Package org.apache.mahout.utils.vectors

Examples of org.apache.mahout.utils.vectors.TermInfo

130
131
132
133
134
135
136
137
138
139
140
      writer.addDocument(doc);
    }
    writer.close();
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content", mapper);
   
    int i = 0;
    for (Vector vector : iterable) {
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  }
 
  public void testIterable() throws Exception {
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content", mapper);
   
    //TODO: do something more meaningful here
    for (Vector vector : iterable) {
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
          }
          int maxDFPercent = 99;
          if (cmdLine.hasOption(maxDFPercentOpt)) {
            maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString());
          }
          TermInfo termInfo = new CachedTermInfo(reader, field, minDf, maxDFPercent);
          VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
          double norm = LuceneIterable.NO_NORMALIZING;
          if (cmdLine.hasOption(powerOpt)) {
            String power = cmdLine.getValue(powerOpt).toString();
            if (power.equals("INF")) {
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
      writer.addDocument(doc);
    }
    writer.close();
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
    Iterable<Vector> iterable = new LuceneIterable(reader, "id", "content", mapper);

    int i = 0;
    for (Vector vector : iterable) {
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
      writer.addDocument(doc);
    }
    writer.close();
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);

    int numTerms = 0;
    for (Iterator<TermEntry> it = termInfo.getAllEntries(); it.hasNext();) {
      it.next();
      numTerms++;
    }
    termDictionary = new String[numTerms];
    int i = 0;
    for (Iterator<TermEntry> it = termInfo.getAllEntries(); it.hasNext();) {
      String term = it.next().term;
      termDictionary[i] = term;
      System.out.println(i + " " + term);
      i++;
    }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
  @Test
  public void testIterable() throws Exception {
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content", mapper);

    //TODO: do something more meaningful here
    for (Vector vector : iterable) {
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
      weight = new TFIDF();
    } else {
      throw new IllegalArgumentException("Weight type " + weightType + " is not supported");
    }

    TermInfo termInfo = new CachedTermInfo(reader, field, minDf, maxDFPercent);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);

    LuceneIterable iterable;
    if (norm == LuceneIterable.NO_NORMALIZING) {
      iterable = new LuceneIterable(reader, idField, field, mapper, LuceneIterable.NO_NORMALIZING, maxPercentErrorDocs);
View Full Code Here
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
    } finally {
      Closeables.closeQuietly(writer);
    }
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
   
    int numTerms = 0;
    for (Iterator<TermEntry> it = termInfo.getAllEntries(); it.hasNext();) {
      it.next();
      numTerms++;
    }
    termDictionary = new String[numTerms];
    int i = 0;
    for (Iterator<TermEntry> it = termInfo.getAllEntries(); it.hasNext();) {
      String term = it.next().getTerm();
      termDictionary[i] = term;
      System.out.println(i + " " + term);
      i++;
    }
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
        int maxDFPercent = 99;
        if (cmdLine.hasOption(maxDFPercentOpt)) {
          maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString());
        }

        TermInfo termInfo = new CachedTermInfo(reader, field, minDf, maxDFPercent);
        VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);

        double norm = LuceneIterable.NO_NORMALIZING;
        if (cmdLine.hasOption(powerOpt)) {
          String power = cmdLine.getValue(powerOpt).toString();
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
    } finally {
      Closeables.closeQuietly(writer);
    }
    IndexReader reader = IndexReader.open(directory, true);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    VectorMapper mapper = new TFDFMapper(reader, weight, termInfo);
    Iterable<Vector> iterable = new LuceneIterable(reader, "id", "content", mapper);

    int i = 0;
    for (Vector vector : iterable) {
View Full Code Here
TOP

Related Classes of org.apache.mahout.utils.vectors.TermInfo

  • org.apache.mahout.clustering.dirichlet.TestL1ModelClustering
  • org.apache.mahout.clustering.TestClusterDumper
  • org.apache.mahout.utils.vectors.lucene.Driver
  • org.apache.mahout.utils.vectors.lucene.LuceneIterableTest
    • 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.