Java FileSplit类代码示例

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void test() throws Exception {

    CSVRecordReader rr = new CSVRecordReader(0, ',');
    rr.initialize(new FileSplit(new ClassPathResource("iris.dat").getFile()));

    CSVRecordReader rr2 = new CSVRecordReader(0, ',');
    rr2.initialize(new FileSplit(new ClassPathResource("iris.dat").getFile()));

    RecordReader rrC = new ConcatenatingRecordReader(rr, rr2);

    int count = 0;
    while(rrC.hasNext()){
        rrC.next();
        count++;
    }

    assertEquals(300, count);
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
public void load(int batchSize, int numExamples, int numLabels, PathLabelGenerator labelGenerator,
                double splitTrainTest, Random rng) {
    if (!imageFilesExist()) {
        if (!fullDir.exists() || fullDir.listFiles() == null || fullDir.listFiles().length == 0) {
            fullDir.mkdir();

            if (useSubset) {
                log.info("Downloading {} subset...", localDir);
                downloadAndUntar(lfwSubsetData, fullDir);
            } else {
                log.info("Downloading {}...", localDir);
                downloadAndUntar(lfwData, fullDir);
                downloadAndUntar(lfwLabel, fullDir);
            }
        }
    }
    FileSplit fileSplit = new FileSplit(fullDir, ALLOWED_FORMATS, rng);
    BalancedPathFilter pathFilter = new BalancedPathFilter(rng, ALLOWED_FORMATS, labelGenerator, numExamples,
                    numLabels, 0, batchSize, null);
    inputSplit = fileSplit.sample(pathFilter, numExamples * splitTrainTest, numExamples * (1 - splitTrainTest));
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testReader() throws Exception {
    TfidfVectorizer vectorizer = new TfidfVectorizer();
    Configuration conf = new Configuration();
    conf.setInt(TfidfVectorizer.MIN_WORD_FREQUENCY, 1);
    conf.setBoolean(RecordReader.APPEND_LABEL, true);
    vectorizer.initialize(conf);
    TfidfRecordReader reader = new TfidfRecordReader();
    reader.initialize(conf, new FileSplit(new ClassPathResource("labeled").getFile()));
    int count = 0;
    int[] labelAssertions = new int[3];
    while (reader.hasNext()) {
        Collection<Writable> record = reader.next();
        Iterator<Writable> recordIter = record.iterator();
        NDArrayWritable writable = (NDArrayWritable) recordIter.next();
        labelAssertions[count] = recordIter.next().toInt();
        count++;
    }

    assertArrayEquals(new int[] {0, 1, 2}, labelAssertions);
    assertEquals(3, reader.getLabels().size());
    assertEquals(3, count);
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testRecordMetaData() throws Exception {
    TfidfVectorizer vectorizer = new TfidfVectorizer();
    Configuration conf = new Configuration();
    conf.setInt(TfidfVectorizer.MIN_WORD_FREQUENCY, 1);
    conf.setBoolean(RecordReader.APPEND_LABEL, true);
    vectorizer.initialize(conf);
    TfidfRecordReader reader = new TfidfRecordReader();
    reader.initialize(conf, new FileSplit(new ClassPathResource("labeled").getFile()));

    while (reader.hasNext()) {
        Record record = reader.nextRecord();
        assertNotNull(record.getMetaData().getURI());
        assertEquals(record.getMetaData().getReaderClass(), TfidfRecordReader.class);
    }
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testReadRecordFromMetaData() throws Exception {
    TfidfVectorizer vectorizer = new TfidfVectorizer();
    Configuration conf = new Configuration();
    conf.setInt(TfidfVectorizer.MIN_WORD_FREQUENCY, 1);
    conf.setBoolean(RecordReader.APPEND_LABEL, true);
    vectorizer.initialize(conf);
    TfidfRecordReader reader = new TfidfRecordReader();
    reader.initialize(conf, new FileSplit(new ClassPathResource("labeled").getFile()));

    Record record = reader.nextRecord();

