Package org.fnlp.ml.classifier.bayes

Examples of org.fnlp.ml.classifier.bayes.BayesClassifier

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
    System.out.print("..Spliting complete!\n");

    System.out.print("Training...\n");
    af.setStopIncrement(true);
    BayesTrainer trainer=new BayesTrainer();
    BayesClassifier classifier= (BayesClassifier) trainer.train(trainset);
    System.out.print("..Training complete!\n");
    System.out.print("Saving model...\n");
    classifier.saveTo(bayesModelFile); 
    classifier = null;
    System.out.print("..Saving model complete!\n");
    /**
     * 测试
     */
    System.out.print("Loading model...\n");
    BayesClassifier bayes;
    bayes =BayesClassifier.loadFrom(bayesModelFile);
    System.out.print("..Loading model complete!\n");
   
    System.out.println("Testing Bayes...");
    int flag=0;
    float[] percents_cs=new float[]{1.0f,0.9f,0.8f,0.7f,0.5f,0.3f,0.2f,0.1f};
    int[] counts_cs=new int[10];
    for(int test=0;test<percents_cs.length;test++){
      System.out.println("Testing Bayes"+percents_cs[test]+"...");
      if(test!=0)
        bayes.fS_CS(percents_cs[test]);
      int count=0;
      for(int i=0;i<testset.size();i++){
        Instance data = testset.getInstance(i);
        Integer gold = (Integer) data.getTarget();
        Predict<String> pres=bayes.classify(data, Type.STRING, 3);
        String pred_label=pres.getLabel();
        String gold_label = bayes.getLabel(gold);
       
        if(pred_label.equals(gold_label)){
          count++;
        }
        else{
          flag=i;
//          System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getTempData());
//          for(int j=0;j<3;j++)
//            System.out.println(pres.getLabel(j)+":"+pres.getScore(j));
        }
      }
      counts_cs[test]=count;
      System.out.println("Bayes Precision("+percents_cs[test]+"):"
      +((float)count/testset.size())+"("+count+"/"+testset.size()+")");
    }
    bayes.noFeatureSelection();
    float[] percents_csmax=new float[]{1.0f,0.9f,0.8f,0.7f,0.5f,0.3f,0.2f,0.1f};
    int[] counts_csmax=new int[10];
    for(int test=0;test<percents_csmax.length;test++){
      System.out.println("Testing Bayes"+percents_csmax[test]+"...");
      if(test!=0)
        bayes.fS_CS_Max(percents_csmax[test]);
      int count=0;
      for(int i=0;i<testset.size();i++){
        Instance data = testset.getInstance(i);
        Integer gold = (Integer) data.getTarget();
        Predict<String> pres=bayes.classify(data, Type.STRING, 3);
        String pred_label=pres.getLabel();
        String gold_label = bayes.getLabel(gold);
       
        if(pred_label.equals(gold_label)){
          count++;
        }
        else{
//          System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getTempData());
//          for(int j=0;j<3;j++)
//            System.out.println(pres.getLabel(j)+":"+pres.getScore(j));
        }
      }
      counts_csmax[test]=count;
      System.out.println("Bayes Precision("+percents_csmax[test]+"):"
      +((float)count/testset.size())+"("+count+"/"+testset.size()+")");
    }
    bayes.noFeatureSelection();
    float[] percents_ig=new float[]{1.0f,0.9f,0.8f,0.7f,0.5f,0.3f,0.2f,0.1f};
    int[] counts_ig=new int[10];
    for(int test=0;test<percents_ig.length;test++){
      System.out.println("Testing Bayes"+percents_ig[test]+"...");
      if(test!=0)
        bayes.fS_IG(percents_ig[test]);
      int count=0;
      for(int i=0;i<testset.size();i++){
        Instance data = testset.getInstance(i);
        Integer gold = (Integer) data.getTarget();
        Predict<String> pres=bayes.classify(data, Type.STRING, 3);
        String pred_label=pres.getLabel();
        String gold_label = bayes.getLabel(gold);
       
        if(pred_label.equals(gold_label)){
          count++;
        }
        else{
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
    InstanceSet testset = splitsets[1]; 
    System.out.print("..Spliting complete!\n");

