Java Code Examples for org.datavec.api.records.reader.RecordReader#loadFromMetaData()

/**
 * Load a multiple sequence examples to a DataSet, using the provided
 * RecordMetaData instances.
 *
 * @param list
 *            List of RecordMetaData instances to load from. Should have been
 *            produced by the record reader provided to the
 *            SequenceRecordReaderDataSetIterator constructor
 * @return DataSet with the specified examples
 * @throws IOException
 *             If an error occurs during loading of the data
 */
public MultiDataSet loadFromMetaData(List<RecordMetaData> list) throws IOException {
	// First: load the next values from the RR / SeqRRs
	Map<String, List<List<Writable>>> nextRRVals = new HashMap<>();
	List<RecordMetaDataComposableMap> nextMetas = (collectMetaData ? new ArrayList<RecordMetaDataComposableMap>()
			: null);

	for (Map.Entry<String, RecordReader> entry : recordReaders.entrySet()) {
		RecordReader rr = entry.getValue();

		List<RecordMetaData> thisRRMeta = new ArrayList<>();
		for (RecordMetaData m : list) {
			RecordMetaDataComposableMap m2 = (RecordMetaDataComposableMap) m;
			thisRRMeta.add(m2.getMeta().get(entry.getKey()));
		}

		List<Record> fromMeta = rr.loadFromMetaData(thisRRMeta);
		List<List<Writable>> writables = new ArrayList<>(list.size());
		for (Record r : fromMeta) {
			writables.add(r.getRecord());
		}

		nextRRVals.put(entry.getKey(), writables);
	}

	return nextMultiDataSet(nextRRVals, nextMetas);

}
 

@Test
public void testRecordReaderMetaDataList() throws Exception {
    val recordsToWrite = recordToWrite();
    //send file
    File tmp =  tmpDataFile(recordsToWrite);
    RecordReader recordReader = new ArrowRecordReader();
    RecordMetaDataIndex recordMetaDataIndex = new RecordMetaDataIndex(0,tmp.toURI(),ArrowRecordReader.class);
    recordReader.loadFromMetaData(Arrays.<RecordMetaData>asList(recordMetaDataIndex));

    Record record = recordReader.nextRecord();
    assertEquals(2,record.getRecord().size());

}
 

@Test
public void testRecordReaderMetaData() throws Exception {
    val recordsToWrite = recordToWrite();
    //send file
    File tmp =  tmpDataFile(recordsToWrite);
    RecordReader recordReader = new ArrowRecordReader();
    RecordMetaDataIndex recordMetaDataIndex = new RecordMetaDataIndex(0,tmp.toURI(),ArrowRecordReader.class);
    recordReader.loadFromMetaData(recordMetaDataIndex);

    Record record = recordReader.nextRecord();
    assertEquals(2,record.getRecord().size());
}
 

@Test
public void testAppendingLabelsMetaData() throws Exception {
    ClassPathResource cpr = new ClassPathResource("json/json_test_0.txt");
    String path = cpr.getFile().getAbsolutePath().replace("0", "%d");

    InputSplit is = new NumberedFileInputSplit(path, 0, 2);

    //Insert at the end:
    RecordReader rr = new JacksonRecordReader(getFieldSelection(), new ObjectMapper(new JsonFactory()), false, -1,
                    new LabelGen());
    rr.initialize(is);

    List<List<Writable>> out = new ArrayList<>();
    while (rr.hasNext()) {
        out.add(rr.next());
    }
    assertEquals(3, out.size());

    rr.reset();

    List<List<Writable>> out2 = new ArrayList<>();
    List<Record> outRecord = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    while (rr.hasNext()) {
        Record r = rr.nextRecord();
        out2.add(r.getRecord());
        outRecord.add(r);
        meta.add(r.getMetaData());
    }

    assertEquals(out, out2);

    List<Record> fromMeta = rr.loadFromMetaData(meta);
    assertEquals(outRecord, fromMeta);
}
 

@Test
public void testRegexLineRecordReaderMeta() throws Exception {
    String regex = "(\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2}\\.\\d{3}) (\\d+) ([A-Z]+) (.*)";

    RecordReader rr = new RegexLineRecordReader(regex, 1);
    rr.initialize(new FileSplit(new ClassPathResource("/logtestdata/logtestfile0.txt").getFile()));