    Record reread = reader.loadFromMetaData(record.getMetaData());

    assertEquals(record.getRecord().size(), 2);
    assertEquals(reread.getRecord().size(), 2);
    assertEquals(record.getRecord().get(0), reread.getRecord().get(0));
    assertEquals(record.getRecord().get(1), reread.getRecord().get(1));
    assertEquals(record.getMetaData(), reread.getMetaData());
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testCodecReader() throws Exception {
    File file = new ClassPathResource("fire_lowres.mp4").getFile();
    SequenceRecordReader reader = new CodecRecordReader();
    Configuration conf = new Configuration();
    conf.set(CodecRecordReader.RAVEL, "true");
    conf.set(CodecRecordReader.START_FRAME, "160");
    conf.set(CodecRecordReader.TOTAL_FRAMES, "500");
    conf.set(CodecRecordReader.ROWS, "80");
    conf.set(CodecRecordReader.COLUMNS, "46");
    reader.initialize(new FileSplit(file));
    reader.setConf(conf);
    assertTrue(reader.hasNext());
    List<List<Writable>> record = reader.sequenceRecord();
    //        System.out.println(record.size());

    Iterator<List<Writable>> it = record.iterator();
    List<Writable> first = it.next();
    //        System.out.println(first);

    //Expected size: 80x46x3
    assertEquals(1, first.size());
    assertEquals(80 * 46 * 3, ((ArrayWritable) first.iterator().next()).length());
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testCodecReaderMeta() throws Exception {
    File file = new ClassPathResource("fire_lowres.mp4").getFile();
    SequenceRecordReader reader = new CodecRecordReader();
    Configuration conf = new Configuration();
    conf.set(CodecRecordReader.RAVEL, "true");
    conf.set(CodecRecordReader.START_FRAME, "160");
    conf.set(CodecRecordReader.TOTAL_FRAMES, "500");
    conf.set(CodecRecordReader.ROWS, "80");
    conf.set(CodecRecordReader.COLUMNS, "46");
    reader.initialize(new FileSplit(file));
    reader.setConf(conf);
    assertTrue(reader.hasNext());
    List<List<Writable>> record = reader.sequenceRecord();
    assertEquals(500, record.size()); //500 frames

    reader.reset();
    SequenceRecord seqR = reader.nextSequence();
    assertEquals(record, seqR.getSequenceRecord());
    RecordMetaData meta = seqR.getMetaData();
    //        System.out.println(meta);
    assertTrue(meta.getURI().toString().endsWith("fire_lowres.mp4"));

    SequenceRecord fromMeta = reader.loadSequenceFromMetaData(meta);
    assertEquals(seqR, fromMeta);
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Ignore
@Test
public void testNativeCodecReader() throws Exception {
    File file = new ClassPathResource("fire_lowres.mp4").getFile();
    SequenceRecordReader reader = new NativeCodecRecordReader();
    Configuration conf = new Configuration();
    conf.set(CodecRecordReader.RAVEL, "true");
    conf.set(CodecRecordReader.START_FRAME, "160");
    conf.set(CodecRecordReader.TOTAL_FRAMES, "500");
    conf.set(CodecRecordReader.ROWS, "80");
    conf.set(CodecRecordReader.COLUMNS, "46");
    reader.initialize(new FileSplit(file));
    reader.setConf(conf);
    assertTrue(reader.hasNext());
    List<List<Writable>> record = reader.sequenceRecord();
    //        System.out.println(record.size());

    Iterator<List<Writable>> it = record.iterator();
    List<Writable> first = it.next();
    //        System.out.println(first);

    //Expected size: 80x46x3
    assertEquals(1, first.size());
    assertEquals(80 * 46 * 3, ((ArrayWritable) first.iterator().next()).length());
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void simpleTransformTest() throws Exception {
    Schema schema = new Schema.Builder().addColumnDouble("0").addColumnDouble("1").addColumnDouble("2")
                    .addColumnDouble("3").addColumnDouble("4").build();
    TransformProcess transformProcess = new TransformProcess.Builder(schema).removeColumns("0").build();
    CSVRecordReader csvRecordReader = new CSVRecordReader();
    csvRecordReader.initialize(new FileSplit(new ClassPathResource("iris.dat").getFile()));
    TransformProcessRecordReader transformProcessRecordReader =
                    new TransformProcessRecordReader(csvRecordReader, transformProcess);
    assertEquals(4, transformProcessRecordReader.next().size());

}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testRegexLineRecordReader() 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<Writable> exp0 = Arrays.asList((Writable) new Text("2016-01-01 23:59:59.001"), new Text("1"),
                    new Text("DEBUG"), new Text("First entry message!"));
    List<Writable> exp1 = Arrays.asList((Writable) new Text("2016-01-01 23:59:59.002"), new Text("2"),
                    new Text("INFO"), new Text("Second entry message!"));
    List<Writable> exp2 = Arrays.asList((Writable) new Text("2016-01-01 23:59:59.003"), new Text("3"),
                    new Text("WARN"), new Text("Third entry message!"));
    assertEquals(exp0, rr.next());
    assertEquals(exp1, rr.next());
    assertEquals(exp2, rr.next());
    assertFalse(rr.hasNext());

