Package uk.ac.cam.ha293.tweetlabel.classify

Examples of uk.ac.cam.ha293.tweetlabel.classify.FullAlchemyClassification

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
    //need a mapping between documents and toptopics
    topTopics = new ArrayList<String>();
    for(int i=0; i<numDocs; i++) {
      String topTopic = "";
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification cl = new FullAlchemyClassification(docIDLookup.get(i).getId());
        if(cl.getCategorySet().size()==0) topTopic="NO_TOP_TOPIC";
        else topTopic = cl.getCategorySet().toArray(new String[0])[0];
      } else if(topicType.equals("calais")) {
        FullCalaisClassification cl = new FullCalaisClassification(docIDLookup.get(i).getId());
        if(cl.getCategorySet().size()==0) topTopic="NO_TOP_TOPIC";
        else topTopic = cl.getCategorySet().toArray(new String[0])[0];
        //Required because of Calais' stupid classification system
        if(topTopic.equals("Other")) {
          if(cl.getCategorySet().size()==1) topTopic="NO_TOP_TOPIC";
          else topTopic = cl.getCategorySet().toArray(new String[0])[1];
        }
      } else if(topicType.equals("textwise")) {
        FullTextwiseClassification cl = new FullTextwiseClassification(docIDLookup.get(i).getId(),true);
        if(cl.getCategorySet().size()==0) topTopic="NO_TOP_TOPIC";
        else topTopic = cl.getCategorySet().toArray(new String[0])[0];
      }
      if(verbose) System.out.println("Document "+i+" found to have top topic "+topTopic+", id "+topicIDs.get(topTopic));
      topTopics.add(topTopic);
     
      //add this id to the topTopics map
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
  public void fillAlchemy() {
    //get clasifications
    System.out.println("Filling from Alchemy classifications");
    FullAlchemyClassification[] classifications = new FullAlchemyClassification[d];
    for(long id : Tools.getCSVUserIDs()) {
      classifications[indexLookup.get(id)] = new FullAlchemyClassification(id);
    }
   
    //cosine similarities!
    for(int m=0; m<d; m++) {
      System.out.println("On row "+m);
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
  public void fillAlchemyJS() {
    //get clasifications
    System.out.println("Filling from Alchemy classifications");
    FullAlchemyClassification[] classifications = new FullAlchemyClassification[d];
    for(long id : Tools.getCSVUserIDs()) {
      classifications[indexLookup.get(id)] = new FullAlchemyClassification(id);
    }
   
    //cosine similarities!
    for(int m=0; m<d; m++) {
      System.out.println("On row "+m);
View Full Code Here
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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
  public void fillRestricted(boolean baseline, String topicType, int topTopics, double alpha) {
    List<Map<String,Double>> classifications = new ArrayList<Map<String,Double>>();
    if(baseline) {
      if(topicType.equals("alchemy")) {
        for(long id : Tools.getCSVUserIDs()) {
          FullAlchemyClassification c = new FullAlchemyClassification(id);
          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 if(topicType.equals("calais")) {
        for(long id : Tools.getCSVUserIDs()) {
          FullCalaisClassification c = new FullCalaisClassification(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);
        }
      } 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
717
718
719
720
721
722
723
724
725
726
727
728
729
730
        //if(fac.getScore(topic) < scoreThreshold) break; //stop getting low-prob topics
        topics.add(topic);
        count++;
      }
    } else if(topicType.equals("calais")) {
      FullCalaisClassification fcc = new FullCalaisClassification(userID);
      int topTopics = 3;
      int count = 0;
      for(String topic : fcc.getCategorySet()) {
        if(topic.equals("Other")) continue; //really prominent...
        if(count == topTopics) break; //stop getting more than 3 topics
        //if(fac.getScore(topic) < scoreThreshold) break; //stop getting low-prob topics
        topics.add(topic);
        count++;
View Full Code Here
382
383
384
385
386
387
388
389
390
391
392
393
394
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("calais")) {
        for(long id : Tools.getCSVUserIDs()) {
          FullCalaisClassification c = new FullCalaisClassification(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);
        }
      } 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
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
      FullAlchemyClassification c = new FullAlchemyClassification(uid);
      for(String cat : c.getCategorySet()) {
        valueSet.add(c.getScore(cat));
      }
    } else if(topicType.equals("calais")) {
      FullCalaisClassification c = new FullCalaisClassification(uid);
      for(String cat : c.getCategorySet()) {
        valueSet.add(c.getScore(cat));
      }
    } else if(topicType.equals("textwise")) {
      FullCalaisClassification c = new FullCalaisClassification(uid);
      for(String cat : c.getCategorySet()) {
        valueSet.add(c.getScore(cat));
      }
    }
    return valueSet;
  }
View Full Code Here
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,false,reduction,uid);
              double sim = llda.cosineSimilarity(baseline);
              cosineSum += sim;
              cosineCount++;
            } else if(topicType.equals("calais")) {
              FullCalaisClassification baseline = new FullCalaisClassification(uid);
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,false,reduction,uid);
              double sim = llda.cosineSimilarity(baseline);
              cosineSum += sim;
              cosineCount++;
            } else if(topicType.equals("textwiseproper")) {
View Full Code Here
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
            if(kCount == k) break;
            kCount++;
            baselineTopicSet.add(topic);
          }
        } else if(topicType.equals("calais")) {
          FullCalaisClassification baseline = new FullCalaisClassification(uid);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            if(kCount == k) break;
            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
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
            if(kCount == k) break;
            kCount++;
            baselineTopicSet.add(topic);
          }
        } else if(topicType.equals("calais")) {
          FullCalaisClassification baseline = new FullCalaisClassification(uid);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            if(kCount == k) break;
            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
TOP

Related Classes of uk.ac.cam.ha293.tweetlabel.classify.FullAlchemyClassification

  • 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.