Package edu.umd.cloud9.io.map

Examples of edu.umd.cloud9.io.map.String2FloatOpenHashMapWritable

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    assertEquals(22.0f, m.get("there"), 10e-6);
  }

  @Test
  public void testAccent() throws IOException {
    String2FloatOpenHashMapWritable map1 = new String2FloatOpenHashMapWritable();

    // '\u00E0': [LATIN SMALL LETTER A WITH GRAVE]
    // '\u00E6': [LATIN SMALL LETTER AE]
    // '\u00E7': [LATIN SMALL LETTER C WITH CEDILLA]
    // '\u00FC': [LATIN SMALL LETTER U WITH DIAERESIS]

    map1.put("\u00E0", 1.0f);
    map1.put("\u00E6", 2.0f);
    map1.put("\u00E7", 3.0f);
    map1.put("\u00FC", 4.0f);

    assertEquals(1.0f, map1.getFloat("\u00E0"), 10e-6);
    assertEquals(2.0f, map1.getFloat("\u00E6"), 10e-6);
    assertEquals(3.0f, map1.getFloat("\u00E7"), 10e-6);
    assertEquals(4.0f, map1.getFloat("\u00FC"), 10e-6);

    map1.put("\u00E0", 10.0f);
    map1.remove("\u00E6");
    map1.remove("\u00E7");
    map1.put("\u00E7", 2.0f);

    assertEquals(10.0f, map1.getFloat("\u00E0"), 10e-6);
    assertEquals(2.0f, map1.getFloat("\u00E7"), 10e-6);
    assertEquals(4.0f, map1.getFloat("\u00FC"), 10e-6);

    assertEquals(3, map1.size());

    // Test serialization
    String2FloatOpenHashMapWritable map2 = String2FloatOpenHashMapWritable.create(map1.serialize());

    assertEquals(10.0f, map2.getFloat("\u00E0"), 10e-6);
    assertEquals(2.0f, map2.getFloat("\u00E7"), 10e-6);
    assertEquals(4.0f, map2.getFloat("\u00FC"), 10e-6);
  }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
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
124
    assertEquals(4.0f, map2.getFloat("\u00FC"), 10e-6);
  }

  @Test
  public void testJp() throws IOException {
    String2FloatOpenHashMapWritable map1 = new String2FloatOpenHashMapWritable();
    BufferedReader in = new BufferedReader(new InputStreamReader(
        new FileInputStream("etc/jp-sample.txt"), "UTF8"));

    List<String> list = Lists.newArrayList();
    int cnt = 0;
    String line;
    while ((line = in.readLine()) != null) {
      list.add(line);
      map1.put(line, cnt++);
    }

    for (int i = 0; i < list.size(); i++) {
      assertEquals((float) i, map1.get(list.get(i)), 10e-6);
    }
    assertEquals(5, map1.size());

    // Test serialization
    String2FloatOpenHashMapWritable map2 = String2FloatOpenHashMapWritable.create(map1.serialize());
    for (int i = 0; i < list.size(); i++) {
      assertEquals((float) i, map2.get(list.get(i)), 10e-6);
    }
    assertEquals(5, map2.size());

    for (int i = 0; i < list.size(); i++) {
      map2.remove(list.get(i));
    }
    assertEquals(5, map1.size());
    assertEquals(0, map2.size());

    in.close();
  }
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
190
      return null;
    }
    PriorityQueue<PairOfFloatInt> eS = f2eProbs.get(f).getTranslationsWithProbs(lexProbThreshold);

    if (!eS.isEmpty()) {
      PairOfFloatInt entry = eS.poll();
      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);
      return eTerm;
    }
    return token;
  }
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
215
216
    float sumProbEF = 0;
    int numTrans = 0;
    //tf(e) = sum_f{tf(f)*prob(e|f)}
    while (numTrans < numTransPerToken && !eS.isEmpty()) {
      PairOfFloatInt entry = eS.poll();
      float probEF = entry.getLeftElement();
      int e = entry.getRightElement();
      String eTerm = eVocab_f2e.get(e);

      //      LOG.info("Pr("+eTerm+"|"+token+")="+probEF);

      if (probEF > 0 && e > 0 && !docLangTokenizer.isStopWord(eTerm) && (translateOnly == null || !translateOnly.equals("indri") || indriPuncPattern.matcher(eTerm).matches()) && (pairsInSCFG == null || pairsInSCFG.contains(new PairOfStrings(token,eTerm)))) {     
View Full Code Here
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
            curIndex = prevIndex;    // revert curIndex value since we're skipping this one
            skipTerm = true;
            continue;
          }
          logger.debug("Processing: "+srcTerm+" with index: "+curIndex);     
          topTrans.add(new PairOfFloatString(prob, trgTerm));
          sumOfProbs += prob;
          logger.debug("Added to queue: "+trgTerm+" with prob: "+prob+" (sum: "+sumOfProbs+")");     
        }else if(!earlyTerminate && !skipTerm && !delims.contains(srcTerm)){  //continue adding translation term,prob pairs (except if early termination is ON)
          topTrans.add(new PairOfFloatString(prob, trgTerm));
          sumOfProbs += prob;
          logger.debug("Added to queue: "+trgTerm+" with prob: "+prob+" (sum: "+sumOfProbs+")");     

