/** * Sets whether output instances contain 0 or 1 indicating word presence, or * word counts. * * @param outputWordCounts true if word counts should be output. */ public void setOutputWordCounts(boolean outputWordCounts) { m_dictionaryBuilder.setOutputWordCounts(outputWordCounts); }
/** * Sets whether output instances contain 0 or 1 indicating word presence, or * word counts. * * @param outputWordCounts true if word counts should be output. */ public void setOutputWordCounts(boolean outputWordCounts) { m_dictionaryBuilder.setOutputWordCounts(outputWordCounts); }
/** * Sets whether output instances contain 0 or 1 indicating word presence, or * word counts. * * @param outputWordCounts true if word counts should be output. */ @OptionMetadata(displayName = "Output word counts", description = "Output word counts rather than boolean 0 or 1 (indicating presence or absence of " + "a word", commandLineParamName = "C", commandLineParamSynopsis = "-C", commandLineParamIsFlag = true, displayOrder = 3) public void setOutputWordCounts(boolean outputWordCounts) { m_vectorizer.setOutputWordCounts(outputWordCounts); }
/** * Sets whether output instances contain 0 or 1 indicating word presence, or * word counts. * * @param outputWordCounts true if word counts should be output. */ @OptionMetadata(displayName = "Output word counts", description = "Output word counts rather than boolean 0 or 1 (indicating presence or absence of " + "a word", commandLineParamName = "C", commandLineParamSynopsis = "-C", commandLineParamIsFlag = true, displayOrder = 3) public void setOutputWordCounts(boolean outputWordCounts) { m_vectorizer.setOutputWordCounts(outputWordCounts); }
setOutputWordCounts(Utils.getFlag('C', options));
setOutputWordCounts(Utils.getFlag('C', options));
public void testVectorizeInstanceWordCountsNoClass() throws Exception { Instances data1 = getData1(); Instances structure = new Instances(data1, 0); DictionaryBuilder builder = new DictionaryBuilder(); builder.setMinTermFreq(2); builder.setOutputWordCounts(true); builder.setup(structure); for (int i = 0; i < data1.numInstances(); i++) { builder.processInstance(data1.instance(i)); } builder.finalizeDictionary(); Instance vectorized = builder.vectorizeInstance(data1.instance(0)); assertEquals(2, vectorized.numAttributes()); // "the" occurs twice in the first index and "over" once assertEquals(2, (int) vectorized.value(0)); assertEquals(1, (int) vectorized.value(1)); }
public void testVectorizeInstanceWordCountsNoClass() throws Exception { Instances data1 = getData1(); Instances structure = new Instances(data1, 0); DictionaryBuilder builder = new DictionaryBuilder(); builder.setMinTermFreq(2); builder.setOutputWordCounts(true); builder.setup(structure); for (int i = 0; i < data1.numInstances(); i++) { builder.processInstance(data1.instance(i)); } builder.finalizeDictionary(); Instance vectorized = builder.vectorizeInstance(data1.instance(0)); assertEquals(2, vectorized.numAttributes()); // "the" occurs twice in the first index and "over" once assertEquals(2, (int) vectorized.value(0)); assertEquals(1, (int) vectorized.value(1)); }