@Test
public void testAddToVector() {
TextValueEncoder enc = new TextValueEncoder("text");
Vector v1 = new DenseVector(200);
enc.addToVector("test1 and more", v1);
enc.flush(1, v1);
// should set 6 distinct locations to 1
assertEquals(6.0, v1.norm(1), 0);
assertEquals(1.0, v1.maxValue(), 0);
// now some fancy weighting
StaticWordValueEncoder w = new StaticWordValueEncoder("text");
w.setDictionary(ImmutableMap.<String, Double>of("word1", 3.0, "word2", 1.5));
enc.setWordEncoder(w);
// should set 6 locations to something
Vector v2 = new DenseVector(200);
enc.addToVector("test1 and more", v2);
enc.flush(1, v2);
// this should set the same 6 locations to the same values
Vector v3 = new DenseVector(200);
w.addToVector("test1", v3);
w.addToVector("and", v3);
w.addToVector("more", v3);
assertEquals(0, v3.minus(v2).norm(1), 0);
// moreover, the locations set in the unweighted case should be the same as in the weighted case
assertEquals(v3.zSum(), v3.dot(v1), 0);
}
public NaiveBayesModel(
Matrix weightMatrix,
Vector weightsPerFeature,
Vector weightsPerLabel,
Vector thetaNormalizer,
float alphaI) {
this.weightsPerLabelAndFeature = weightMatrix;
this.weightsPerFeature = weightsPerFeature;
this.weightsPerLabel = weightsPerLabel;
this.perlabelThetaNormalizer = thetaNormalizer;
this.numFeatures = weightsPerFeature.getNumNondefaultElements();
this.totalWeightSum = weightsPerLabel.zSum();
this.alphaI = alphaI;
}
@Override
public double apply(Vector f) {
return f.zSum();
}