    System.out.print("Training...\n");
    BayesTrainer trainer=new BayesTrainer();
    BayesClassifier classifier= (BayesClassifier) trainer.train(trainset);
    pp.removeTargetPipe();
    classifier.setPipe(pp);
    af.setStopIncrement(true);
    System.out.print("..Training complete!\n");
    System.out.print("Saving model...\n");
    classifier.saveTo(bayesModelFile); 
    classifier = null;
    System.out.print("..Saving model complete!\n");
    /**
     * 测试
     */
    System.out.print("Loading model...\n");
    BayesClassifier bayes;
    bayes =BayesClassifier.loadFrom(bayesModelFile);
//    bayes =classifier;
    System.out.print("..Loading model complete!\n");
   
    System.out.println("Testing Bayes...");
    int count=0;
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
      Integer gold = (Integer) data.getTarget();
      Predict<String> pres=bayes.classify(data, Type.STRING, 3);
      String pred_label=pres.getLabel();
//      String pred_label = bayes.getStringLabel(data);
      String gold_label = bayes.getLabel(gold);
     
      if(pred_label.equals(gold_label)){
        //System.out.println(pred_label+" : "+testsetbayes.getInstance(i).getTempData());
        count++;
      }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
   */
  private static String modelFile = "../example-data/text-classification/modelBayes2.gz";

  public static void main(String[] args) throws Exception {
   
    BayesClassifier bayes;
    bayes =BayesClassifier.loadFrom(modelFile);
   
    /**
     * 分类器使用
     */
    String str = "韦德：不拿冠军就是失败 詹皇：没拿也不意味失败";
    System.out.println("============\n分类："+ str);
    Pipe p = bayes.getPipe();
    Instance inst = new Instance(str);
    try {
      //特征转换
      p.addThruPipe(inst);
    } catch (Exception e) {
      e.printStackTrace();
    }
    String res = bayes.getStringLabel(inst);
    System.out.println("xxx"); 
    System.out.println("类别："+ res); 
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {1,2});
    //分词
//    CWSTagger tag = new CWSTagger("../models/seg.m");
//    Pipe segpp=new CNPipe(tag);
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af); 
    Pipe sparsepp=new StringArray2SV(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet()); 
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,sparsepp});
   
    InstanceSet instset = new InstanceSet(pp,af);
   
    //用不同的Reader读取相应格式的文件
    Reader reader = new FileReader(trainDataPath,"UTF-8",".data");
   
    //读入数据，并进行数据处理
    instset.loadThruStagePipes(reader);
    //将数据集分为训练是和测试集
    float percent = 0.8f;
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 

    /**
     * 测试
     */
    System.out.println("类别 : 文本内容");
    System.out.println("===================");
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
     
      Integer gold = (Integer) data.getTarget();
      Predict<String> pres=bayes.classify(data, Type.STRING, 3);
      String pred_label=pres.getLabel();
//      String pred_label = bayes.getStringLabel(data);
      String gold_label = bayes.getLabel(gold);
     
      if(pred_label.equals(gold_label))
        System.out.println(pred_label+" : "+testset.getInstance(i).getSource());
      else
        System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getSource());
View Full Code Here
TOP

Related Classes of org.fnlp.ml.classifier.bayes.BayesClassifier

  • gnu.trove.iterator.TIntFloatIterator
  • org.fnlp.demo.nlp.tc.TextClassificationBasedOnBayes
  • org.fnlp.demo.nlp.tc.TextClassificationBasedOnBayes2
  • org.fnlp.demo.nlp.tc.TextClassificationTest
  • org.fnlp.ml.classifier.Predict
  • org.fnlp.ml.feature.FeatureSelect
  • org.fnlp.ml.types.sv.HashSparseVector
  • java.util.zip.GZIPOutputStream
  • java.io.ObjectOutputStream
  • org.fnlp.util.exception.LoadModelException
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.