Package uk.ac.cam.ha293.tweetlabel.types

Examples of uk.ac.cam.ha293.tweetlabel.types.Category

178
179
180
181
182
183
184
185
186
187
188
  public void fillTextwiseJS() {
    //get clasifications
    System.out.println("Filling from Textwise classifications");
    FullTextwiseClassification[] classifications = new FullTextwiseClassification[d];
    for(long id : Tools.getCSVUserIDs()) {
      classifications[indexLookup.get(id)] = new FullTextwiseClassification(id,true);
    }
   
    //cosine similarities!
    for(int m=0; m<d; m++) {
      System.out.println("On row "+m);
View Full Code Here
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
          }
          classifications.add(classification);
        }
      } else if(topicType.equals("textwise")) {
        for(long id : Tools.getCSVUserIDs()) {
          FullTextwiseClassification c = new FullTextwiseClassification(id,true);
          Map<String,Double> classification = new HashMap<String,Double>();
          int topicCount = 0;
          for(String topic : c.getCategorySet()) {
            if(topicCount == topTopics) break;
            classification.put(topic, c.getScore(topic));
            topicCount++;
          }
          classifications.add(classification);
        }
      }
    } else {
      for(long id : Tools.getCSVUserIDs()) {
        FullLLDAClassification c = new FullLLDAClassification(topicType,alpha,id);
        Map<String,Double> classification = new HashMap<String,Double>();
        int topicCount = 0;
        for(String topic : c.getCategorySet()) {
          if(topicCount == topTopics) break;
          if(topic.equals("Other")) continue;
          classification.put(topic, c.getScore(topic));
          topicCount++;
        }
        classifications.add(classification);
      }
    }
View Full Code Here
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,false,reduction,uid);
              double sim = llda.cosineSimilarity(baseline);
              cosineSum += sim;
              cosineCount++;
            } else if(topicType.equals("textwiseproper")) {
              FullTextwiseClassification baseline = new FullTextwiseClassification(uid,true);
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,false,reduction,uid);
              double sim = llda.cosineSimilarity(baseline);
              cosineSum += sim;
              cosineCount++;
            }
View Full Code Here
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
            if(topic.equals("Other")) continue;
            kCount++;
            baselineTopicSet.add(topic);
          }
        } else if(topicType.equals("textwise")) {
          FullTextwiseClassification baseline = new FullTextwiseClassification(uid,true);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            if(kCount == k) break;
            kCount++;
            baselineTopicSet.add(topic);
          }
        }
View Full Code Here
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
            if(topic.equals("Other")) continue;
            kCount++;
            baselineTopicSet.add(topic);
          }
        } else if(topicType.equals("textwise")) {
          FullTextwiseClassification baseline = new FullTextwiseClassification(uid,true);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            if(kCount == k) break;
            kCount++;
            baselineTopicSet.add(topic);
          }
        }
View Full Code Here
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
        String topTopic = c.getCategorySet().toArray(new String[1])[0];
        if(topTopic.equals("Other") && c.getCategorySet().size() > 1)  topTopic = c.getCategorySet().toArray(new String[1])[1];
        else if(topTopic.equals("Other")) continue;
        topicCounts.put(topTopic,topicCounts.get(topTopic)+1);
      } else if(topicType.equals("textwise")) {
        FullTextwiseClassification c = new FullTextwiseClassification(uid,true);
        if(c.getCategorySet().size() == 0) continue;
        String topTopic = c.getCategorySet().toArray(new String[1])[0];
        topicCounts.put(topTopic,topicCounts.get(topTopic)+1);
      }
      count++;
    }
    double sum = 0.0;
View Full Code Here
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
          if(topic.equals("Other")) continue;
          kCount++;
          baselineTopicSet.add(topic);
        }
      } else if(topicType.equals("textwise")) {
        FullTextwiseClassification baseline = new FullTextwiseClassification(uid,true);
        kCount=0;
        for(String topic : baseline.getCategorySet()) {
          if(kCount == k) break;
          kCount++;
          baselineTopicSet.add(topic);
        }
      }
View Full Code Here
513
514
515
516
517
518
519
520
521
522
523
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
    Map<String,Integer> urlCategoryCounts = new HashMap<String,Integer>();
   
    for(SimpleTweet tweet : tweets) {
      //System.err.println(tweet.getText());
     
      TextwiseClassification textClassification = TextwiseClassifier.classify(tweet.getText(), false);
     
      textClassification.print();
     
      for(String category : textClassification.getCategories()) {
        if(textCategoryScores.containsKey(category)) {
          textCategoryScores.put(category, textCategoryScores.get(category) + textClassification.lookupScore(category));
          textCategoryCounts.put(category, textCategoryCounts.get(category) + 1);
        } else {
          textCategoryScores.put(category, textClassification.lookupScore(category));
          textCategoryCounts.put(category, 1);
        }
      }
     
      for(String url : tweet.getUrls()) {
       
        //System.err.println(url);
       
        TextwiseClassification urlClassification = TextwiseClassifier.classify(url, true);
       
        urlClassification.print();
       
        for(String category : urlClassification.getCategories()) {
          if(urlCategoryScores.containsKey(category)) {
            urlCategoryScores.put(category, urlCategoryScores.get(category) + urlClassification.lookupScore(category));
            urlCategoryCounts.put(category, urlCategoryCounts.get(category) + 1);
          } else {
            urlCategoryScores.put(category, urlClassification.lookupScore(category));
            urlCategoryCounts.put(category, 1);
          }
        }
      }
     
View Full Code Here
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
    }
   
    Map<String,Double> classifications = new HashMap<String,Double>();
    Map<String,Integer> classificationsCount = new HashMap<String,Integer>();
    for(int i=0; i<concat.length()-500; i+=500) {
      TextwiseClassification textClassification;
      if(i+500>=concat.length()) textClassification = TextwiseClassifier.classify(concat.substring(i,concat.length()), false);
      else textClassification = TextwiseClassifier.classify(concat.substring(i,i+500), false); 
      Map<String,Double> scores = textClassification.getCategoryScores();
      for(String cat : textClassification.getCategories()) {
        if(classifications.containsKey(cat)) {
          classifications.put(cat,classifications.get(cat)+scores.get(cat));
          classificationsCount.put(cat,classificationsCount.get(cat)+1);
        } else {
          classifications.put(cat,scores.get(cat));
View Full Code Here
713
714
715
716
717
718
719
720
721
722
723
724
725
  public static void similarityStuff() {
    String[] topicTypes = {"alchemy","calais","textwiseproper"};
    double[] alphas = {0.25,0.5,0.75,1.0,1.25,1.5,1.75,2.0};
   
    for(double alpha : alphas) {
      SimilarityMatrix lda = SimilarityMatrix.load("lda-50-1000-100-"+alpha);
      for(String topicType : topicTypes) {
        SimilarityMatrix llda = SimilarityMatrix.load("llda-"+topicType+"-"+alpha);
        System.out.println(topicType+"\t"+alpha+"\t"+SpearmanRank.srcc(lda,llda));
      }
    }

   
View Full Code Here
TOP

Related Classes of uk.ac.cam.ha293.tweetlabel.types.Category

  • 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.