Examples with Tuple2 scala.Tuple2 used on opensource projects

Example 21 with Tuple2

use of scala.Tuple2 in project learning-spark by databricks.

the class BasicSaveSequenceFile method main.

public static void main(String[] args) throws Exception {
    if (args.length != 2) {
        throw new Exception("Usage BasicSaveSequenceFile [sparkMaster] [output]");
    }
    String master = args[0];
    String fileName = args[1];
    JavaSparkContext sc = new JavaSparkContext(master, "basicloadsequencefile", System.getenv("SPARK_HOME"), System.getenv("JARS"));
    List<Tuple2<String, Integer>> input = new ArrayList();
    input.add(new Tuple2("coffee", 1));
    input.add(new Tuple2("coffee", 2));
    input.add(new Tuple2("pandas", 3));
    JavaPairRDD<String, Integer> rdd = sc.parallelizePairs(input);
    JavaPairRDD<Text, IntWritable> result = rdd.mapToPair(new ConvertToWritableTypes());
    result.saveAsHadoopFile(fileName, Text.class, IntWritable.class, SequenceFileOutputFormat.class);
}

Example 22 with Tuple2

use of scala.Tuple2 in project learning-spark by databricks.

the class BasicJoinCsv method run.

public void run(String master, String csv1, String csv2) throws Exception {
    JavaSparkContext sc = new JavaSparkContext(master, "basicjoincsv", System.getenv("SPARK_HOME"), System.getenv("JARS"));
    JavaRDD<String> csvFile1 = sc.textFile(csv1);
    JavaRDD<String> csvFile2 = sc.textFile(csv2);
    JavaPairRDD<Integer, String[]> keyedRDD1 = csvFile1.mapToPair(new ParseLine());
    JavaPairRDD<Integer, String[]> keyedRDD2 = csvFile1.mapToPair(new ParseLine());
    JavaPairRDD<Integer, Tuple2<String[], String[]>> result = keyedRDD1.join(keyedRDD2);
    List<Tuple2<Integer, Tuple2<String[], String[]>>> resultCollection = result.collect();
}

Example 23 with Tuple2

use of scala.Tuple2 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 24 with Tuple2

use of scala.Tuple2 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 25 with Tuple2

use of scala.Tuple2 in project deeplearning4j by deeplearning4j.

the class BaseVaeScoreWithKeyFunctionAdapter method call.

@Override
public Iterable<Tuple2<K, Double>> call(Iterator<Tuple2<K, INDArray>> iterator) throws Exception {
    if (!iterator.hasNext()) {
        return Collections.emptyList();
    }
    VariationalAutoencoder vae = getVaeLayer();
    List<Tuple2<K, Double>> ret = new ArrayList<>();
    List<INDArray> collect = new ArrayList<>(batchSize);
    List<K> collectKey = new ArrayList<>(batchSize);
    int totalCount = 0;
    while (iterator.hasNext()) {
        collect.clear();
        collectKey.clear();
        int nExamples = 0;
        while (iterator.hasNext() && nExamples < batchSize) {
            Tuple2<K, INDArray> t2 = iterator.next();
            INDArray features = t2._2();
            int n = features.size(0);
            if (n != 1)
                throw new IllegalStateException("Cannot score examples with one key per data set if " + "data set contains more than 1 example (numExamples: " + n + ")");
            collect.add(features);
            collectKey.add(t2._1());
            nExamples += n;
        }
        totalCount += nExamples;
        INDArray toScore = Nd4j.vstack(collect);
        INDArray scores = computeScore(vae, toScore);
        double[] doubleScores = scores.data().asDouble();
        for (int i = 0; i < doubleScores.length; i++) {
            ret.add(new Tuple2<>(collectKey.get(i), doubleScores[i]));
        }
    }
    if (Nd4j.getExecutioner() instanceof GridExecutioner)
        ((GridExecutioner) Nd4j.getExecutioner()).flushQueueBlocking();
    if (log.isDebugEnabled()) {
        log.debug("Scored {} examples ", totalCount);
    }
    return ret;
}