Examples with FileSplit org.datavec.api.split.FileSplit used on opensource projects

Example 16 with FileSplit

use of org.datavec.api.split.FileSplit in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testsBasicMeta.

@Test
public void testsBasicMeta() throws Exception {
    //As per testBasic - but also loading metadata
    RecordReader rr2 = new CSVRecordReader(0, ",");
    rr2.initialize(new FileSplit(new ClassPathResource("iris.txt").getTempFileFromArchive()));
    RecordReaderMultiDataSetIterator rrmdsi = new RecordReaderMultiDataSetIterator.Builder(10).addReader("reader", rr2).addInput("reader", 0, 3).addOutputOneHot("reader", 4, 3).build();
    rrmdsi.setCollectMetaData(true);
    int count = 0;
    while (rrmdsi.hasNext()) {
        MultiDataSet mds = rrmdsi.next();
        MultiDataSet fromMeta = rrmdsi.loadFromMetaData(mds.getExampleMetaData(RecordMetaData.class));
        assertEquals(mds, fromMeta);
        count++;
    }
    assertEquals(150 / 10, count);
}

Example 17 with FileSplit

use of org.datavec.api.split.FileSplit in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testsBasic.

@Test
public void testsBasic() throws Exception {
    //Load details from CSV files; single input/output -> compare to RecordReaderDataSetIterator
    RecordReader rr = new CSVRecordReader(0, ",");
    rr.initialize(new FileSplit(new ClassPathResource("iris.txt").getTempFileFromArchive()));
    RecordReaderDataSetIterator rrdsi = new RecordReaderDataSetIterator(rr, 10, 4, 3);
    RecordReader rr2 = new CSVRecordReader(0, ",");
    rr2.initialize(new FileSplit(new ClassPathResource("iris.txt").getTempFileFromArchive()));
    MultiDataSetIterator rrmdsi = new RecordReaderMultiDataSetIterator.Builder(10).addReader("reader", rr2).addInput("reader", 0, 3).addOutputOneHot("reader", 4, 3).build();
    while (rrdsi.hasNext()) {
        DataSet ds = rrdsi.next();
        INDArray fds = ds.getFeatureMatrix();
        INDArray lds = ds.getLabels();
        MultiDataSet mds = rrmdsi.next();
        assertEquals(1, mds.getFeatures().length);
        assertEquals(1, mds.getLabels().length);
        assertNull(mds.getFeaturesMaskArrays());
        assertNull(mds.getLabelsMaskArrays());
        INDArray fmds = mds.getFeatures(0);
        INDArray lmds = mds.getLabels(0);
        assertNotNull(fmds);
        assertNotNull(lmds);
        assertEquals(fds, fmds);
        assertEquals(lds, lmds);
    }
    assertFalse(rrmdsi.hasNext());
    //need to manually extract
    for (int i = 0; i < 3; i++) {
        new ClassPathResource(String.format("csvsequence_%d.txt", i)).getTempFileFromArchive();
        new ClassPathResource(String.format("csvsequencelabels_%d.txt", i)).getTempFileFromArchive();
        new ClassPathResource(String.format("csvsequencelabelsShort_%d.txt", i)).getTempFileFromArchive();
    }
    //Load time series from CSV sequence files; compare to SequenceRecordReaderDataSetIterator
    ClassPathResource resource = new ClassPathResource("csvsequence_0.txt");
    String featuresPath = resource.getTempFileFromArchive().getAbsolutePath().replaceAll("0", "%d");
    resource = new ClassPathResource("csvsequencelabels_0.txt");
    String labelsPath = resource.getTempFileFromArchive().getAbsolutePath().replaceAll("0", "%d");
    SequenceRecordReader featureReader = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader = new CSVSequenceRecordReader(1, ",");
    featureReader.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    SequenceRecordReaderDataSetIterator iter = new SequenceRecordReaderDataSetIterator(featureReader, labelReader, 1, 4, false);
    SequenceRecordReader featureReader2 = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader2 = new CSVSequenceRecordReader(1, ",");
    featureReader2.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader2.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    MultiDataSetIterator srrmdsi = new RecordReaderMultiDataSetIterator.Builder(1).addSequenceReader("in", featureReader2).addSequenceReader("out", labelReader2).addInput("in").addOutputOneHot("out", 0, 4).build();
    while (iter.hasNext()) {
        DataSet ds = iter.next();
        INDArray fds = ds.getFeatureMatrix();
        INDArray lds = ds.getLabels();
        MultiDataSet mds = srrmdsi.next();
        assertEquals(1, mds.getFeatures().length);
        assertEquals(1, mds.getLabels().length);
        assertNull(mds.getFeaturesMaskArrays());
        assertNull(mds.getLabelsMaskArrays());
        INDArray fmds = mds.getFeatures(0);
        INDArray lmds = mds.getLabels(0);
        assertNotNull(fmds);
        assertNotNull(lmds);
        assertEquals(fds, fmds);
        assertEquals(lds, lmds);
    }
    assertFalse(srrmdsi.hasNext());
}

Example 18 with FileSplit

use of org.datavec.api.split.FileSplit in project deeplearning4j by deeplearning4j.

the class EvalTest method testEvaluationWithMetaData.

