Package org.apache.mahout.vectorizer

Examples of org.apache.mahout.vectorizer.Weight

113
114
115
116
117
118
119
120
121
122
123
      doc.add(text);
      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;
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
      doc.add(text);
      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();
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
  }

  @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
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
    Preconditions.checkArgument(maxDFPercent <= 99, "maxDFPercent must be <= 99");

    Directory dir = FSDirectory.open(file);
    IndexReader reader = IndexReader.open(dir, true);

    Weight weight;
    if ("tf".equalsIgnoreCase(weightType)) {
      weight = new TF();
    } else if ("tfidf".equalsIgnoreCase(weightType)) {
      weight = new TFIDF();
    } else {
View Full Code Here
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
154
155
156
157
158
159
160
161
162
163
164
        }

        Directory dir = FSDirectory.open(file);
        IndexReader reader = IndexReader.open(dir, true);

        Weight weight;
        if (cmdLine.hasOption(weightOpt)) {
          String wString = cmdLine.getValue(weightOpt).toString();
          if ("tf".equalsIgnoreCase(wString)) {
            weight = new TF();
          } else if ("tfidf".equalsIgnoreCase(wString)) {
View Full Code Here
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
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
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
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
TOP

Related Classes of org.apache.mahout.vectorizer.Weight

  • 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.