Examples with SequenceRecordReaderDataSetIterator org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator used on opensource projects

Example 1 with SequenceRecordReaderDataSetIterator

use of org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator in project deeplearning4j by deeplearning4j.

the class TestRecordReaders method testClassIndexOutsideOfRangeRRMDSI_MultipleReaders.

@Test
public void testClassIndexOutsideOfRangeRRMDSI_MultipleReaders() {
    Collection<Collection<Collection<Writable>>> c1 = new ArrayList<>();
    Collection<Collection<Writable>> seq1 = new ArrayList<>();
    seq1.add(Arrays.<Writable>asList(new DoubleWritable(0.0)));
    seq1.add(Arrays.<Writable>asList(new DoubleWritable(0.0)));
    c1.add(seq1);
    Collection<Collection<Writable>> seq2 = new ArrayList<>();
    seq2.add(Arrays.<Writable>asList(new DoubleWritable(0.0)));
    seq2.add(Arrays.<Writable>asList(new DoubleWritable(0.0)));
    c1.add(seq2);
    Collection<Collection<Collection<Writable>>> c2 = new ArrayList<>();
    Collection<Collection<Writable>> seq1a = new ArrayList<>();
    seq1a.add(Arrays.<Writable>asList(new IntWritable(0)));
    seq1a.add(Arrays.<Writable>asList(new IntWritable(1)));
    c2.add(seq1a);
    Collection<Collection<Writable>> seq2a = new ArrayList<>();
    seq2a.add(Arrays.<Writable>asList(new IntWritable(0)));
    seq2a.add(Arrays.<Writable>asList(new IntWritable(2)));
    c2.add(seq2a);
    CollectionSequenceRecordReader csrr = new CollectionSequenceRecordReader(c1);
    CollectionSequenceRecordReader csrrLabels = new CollectionSequenceRecordReader(c2);
    DataSetIterator dsi = new SequenceRecordReaderDataSetIterator(csrr, csrrLabels, 2, 2);
    try {
        DataSet ds = dsi.next();
        fail("Expected exception");
    } catch (DL4JException e) {
        System.out.println("testClassIndexOutsideOfRangeRRMDSI_MultipleReaders(): " + e.getMessage());
    } catch (Exception e) {
        e.printStackTrace();
        fail();
    }
}

Example 2 with SequenceRecordReaderDataSetIterator

use of org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator in project deeplearning4j by deeplearning4j.

the class TestDataVecDataSetFunctions method testDataVecSequencePairDataSetFunctionVariableLength.

@Test
public void testDataVecSequencePairDataSetFunctionVariableLength() throws Exception {
    //Same sort of test as testDataVecSequencePairDataSetFunction() but with variable length time series (labels shorter, align end)
    //Convert data to a SequenceFile:
    File f = new File("src/test/resources/csvsequence/csvsequence_0.txt");
    String pathFeatures = f.getAbsolutePath();
    String folderFeatures = pathFeatures.substring(0, pathFeatures.length() - 17);
    pathFeatures = folderFeatures + "*";
    File f2 = new File("src/test/resources/csvsequencelabels/csvsequencelabelsShort_0.txt");
    String pathLabels = f2.getPath();
    String folderLabels = pathLabels.substring(0, pathLabels.length() - 28);
    pathLabels = folderLabels + "*";
    //Extract a number from the file name
    PathToKeyConverter pathConverter = new PathToKeyConverterNumber();
    JavaPairRDD<Text, BytesPairWritable> toWrite = DataVecSparkUtil.combineFilesForSequenceFile(sc, pathFeatures, pathLabels, pathConverter);
    Path p = Files.createTempDirectory("dl4j_testSeqPairFnVarLength");
    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(4, false, DataVecSequencePairDataSetFunction.AlignmentMode.ALIGN_END);
    JavaRDD<DataSet> data = writables.map(pairFn);
    List<DataSet> sparkData = data.collect();
    //Now: do the same thing locally (SequenceRecordReaderDataSetIterator) and compare
    String featuresPath = f.getPath().replaceAll("0", "%d");
    String labelsPath = f2.getPath().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, SequenceRecordReaderDataSetIterator.AlignmentMode.ALIGN_END);
    List<DataSet> localData = new ArrayList<>(3);
    while (iter.hasNext()) localData.add(iter.next());
    assertEquals(3, sparkData.size());
    assertEquals(3, localData.size());
    //1 example, 3 values, 4 time steps
    int[] fShapeExp = new int[] { 1, 3, 4 };
    //1 example, 4 values/classes, 4 time steps (after padding)
    int[] lShapeExp = new int[] { 1, 4, 4 };
    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);
        //Expect mask array for labels
        assertNotNull(dsSpark.getLabelsMaskArray());
        INDArray fSpark = dsSpark.getFeatureMatrix();
        INDArray fLocal = dsLocal.getFeatureMatrix();
        INDArray lSpark = dsSpark.getLabels();
        INDArray lLocal = dsLocal.getLabels();
        assertArrayEquals(fShapeExp, fSpark.shape());
        assertArrayEquals(fShapeExp, fLocal.shape());
        assertArrayEquals(lShapeExp, lSpark.shape());
        assertArrayEquals(lShapeExp, 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);
    //-------------------------------------------------
    //NOW: test same thing, but for align start...
    DataVecSequencePairDataSetFunction pairFnAlignStart = new DataVecSequencePairDataSetFunction(4, false, DataVecSequencePairDataSetFunction.AlignmentMode.ALIGN_START);
    JavaRDD<DataSet> rddDataAlignStart = writables.map(pairFnAlignStart);
    List<DataSet> sparkDataAlignStart = rddDataAlignStart.collect();
    //re-initialize to reset
    featureReader.initialize(new NumberedFileInputSplit(featuresPath, 0, 2));
    labelReader.initialize(new NumberedFileInputSplit(labelsPath, 0, 2));
    SequenceRecordReaderDataSetIterator iterAlignStart = new SequenceRecordReaderDataSetIterator(featureReader, labelReader, 1, 4, false, SequenceRecordReaderDataSetIterator.AlignmentMode.ALIGN_START);
    List<DataSet> localDataAlignStart = new ArrayList<>(3);
    while (iterAlignStart.hasNext()) localDataAlignStart.add(iterAlignStart.next());
    assertEquals(3, sparkDataAlignStart.size());
    assertEquals(3, localDataAlignStart.size());
    for (int i = 0; i < 3; i++) {
        //Check shapes etc. data sets order may differ for spark vs. local
        DataSet dsSpark = sparkDataAlignStart.get(i);
        DataSet dsLocal = localDataAlignStart.get(i);
        //Expect mask array for labels
        assertNotNull(dsSpark.getLabelsMaskArray());
        INDArray fSpark = dsSpark.getFeatureMatrix();
        INDArray fLocal = dsLocal.getFeatureMatrix();
        INDArray lSpark = dsSpark.getLabels();
        INDArray lLocal = dsLocal.getLabels();
        assertArrayEquals(fShapeExp, fSpark.shape());
        assertArrayEquals(fShapeExp, fLocal.shape());
        assertArrayEquals(lShapeExp, lSpark.shape());
        assertArrayEquals(lShapeExp, lLocal.shape());
    }
    //Check that results are the same (order not withstanding)
    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;
            }
        }
    }
    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 3 with SequenceRecordReaderDataSetIterator

