@Test
public void testConstant() {
double tolerancePerc = 10.0; // 10% of correct value
int nSamples = 500;
int nFeatures = 3;
int constant = 100;
INDArray featureSet = Nd4j.zeros(nSamples, nFeatures).add(constant);
INDArray labelSet = Nd4j.zeros(nSamples, 1);
DataSet sampleDataSet = new DataSet(featureSet, labelSet);
NormalizerStandardize myNormalizer = new NormalizerStandardize();
myNormalizer.fit(sampleDataSet);
// Checking if we gets nans
assertFalse(Double.isNaN(myNormalizer.getStd().getDouble(0)));
myNormalizer.transform(sampleDataSet);
// Checking if we gets nans, because std dev is zero
assertFalse(Double.isNaN(sampleDataSet.getFeatures().min(0, 1).getDouble(0)));
// Checking to see if transformed values are close enough to zero
assertEquals(
Transforms.abs(sampleDataSet.getFeatures()).max(0, 1).getDouble(0, 0),
0,
constant * tolerancePerc / 100.0);
myNormalizer.revert(sampleDataSet);
// Checking if we gets nans, because std dev is zero
assertFalse(Double.isNaN(sampleDataSet.getFeatures().min(0, 1).getDouble(0)));
assertEquals(
Transforms.abs(sampleDataSet.getFeatures().sub(featureSet)).min(0, 1).getDouble(0),
0,
constant * tolerancePerc / 100.0);
}
@Test
public void testRevert() {
double tolerancePerc = 0.01; // 0.01% of correct value
int nSamples = 500;
int nFeatures = 3;
INDArray featureSet = Nd4j.randn(nSamples, nFeatures);
INDArray labelSet = Nd4j.zeros(nSamples, 1);
DataSet sampleDataSet = new DataSet(featureSet, labelSet);
NormalizerStandardize myNormalizer = new NormalizerStandardize();
myNormalizer.fit(sampleDataSet);
DataSet transformed = sampleDataSet.copy();
myNormalizer.transform(transformed);
// System.out.println(transformed.getFeatures());
myNormalizer.revert(transformed);
// System.out.println(transformed.getFeatures());
INDArray delta =
Transforms.abs(transformed.getFeatures().sub(sampleDataSet.getFeatures()))
.div(sampleDataSet.getFeatures());
double maxdeltaPerc = delta.max(0, 1).mul(100).getDouble(0, 0);
assertTrue(maxdeltaPerc < tolerancePerc);
}