Examples of TFIDF

Examples of org.apache.mahout.vectorizer.TFIDF

85
86
87
88
89
90
91
92
93
94
95
    Weight weight;
    if ("tf".equalsIgnoreCase(weightType)) {
      weight = new TF();
    } else if ("tfidf".equalsIgnoreCase(weightType)) {
      weight = new TFIDF();
    } else {
      throw new IllegalArgumentException("Weight type " + weightType + " is not supported");
    }

    TermInfo termInfo = new CachedTermInfo(reader, field, minDf, maxDFPercent);
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

128
129
130
131
132
133
134
135
136
137
138
      }
    } 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();
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
        if (cmdLine.hasOption(weightOpt)) {
          String wString = cmdLine.getValue(weightOpt).toString();
          if ("tf".equalsIgnoreCase(wString)) {
            weight = new TF();
          } else if ("tfidf".equalsIgnoreCase(wString)) {
            weight = new TFIDF();
          } else {
            throw new OptionException(weightOpt);
          }
        } else {
          weight = new TFIDF();
        }

        String field = cmdLine.getValue(fieldOpt).toString();

        int minDf = 1;
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

135
136
137
138
139
140
141
142
143
144
145
      }
    } 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;
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

58
59
60
61
62
63
64
65
66
67
68
  }

  @Test
  public void testIterable() throws Exception {
    IndexReader reader = DirectoryReader.open(directory);
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content", termInfo,weight);

    //TODO: do something more meaningful here
    for (Vector vector : iterable) {
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

88
89
90
91
92
93
94
95
96
97
98
  public void testIterableNoTermVectors() throws IOException {
    RAMDirectory directory = createTestIndex(Field.TermVector.NO);
    IndexReader reader = DirectoryReader.open(directory);
   
   
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content",  termInfo,weight);

    Iterator<Vector> iterator = iterable.iterator();
    iterator.hasNext();
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

105
106
107
108
109
110
111
112
113
114
115
    RAMDirectory directory = createTestIndex(Field.TermVector.YES, new RAMDirectory(), true, 0);
    //get real vectors
    createTestIndex(Field.TermVector.NO, directory, false, 5);
    IndexReader reader = DirectoryReader.open(directory);

    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
   
    boolean exceptionThrown;
    //0 percent tolerance
    LuceneIterable iterable = new LuceneIterable(reader, "id", "content", termInfo,weight);
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

92
93
94
95
96
97
98
99
100
101
102
    Weight weight;
    if ("tf".equalsIgnoreCase(weightType)) {
      weight = new TF();
    } else if ("tfidf".equalsIgnoreCase(weightType)) {
      weight = new TFIDF();
    } else {
      throw new IllegalArgumentException("Weight type " + weightType + " is not supported");
    }

    TermInfo termInfo = new CachedTermInfo(reader, field, minDf, maxDFPercent);
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

125
126
127
128
129
130
131
132
133
134
135
    }
   
    IndexReader reader = DirectoryReader.open(directory);
  

    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();
View Full Code Here

Examples of org.apache.mahout.vectorizer.TFIDF

156
157
158
159
160
161
162
163
164
165
166
   
    IndexReader reader = DirectoryReader.open(directory);
    System.out.println("Number of documents: \t"+reader.numDocs());
   
   
    Weight weight = new TFIDF();
    TermInfo termInfo = new CachedTermInfo(reader, "content", 1, 100);
    Iterable<Vector> iterable = new LuceneIterable(reader, "id", "content", termInfo,weight);
   
    int i = 0;
    for (Vector vector : iterable) {
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.