use of org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator 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 4 with SequenceRecordReaderDataSetIterator

use of org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator in project deeplearning4j by deeplearning4j.

the class TestRecordReaders method testClassIndexOutsideOfRangeRRMDSI.

@Test
public void testClassIndexOutsideOfRangeRRMDSI() {
    Collection<Collection<Collection<Writable>>> c = new ArrayList<>();
    Collection<Collection<Writable>> seq1 = new ArrayList<>();
    seq1.add(Arrays.<Writable>asList(new DoubleWritable(0.0), new IntWritable(0)));
    seq1.add(Arrays.<Writable>asList(new DoubleWritable(0.0), new IntWritable(1)));
    c.add(seq1);
    Collection<Collection<Writable>> seq2 = new ArrayList<>();
    seq2.add(Arrays.<Writable>asList(new DoubleWritable(0.0), new IntWritable(0)));
    seq2.add(Arrays.<Writable>asList(new DoubleWritable(0.0), new IntWritable(2)));
    c.add(seq2);
    CollectionSequenceRecordReader csrr = new CollectionSequenceRecordReader(c);
    DataSetIterator dsi = new SequenceRecordReaderDataSetIterator(csrr, 2, 2, 1);
    try {
        DataSet ds = dsi.next();
        fail("Expected exception");
    } catch (DL4JException e) {
        System.out.println("testClassIndexOutsideOfRangeRRMDSI(): " + e.getMessage());
    } catch (Exception e) {
        e.printStackTrace();
        fail();
    }
}

Example 5 with SequenceRecordReaderDataSetIterator

use of org.deeplearning4j.datasets.datavec.SequenceRecordReaderDataSetIterator in project deeplearning4j by deeplearning4j.

the class TestDataVecDataSetFunctions method testDataVecSequenceDataSetFunction.

@Test
public void testDataVecSequenceDataSetFunction() throws Exception {
    JavaSparkContext sc = getContext();
    //Test Spark record reader functionality vs. local
    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 + "*";
    JavaPairRDD<String, PortableDataStream> origData = sc.binaryFiles(path);
    //3 CSV sequences
    assertEquals(3, origData.count());
    SequenceRecordReader seqRR = new CSVSequenceRecordReader(1, ",");
    SequenceRecordReaderFunction rrf = new SequenceRecordReaderFunction(seqRR);
    JavaRDD<List<List<Writable>>> rdd = origData.map(rrf);
    JavaRDD<DataSet> data = rdd.map(new DataVecSequenceDataSetFunction(2, -1, true, null, null));
    List<DataSet> collected = data.collect();
    //Load normally (i.e., not via Spark), and check that we get the same results (order not withstanding)
    InputSplit is = new FileSplit(new File(folder), new String[] { "txt" }, true);
    SequenceRecordReader seqRR2 = new CSVSequenceRecordReader(1, ",");
    seqRR2.initialize(is);
    SequenceRecordReaderDataSetIterator iter = new SequenceRecordReaderDataSetIterator(seqRR2, 1, -1, 2, true);
    List<DataSet> listLocal = new ArrayList<>(3);
    while (iter.hasNext()) {
        listLocal.add(iter.next());
    }
    //Compare:
    assertEquals(3, collected.size());
    assertEquals(3, listLocal.size());
    //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 = collected.get(i);
        for (int j = 0; j < 3; j++) {
            if (ds.equals(listLocal.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);
}