    List<List<Writable>> list = new ArrayList<>();
    while (rr.hasNext()) {
        list.add(rr.next());
    }
    assertEquals(3, list.size());

    List<Record> list2 = new ArrayList<>();
    List<List<Writable>> list3 = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    rr.reset();
    int count = 1; //Start by skipping 1 line
    while (rr.hasNext()) {
        Record r = rr.nextRecord();
        list2.add(r);
        list3.add(r.getRecord());
        meta.add(r.getMetaData());

        assertEquals(count++, ((RecordMetaDataLine) r.getMetaData()).getLineNumber());
    }

    List<Record> fromMeta = rr.loadFromMetaData(meta);

    assertEquals(list, list3);
    assertEquals(list2, fromMeta);
}
 

@Test
public void testRecordReaderMetaDataList() throws Exception {
    val recordsToWrite = recordToWrite();
    //send file
    File tmp =  tmpDataFile(recordsToWrite);
    RecordReader recordReader = new ArrowRecordReader();
    RecordMetaDataIndex recordMetaDataIndex = new RecordMetaDataIndex(0,tmp.toURI(),ArrowRecordReader.class);
    recordReader.loadFromMetaData(Arrays.<RecordMetaData>asList(recordMetaDataIndex));

    Record record = recordReader.nextRecord();
    assertEquals(2,record.getRecord().size());

}
 

@Test
public void testRecordReaderMetaData() throws Exception {
    val recordsToWrite = recordToWrite();
    //send file
    File tmp =  tmpDataFile(recordsToWrite);
    RecordReader recordReader = new ArrowRecordReader();
    RecordMetaDataIndex recordMetaDataIndex = new RecordMetaDataIndex(0,tmp.toURI(),ArrowRecordReader.class);
    recordReader.loadFromMetaData(recordMetaDataIndex);

    Record record = recordReader.nextRecord();
    assertEquals(2,record.getRecord().size());
}
 

@Test
public void testAppendingLabelsMetaData() throws Exception {
    ClassPathResource cpr = new ClassPathResource("datavec-api/json/");
    File f = testDir.newFolder();
    cpr.copyDirectory(f);
    String path = new File(f, "json_test_%d.txt").getAbsolutePath();

    InputSplit is = new NumberedFileInputSplit(path, 0, 2);

    //Insert at the end:
    RecordReader rr = new JacksonRecordReader(getFieldSelection(), new ObjectMapper(new JsonFactory()), false, -1,
                    new LabelGen());
    rr.initialize(is);

    List<List<Writable>> out = new ArrayList<>();
    while (rr.hasNext()) {
        out.add(rr.next());
    }
    assertEquals(3, out.size());

    rr.reset();

    List<List<Writable>> out2 = new ArrayList<>();
    List<Record> outRecord = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    while (rr.hasNext()) {
        Record r = rr.nextRecord();
        out2.add(r.getRecord());
        outRecord.add(r);
        meta.add(r.getMetaData());
    }

    assertEquals(out, out2);

    List<Record> fromMeta = rr.loadFromMetaData(meta);
    assertEquals(outRecord, fromMeta);
}
 

@Test
public void testRegexLineRecordReaderMeta() throws Exception {
    String regex = "(\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2}\\.\\d{3}) (\\d+) ([A-Z]+) (.*)";

    RecordReader rr = new RegexLineRecordReader(regex, 1);
    rr.initialize(new FileSplit(new ClassPathResource("datavec-api/logtestdata/logtestfile0.txt").getFile()));

    List<List<Writable>> list = new ArrayList<>();
    while (rr.hasNext()) {
        list.add(rr.next());
    }
    assertEquals(3, list.size());

    List<Record> list2 = new ArrayList<>();
    List<List<Writable>> list3 = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    rr.reset();
    int count = 1; //Start by skipping 1 line
    while (rr.hasNext()) {
        Record r = rr.nextRecord();
        list2.add(r);
        list3.add(r.getRecord());
        meta.add(r.getMetaData());

        assertEquals(count++, ((RecordMetaDataLine) r.getMetaData()).getLineNumber());
    }

    List<Record> fromMeta = rr.loadFromMetaData(meta);

    assertEquals(list, list3);
    assertEquals(list2, fromMeta);
}
 

@Test
    public void testRecordReaderMetaData() throws Exception {

        RecordReader csv = new CSVRecordReader();
        csv.initialize(new FileSplit(Resources.asFile("iris.txt")));