@Test
public void testEvaluationWithMetaData() throws Exception {
    RecordReader csv = new CSVRecordReader();
    csv.initialize(new FileSplit(new ClassPathResource("iris.txt").getTempFileFromArchive()));
    int batchSize = 10;
    int labelIdx = 4;
    int numClasses = 3;
    RecordReaderDataSetIterator rrdsi = new RecordReaderDataSetIterator(csv, batchSize, labelIdx, numClasses);
    NormalizerStandardize ns = new NormalizerStandardize();
    ns.fit(rrdsi);
    rrdsi.setPreProcessor(ns);
    rrdsi.reset();
    Nd4j.getRandom().setSeed(12345);
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).iterations(1).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).updater(Updater.SGD).learningRate(0.1).list().layer(0, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).activation(Activation.SOFTMAX).nIn(4).nOut(3).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();
    for (int i = 0; i < 4; i++) {
        net.fit(rrdsi);
        rrdsi.reset();
    }
    Evaluation e = new Evaluation();
    //*** New: Enable collection of metadata (stored in the DataSets) ***
    rrdsi.setCollectMetaData(true);
    while (rrdsi.hasNext()) {
        DataSet ds = rrdsi.next();
        //*** New - cross dependencies here make types difficult, usid Object internally in DataSet for this***
        List<RecordMetaData> meta = ds.getExampleMetaData(RecordMetaData.class);
        INDArray out = net.output(ds.getFeatures());
        //*** New - evaluate and also store metadata ***
        e.eval(ds.getLabels(), out, meta);
    }
    System.out.println(e.stats());
    System.out.println("\n\n*** Prediction Errors: ***");
    //*** New - get list of prediction errors from evaluation ***
    List<Prediction> errors = e.getPredictionErrors();
    List<RecordMetaData> metaForErrors = new ArrayList<>();
    for (Prediction p : errors) {
        metaForErrors.add((RecordMetaData) p.getRecordMetaData());
    }
    //*** New - dynamically load a subset of the data, just for prediction errors ***
    DataSet ds = rrdsi.loadFromMetaData(metaForErrors);
    INDArray output = net.output(ds.getFeatures());
    int count = 0;
    for (Prediction t : errors) {
        System.out.println(t + "\t\tRaw Data: " + //*** New - load subset of data from MetaData object (usually batched for efficiency) ***
        csv.loadFromMetaData((RecordMetaData) t.getRecordMetaData()).getRecord() + "\tNormalized: " + ds.getFeatureMatrix().getRow(count) + "\tLabels: " + ds.getLabels().getRow(count) + "\tNetwork predictions: " + output.getRow(count));
        count++;
    }
    int errorCount = errors.size();
    double expAcc = 1.0 - errorCount / 150.0;
    assertEquals(expAcc, e.accuracy(), 1e-5);
    ConfusionMatrix<Integer> confusion = e.getConfusionMatrix();
    int[] actualCounts = new int[3];
    int[] predictedCounts = new int[3];
    for (int i = 0; i < 3; i++) {
        for (int j = 0; j < 3; j++) {
            //(actual,predicted)
            int entry = confusion.getCount(i, j);
            List<Prediction> list = e.getPredictions(i, j);
            assertEquals(entry, list.size());
            actualCounts[i] += entry;
            predictedCounts[j] += entry;
        }
    }
    for (int i = 0; i < 3; i++) {
        List<Prediction> actualClassI = e.getPredictionsByActualClass(i);
        List<Prediction> predictedClassI = e.getPredictionByPredictedClass(i);
        assertEquals(actualCounts[i], actualClassI.size());
        assertEquals(predictedCounts[i], predictedClassI.size());
    }
}

Example 19 with FileSplit

use of org.datavec.api.split.FileSplit in project deeplearning4j by deeplearning4j.

the class RecordReaderDataSetiteratorTest method testSequenceRecordReaderSingleReaderWithEmptySequenceThrows.

@Test(expected = ZeroLengthSequenceException.class)
public void testSequenceRecordReaderSingleReaderWithEmptySequenceThrows() throws Exception {
    SequenceRecordReader reader = new CSVSequenceRecordReader(1, ",");
    reader.initialize(new FileSplit(new ClassPathResource("empty.txt").getTempFileFromArchive()));
    new SequenceRecordReaderDataSetIterator(reader, 1, -1, 1, true).next();
}

Example 20 with FileSplit

use of org.datavec.api.split.FileSplit in project deeplearning4j by deeplearning4j.

the class RecordReaderDataSetiteratorTest method testRecordReaderMetaData.

@Test
public void testRecordReaderMetaData() throws Exception {
    RecordReader csv = new CSVRecordReader();
    csv.initialize(new FileSplit(new ClassPathResource("iris.txt").getTempFileFromArchive()));
    int batchSize = 10;
    int labelIdx = 4;
    int numClasses = 3;
    RecordReaderDataSetIterator rrdsi = new RecordReaderDataSetIterator(csv, batchSize, labelIdx, numClasses);
    rrdsi.setCollectMetaData(true);
    while (rrdsi.hasNext()) {
        DataSet ds = rrdsi.next();
        List<RecordMetaData> meta = ds.getExampleMetaData(RecordMetaData.class);
        int i = 0;
        for (RecordMetaData m : meta) {
            Record r = csv.loadFromMetaData(m);
            INDArray row = ds.getFeatureMatrix().getRow(i);
            System.out.println(m.getLocation() + "\t" + r.getRecord() + "\t" + row);
            for (int j = 0; j < 4; j++) {
                double exp = r.getRecord().get(j).toDouble();
                double act = row.getDouble(j);
                assertEquals(exp, act, 1e-6);
            }
            i++;
        }
        System.out.println();
        DataSet fromMeta = rrdsi.loadFromMetaData(meta);
        assertEquals(ds, fromMeta);
    }
}