@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 testTransform() {
/*Random dataset is generated such that
AX + B where X is from a normal distribution with mean 0 and std 1
The mean of above will be B and std A
Obtained mean and std dev are compared to theoretical
Transformed values should be the same as X with the same seed.
*/
long randSeed = 7139183;
int nFeatures = 2;
int nSamples = 6400;
int bsize = 8;
int a = 2;
int b = 10;
INDArray sampleMean, sampleStd, sampleMeanDelta, sampleStdDelta, delta, deltaPerc;
double maxDeltaPerc, sampleMeanSEM;
genRandomDataSet normData = new genRandomDataSet(nSamples, nFeatures, a, b, randSeed);
genRandomDataSet expectedData = new genRandomDataSet(nSamples, nFeatures, 1, 0, randSeed);
genRandomDataSet beforeTransformData =
new genRandomDataSet(nSamples, nFeatures, a, b, randSeed);
NormalizerStandardize myNormalizer = new NormalizerStandardize();
DataSetIterator normIterator = normData.getIter(bsize);
DataSetIterator expectedIterator = expectedData.getIter(bsize);
DataSetIterator beforeTransformIterator = beforeTransformData.getIter(bsize);
myNormalizer.fit(normIterator);
double tolerancePerc = 5.0; // within 5%
sampleMean = myNormalizer.getMean();
sampleMeanDelta = Transforms.abs(sampleMean.sub(normData.theoreticalMean));
assertTrue(
sampleMeanDelta.mul(100).div(normData.theoreticalMean).max(1).getDouble(0, 0)
< tolerancePerc);
// sanity check to see if it's within the theoretical standard error of mean
sampleMeanSEM = sampleMeanDelta.div(normData.theoreticalSEM).max(1).getDouble(0, 0);
assertTrue(sampleMeanSEM < 2.6); // 99% of the time it should be within this many SEMs
tolerancePerc = 10.0; // within 10%
sampleStd = myNormalizer.getStd();
sampleStdDelta = Transforms.abs(sampleStd.sub(normData.theoreticalStd));
assertTrue(
sampleStdDelta.div(normData.theoreticalStd).max(1).mul(100).getDouble(0, 0)
< tolerancePerc);
normIterator.setPreProcessor(myNormalizer);
while (normIterator.hasNext()) {
INDArray before = beforeTransformIterator.next().getFeatures();
INDArray after = normIterator.next().getFeatures();
INDArray expected = expectedIterator.next().getFeatures();
delta = Transforms.abs(after.sub(expected));
deltaPerc = delta.div(before.sub(expected));
deltaPerc.muli(100);
maxDeltaPerc = deltaPerc.max(0, 1).getDouble(0, 0);
// System.out.println("=== BEFORE ===");
// System.out.println(before);
// System.out.println("=== AFTER ===");
// System.out.println(after);
// System.out.println("=== SHOULD BE ===");
// System.out.println(expected);
assertTrue(maxDeltaPerc < tolerancePerc);
}
}
