Java NormalizerStandardize.fitLabel方法代码示例

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Override
public NormalizerStandardize restore(@NonNull InputStream stream) throws IOException {
    DataInputStream dis = new DataInputStream(stream);

    boolean fitLabels = dis.readBoolean();

    NormalizerStandardize result = new NormalizerStandardize(Nd4j.read(dis), Nd4j.read(dis));
    result.fitLabel(fitLabels);
    if (fitLabels) {
        result.setLabelStats(Nd4j.read(dis), Nd4j.read(dis));
    }

    return result;
}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testBruteForce() {
    /* This test creates a dataset where feature values are multiples of consecutive natural numbers
       The obtained values are compared to the theoretical mean and std dev
     */
    double tolerancePerc = 0.01;
    int nSamples = 5120;
    int x = 1, y = 2, z = 3;

    INDArray featureX = Nd4j.linspace(1, nSamples, nSamples).reshape(nSamples, 1).mul(x);
    INDArray featureY = featureX.mul(y);
    INDArray featureZ = featureX.mul(z);
    INDArray featureSet = Nd4j.concat(1, featureX, featureY, featureZ);
    INDArray labelSet = featureSet.dup().getColumns(new int[] {0});
    DataSet sampleDataSet = new DataSet(featureSet, labelSet);

    double meanNaturalNums = (nSamples + 1) / 2.0;
    INDArray theoreticalMean =
                    Nd4j.create(new double[] {meanNaturalNums * x, meanNaturalNums * y, meanNaturalNums * z});
    INDArray theoreticallabelMean = theoreticalMean.dup().getColumns(new int[] {0});
    double stdNaturalNums = Math.sqrt((nSamples * nSamples - 1) / 12.0);
    INDArray theoreticalStd =
                    Nd4j.create(new double[] {stdNaturalNums * x, stdNaturalNums * y, stdNaturalNums * z});
    INDArray theoreticallabelStd = theoreticalStd.dup().getColumns(new int[] {0});

    NormalizerStandardize myNormalizer = new NormalizerStandardize();
    myNormalizer.fitLabel(true);
    myNormalizer.fit(sampleDataSet);

    INDArray meanDelta = Transforms.abs(theoreticalMean.sub(myNormalizer.getMean()));
    INDArray labelDelta = Transforms.abs(theoreticallabelMean.sub(myNormalizer.getLabelMean()));
    INDArray meanDeltaPerc = meanDelta.div(theoreticalMean).mul(100);
    INDArray labelDeltaPerc = labelDelta.div(theoreticallabelMean).mul(100);
    double maxMeanDeltaPerc = meanDeltaPerc.max(1).getDouble(0, 0);
    assertTrue(maxMeanDeltaPerc < tolerancePerc);
    assertTrue(labelDeltaPerc.max(1).getDouble(0, 0) < tolerancePerc);

    INDArray stdDelta = Transforms.abs(theoreticalStd.sub(myNormalizer.getStd()));
    INDArray stdDeltaPerc = stdDelta.div(theoreticalStd).mul(100);
    INDArray stdlabelDeltaPerc =
                    Transforms.abs(theoreticallabelStd.sub(myNormalizer.getLabelStd())).div(theoreticallabelStd);
    double maxStdDeltaPerc = stdDeltaPerc.max(1).mul(100).getDouble(0, 0);
    double maxlabelStdDeltaPerc = stdlabelDeltaPerc.max(1).getDouble(0, 0);
    assertTrue(maxStdDeltaPerc < tolerancePerc);
    assertTrue(maxlabelStdDeltaPerc < tolerancePerc);


    // SAME TEST WITH THE ITERATOR
    int bSize = 10;
    tolerancePerc = 0.1; // 1% of correct value
    DataSetIterator sampleIter = new TestDataSetIterator(sampleDataSet, bSize);
    myNormalizer.fit(sampleIter);

    meanDelta = Transforms.abs(theoreticalMean.sub(myNormalizer.getMean()));
    meanDeltaPerc = meanDelta.div(theoreticalMean).mul(100);
    maxMeanDeltaPerc = meanDeltaPerc.max(1).getDouble(0, 0);
    assertTrue(maxMeanDeltaPerc < tolerancePerc);

    stdDelta = Transforms.abs(theoreticalMean.sub(myNormalizer.getMean()));
    stdDeltaPerc = stdDelta.div(theoreticalStd).mul(100);
    maxStdDeltaPerc = stdDeltaPerc.max(1).getDouble(0, 0);
    assertTrue(maxStdDeltaPerc < tolerancePerc);
}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@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 = 2227724;

