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

Example 16 with CSVSequenceRecordReader

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

the class RecordReaderDataSetiteratorTest method testSequenceRecordReaderSingleReaderMetaData.

@Test
public void testSequenceRecordReaderSingleReaderMetaData() throws Exception {
    //need to manually extract
    for (int i = 0; i < 3; i++) {
        new ClassPathResource(String.format("csvsequenceSingle_%d.txt", i)).getTempFileFromArchive();
    }
    ClassPathResource resource = new ClassPathResource("csvsequenceSingle_0.txt");
    String path = resource.getTempFileFromArchive().getAbsolutePath().replaceAll("0", "%d");
    SequenceRecordReader reader = new CSVSequenceRecordReader(1, ",");
    reader.initialize(new NumberedFileInputSplit(path, 0, 2));
    SequenceRecordReaderDataSetIterator iteratorClassification = new SequenceRecordReaderDataSetIterator(reader, 1, 3, 0, false);
    SequenceRecordReader reader2 = new CSVSequenceRecordReader(1, ",");
    reader2.initialize(new NumberedFileInputSplit(path, 0, 2));
    SequenceRecordReaderDataSetIterator iteratorRegression = new SequenceRecordReaderDataSetIterator(reader2, 1, 3, 0, true);
    iteratorClassification.setCollectMetaData(true);
    iteratorRegression.setCollectMetaData(true);
    while (iteratorClassification.hasNext()) {
        DataSet ds = iteratorClassification.next();
        DataSet fromMeta = iteratorClassification.loadFromMetaData(ds.getExampleMetaData(RecordMetaData.class));
        assertEquals(ds, fromMeta);
    }
    while (iteratorRegression.hasNext()) {
        DataSet ds = iteratorRegression.next();
        DataSet fromMeta = iteratorRegression.loadFromMetaData(ds.getExampleMetaData(RecordMetaData.class));
        assertEquals(ds, fromMeta);
    }
}

Example 17 with CSVSequenceRecordReader

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

the class RecordReaderDataSetiteratorTest method testSequenceRecordReaderMeta.

@Test
public void testSequenceRecordReaderMeta() 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();
    }
    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);
    iter.setCollectMetaData(true);
    assertEquals(3, iter.inputColumns());
    assertEquals(4, iter.totalOutcomes());
    while (iter.hasNext()) {
        DataSet ds = iter.next();
        List<RecordMetaData> meta = ds.getExampleMetaData(RecordMetaData.class);
        DataSet fromMeta = iter.loadFromMetaData(meta);
        assertEquals(ds, fromMeta);
    }
}

Example 18 with CSVSequenceRecordReader

use of org.datavec.api.records.reader.impl.csv.CSVSequenceRecordReader 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);
}