Package org.apache.mahout.vectorizer

Examples of org.apache.mahout.vectorizer.TFIDF

82
83
84
85
86
87
88
89
90
91
92
  }

  @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
111
112
113
114
115
116
117
118
119
120
121
  @Test(expected = IllegalStateException.class)
  public void testIterableNoTermVectors() throws IOException {
    RAMDirectory directory = createTestIndex(TYPE_NO_TERM_VECTORS);
    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();
    Iterators.advance(iterator, 1);
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
    RAMDirectory directory = createTestIndex(TYPE_TERM_VECTORS, new RAMDirectory(), 0);
    //get real vectors
    createTestIndex(TYPE_NO_TERM_VECTORS, directory, 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
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
148
149
150
151
152
153
154
155
156
157
158
      }
    } 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
56
57
58
59
60
61
62
63
64
65
66
  }

  @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
86
87
88
89
90
91
92
93
94
95
96
  @Test(expected = IllegalStateException.class)
  public void testIterable_noTermVectors() throws IOException {
    RAMDirectory directory = createTestIndex(Field.TermVector.NO);

    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);

    Iterator<Vector> iterator = iterable.iterator();
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    RAMDirectory directory = createTestIndex(Field.TermVector.YES, new RAMDirectory(), true, 0);
    //get real vectors
    createTestIndex(Field.TermVector.NO, directory, false, 5);
     
    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);
   
    boolean exceptionThrown;
    //0 percent tolerance
View Full Code Here
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
121
122
123
124
125
126
127
128
129
130
131
    }

    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
TOP

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

  • 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.