Java-ML:Java Machine Learning Library

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Documentation

• Getting started
• Data manipulation
• Clustering
• Clustering basics
• Cluster evaluation
• Weka clustering
• Feature selection
• Classification
• Databases
• Developer documentation
  

• References
  

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：Learning machine earning Library BRARY Java

1. /**
   
2. * This file is part of the Java Machine Learning Library
   
3. *
   
4. * The Java Machine Learning Library is free software; you can redistribute it and/or modify
   
5. * it under the terms of the GNU General Public License as published by
   
6. * the Free Software Foundation; either version 2 of the License, or
   
7. * (at your option) any later version.
   
8. *
   
9. * The Java Machine Learning Library is distributed in the hope that it will be useful,
   
10. * but WITHOUT ANY WARRANTY; without even the implied warranty of
    
11. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    
12. * GNU General Public License for more details.
    
13. *
    
14. * You should have received a copy of the GNU General Public License
    
15. * along with the Java Machine Learning Library; if not, write to the Free Software
    
16. * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
    
17. *
    
18. * Copyright (c) 2006-2009, Thomas Abeel
    
19. *
    
20. * Project: http://java-ml.sourceforge.net/
    
21. *
    
22. */
    
23. package tutorials.clustering;
    
24. 
    
25. import java.io.File;
    
26. 
    
27. import net.sf.javaml.clustering.Clusterer;
    
28. import net.sf.javaml.clustering.KMeans;
    
29. import net.sf.javaml.core.Dataset;
    
30. import net.sf.javaml.tools.data.FileHandler;
    
31. 
    
32. /**
    
33. * This tutorial shows how to use a clustering algorithm to cluster a data set.
    
34. *
    
35. *
    
36. * @author Thomas Abeel
    
37. *
    
38. */
    
39. public class TutorialKMeans {
    
40. 
    
41.     /**
    
42.      * Tests the k-means algorithm with default parameter settings.
    
43.      */
    
44.     public static void main(String[] args) throws Exception {
    
45. 
    
46.         /* Load a dataset */
    
47.         Dataset data = FileHandler.loadDataset(new File("devtools/data/iris.data"), 4, ",");
    
48.         /*
    
49.          * Create a new instance of the KMeans algorithm, with no options
    
50.          * specified. By default this will generate 4 clusters.
    
51.          */
    
52.         Clusterer km = new KMeans();
    
53.         /*
    
54.          * Cluster the data, it will be returned as an array of data sets, with
    
55.          * each dataset representing a cluster
    
56.          */
    
57.         Dataset[] clusters = km.cluster(data);
    
58.         System.out.println("Cluster count: " + clusters.length);
    
59. 
    
60.     }
    
61. 
    
62. }

复制代码

1. **
   
2. * This file is part of the Java Machine Learning Library
   
3. *
   
4. * The Java Machine Learning Library is free software; you can redistribute it and/or modify
   
5. * it under the terms of the GNU General Public License as published by
   
6. * the Free Software Foundation; either version 2 of the License, or
   
7. * (at your option) any later version.
   
8. *
   
9. * The Java Machine Learning Library is distributed in the hope that it will be useful,
   
10. * but WITHOUT ANY WARRANTY; without even the implied warranty of
    
11. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    
12. * GNU General Public License for more details.
    
13. *
    
14. * You should have received a copy of the GNU General Public License
    
15. * along with the Java Machine Learning Library; if not, write to the Free Software
    
16. * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
    
17. *
    
18. * Copyright (c) 2006-2009, Thomas Abeel
    
19. *
    
20. * Project: http://java-ml.sourceforge.net/
    
21. *
    
22. */
    
23. package tutorials.clustering;
    
24. 
    
25. import java.io.File;
    
26. 
    
27. import net.sf.javaml.clustering.Clusterer;
    
28. import net.sf.javaml.clustering.KMeans;
    
29. import net.sf.javaml.clustering.evaluation.AICScore;
    
30. import net.sf.javaml.clustering.evaluation.BICScore;
    
31. import net.sf.javaml.clustering.evaluation.ClusterEvaluation;
    
32. import net.sf.javaml.clustering.evaluation.SumOfSquaredErrors;
    
33. import net.sf.javaml.core.Dataset;
    
34. import net.sf.javaml.tools.data.FileHandler;
    
35. 
    
36. /**
    
37. * Shows how to use the different cluster evaluation measure that are
    
38. * implemented in Java-ML.
    
39. *
    
40. * @see net.sf.javaml.clustering.evaluation.*
    
41. *
    
42. * @author Thomas Abeel
    
43. *
    
44. */
    
45. public class TutorialClusterEvaluation {
    
46. 
    
47.     public static void main(String[] args) throws Exception {
    
48.         /* Load a dataset */
    
49.         Dataset data = FileHandler.loadDataset(new File("devtools/data/iris.data"), 4, ",");
    
50.         /*
    
51.          * Create a new instance of the KMeans algorithm that will create 3
    
52.          * clusters and create one that will make 4 clusters.
    
53.          */
    
54.         Clusterer km3 = new KMeans(3);
    
55.         Clusterer km4 = new KMeans(4);
    
56.         /*
    
57.          * Cluster the data, we will create 3 and 4 clusters.
    
58.          */
    
59.         Dataset[] clusters3 = km3.cluster(data);
    
60.         Dataset[] clusters4 = km4.cluster(data);
    
61. 
    
62.         ClusterEvaluation aic = new AICScore();
    
63.         ClusterEvaluation bic = new BICScore();
    
64.         ClusterEvaluation sse = new SumOfSquaredErrors();
    
65. 
    
66.         double aicScore3 = aic.score(clusters3);
    
67.         double bicScore3 = bic.score(clusters3);
    
68.         double sseScore3 = sse.score(clusters3);
    
69. 
    
