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

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

158
159
160
161
162
163
164
165
166
167
168
      Corpus corpus = new Corpus(topicType);
      int count = 0;
      for(Long userID : Tools.getCSVUserIDs()) {
        if(count % 50 == 0) System.out.println("Added "+count+" profiles to Corpus");
        count++;
        SimpleProfile profile = Profiler.loadCSVProfile(userID);
        profile.reduceBy(reduction);
        corpus.addDocument(profile.asDocument(topicType));
      }
      return corpus; 
    }
View Full Code Here
171
172
173
174
175
176
177
178
179
180
      Corpus corpus = new Corpus(topicType);
      int count = 0;
      for(Long userID : Tools.getCSVUserIDs()) {
        if(count % 50 == 0) System.out.println("Added "+count+" profiles to Corpus");
        count++;
        SimpleProfile profile = Profiler.loadCSVProfile(userID);
        corpus.addDocument(profile.asDocument(topicType));
      }
      return corpus;
    }
View Full Code Here
331
332
333
334
335
336
337
338
339
340
341
342
  public static void alchemyClassificationRoutine() {
    System.out.println("Beginning complete Alchemy classification...");
    Profiler profiler = new Profiler();
    while(!synchronisedUserIDList.isEmpty()) {
      long currentID = synchronisedUserIDList.remove(0);
      SimpleProfile profile = profiler.loadCSVProfile(currentID);
      if(!profile.classifyAlchemy()) {
        System.err.println("Failed to classify profile properly, probably reached the daily limit");
        return;
      }
    }
    System.out.println("Classification thread complete");
View Full Code Here
357
358
359
360
361
362
363
364
365
366
367
368
 
  public static void liwcClassificationRoutine() {
    System.out.println("Beginning complete LIWC classification...");
    while(!synchronisedUserIDList.isEmpty()) {
      long currentID = synchronisedUserIDList.remove(0);
      SimpleProfile profile = Profiler.loadCSVProfile(currentID);
      if(!profile.classifyLIWC()) {
        System.err.println("Failed to classify profile "+currentID+" properly using the LIWC");
        return;
      }
    }
  }
View Full Code Here
381
382
383
384
385
386
387
388
389
390
391
392
 
  public static void calaisClassificationRoutine() {
    System.out.println("Beginning complete Calais classification...");
    while(!synchronisedUserIDList.isEmpty()) {
      long currentID = synchronisedUserIDList.remove(0);
      SimpleProfile profile = Profiler.loadCSVProfile(currentID);
      if(!profile.classifyCalais()) {
        System.err.println("Failed to classify profile "+currentID+" properly using Calais");
        return;
      }
    }
  }
View Full Code Here
406
407
408
409
410
411
412
413
414
415
416
417
  public static void textwiseClassificationRoutine() {
    System.out.println("Beginning complete Textwise classification...");
    Profiler profiler = new Profiler();
    while(!synchronisedUserIDList.isEmpty()) {
      long currentID = synchronisedUserIDList.remove(0);
      SimpleProfile profile = profiler.loadCSVProfile(currentID);
      if(!profile.classifyTextwise()) {
        System.err.println("Failed to classify profile "+currentID+" properly using Textwise");
        return;
      }
    }
  }
View Full Code Here
431
432
433
434
435
436
437
438
439
440
441
442
  public static void properTextwiseClassificationRoutine() {
    System.out.println("Beginning complete Textwise classification...");
    Profiler profiler = new Profiler();
    while(!synchronisedUserIDList.isEmpty()) {
      long currentID = synchronisedUserIDList.remove(0);
      SimpleProfile profile = profiler.loadCSVProfile(currentID);
      if(!profile.classifyTextwiseProper()) {
        System.err.println("Failed to classify profile "+currentID+" properly using Textwise");
        return;
      }
    }
  }
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
      System.err.println("An error occured");
    }
  }
 
  public SimpleProfile asSimpleProfile() {
    SimpleProfile profile = new SimpleProfile(0);
    for(String document : documents) {
      profile.addTweet(new SimpleTweet(0,0,document));
    }
    return profile;
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
  }
 
  public SimpleProfile asSimpleProfile() {
    SimpleProfile profile = new SimpleProfile(0);
    for(String document : documents) {
      profile.addTweet(new SimpleTweet(0,0,document));
    }
    return profile;
  }
View Full Code Here
85
86
87
88
89
90
91
92
93
 
  public List<CategoryScore> logClassify(String document) {
    List<CategoryScore> categoryScores = new ArrayList<CategoryScore>();
    for(Category category : categories.keySet()) {
      double logP = logPOfCategoryGivenDocument(category, Tools.LIWCStripTweet(document));
      categoryScores.add(new CategoryScore(category,logP));     
    }
    return categoryScores;
  }
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.