Package uk.ac.cam.ha293.tweetlabel.util

Examples of uk.ac.cam.ha293.tweetlabel.util.Stopwords

28
29
30
31
32
33
34
35
36
37
38
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : uids) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        FullLLDAClassification inferred = new FullLLDAClassification(topicType,alpha,uid);
        double sim = inferred.cosineSimilarity(baseline);
        cosineSum += sim;
        squareSum += sim*sim;
        cosineCount++;
 
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : uids) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        FullLLDAClassification inferred = new FullLLDAClassification(topicType,alpha,uid);
        double sim = cosineKSimilarity(baseline,inferred,k);
        cosineSum += sim;
        squareSum += sim*sim;
        cosineCount++;
 
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : uids) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        FullLLDAClassification inferred = new FullLLDAClassification(topicType,alpha,fewerProfiles,reduction,uid);
        if(inferred.getCategorySet().isEmpty()) continue;
        double sim = inferred.cosineSimilarity(baseline);
        cosineSum += sim;
        squareSum += sim*sim;
 
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : uids) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        FullLLDAClassification inferred = new FullLLDAClassification(topicType,alpha,fewerProfiles,reduction,uid);
        if(inferred.getCategorySet().isEmpty()) continue;
        double sim = cosineKSimilarity(baseline,inferred,k);
        cosineSum += sim;
        squareSum += sim*sim;
 
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : Tools.getCSVUserIDs()) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification fac = new FullAlchemyClassification(uid);
        FullSVMClassification fsm = new FullSVMClassification(topicType,uid);
        double sim = fsm.cosineSimilarity(fac);
        cosineSum += sim;
        squareSum += sim*sim;
        cosineCount++;
 
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
    double cosineSum = 0.0;
    int cosineCount = 0;
    double squareSum = 0.0;
    for(Long uid : Tools.getCSVUserIDs()) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification fac = new FullAlchemyClassification(uid);
        FullSVMClassification fsm = new FullSVMClassification(topicType,uid);
        double sim = cosineKSimilarity(fac,fsm,k);
        cosineSum += sim;
        squareSum += sim*sim;
        cosineCount++;
 
View Full Code Here
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
    //firstly create the baseline profile sets
    //IMPORTANT: profiles with no classifications aren't included in sets!
    for(Long uid : uids) {
      String topTopic = "";
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification c = new FullAlchemyClassification(uid);
        if(c.getCategorySet().size()==0) continue;
        topTopic = c.getCategorySet().toArray(new String[0])[0];
      } else if(topicType.equals("calais")) {
        FullCalaisClassification c = new FullCalaisClassification(uid);
        if(c.getCategorySet().size()==0) continue;
        topTopic = c.getCategorySet().toArray(new String[0])[0];
      } else if(topicType.equals("textwiseproper")) {
        FullTextwiseClassification c = new FullTextwiseClassification(uid,true);
        if(c.getCategorySet().size()==0) continue;
        topTopic = c.getCategorySet().toArray(new String[0])[0];
      }
      if(profileSets.containsKey(topTopic)) {
        profileSets.get(topTopic).add(uid);
      } else {
        Set<Long> newSet = new HashSet<Long>();
View Full Code Here
378
379
380
381
382
383
384
385
386
387
388
          FileOutputStream fileOut = new FileOutputStream("cosinesims/"+topicType+"-"+alpha+".csv");
          PrintWriter writeOut = new PrintWriter(fileOut);
          writeOut.println("\"uid\",\"similarity\"");
          if(topicType.equals("alchemy")) {
            for(long uid : uids) {
              FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,uid);
              writeOut.println(uid+","+llda.cosineSimilarity(baseline));
            }
          } else if(topicType.equals("calais")) {
            for(long uid : uids) {
View Full Code Here
475
476
477
478
479
480
481
482
483
484
485
    double squareSum = 0.0;
    int cosineCount = 0;
    for(Long uid : uids) {
      //System.out.println(cosineCount);
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        FullLLDAClassification inferred = new FullLLDAClassification(topicType,alpha,uid);
        double sim = inferred.jsDivergence(baseline);
        cosineSum += sim;
        squareSum += sim*sim;
        cosineCount++;
 
View Full Code Here
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
    }
    Set<Long> noClassifications = new HashSet<Long>();
    for(Long uid : Tools.getCSVUserIDs()) {
      String topTopic = "";
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification c = new FullAlchemyClassification(uid);
        if(c.getCategorySet().size()==0) {
          noClassifications.add(uid);
          continue;
        }
        topTopic = c.getCategorySet().toArray(new String[1])[0];
      } else if(topicType.equals("calais")) {
        FullCalaisClassification c = new FullCalaisClassification(uid);
        if(c.getCategorySet().size()==0) {
          noClassifications.add(uid);
          continue;
        }
        topTopic = c.getCategorySet().toArray(new String[1])[0];
        if(topTopic.equals("Other") && c.getCategorySet().size() < 2) {
          noClassifications.add(uid);
          continue;
        } else if(topTopic.equals("Other")) {
          topTopic = c.getCategorySet().toArray(new String[1])[1];
        }
      } else if(topicType.equals("textwise")) {
        FullTextwiseClassification c = new FullTextwiseClassification(uid,true);
        if(c.getCategorySet().size()==0) {
          noClassifications.add(uid);
          continue;
        }
        topTopic = c.getCategorySet().toArray(new String[1])[0];
      }
      if(svm) {
        FullSVMClassification svmClassification = new FullSVMClassification(topicType,uid);
        String topSVMTopic = svmClassification.getCategorySet().toArray(new String[1])[0];
        gtTopicSets.get(topTopic).add(uid);
View Full Code Here
TOP

Related Classes of uk.ac.cam.ha293.tweetlabel.util.Stopwords

  • cc.mallet.pipe.CharSequence2TokenSequence
  • cc.mallet.pipe.Pipe
  • cc.mallet.pipe.PrintInputAndTarget
  • cc.mallet.pipe.SerialPipes
  • cc.mallet.pipe.TokenSequence2FeatureSequence
  • cc.mallet.pipe.TokenSequenceLowercase
  • cc.mallet.pipe.TokenSequenceRemoveStopwords
  • cc.mallet.topics.ParallelTopicModel
  • cc.mallet.topics.SimpleLDA
  • cc.mallet.types.Instance
    • 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.