70.         double aicScore4 = aic.score(clusters4);
    
71.         double bicScore4 = bic.score(clusters4);
    
72.         double sseScore4 = sse.score(clusters4);
    
73. 
    
74.         System.out.println("AIC score: " + aicScore3+"\t"+aicScore4);
    
75.         System.out.println("BIC score: " + bicScore3+"\t"+bicScore4);
    
76.         System.out.println("Sum of squared errors: " + sseScore3+"\t"+sseScore4);
    
77.         
    
78.     }
    
79. }

复制代码

1. /**
   
2. * This file is part of the Java Machine Learning Library
   
3. *
   
4. * The Java Machine Learning Library is free software; you can redistribute it and/or modify
   
5. * it under the terms of the GNU General Public License as published by
   
6. * the Free Software Foundation; either version 2 of the License, or
   
7. * (at your option) any later version.
   
8. *
   
9. * The Java Machine Learning Library is distributed in the hope that it will be useful,
   
10. * but WITHOUT ANY WARRANTY; without even the implied warranty of
    
11. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    
12. * GNU General Public License for more details.
    
13. *
    
14. * You should have received a copy of the GNU General Public License
    
15. * along with the Java Machine Learning Library; if not, write to the Free Software
    
16. * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
    
17. *
    
18. * Copyright (c) 2006-2009, Thomas Abeel
    
19. *
    
20. * Project: http://java-ml.sourceforge.net/
    
21. *
    
22. */
    
23. package tutorials.tools;
    
24. 
    
25. import java.io.File;
    
26. 
    
27. import net.sf.javaml.clustering.Clusterer;
    
28. import net.sf.javaml.core.Dataset;
    
29. import net.sf.javaml.tools.data.FileHandler;
    
30. import net.sf.javaml.tools.weka.WekaClusterer;
    
31. import weka.clusterers.XMeans;
    
32. 
    
33. /**
    
34. * Tutorial how to use a Weka classifier in Java-ML.
    
35. *
    
36. * @author Thomas Abeel
    
37. *
    
38. */
    
39. public class TutorialWekaClusterer {
    
40. 
    
41.     public static void main(String[] args) throws Exception {
    
42.         /* Load data */
    
43.         Dataset data = FileHandler.loadDataset(new File("devtools/data/iris.data"), 4, ",");
    
44.         /* Create Weka classifier */
    
45.         XMeans xm = new XMeans();
    
46.         /* Wrap Weka clusterer in bridge */
    
47.         Clusterer jmlxm = new WekaClusterer(xm);
    
48.         /* Perform clustering */
    
49.         Dataset[] clusters = jmlxm.cluster(data);
    
50.         /* Output results */
    
51.         System.out.println(clusters.length);
    
52.     }
    
53. }

复制代码

Feature scoring

1. /* Load the iris data set */
   
2. Dataset data = FileHandler.loadDataset(new File("iris.data"), 4, ",");
   
3. /* Create a feature scoring algorithm */
   
4. GainRatio ga = new GainRatio();
   
5. /* Apply the algorithm to the data set */
   
6. ga.build(data);
   
7. /* Print out the score of each attribute */
   
8. for (int i = 0; i < ga.noAttributes(); i++)
   
9.     System.out.println(ga.score(i));

复制代码

Feature Ranking

1. /* Load the iris data set */
   
2. Dataset data = FileHandler.loadDataset(new File("iris.data"), 4, ",");
   
3. /* Create a feature ranking algorithm */
   
4. RecursiveFeatureEliminationSVM svmrfe = new RecursiveFeatureEliminationSVM(0.2);
   
5. /* Apply the algorithm to the data set */
   
6. svmrfe.build(data);
   
7. /* Print out the rank of each attribute */
   
8. for (int i = 0; i < svmrfe.noAttributes(); i++)
   
9.     System.out.println(svmrfe.rank(i));

复制代码

Feature subset selection
Thu, 01/15/2009 - 15:47 — Thomas Abeel
Subset selection algorithms differ with the scoring and ranking methods in that they only provide a set of features that are selected without further information on the quality of each feature individually.
Subset selection algorithms provide the method

1. /* Load the iris data set */
   
2. Dataset data = FileHandler.loadDataset(new File("iris.data"), 4, ",");
   
3. /* Construct a greedy forward subset selector */
   
4. GreedyForwardSelection ga = new GreedyForwardSelection(1, new PearsonCorrelationCoefficient());
   
5. /* Apply the algorithm to the data set */
   
6. ga.build(data);
   
7. /* Print out the attribute that has been selected */
   
8. System.out.println(ga.selectedAttributes());

复制代码

Ensemble feature ranking[size=0.92em]Thu, 01/15/2009 - 15:45 — Thomas Abeel

The ensemble feature ranking algorithm is another form of feature ranking and as such provides the following method to determine the rank of a feature. Lower ranks are better.

1. /* Load the iris data set */
   
2. Dataset data = FileHandler.loadDataset(new File("devtools/data/iris.data"), 4, ",");
   
3. /* Create a feature ranking algorithm */
   
4. RecursiveFeatureEliminationSVM[] svmrfes = new RecursiveFeatureEliminationSVM[10];
   
5. for (int i = 0; i < svmrfes.length; i++)
   
6.     svmrfes[i] = new RecursiveFeatureEliminationSVM(0.2);
   
7. LinearRankingEnsemble ensemble = new LinearRankingEnsemble(svmrfes);
   
8. /* Build the ensemble */
   
9. ensemble.build(data);
   
10. /* Get rank of i-th feature */
    
11. int rank=ensemble.rank(i)

复制代码

谢谢分享