Java NormalizerStandardize.transform方法代码示例

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testBruteForce4d() {
    Construct4dDataSet imageDataSet = new Construct4dDataSet(10, 5, 10, 15);

    NormalizerStandardize myNormalizer = new NormalizerStandardize();
    myNormalizer.fit(imageDataSet.sampleDataSet);
    assertEquals(imageDataSet.expectedMean, myNormalizer.getMean());

    float aat = Transforms.abs(myNormalizer.getStd().div(imageDataSet.expectedStd).sub(1)).maxNumber().floatValue();
    float abt = myNormalizer.getStd().maxNumber().floatValue();
    float act = imageDataSet.expectedStd.maxNumber().floatValue();
    System.out.println("ValA: " + aat);
    System.out.println("ValB: " + abt);
    System.out.println("ValC: " + act);
    assertTrue(aat < 0.05);

    NormalizerMinMaxScaler myMinMaxScaler = new NormalizerMinMaxScaler();
    myMinMaxScaler.fit(imageDataSet.sampleDataSet);
    assertEquals(imageDataSet.expectedMin, myMinMaxScaler.getMin());
    assertEquals(imageDataSet.expectedMax, myMinMaxScaler.getMax());

    DataSet copyDataSet = imageDataSet.sampleDataSet.copy();
    myNormalizer.transform(copyDataSet);
}
 

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

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testMeanStdZeros() {
    List<List<Writable>> data = new ArrayList<>();
    Schema.Builder builder = new Schema.Builder();
    int numColumns = 6;
    for (int i = 0; i < numColumns; i++)
        builder.addColumnDouble(String.valueOf(i));

    for (int i = 0; i < 5; i++) {
        List<Writable> record = new ArrayList<>(numColumns);
        data.add(record);
        for (int j = 0; j < numColumns; j++) {
            record.add(new DoubleWritable(1.0));
        }

    }

    INDArray arr = RecordConverter.toMatrix(data);

    Schema schema = builder.build();
    JavaRDD<List<Writable>> rdd = sc.parallelize(data);
    DataRowsFacade dataFrame = DataFrames.toDataFrame(schema, rdd);

    //assert equivalent to the ndarray pre processing
    NormalizerStandardize standardScaler = new NormalizerStandardize();
    standardScaler.fit(new DataSet(arr.dup(), arr.dup()));
    INDArray standardScalered = arr.dup();
    standardScaler.transform(new DataSet(standardScalered, standardScalered));
    DataNormalization zeroToOne = new NormalizerMinMaxScaler();
    zeroToOne.fit(new DataSet(arr.dup(), arr.dup()));
    INDArray zeroToOnes = arr.dup();
    zeroToOne.transform(new DataSet(zeroToOnes, zeroToOnes));
    List<Row> rows = Normalization.stdDevMeanColumns(dataFrame, dataFrame.get().columns());
    INDArray assertion = DataFrames.toMatrix(rows);
    //compare standard deviation
    assertTrue(standardScaler.getStd().equalsWithEps(assertion.getRow(0), 1e-1));
    //compare mean
    assertTrue(standardScaler.getMean().equalsWithEps(assertion.getRow(1), 1e-1));

}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testUnderOverflow() {
    // This dataset will be basically constant with a small std deviation
    // And the constant is large. Checking if algorithm can handle
    double tolerancePerc = 1; //Within 1 %
    double toleranceAbs = 0.0005;
    int nSamples = 1000;
    int bSize = 10;
    int x = -1000000, y = 1000000;
    double z = 1000000;

    INDArray featureX = Nd4j.rand(nSamples, 1).mul(1).add(x);
    INDArray featureY = Nd4j.rand(nSamples, 1).mul(2).add(y);
    INDArray featureZ = Nd4j.rand(nSamples, 1).mul(3).add(z);
    INDArray featureSet = Nd4j.concat(1, featureX, featureY, featureZ);
    INDArray labelSet = Nd4j.zeros(nSamples, 1);
    DataSet sampleDataSet = new DataSet(featureSet, labelSet);
    DataSetIterator sampleIter = new TestDataSetIterator(sampleDataSet, bSize);

    INDArray theoreticalMean = Nd4j.create(new double[] {x, y, z});

    NormalizerStandardize myNormalizer = new NormalizerStandardize();
    myNormalizer.fit(sampleIter);

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

    //this just has to not barf
    //myNormalizer.transform(sampleIter);
    myNormalizer.transform(sampleDataSet);
}
 

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

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Override
public void normalize() {
    //FeatureUtil.normalizeMatrix(getFeatures());
    NormalizerStandardize inClassPreProcessor = new NormalizerStandardize();
    inClassPreProcessor.fit(this);
    inClassPreProcessor.transform(this);
}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void testRocMultiToHtml() throws Exception {
    DataSetIterator iter = new IrisDataSetIterator(150, 150);