          // keep top numTrans translations
          if(topTrans.size() > numTrans){
            PairOfFloatString pair = topTrans.pollFirst();
            float removedProb = pair.getLeftElement();
            sumOfProbs -= removedProb;
            logger.debug("Removed from queue: "+pair.getRightElement()+" (sum: "+sumOfProbs+")");     
          }
        }else{
          logger.debug("Skipped line: "+line);
        }
      }
View Full Code Here
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
          continue;
        }
        prob = ttable.get(srcIndex, trgIndex);
        logger.debug("Found: " + trgTerm + " with " + prob);

        topTrans.add(new PairOfFloatString(prob, trgTerm));
        // keep top numTrans translations
        if (topTrans.size() > numTrans) {
          float removedProb = topTrans.pollFirst().getLeftElement();
          sumOfProbs -= removedProb;
        }
View Full Code Here
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
    List<Integer> sortedIndices = new ArrayList<Integer>();
    HMapIF index2ProbMap = new HMapIF();

    float sumOfProbs = 0.0f;    //only extract the top K<15 if the mass prob. exceeds MAX_probThreshold
    while(!topTrans.isEmpty() && sumOfProbs < cumProbThreshold){
      PairOfFloatString e = topTrans.pollLast();
      String term = e.getRightElement();
      float pr = e.getLeftElement()/cumProb;    // normalize
      logger.debug(term+"-->"+pr);
      int trgIndex = trgVocab.addOrGet(term);
      sumOfProbs += e.getLeftElement();         // keep track of unnormalized cumulative prob for determining cutoff
      sortedIndices.add(trgIndex);
      index2ProbMap.put(trgIndex, pr);
    }

    // to enable faster access with binary search, we sort entries by vocabulary index.
View Full Code Here
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
          int e2 = eVocabTrg.get(eTerm);        

          float prob2 = f2e_Probs.get(f2, e2);
          float prob = prob1*prob2;
          sumOfProbs += prob;
          topTrans.add(new PairOfFloatString(prob, fTerm));
        }
        logger.info("Adding "+eTerm);
        addToTable(e1, topTrans, sumOfProbs, table, fVocabTrg, 1.0f, stats);     
      }
      logger.info(stats);
View Full Code Here
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
            curIndex = prevIndex;    // revert curIndex value since we're skipping this one
            skipTerm = true;
            continue;
          }
          logger.debug("Processing: "+srcTerm+" with index: "+curIndex);     
          topTrans.add(new PairOfFloatString(prob, trgTerm));
          sumOfProbs += prob;
          logger.debug("Added to queue: "+trgTerm+" with prob: "+prob+" (sum: "+sumOfProbs+")");     
        }else if(!earlyTerminate && !skipTerm && !delims.contains(srcTerm)){  //continue adding translation term,prob pairs (except if early termination is ON)
          topTrans.add(new PairOfFloatString(prob, trgTerm));
          sumOfProbs += prob;
          logger.debug("Added to queue: "+trgTerm+" with prob: "+prob+" (sum: "+sumOfProbs+")");     

          // keep top numTrans translations
          if(topTrans.size() > numTrans){
            PairOfFloatString pair = topTrans.pollFirst();
            float removedProb = pair.getLeftElement();
            sumOfProbs -= removedProb;
            logger.debug("Removed from queue: "+pair.getRightElement()+" (sum: "+sumOfProbs+")");     
          }
        }else{
          logger.debug("Skipped line: "+line);
        }
        //        // line processed: check if early terminate
View Full Code Here
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
      logger.debug("Processing: "+srcTerm+" with index: "+curIndex+" ("+srcIndex+")");
      for(int trgIndex : translations){
        trgTerm = trgVocab.get(trgIndex);
        prob = ttable.get(srcIndex, trgIndex);

        topTrans.add(new PairOfFloatString(prob, trgTerm));
        // keep top numTrans translations
        if(topTrans.size() > numTrans){
          float removedProb = topTrans.pollFirst().getLeftElement();
          sumOfProbs -= removedProb;
        }
View Full Code Here
TOP

Related Classes of edu.umd.cloud9.io.map.String2FloatOpenHashMapWritable

  • bak.pcj.IntIterator
  • edu.umd.cloud9.example.bfs.BfsNodeTest
  • edu.umd.cloud9.example.pagerank.PageRankNodeTest
  • edu.umd.cloud9.io.array.ArrayListOfIntsWritable
  • edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.map.HMapIDW
  • edu.umd.cloud9.io.map.HMapIDWTest
    • 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.