        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.getFeatures().getRow(i);
//                if(i <= 3) {
//                    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("Failed on idx: " + j, exp, act, 1e-6);
                }
                i++;
            }
//            System.out.println();

            DataSet fromMeta = rrdsi.loadFromMetaData(meta);
            assertEquals(ds, fromMeta);
        }
    }
 

@Test
public void testLineReaderMetaData() throws Exception {
    String tempDir = System.getProperty("java.io.tmpdir");
    File tmpdir = new File(tempDir, "tmpdir-testLineReader");
    if (tmpdir.exists())
        tmpdir.delete();
    tmpdir.mkdir();

    File tmp1 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp1.txt"));
    File tmp2 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp2.txt"));
    File tmp3 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp3.txt"));

    FileUtils.writeLines(tmp1, Arrays.asList("1", "2", "3"));
    FileUtils.writeLines(tmp2, Arrays.asList("4", "5", "6"));
    FileUtils.writeLines(tmp3, Arrays.asList("7", "8", "9"));

    InputSplit split = new FileSplit(tmpdir);

    RecordReader reader = new LineRecordReader();
    reader.initialize(split);

    List<List<Writable>> list = new ArrayList<>();
    while (reader.hasNext()) {
        list.add(reader.next());
    }
    assertEquals(9, list.size());


    List<List<Writable>> out2 = new ArrayList<>();
    List<Record> out3 = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    reader.reset();
    int count = 0;
    while (reader.hasNext()) {
        Record r = reader.nextRecord();
        out2.add(r.getRecord());
        out3.add(r);
        meta.add(r.getMetaData());
        int fileIdx = count / 3;
        URI uri = r.getMetaData().getURI();
        assertEquals(uri, split.locations()[fileIdx]);
        count++;
    }

    assertEquals(list, out2);

    List<Record> fromMeta = reader.loadFromMetaData(meta);
    assertEquals(out3, fromMeta);

    //try: second line of second and third files only...
    List<RecordMetaData> subsetMeta = new ArrayList<>();
    subsetMeta.add(meta.get(4));
    subsetMeta.add(meta.get(7));
    List<Record> subset = reader.loadFromMetaData(subsetMeta);
    assertEquals(2, subset.size());
    assertEquals(out3.get(4), subset.get(0));
    assertEquals(out3.get(7), subset.get(1));


    try {
        FileUtils.deleteDirectory(tmpdir);
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

@Test
public void testLineReaderMetaData() throws Exception {
    File tmpdir = testDir.newFolder();

    File tmp1 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp1.txt"));
    File tmp2 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp2.txt"));
    File tmp3 = new File(FilenameUtils.concat(tmpdir.getPath(), "tmp3.txt"));

    FileUtils.writeLines(tmp1, Arrays.asList("1", "2", "3"));
    FileUtils.writeLines(tmp2, Arrays.asList("4", "5", "6"));
    FileUtils.writeLines(tmp3, Arrays.asList("7", "8", "9"));

    InputSplit split = new FileSplit(tmpdir);

    RecordReader reader = new LineRecordReader();
    reader.initialize(split);

    List<List<Writable>> list = new ArrayList<>();
    while (reader.hasNext()) {
        list.add(reader.next());
    }
    assertEquals(9, list.size());


    List<List<Writable>> out2 = new ArrayList<>();
    List<Record> out3 = new ArrayList<>();
    List<RecordMetaData> meta = new ArrayList<>();
    reader.reset();
    int count = 0;
    while (reader.hasNext()) {
        Record r = reader.nextRecord();
        out2.add(r.getRecord());
        out3.add(r);
        meta.add(r.getMetaData());
        int fileIdx = count / 3;
        URI uri = r.getMetaData().getURI();
        assertEquals(uri, split.locations()[fileIdx]);
        count++;
    }

    assertEquals(list, out2);

    List<Record> fromMeta = reader.loadFromMetaData(meta);
    assertEquals(out3, fromMeta);

    //try: second line of second and third files only...
    List<RecordMetaData> subsetMeta = new ArrayList<>();
    subsetMeta.add(meta.get(4));
    subsetMeta.add(meta.get(7));
    List<Record> subset = reader.loadFromMetaData(subsetMeta);
    assertEquals(2, subset.size());
    assertEquals(out3.get(4), subset.get(0));
    assertEquals(out3.get(7), subset.get(1));
}