Examples with CSVSequenceRecordReader org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader used on opensource projects

Example 6 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader in project deeplearning4j by deeplearning4j.

the class TestDataVecDataSetFunctions method testDataVecSequencePairDataSetFunction.

@Test
public void testDataVecSequencePairDataSetFunction() throws Exception {
    JavaSparkContext sc = getContext();
    //Convert data to a SequenceFile:
    File f = new File("src/test/resources/csvsequence/csvsequence_0.txt");
    String path = f.getPath();
    String folder = path.substring(0, path.length() - 17);
    path = folder + "*";
    PathToKeyConverter pathConverter = new PathToKeyConverterFilename();
    JavaPairRDD<Text, BytesPairWritable> toWrite = DataVecSparkUtil.combineFilesForSequenceFile(sc, path, path, pathConverter);
    Path p = Files.createTempDirectory("dl4j_testSeqPairFn");
    p.toFile().deleteOnExit();
    String outPath = p.toString() + "/out";
    new File(outPath).deleteOnExit();
    toWrite.saveAsNewAPIHadoopFile(outPath, Text.class, BytesPairWritable.class, SequenceFileOutputFormat.class);
    //Load from sequence file:
    JavaPairRDD<Text, BytesPairWritable> fromSeq = sc.sequenceFile(outPath, Text.class, BytesPairWritable.class);
    SequenceRecordReader srr1 = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader srr2 = new CSVSequenceRecordReader(1, ",");
    PairSequenceRecordReaderBytesFunction psrbf = new PairSequenceRecordReaderBytesFunction(srr1, srr2);
    JavaRDD<Tuple2<List<List<Writable>>, List<List<Writable>>>> writables = fromSeq.map(psrbf);
    //Map to DataSet:
    DataVecSequencePairDataSetFunction pairFn = new DataVecSequencePairDataSetFunction();
    JavaRDD<DataSet> data = writables.map(pairFn);
    List<DataSet> sparkData = data.collect();
    //Now: do the same thing locally (SequenceRecordReaderDataSetIterator) and compare
    String featuresPath = f.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(featuresPath, 0, 2));
    SequenceRecordReaderDataSetIterator iter = new SequenceRecordReaderDataSetIterator(featureReader, labelReader, 1, -1, true);
    List<DataSet> localData = new ArrayList<>(3);
    while (iter.hasNext()) localData.add(iter.next());
    assertEquals(3, sparkData.size());
    assertEquals(3, localData.size());
    for (int i = 0; i < 3; i++) {
        //Check shapes etc. data sets order may differ for spark vs. local
        DataSet dsSpark = sparkData.get(i);
        DataSet dsLocal = localData.get(i);
        assertNull(dsSpark.getFeaturesMaskArray());
        assertNull(dsSpark.getLabelsMaskArray());
        INDArray fSpark = dsSpark.getFeatureMatrix();
        INDArray fLocal = dsLocal.getFeatureMatrix();
        INDArray lSpark = dsSpark.getLabels();
        INDArray lLocal = dsLocal.getLabels();
        //1 example, 3 values, 3 time steps
        int[] s = new int[] { 1, 3, 4 };
        assertArrayEquals(s, fSpark.shape());
        assertArrayEquals(s, fLocal.shape());
        assertArrayEquals(s, lSpark.shape());
        assertArrayEquals(s, lLocal.shape());
    }
    //Check that results are the same (order not withstanding)
    boolean[] found = new boolean[3];
    for (int i = 0; i < 3; i++) {
        int foundIndex = -1;
        DataSet ds = sparkData.get(i);
        for (int j = 0; j < 3; j++) {
            if (ds.equals(localData.get(j))) {
                if (foundIndex != -1)
                    //Already found this value -> suggests this spark value equals two or more of local version? (Shouldn't happen)
                    fail();
                foundIndex = j;
                if (found[foundIndex])
                    //One of the other spark values was equal to this one -> suggests duplicates in Spark list
                    fail();
                //mark this one as seen before
                found[foundIndex] = true;
            }
        }
    }
    int count = 0;
    for (boolean b : found) if (b)
        count++;
    //Expect all 3 and exactly 3 pairwise matches between spark and local versions
    assertEquals(3, count);
}

Example 7 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader in project deeplearning4j by deeplearning4j.

the class RecordReaderDataSetiteratorTest method testSequenceRecordReaderTwoReadersWithEmptyFeatureSequenceThrows.

@Test(expected = ZeroLengthSequenceException.class)
public void testSequenceRecordReaderTwoReadersWithEmptyFeatureSequenceThrows() throws Exception {
    SequenceRecordReader featureReader = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader = new CSVSequenceRecordReader(1, ",");
    featureReader.initialize(new FileSplit(new ClassPathResource("empty.txt").getTempFileFromArchive()));
    labelReader.initialize(new FileSplit(new ClassPathResource("csvsequencelabels_0.txt").getTempFileFromArchive()));
    new SequenceRecordReaderDataSetIterator(featureReader, labelReader, 1, -1, true).next();
}

Example 8 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testSplittingCSVSequence.

