Package uk.ac.cam.ha293.tweetlabel.topics

Examples of uk.ac.cam.ha293.tweetlabel.topics.SimpleMalletLDA

244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
    Map<String,Double> urlCategoryScores = new HashMap<String,Double>();
    Map<String,Integer> urlCategoryCounts = new HashMap<String,Integer>();
   
    for(SimpleTweet tweet : tweets) {
      //Handle tweet content classification
      AlchemyClassification textClassification = AlchemyClassifier.classifyText(tweet.getText());
      if(textClassification == null) {
        System.err.println("Daily Transaction Limit has been reached (or a null classification was given weirdly)");
        return false;
      }
     
      writeOutTweets.print(tweet.getTweetID()+","+textClassification.getCategory()+","+textClassification.getScore());
      System.err.println("JUST WROTE TWEEET OUT");
     
      if(textCategoryScores.containsKey(textClassification.getCategory())) {
        //Add the new value, since the key already exists
        textCategoryScores.put(textClassification.getCategory(), textCategoryScores.get(textClassification.getCategory()) + textClassification.getScore());
        textCategoryCounts.put(textClassification.getCategory(), textCategoryCounts.get(textClassification.getCategory()) + 1);
      } else {
        //Insert the category into the map
        textCategoryScores.put(textClassification.getCategory(), textClassification.getScore());
        textCategoryCounts.put(textClassification.getCategory(), 1);
      }
     
      //Handle URL classification
      for(String url : tweet.getUrls()) {
        AlchemyClassification urlClassification = AlchemyClassifier.classifyURL(url);
        if(urlClassification == null) {
          System.err.println("Daily Transaction Limit has been reached (or a null classification was given weirdly)");
          return false;
        }
       
        writeOutTweets.print(","+urlClassification.getCategory()+","+urlClassification.getScore());
       
        if(urlCategoryScores.containsKey(urlClassification.getCategory())) {
          //Add the new value, since the key already exists
          urlCategoryScores.put(urlClassification.getCategory(), urlCategoryScores.get(urlClassification.getCategory()) + urlClassification.getScore());
          urlCategoryCounts.put(urlClassification.getCategory(), urlCategoryCounts.get(urlClassification.getCategory()) + 1);
        } else {
          //Insert the category into the map
          urlCategoryScores.put(urlClassification.getCategory(), urlClassification.getScore());
          urlCategoryCounts.put(urlClassification.getCategory(), 1);
        }
      }

      //writeOutTweets.println();
    }
View Full Code Here
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
        if(count < startFromHere) {count++;continue;}
        String[] split = nextLine.split("\t");
        long uid = Long.parseLong(split[0]);
        BigInteger tid = new BigInteger(split[1]);
        String tweet = split[2];
        AlchemyClassification c = AlchemyClassifier.classifyText(tweet);
        while(c == null) {
          c = AlchemyClassifier.classifyText(tweet);
         
        }
        System.out.println(count+"\t"+uid+"\t"+tid+"\t"+c.getCategory()+"\t"+c.getScore());
        //writeOut += uid+"\t"+tid+"\t"+c.getCategory()+"\t"+c.getScore()+"\n";
        count++;
      }
      //write.print(writeOut);
      //write.close();
View Full Code Here
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
   
    Map<String,Double> resultsMap = new HashMap<String,Double>();
    Map<String,Integer> countsMap = new HashMap<String,Integer>();
   
    for(SimpleTweet tweet : tweets) {
      CalaisClassification classification = CalaisClassifier.classifyText(tweet.getText());
      if(classification == null) {
        //Normally this is because of a <100 char tweet
        continue;
      }
      for(String category : classification.getCategories()) {
        double score = classification.lookupScore(category);     
        if(resultsMap.containsKey(category)) {
          resultsMap.put(category, resultsMap.get(category) + score);
          countsMap.put(category, countsMap.get(category) + 1);
        } else {
          resultsMap.put(category, score);
View Full Code Here
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
  //For use in Corpus' getFullProfileCorpus(topicType) method
  public Document asLLDADocument(String topicType) {
    Set<String> topics = new HashSet<String>();
    //Note: if not LIWC or LIWCNB, we have no topics yet!
    if(topicType.equals("alchemy")) {
      FullAlchemyClassification fac = new FullAlchemyClassification(userID);
      int topTopics = 3;
      //alchemy too sparse to threshold
      int count = 0;
      for(String topic : fac.getCategorySet()) {
        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
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
public class Diversity {
 
  private static Set<Double> diversitySet(String topicType, long uid) {
    Set<Double> valueSet = new HashSet<Double>();
    if(topicType.equals("alchemy")) {
      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
993
994
995
996
997
998
999
1000
1001
1002
1003
          //get average cosine similarity to baseline
          double cosineSum = 0.0;
          int cosineCount = 0;
          for(Long uid : uids) {
            if(topicType.equals("alchemy")) {
              FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
              FullLLDAClassification llda = new FullLLDAClassification(topicType,alpha,false,reduction,uid);
              double sim = llda.cosineSimilarity(baseline);
              cosineSum += sim;
              cosineCount++;
            } else if(topicType.equals("calais")) {
View Full Code Here
1041
1042
1043
1044
1045
1046
1047
1048
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++;
          lldaTopicSet.add(topic);
        }
        if(topicType.equals("alchemy")) {
          FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            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
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
          kCount++;
          svmTopicSet.add(topic);
          System.out.println("Adding topic "+topic+" "+svm.getScore(topic));
        }
        if(topicType.equals("alchemy")) {
          FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
          kCount=0;
          for(String topic : baseline.getCategorySet()) {
            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
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
    for(String topic : Tools.getTopics(topicType)) {
      topicCounts.put(topic, 0);
    }
    for(Long uid : Tools.getCSVUserIDs()) {
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification c = new FullAlchemyClassification(uid);
        if(c.getCategorySet().size() == 0) continue;
        String topTopic = c.getCategorySet().toArray(new String[1])[0];
        topicCounts.put(topTopic,topicCounts.get(topTopic)+1);
      } else if(topicType.equals("calais")) {
        FullCalaisClassification c = new FullCalaisClassification(uid);
        if(c.getCategorySet().size() == 0) continue;
        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
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
        if(kCount == k) break;
        kCount++;
        lldaTopicSet.add(topic);
      }
      if(topicType.equals("alchemy")) {
        FullAlchemyClassification baseline = new FullAlchemyClassification(uid);
        kCount=0;
        for(String topic : baseline.getCategorySet()) {
          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.topics.SimpleMalletLDA

  • 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.