Package org.fnlp.nlp.pipe

Examples of org.fnlp.nlp.pipe.Pipe

59
60
61
62
63
64
65
66
67
68
69
70
71
72
   
    long start = System.currentTimeMillis();

    path = "./example-data/data-classification.txt";

    Pipe lpipe = new Target2Label(al);
    Pipe fpipe = new StringArray2IndexArray(factory, true);
    //构造转换器组
    Pipe pipe = new SeriesPipes(new Pipe[]{lpipe,fpipe});
   
    //构建训练集
    train = new InstanceSet(pipe, factory);
    SimpleFileReader reader = new SimpleFileReader (path,true);
    train.loadThruStagePipes(reader);
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
   */
  private static String knnModelFile = dataPath+"modelKnn.gz";

  public static void main(String[] args) throws Exception {
    //分词
    Pipe removepp=new RemoveWords();
    CWSTagger tag = new CWSTagger("../models/seg.m");
    Pipe segpp=new CNPipe(tag);
    Pipe s2spp=new Strings2StringArray();
   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    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[]{removepp,segpp,s2spp,targetpp,sparsepp});

    /**
     * Knn
 
View Full Code Here
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
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
   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(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,indexpp});
   
    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);
       
    float percent = 0.8f;
   
    //将数据集分为训练是和测试集
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 
   
    /**
     * 建立分类器
     */   
    OnlineTrainer trainer = new OnlineTrainer(af);
    Linear pclassifier = trainer.train(trainset);
    pp.removeTargetPipe();
    pclassifier.setPipe(pp);
    af.setStopIncrement(true);
   
    //将分类器保存到模型文件
    pclassifier.saveTo(modelFile); 
    pclassifier = null;
   
    //从模型文件读入分类器
    Linear cl =Linear.loadFrom(modelFile);
   
    //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("===================");
    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+" : "+testset.getInstance(i).getSource());
      else
        System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getSource());
    }
   
   
    /**
     * 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 = cl.getPipe();
    Instance inst = new Instance(str);
    try {
      //特征转换
      p.addThruPipe(inst);
    } catch (Exception e) {
      e.printStackTrace();
    }
    String res = cl.getStringLabel(inst);
    System.out.println("类别："+ res);
View Full Code Here
74
75
76
77
78
79
80
81
82
    AlphabetFactory.defaultFeatureType = Type.String;
    // 将样本通过Pipe抽取特征
    features = factory.DefaultFeatureAlphabet();
    featurePipe = new Sequence2FeatureSequence(templets, features, labels);
    AddCharRange typePip = new AddCharRange();
    Pipe weightPipe = new WeightPipe(true);
    Pipe pipe = new SeriesPipes(new Pipe[] { new Target2Label(labels),  typePip, featurePipe, weightPipe  });
    return pipe;
  }
View Full Code Here
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
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
     * Bayes
     */
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    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});

    System.out.print("\nReading data......\n");
    InstanceSet instset = new InstanceSet(pp,af); 
    Reader reader = new MyDocumentReader(trainDataPath,"gbk");
    instset.loadThruStagePipes(reader);
    System.out.print("..Reading data complete\n");
   
    //将数据集分为训练是和测试集
    System.out.print("Sspliting....");
    float percent = 0.9f;
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    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++;
      }
      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});
View Full Code Here
108
109
110
111
112
113
114
115
    // 将样本通过Pipe抽取特征
    IFeatureAlphabet features = factory.DefaultFeatureAlphabet();
    featurePipe = new Sequence2FeatureSequence(templets, features, labels);

    Pipe pipe = new SeriesPipes(new Pipe[] { new Target2Label(labels), featurePipe });
    return pipe;
  }
View Full Code Here
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
     * @throws Exception
     */
    public void loadThruStagePipes(Reader reader) throws Exception {
        SeriesPipes p = (SeriesPipes) pipes;
        // 通过迭代加入样本
        Pipe p1 = p.getPipe(0);
        while (reader.hasNext()) {
            Instance inst = reader.next();
            if(inst!=null){
                if (p1 != null)
                    p1.addThruPipe(inst);
                this.add(inst);
              
            };
        }
        for (int i = 1; i < p.size(); i++)
View Full Code Here
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
     * @throws Exception
     */
    public void loadThruStagePipesForMultiCorpus(Reader[] readers, String[] corpusNames) throws Exception {
        SeriesPipes p = (SeriesPipes) pipes;
        // 通过迭代加入样本
        Pipe p1 = p.getPipe(0);
        for(int i = 0; i < readers.length; i++) {
          while (readers[i].hasNext()) {
              Instance inst = readers[i].next();
              inst.setClasue(corpusNames[i]);
              if(inst!=null){
                  if (p1 != null)
                      p1.addThruPipe(inst);
                  this.add(inst);
              };
          }
        }
       
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(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,indexpp});
   
    InstanceSet trainset = new InstanceSet(pp,af);
View Full Code Here
238
239
240
241
242
243
244
245
246
      features = factory.DefaultFeatureAlphabet();
    else
      features = factory.rebuildFeatureAlphabet("feature");
    featurePipe = new Sequence2FeatureSequence(templets, features, labels);

    Pipe pipe = new SeriesPipes(new Pipe[] { prePipe,
        new Target2Label(labels), featurePipe });
    return pipe;
  }
View Full Code Here
TOP

Related Classes of org.fnlp.nlp.pipe.Pipe

  • org.fnlp.app.tc.TextClassifier
  • org.fnlp.demo.ml.HierClassifierUsage2
  • org.fnlp.demo.ml.SequenceLabeling
  • org.fnlp.demo.ml.SimpleClassifier2
  • org.fnlp.demo.nlp.tc.TextClassificationBasedOnBayes
  • org.fnlp.demo.nlp.tc.TextClassificationBasedOnBayes2
  • org.fnlp.demo.nlp.tc.TextClassificationBasedOnKNN
  • org.fnlp.demo.nlp.tc.TextClassificationCustom
  • org.fnlp.demo.nlp.tc.TextClassificationCustom1
  • org.fnlp.demo.nlp.tc.TextClassificationTest
    • 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.