Package org.fnlp.ml.types

Examples of org.fnlp.ml.types.Instance

47
48
49
50
51
52
53
54
55
56
57
  private String str;
  public MyDocumentWriter(String str){
    this.str = str;
    fgr = new FileGroupReader(str);
    this.llist = new LinkedList<Instance>();
    Instance in = null; FeatureGeter fp = null;
    ARInstanceGetter arip = null;
    while(fgr.hasNext()){
      in = fgr.next();
      fp = new FeatureGeter(in);
      arip = new ARInstanceGetter(fp);
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
      out = new OutputStreamWriter(new FileOutputStream(f));
    } catch (FileNotFoundException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
    Instance mi = null;
    while(it.hasNext()){
      mi = (Instance) it.next();
      try {   
        out.write(mi.getTarget()+" ");
        int[] dat = (int[]) mi.getData();
        for(int i=0;i<dat.length;i++)
          out.write(dat[i]+" ");
        out.write('\n');
        out.flush();
      } catch (IOException e) {
View Full Code Here
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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
    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++;
      }
      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));
      }
    }
    int bayesCount=count;
    System.out.println("..Testing Bayes complete!");
    System.out.println("Bayes Precision:"+((float)bayesCount/testset.size())+"("+bayesCount+"/"+testset.size()+")");


    /**
     * Knn
     */
    System.out.print("\nKnn\n");
    //建立字典管理器
    AlphabetFactory af2 = AlphabetFactory.buildFactory();
    //使用n元特征
    ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    sparsepp=new StringArray2SV(af2);
    //将目标值对应的索引号作为类别
    targetpp = new Target2Label(af2.DefaultLabelAlphabet()); 
    //建立pipe组合
    pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,sparsepp});

    System.out.print("Init dataset...");
    trainset.setAlphabetFactory(af2); 
    trainset.setPipes(pp); 
    testset.setAlphabetFactory(af2); 
    testset.setPipes(pp);     
    for(int i=0;i<trainset.size();i++){
      Instance inst=trainset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }   
    for(int i=0;i<testset.size();i++){
      Instance inst=testset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }

    System.out.print("complete!\n");
    System.out.print("Training Knn...\n");
    SparseVectorSimilarity sim=new SparseVectorSimilarity();
    pp.removeTargetPipe();
    KNNClassifier knn=new KNNClassifier(trainset, pp, sim, af2, 7); 
    af2.setStopIncrement(true); 
    System.out.print("..Training compelte!\n");
    System.out.print("Saving model...\n");
    knn.saveTo(knnModelFile); 
    knn = null;
    System.out.print("..Saving model compelte!\n");

   
    System.out.print("Loading model...\n");
    knn =KNNClassifier.loadFrom(knnModelFile);
    System.out.print("..Loading model compelte!\n");
    System.out.println("Testing Knn...\n");
    count=0;
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
      Integer gold = (Integer) data.getTarget();
      Predict<String> pres=(Predict<String>) knn.classify(data, Type.STRING, 3);
      String pred_label=pres.getLabel();
      String gold_label = knn.getLabel(gold);
     
      if(pred_label.equals(gold_label)){
        //System.out.println(pred_label+" : "+testsetknn.getInstance(i).getTempData());
        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));
      }
    }
    int knnCount=count;
    System.out.println("..Testing Knn Complete");
    System.out.println("Bayes Precision:"+((float)bayesCount/testset.size())+"("+bayesCount+"/"+testset.size()+")");
    System.out.println("Knn Precision:"+((float)knnCount/testset.size())+"("+knnCount+"/"+testset.size()+")");
   
    //建立字典管理器
    AlphabetFactory af3 = AlphabetFactory.buildFactory();
    //使用n元特征
    ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af3);
    //将目标值对应的索引号作为类别
    targetpp = new Target2Label(af3.DefaultLabelAlphabet());   
   
    //建立pipe组合
    pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,indexpp});
   
    trainset.setAlphabetFactory(af3); 
    trainset.setPipes(pp); 
    testset.setAlphabetFactory(af3); 
    testset.setPipes(pp);
    for(int i=0;i<trainset.size();i++){
      Instance inst=trainset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }   
    for(int i=0;i<testset.size();i++){
      Instance inst=testset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }     
   
    /**
     * 建立分类器
     */   
    OnlineTrainer trainer3 = new OnlineTrainer(af3);
    Linear pclassifier = trainer3.train(trainset);
    pp.removeTargetPipe();
    pclassifier.setPipe(pp);
    af.setStopIncrement(true);
   
    //将分类器保存到模型文件
    pclassifier.saveTo(linearModelFile); 
    pclassifier = null;
   
    //从模型文件读入分类器
    Linear cl =Linear.loadFrom(linearModelFile);
   
    //性能评测
    Evaluation eval = new Evaluation(testset);
    eval.eval(cl,1);
    /**
     * 测试
     */
    System.out.println("类别 : 文本内容");
    System.out.println("===================");
    count=0;
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
     