@Test
public void testSplittingCSVSequence() throws Exception {
    //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();
    }
    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("seq1", featureReader2).addSequenceReader("seq2", labelReader2).addInput("seq1", 0, 1).addInput("seq1", 2, 2).addOutputOneHot("seq2", 0, 4).build();
    while (iter.hasNext()) {
        DataSet ds = iter.next();
        INDArray fds = ds.getFeatureMatrix();
        INDArray lds = ds.getLabels();
        MultiDataSet mds = srrmdsi.next();
        assertEquals(2, mds.getFeatures().length);
        assertEquals(1, mds.getLabels().length);
        assertNull(mds.getFeaturesMaskArrays());
        assertNull(mds.getLabelsMaskArrays());
        INDArray[] fmds = mds.getFeatures();
        INDArray[] lmds = mds.getLabels();
        assertNotNull(fmds);
        assertNotNull(lmds);
        for (int i = 0; i < fmds.length; i++) assertNotNull(fmds[i]);
        for (int i = 0; i < lmds.length; i++) assertNotNull(lmds[i]);
        INDArray expIn1 = fds.get(NDArrayIndex.all(), NDArrayIndex.interval(0, 1, true), NDArrayIndex.all());
        INDArray expIn2 = fds.get(NDArrayIndex.all(), NDArrayIndex.interval(2, 2, true), NDArrayIndex.all());
        assertEquals(expIn1, fmds[0]);
        assertEquals(expIn2, fmds[1]);
        assertEquals(lds, lmds[0]);
    }
    assertFalse(srrmdsi.hasNext());
}

Example 9 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testSplittingCSVSequenceMeta.

@Test
public void testSplittingCSVSequenceMeta() throws Exception {
    //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();
    }
    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));
    SequenceRecordReader featureReader2 = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader2 = new CSVSequenceRecordReader(1, ",");
    featureReader2.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader2.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    RecordReaderMultiDataSetIterator srrmdsi = new RecordReaderMultiDataSetIterator.Builder(1).addSequenceReader("seq1", featureReader2).addSequenceReader("seq2", labelReader2).addInput("seq1", 0, 1).addInput("seq1", 2, 2).addOutputOneHot("seq2", 0, 4).build();
    srrmdsi.setCollectMetaData(true);
    int count = 0;
    while (srrmdsi.hasNext()) {
        MultiDataSet mds = srrmdsi.next();
        MultiDataSet fromMeta = srrmdsi.loadFromMetaData(mds.getExampleMetaData(RecordMetaData.class));
        assertEquals(mds, fromMeta);
        count++;
    }
    assertEquals(3, count);
}

Example 10 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testVariableLengthTSMeta.

@Test
public void testVariableLengthTSMeta() throws Exception {
    //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();
    }
    //Set up SequenceRecordReaderDataSetIterators for comparison
    ClassPathResource resource = new ClassPathResource("csvsequence_0.txt");
    String featuresPath = resource.getTempFileFromArchive().getAbsolutePath().replaceAll("0", "%d");
    resource = new ClassPathResource("csvsequencelabelsShort_0.txt");
    String labelsPath = resource.getTempFileFromArchive().getAbsolutePath().replaceAll("0", "%d");
    //Set up
    SequenceRecordReader featureReader3 = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader3 = new CSVSequenceRecordReader(1, ",");
    featureReader3.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader3.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    SequenceRecordReader featureReader4 = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReader labelReader4 = new CSVSequenceRecordReader(1, ",");
    featureReader4.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader4.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    RecordReaderMultiDataSetIterator rrmdsiStart = new RecordReaderMultiDataSetIterator.Builder(1).addSequenceReader("in", featureReader3).addSequenceReader("out", labelReader3).addInput("in").addOutputOneHot("out", 0, 4).sequenceAlignmentMode(RecordReaderMultiDataSetIterator.AlignmentMode.ALIGN_START).build();
    RecordReaderMultiDataSetIterator rrmdsiEnd = new RecordReaderMultiDataSetIterator.Builder(1).addSequenceReader("in", featureReader4).addSequenceReader("out", labelReader4).addInput("in").addOutputOneHot("out", 0, 4).sequenceAlignmentMode(RecordReaderMultiDataSetIterator.AlignmentMode.ALIGN_END).build();
    rrmdsiStart.setCollectMetaData(true);
    rrmdsiEnd.setCollectMetaData(true);
    int count = 0;
    while (rrmdsiStart.hasNext()) {
        MultiDataSet mdsStart = rrmdsiStart.next();
        MultiDataSet mdsEnd = rrmdsiEnd.next();
        MultiDataSet mdsStartFromMeta = rrmdsiStart.loadFromMetaData(mdsStart.getExampleMetaData(RecordMetaData.class));
        MultiDataSet mdsEndFromMeta = rrmdsiEnd.loadFromMetaData(mdsEnd.getExampleMetaData(RecordMetaData.class));
        assertEquals(mdsStart, mdsStartFromMeta);
        assertEquals(mdsEnd, mdsEndFromMeta);
        count++;
    }
    assertFalse(rrmdsiStart.hasNext());
    assertFalse(rrmdsiEnd.hasNext());
    assertEquals(3, count);
}