Package org.apache.mahout.utils.vectors.lucene

Examples of org.apache.mahout.utils.vectors.lucene.CachedTermInfo

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
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
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
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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
   
    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();
      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
157
158
159
160
161
162
163
164
165
166
167
    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) {
      assertNotNull(vector);
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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
      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().getTerm();
      termDictionary[i] = term;
      System.out.println(i + " " + term);
      i++;
    }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
   
    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();
      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
TOP

Related Classes of org.apache.mahout.utils.vectors.lucene.CachedTermInfo

  • org.apache.lucene.index.Term
  • org.apache.lucene.index.TermEnum
  • org.apache.lucene.index.Terms
  • org.apache.lucene.index.TermsEnum
  • org.apache.lucene.util.BytesRef
  • org.apache.mahout.clustering.dirichlet.TestL1ModelClustering
  • org.apache.mahout.clustering.TestClusterDumper
  • org.apache.mahout.utils.vectors.TermEntry
    • 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.