    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).list()
                    .layer(0, new DenseLayer.Builder().nIn(4).nOut(4).activation(Activation.TANH).build()).layer(1,
                                    new OutputLayer.Builder().nIn(4).nOut(3).activation(Activation.SOFTMAX)
                                                    .lossFunction(LossFunctions.LossFunction.MCXENT).build())
                    .build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();

    NormalizerStandardize ns = new NormalizerStandardize();
    DataSet ds = iter.next();
    ns.fit(ds);
    ns.transform(ds);

    for (int i = 0; i < 30; i++) {
        net.fit(ds);
    }

    for (int numSteps : new int[] {20, 0}) {
        ROCMultiClass roc = new ROCMultiClass(numSteps);
        iter.reset();

        INDArray f = ds.getFeatures();
        INDArray l = ds.getLabels();
        INDArray out = net.output(f);
        roc.eval(l, out);


        String str = EvaluationTools.rocChartToHtml(roc, Arrays.asList("setosa", "versicolor", "virginica"));
        System.out.println(str);
    }
}
 

import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize; //导入方法依赖的package包/类
@Test
public void normalizationTests() {
    List<List<Writable>> data = new ArrayList<>();
    Schema.Builder builder = new Schema.Builder();
    int numColumns = 6;
    for (int i = 0; i < numColumns; i++)
        builder.addColumnDouble(String.valueOf(i));

    for (int i = 0; i < 5; i++) {
        List<Writable> record = new ArrayList<>(numColumns);
        data.add(record);
        for (int j = 0; j < numColumns; j++) {
            record.add(new DoubleWritable(1.0));
        }

    }

    INDArray arr = RecordConverter.toMatrix(data);

    Schema schema = builder.build();
    JavaRDD<List<Writable>> rdd = sc.parallelize(data);
    assertEquals(schema, DataFrames.fromStructType(DataFrames.fromSchema(schema)));
    assertEquals(rdd.collect(), DataFrames.toRecords(DataFrames.toDataFrame(schema, rdd)).getSecond().collect());

    DataRowsFacade dataFrame = DataFrames.toDataFrame(schema, rdd);
    dataFrame.get().show();
    Normalization.zeromeanUnitVariance(dataFrame).get().show();
    Normalization.normalize(dataFrame).get().show();

    //assert equivalent to the ndarray pre processing
    NormalizerStandardize standardScaler = new NormalizerStandardize();
    standardScaler.fit(new DataSet(arr.dup(), arr.dup()));
    INDArray standardScalered = arr.dup();
    standardScaler.transform(new DataSet(standardScalered, standardScalered));
    DataNormalization zeroToOne = new NormalizerMinMaxScaler();
    zeroToOne.fit(new DataSet(arr.dup(), arr.dup()));
    INDArray zeroToOnes = arr.dup();
    zeroToOne.transform(new DataSet(zeroToOnes, zeroToOnes));

    INDArray zeroMeanUnitVarianceDataFrame =
                    RecordConverter.toMatrix(Normalization.zeromeanUnitVariance(schema, rdd).collect());
    INDArray zeroMeanUnitVarianceDataFrameZeroToOne =
                    RecordConverter.toMatrix(Normalization.normalize(schema, rdd).collect());
    assertEquals(standardScalered, zeroMeanUnitVarianceDataFrame);
    assertTrue(zeroToOnes.equalsWithEps(zeroMeanUnitVarianceDataFrameZeroToOne, 1e-1));

}
 

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

    DataSetIterator iter = new IrisDataSetIterator(150, 150);

    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).list()
                    .layer(0, new DenseLayer.Builder().nIn(4).nOut(4).activation(Activation.TANH).build()).layer(1,
                                    new OutputLayer.Builder().nIn(4).nOut(2).activation(Activation.SOFTMAX)
                                                    .lossFunction(LossFunctions.LossFunction.MCXENT).build())
                    .build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();

    NormalizerStandardize ns = new NormalizerStandardize();
    DataSet ds = iter.next();
    ns.fit(ds);
    ns.transform(ds);

    INDArray newLabels = Nd4j.create(150, 2);
    newLabels.getColumn(0).assign(ds.getLabels().getColumn(0));
    newLabels.getColumn(0).addi(ds.getLabels().getColumn(1));
    newLabels.getColumn(1).assign(ds.getLabels().getColumn(2));
    ds.setLabels(newLabels);

    for (int i = 0; i < 30; i++) {
        net.fit(ds);
    }

    for (int numSteps : new int[] {20, 0}) {
        ROC roc = new ROC(numSteps);
        iter.reset();

        INDArray f = ds.getFeatures();
        INDArray l = ds.getLabels();
        INDArray out = net.output(f);
        roc.eval(l, out);


        String str = EvaluationTools.rocChartToHtml(roc);
        //            System.out.println(str);
    }
}