Examples of TFIDFSimilarity

Examples of org.apache.lucene.search.similarities.TFIDFSimilarity

250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
          return hyperbolicTf(freq);
        }
      };
    ss.setHyperbolicTfFactors(3.3f, 7.7f, Math.E, 5.0f);
   
    TFIDFSimilarity s = ss;

    for (int i = 1; i <=1000; i++) {
      assertTrue("MIN tf: i="+i+" : s="+s.tf(i),
                 3.3f <= s.tf(i));
      assertTrue("MAX tf: i="+i+" : s="+s.tf(i),
                 s.tf(i) <= 7.7f);
    }
    assertEquals("MID tf", 3.3f+(7.7f - 3.3f)/2.0f, s.tf(5), 0.00001f);
   
    // stupidity
    assertEquals("tf zero", 0.0f, s.tf(0), 0.0f);
   
  }
View Full Code Here

Examples of org.apache.lucene.search.similarities.TFIDFSimilarity

56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
  }

  @Override
  public FunctionValues getValues(Map context, AtomicReaderContext readerContext) throws IOException {
    IndexSearcher searcher = (IndexSearcher)context.get("searcher");
    final TFIDFSimilarity similarity = IDFValueSource.asTFIDF(searcher.getSimilarity(), field);
    if (similarity == null) {
      throw new UnsupportedOperationException("requires a TFIDFSimilarity (such as DefaultSimilarity)");
    }
    final NumericDocValues norms = readerContext.reader().getNormValues(field);

    if (norms == null) {
      return new ConstDoubleDocValues(0.0, this);
    }
   
    return new FloatDocValues(this) {
      @Override
      public float floatVal(int doc) {
        return similarity.decodeNormValue(norms.get(doc));
      }
    };
  }
View Full Code Here

Examples of org.apache.lucene.search.similarities.TFIDFSimilarity

48
49
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
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
125
126
127
128
129
130
131
132
133
134
135
  @Override
  public FunctionValues getValues(Map context, AtomicReaderContext readerContext) throws IOException {
    Fields fields = readerContext.reader().fields();
    final Terms terms = fields.terms(indexedField);
    IndexSearcher searcher = (IndexSearcher)context.get("searcher");
    final TFIDFSimilarity similarity = IDFValueSource.asTFIDF(searcher.getSimilarity(), indexedField);
    if (similarity == null) {
      throw new UnsupportedOperationException("requires a TFIDFSimilarity (such as DefaultSimilarity)");
    }

    return new FloatDocValues(this) {
      DocsEnum docs ;
      int atDoc;
      int lastDocRequested = -1;

      { reset(); }

      public void reset() throws IOException {
        // no one should call us for deleted docs?
       
        if (terms != null) {
          final TermsEnum termsEnum = terms.iterator(null);
          if (termsEnum.seekExact(indexedBytes)) {
            docs = termsEnum.docs(null, null);
          } else {
            docs = null;
          }
        } else {
          docs = null;
        }

        if (docs == null) {
          docs = new DocsEnum() {
            @Override
            public int freq() {
              return 0;
            }

            @Override
            public int docID() {
              return DocIdSetIterator.NO_MORE_DOCS;
            }

            @Override
            public int nextDoc() {
              return DocIdSetIterator.NO_MORE_DOCS;
            }

            @Override
            public int advance(int target) {
              return DocIdSetIterator.NO_MORE_DOCS;
            }

            @Override
            public long cost() {
              return 0;
            }
          };
        }
        atDoc = -1;
      }

      @Override
      public float floatVal(int doc) {
        try {
          if (doc < lastDocRequested) {
            // out-of-order access.... reset
            reset();
          }
          lastDocRequested = doc;

          if (atDoc < doc) {
            atDoc = docs.advance(doc);
          }

          if (atDoc > doc) {
            // term doesn't match this document... either because we hit the
            // end, or because the next doc is after this doc.
            return similarity.tf(0);
          }

          // a match!
          return similarity.tf(docs.freq());
        } catch (IOException e) {
          throw new RuntimeException("caught exception in function "+description()+" : doc="+doc, e);
        }
      }
    };
View Full Code Here

Examples of org.apache.lucene.search.similarities.TFIDFSimilarity

46
47
48
49
50
51
52
53
54
55
56
57
58
  }

  @Override
  public FunctionValues getValues(Map context, AtomicReaderContext readerContext) throws IOException {
    IndexSearcher searcher = (IndexSearcher)context.get("searcher");
    TFIDFSimilarity sim = asTFIDF(searcher.getSimilarity(), field);
    if (sim == null) {
      throw new UnsupportedOperationException("requires a TFIDFSimilarity (such as DefaultSimilarity)");
    }
    int docfreq = searcher.getIndexReader().docFreq(new Term(indexedField, indexedBytes));
    float idf = sim.idf(docfreq, searcher.getIndexReader().maxDoc());
    return new ConstDoubleDocValues(idf, this);
  }
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.