    //Test reset:
    rr.reset();
    assertEquals(exp0, rr.next());
    assertEquals(exp1, rr.next());
    assertEquals(exp2, rr.next());
    assertFalse(rr.hasNext());
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testReset() throws Exception {
    CSVRecordReader rr = new CSVRecordReader(0, ',');
    rr.initialize(new FileSplit(new ClassPathResource("iris.dat").getFile()));

    int nResets = 5;
    for (int i = 0; i < nResets; i++) {

        int lineCount = 0;
        while (rr.hasNext()) {
            List<Writable> line = rr.next();
            assertEquals(5, line.size());
            lineCount++;
        }
        assertFalse(rr.hasNext());
        assertEquals(150, lineCount);
        rr.reset();
    }
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testResetWithSkipLines() throws Exception {
    CSVRecordReader rr = new CSVRecordReader(10, ',');
    rr.initialize(new FileSplit(new ClassPathResource("iris.dat").getFile()));
    int lineCount = 0;
    while (rr.hasNext()) {
        rr.next();
        ++lineCount;
    }
    assertEquals(140, lineCount);
    rr.reset();
    lineCount = 0;
    while (rr.hasNext()) {
        rr.next();
        ++lineCount;
    }
    assertEquals(140, lineCount);
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test(expected = NoSuchElementException.class)
public void testCsvSkipAllLines() throws IOException, InterruptedException {
    final int numLines = 4;
    final List<Writable> lineList = Arrays.asList((Writable) new IntWritable(numLines - 1),
                    (Writable) new Text("one"), (Writable) new Text("two"), (Writable) new Text("three"));
    String header = ",one,two,three";
    List<String> lines = new ArrayList<>();
    for (int i = 0; i < numLines; i++)
        lines.add(Integer.toString(i) + header);
    File tempFile = File.createTempFile("csvSkipLines", ".csv");
    FileUtils.writeLines(tempFile, lines);

    CSVRecordReader rr = new CSVRecordReader(numLines, ',');
    rr.initialize(new FileSplit(tempFile));
    rr.reset();
    assertTrue(!rr.hasNext());
    rr.next();
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testCsvSkipAllButOneLine() throws IOException, InterruptedException {
    final int numLines = 4;
    final List<Writable> lineList = Arrays.<Writable>asList(new Text(Integer.toString(numLines - 1)),
            new Text("one"), new Text("two"), new Text("three"));
    String header = ",one,two,three";
    List<String> lines = new ArrayList<>();
    for (int i = 0; i < numLines; i++)
        lines.add(Integer.toString(i) + header);
    File tempFile = File.createTempFile("csvSkipLines", ".csv");
    FileUtils.writeLines(tempFile, lines);

    CSVRecordReader rr = new CSVRecordReader(numLines - 1, ',');
    rr.initialize(new FileSplit(tempFile));
    rr.reset();
    assertTrue(rr.hasNext());
    assertEquals(rr.next(), lineList);
}
 

import org.datavec.api.split.FileSplit; //导入依赖的package包/类
@Test
public void testNextRecord() throws IOException, InterruptedException {
    SVMLightRecordReader rr = new SVMLightRecordReader();
    Configuration config = new Configuration();
    config.setBoolean(SVMLightRecordReader.ZERO_BASED_INDEXING, false);
    config.setInt(SVMLightRecordReader.NUM_FEATURES, 10);
    config.setBoolean(SVMLightRecordReader.APPEND_LABEL, false);
    rr.initialize(config, new FileSplit(new ClassPathResource("svmlight/basic.txt").getFile()));

    Record record = rr.nextRecord();
    List<Writable> recordList = record.getRecord();
    assertEquals(new DoubleWritable(1.0), recordList.get(1));
    assertEquals(new DoubleWritable(3.0), recordList.get(5));
    assertEquals(new DoubleWritable(4.0), recordList.get(7));

    record = rr.nextRecord();
    recordList = record.getRecord();
    assertEquals(new DoubleWritable(0.1), recordList.get(0));
    assertEquals(new DoubleWritable(6.6), recordList.get(5));
    assertEquals(new DoubleWritable(80.0), recordList.get(7));
}