    int nFeatures = 2;
    int nSamples = 6400;
    int bsize = 8;
    int a = 5;
    int b = 100;
    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();
    myNormalizer.fitLabel(true);
    DataSetIterator normIterator = normData.getIter(bsize);
    DataSetIterator expectedIterator = expectedData.getIter(bsize);
    DataSetIterator beforeTransformIterator = beforeTransformData.getIter(bsize);

    myNormalizer.fit(normIterator);

    double tolerancePerc = 0.5; //within 0.5%
    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 = 5; //within 5%
    sampleStd = myNormalizer.getStd();
    sampleStdDelta = Transforms.abs(sampleStd.sub(normData.theoreticalStd));
    assertTrue(sampleStdDelta.div(normData.theoreticalStd).max(1).mul(100).getDouble(0, 0) < tolerancePerc);

    tolerancePerc = 1; //within 1%
    normIterator.setPreProcessor(myNormalizer);
    while (normIterator.hasNext()) {
        INDArray before = beforeTransformIterator.next().getFeatures();
        DataSet here = normIterator.next();
        assertEquals(here.getFeatures(), here.getLabels()); //bootstrapping existing test on features
        INDArray after = here.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);
    }
}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testBruteForce3dMaskLabels() {

    NormalizerStandardize myNormalizer = new NormalizerStandardize();
    myNormalizer.fitLabel(true);
    NormalizerMinMaxScaler myMinMaxScaler = new NormalizerMinMaxScaler();
    myMinMaxScaler.fitLabel(true);

    //generating a dataset with consecutive numbers as feature values. Dataset also has masks
    int samples = 100;
    INDArray featureScale = Nd4j.create(new float[] {1, 2, 10}).reshape(3, 1);
    int timeStepsU = 5;
    Construct3dDataSet sampleU = new Construct3dDataSet(featureScale, timeStepsU, samples, 1);
    int timeStepsV = 3;
    Construct3dDataSet sampleV = new Construct3dDataSet(featureScale, timeStepsV, samples, sampleU.newOrigin);
    List<DataSet> dataSetList = new ArrayList<DataSet>();
    dataSetList.add(sampleU.sampleDataSet);
    dataSetList.add(sampleV.sampleDataSet);

    DataSet fullDataSetA = DataSet.merge(dataSetList);
    DataSet fullDataSetAA = fullDataSetA.copy();
    //This should be the same datasets as above without a mask
    Construct3dDataSet fullDataSetNoMask =
                    new Construct3dDataSet(featureScale, timeStepsU + timeStepsV, samples, 1);

    //preprocessors - label and feature values are the same
    myNormalizer.fit(fullDataSetA);
    assertEquals(myNormalizer.getMean(), fullDataSetNoMask.expectedMean);
    assertEquals(myNormalizer.getStd(), fullDataSetNoMask.expectedStd);
    assertEquals(myNormalizer.getLabelMean(), fullDataSetNoMask.expectedMean);
    assertEquals(myNormalizer.getLabelStd(), fullDataSetNoMask.expectedStd);

    myMinMaxScaler.fit(fullDataSetAA);
    assertEquals(myMinMaxScaler.getMin(), fullDataSetNoMask.expectedMin);
    assertEquals(myMinMaxScaler.getMax(), fullDataSetNoMask.expectedMax);
    assertEquals(myMinMaxScaler.getLabelMin(), fullDataSetNoMask.expectedMin);
    assertEquals(myMinMaxScaler.getLabelMax(), fullDataSetNoMask.expectedMax);


    //Same Test with an Iterator, values should be close for std, exact for everything else
    DataSetIterator sampleIterA = new TestDataSetIterator(fullDataSetA, 5);
    DataSetIterator sampleIterB = new TestDataSetIterator(fullDataSetAA, 5);

    myNormalizer.fit(sampleIterA);
    assertEquals(myNormalizer.getMean(), fullDataSetNoMask.expectedMean);
    assertEquals(myNormalizer.getLabelMean(), fullDataSetNoMask.expectedMean);
    assertTrue(Transforms.abs(myNormalizer.getStd().div(fullDataSetNoMask.expectedStd).sub(1)).maxNumber()
                    .floatValue() < 0.01);
    assertTrue(Transforms.abs(myNormalizer.getLabelStd().div(fullDataSetNoMask.expectedStd).sub(1)).maxNumber()
                    .floatValue() < 0.01);

    myMinMaxScaler.fit(sampleIterB);
    assertEquals(myMinMaxScaler.getMin(), fullDataSetNoMask.expectedMin);
    assertEquals(myMinMaxScaler.getMax(), fullDataSetNoMask.expectedMax);
    assertEquals(myMinMaxScaler.getLabelMin(), fullDataSetNoMask.expectedMin);
    assertEquals(myMinMaxScaler.getLabelMax(), fullDataSetNoMask.expectedMax);
}