
import weka.core.converters.*;
import java.io.*;

public class callId3
{
    public callId3()
    {}

    public void Main() throws Exception
    {
        Id3 m_classifier = new Id3();

        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\contact-lenses.arff");
        ArffLoader atf = new ArffLoader();
        atf.setFile(inputFile);
        Instances instancesTrain = atf.getDataSet();

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\contact-lenses.arff");
        atf.setFile(inputFile);
        Instances instancesTest = atf.getDataSet();
        instancesTest.setClassIndex(0);

        double sum = instancesTest.numInstances(),right=0.0f;

        instancesTrain.setClassIndex(0);
        m_classifier.buildClassifier(instancesTrain);
        System.out.println(m_classifier.toString());
        System.out.println("");

        for(int i = 0; i < sum ; i++)
        {
            if(m_classifier.classifyInstance(instancesTest.instance(i)) == instancesTest.instance(i).classValue())
            {
                right++;
            }
        }

        System.out.println("Id3 classification precision:"+(right/sum));
    }

//  public static void main(String[] args) throws Exception
    //{
    //  callId3 a = new callId3();
    //  a.Main();
//  }

}

        聚類算法：

        主要是調用了EM算法和KM算法，SVM由於還不會用libsvm，就先放着了，聚類算法的調用的不同分類算法之處就是不必設置分類屬性行號：

        1.調用EM算法;

         

import weka.clusterers.EM;
import weka.core.Instances;
import weka.core.converters.*;
import weka.clusterers.*;
import java.io.*;

public class callEM
{
    public callEM()
    {
    }

    public void Main() throws Exception
    {
        EM m_cluster = new EM();
        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.arff");
        ArffLoader arf = new ArffLoader();
        arf.setFile(inputFile);
        Instances instancesTrain = arf.getDataSet();

         inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.arff");
         arf.setFile(inputFile);
         Instances instancesTest = arf.getDataSet();

         m_cluster.buildClusterer(instancesTrain);
         System.out.println("The number of cluster : "+m_cluster.numberOfClusters());
         int num = m_cluster.numberOfClusters();
         System.out.println("");
         System.out.println(m_cluster.toString());
         System.out.println("");

         double[]  predict = m_cluster.clusterPriors();
         for(int i = 0; i<num ; i++)
         {
            System.out.println("第  "+i+" 個 聚類的先驗爲 ： "+predict[i]);
         }
    }

    public static void main(String[] args) throws Exception
    {
        callEM a = new callEM();
        a.Main();
    }
}

             2.調用KM算法;

import weka.clusterers.*;
import weka.core.converters.*;
import weka.core.Instances;
import java.io.*;

public class callKM
{
    public callKM()
    {

    }

    public void Main() throws Exception
    {
        SimpleKMeans m_cluster = new SimpleKMeans();
        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.arff");
        ArffLoader arf = new ArffLoader();
        arf.setFile(inputFile);
        Instances instancesTrain = arf.getDataSet();

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\cpu.arff");
        arf.setFile(inputFile);
        Instances instancesTest = arf.getDataSet();

        m_cluster.buildClusterer(instancesTrain);

        System.out.println("The number of cluster : "+m_cluster.numberOfClusters());
         int num = m_cluster.numberOfClusters();
         System.out.println("");
         System.out.println(m_cluster.toString());
         System.out.println("");

         int[] size = m_cluster.getClusterSizes();
         int sum = 0;
         for(int i = 0; i<num ; i++)
         {
             sum += size[i];
         }
         for(int i = 0; i<num ; i++)
         {
            System.out.println("第  "+i+" 個 聚類的大小爲 ： "+size[i]+"   所佔比例爲 ： "+(double)size[i]/(double)sum);
         }

    }

    public static void main(String[] args) throws Exception
    {
        callKM a = new callKM();
        a.Main();
    }
}

           關聯規則算法

           只是調用了Apriori算法，調用方法和聚類算法的基本一樣了。。。

           1.調用Apriori算法

            

import weka.associations.*;
import weka.core.converters.*;
import weka.core.Instances;
import java.io.*;

public class callApriori
{
    public callApriori()
    {

    }

    public void Main() throws Exception
    {
        Apriori m_association = new Apriori();
        File inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\contact-lenses.arff");
        ArffLoader arf = new ArffLoader();
        arf.setFile(inputFile);
        Instances instancesTrain = arf.getDataSet();

        inputFile = new File("E:\\資料\\數據挖掘\\weka-3-5-8\\data\\contact-lenses.arff");
        arf.setFile(inputFile);
        Instances instancesTest = arf.getDataSet();

        m_association.buildAssociations(instancesTrain);
        System.out.println("The Number of Rules : "+m_association.getNumRules());
        System.out.println(m_association.toString());
        System.out.println("");

    }

//  public static void main(String[] args) throws Exception
//  {
    //  callApriori a = new callApriori();
//      a.Main();
//  }
}