      Integer gold = (Integer) data.getTarget();
      String pred_label = cl.getStringLabel(data);
      String gold_label = cl.getLabel(gold);
     
      if(pred_label.equals(gold_label)){
        //System.out.println(pred_label+" : "+testsetliner.getInstance(i).getSource());
View Full Code Here
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
    String[][] labelsSet = new String[testSet.size()][];
    String[][] targetSet = new String[testSet.size()][];
    LabelAlphabet labels = cl.getAlphabetFactory().buildLabelAlphabet(
        "labels");
    for (int i = 0; i < testSet.size(); i++) {
      Instance carrier = testSet.get(i);
      int[] pred = (int[]) cl.classify(carrier).getLabel(0);
      if (acc) {
        len += pred.length;
        double e = loss.calc(carrier.getTarget(), pred);
        error += e;
        if(e != 0)
          senError++;
        //测试中英混杂语料
        if(hasENG) {
          String[][] origin = (String[][])carrier.getSource();
          int[] target = (int[])carrier.getTarget();
          for(int j = 0; j < target.length; j++) {
            if(origin[j][0].contains("ENG")) {
              ENG_all++;
              if(target[j] == pred[j])
                ENG_right++;
            }
          }
        }
      }
      labelsSet[i] = labels.lookupString(pred);
      targetSet[i] = labels.lookupString((int[])carrier.getTarget());
    }

    long endtime = System.currentTimeMillis();
    System.out.println("totaltime\t" + (endtime - starttime) / 1000.0);
    System.out.println("feature\t" + (featuretime - starttime) / 1000.0);
View Full Code Here
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
    String[][] labelsSet = new String[testSet.size()][];
    String[][] targetSet = new String[testSet.size()][];
    LabelAlphabet labels = cl.getAlphabetFactory().buildLabelAlphabet(
        "labels");
    for (int i = 0; i < testSet.size(); i++) {
      Instance carrier = testSet.get(i);
      int[] pred = (int[]) cl.classify(carrier).getLabel(0);
      if (acc) {
        len += pred.length;
        double e = loss.calc(carrier.getTarget(), pred);
        error += e;
        if(e != 0)
          senError++;
        //测试中英混杂语料
        if(hasENG) {
          String[][] origin = (String[][])carrier.getSource();
          int[] target = (int[])carrier.getTarget();
          for(int j = 0; j < target.length; j++) {
            if(origin[j][0].contains("ENG")) {
              ENG_all++;
              if(target[j] == pred[j])
                ENG_right++;
            }
          }
        }
      }
      labelsSet[i] = labels.lookupString(pred);
      targetSet[i] = labels.lookupString((int[])carrier.getTarget());
    }

    long endtime = System.currentTimeMillis();
    System.out.println("totaltime\t" + (endtime - starttime) / 1000.0);
    System.out.println("feature\t" + (featuretime - starttime) / 1000.0);
View Full Code Here
43
44
45
46
47
48
49
50
51
52
    pool = Executors.newFixedThreadPool(numThread);
    f= new ArrayList<Future>();
  }

  public void classify(String c) throws Exception{
    Instance inst = new Instance(c);

    ClassifyTask t = new ClassifyTask(inst);
    f.add(pool.submit(t));   
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
    String path=f.getPath();
    int pos=path.lastIndexOf("\\");
    path=path.substring(0, pos);
    pos=path.lastIndexOf("\\");
    path=path.substring(pos+1);
    cur = new Instance(buff.toString(), path);
    cur.setTempData(f.getPath());
    buff = null;
  }
View Full Code Here
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
     * 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);
     
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
     
      beginTimeIter = System.currentTimeMillis();
      for (int ii = 0; ii < numSamples; ii++) {
       
        k++;
        Instance inst = trainset.getInstance(ii);
        Predict pred = (Predict) inferencer.getBest(inst,2);       
       
        float l = loss.calc(pred.getLabel(0), inst.getTarget());
        if (l > 0) {
          err += l;
          errtot++;
          update.update(inst, weights, k, extraweight, pred.getLabel(0), c);
         
        }else{
          if (pred.size() > 1)
            update.update(inst, weights, k, extraweight, pred.getLabel(1), c);
        }
        cnt += inst.length();
        cnttot++;       

        if (!simpleOutput && progress != 0 && ii % progress == 0) {
          System.out.print('.');
          progress += frac;
View Full Code Here
291
292
293
294
295
296
297
298
299
300
301
302
303
304
  public void evaluate(InstanceSet devset) {
    float err = 0;
    float errtot = 0;
    int total = 0;
    for (int i = 0; i < devset.size(); i++) {
      Instance inst = devset.getInstance(i);
      total += inst.length();
      Predict pred = (Predict) inferencer.getBest(inst);
      float l = loss.calc(pred.getLabel(0), inst.getTarget());
      if (l > 0) {
        errtot += 1.0;
        err += l;
      }
View Full Code Here
TOP

Related Classes of org.fnlp.ml.types.Instance

  • org.fnlp.app.tc.TextClassifier
  • org.fnlp.data.reader.DocumentReader
  • org.fnlp.data.reader.FileReader
  • org.fnlp.data.reader.ListReader
  • org.fnlp.data.reader.SequenceReader
  • org.fnlp.data.reader.SimpleFileReader
  • org.fnlp.data.reader.StringReader
  • org.fnlp.data.reader.svmFileReader
  • org.fnlp.demo.ml.HierClassifierUsage1
  • org.fnlp.demo.ml.SequenceLabeling
    • 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.