Java Code Examples for org.apache.spark.api.java.JavaPairRDD#saveAsHadoopFile()

@SuppressWarnings("unchecked")
public static long writeRDDtoHDFS( RDDObject rdd, String path, OutputInfo oinfo )
{
	JavaPairRDD<MatrixIndexes,MatrixBlock> lrdd = (JavaPairRDD<MatrixIndexes, MatrixBlock>) rdd.getRDD();

	//piggyback nnz maintenance on write
	LongAccumulator aNnz = getSparkContextStatic().sc().longAccumulator("nnz");
	lrdd = lrdd.mapValues(new ComputeBinaryBlockNnzFunction(aNnz));

	//save file is an action which also triggers nnz maintenance
	lrdd.saveAsHadoopFile(path,
			oinfo.outputKeyClass,
			oinfo.outputValueClass,
			oinfo.outputFormatClass);

	//return nnz aggregate of all blocks
	return aNnz.value();
}
 

@SuppressWarnings("unchecked")
public static void writeFrameRDDtoHDFS( RDDObject rdd, String path, OutputInfo oinfo )
{
	JavaPairRDD<?, FrameBlock> lrdd = (JavaPairRDD<Long, FrameBlock>) rdd.getRDD();

	//convert keys to writables if necessary
	if( oinfo == OutputInfo.BinaryBlockOutputInfo ) {
		lrdd = ((JavaPairRDD<Long, FrameBlock>)lrdd).mapToPair(
				new LongFrameToLongWritableFrameFunction());
		oinfo = OutputInfo.BinaryBlockFrameOutputInfo;
	}

	//save file is an action which also triggers nnz maintenance
	lrdd.saveAsHadoopFile(path,
			oinfo.outputKeyClass,
			oinfo.outputValueClass,
			oinfo.outputFormatClass);
}
 

@SuppressWarnings("unchecked")
public static long writeMatrixRDDtoHDFS( RDDObject rdd, String path, FileFormat fmt )
{
	JavaPairRDD<MatrixIndexes,MatrixBlock> lrdd = (JavaPairRDD<MatrixIndexes, MatrixBlock>) rdd.getRDD();
	InputOutputInfo oinfo = InputOutputInfo.get(DataType.MATRIX, fmt);
	
	//piggyback nnz maintenance on write
	LongAccumulator aNnz = getSparkContextStatic().sc().longAccumulator("nnz");
	lrdd = lrdd.mapValues(new ComputeBinaryBlockNnzFunction(aNnz));

	//save file is an action which also triggers nnz maintenance
	lrdd.saveAsHadoopFile(path,
		oinfo.keyClass,
		oinfo.valueClass,
		oinfo.outputFormatClass);

	//return nnz aggregate of all blocks
	return aNnz.value();
}
 

@SuppressWarnings("unchecked")
public static void writeFrameRDDtoHDFS( RDDObject rdd, String path, FileFormat fmt)
{
	JavaPairRDD<?, FrameBlock> lrdd = (JavaPairRDD<Long, FrameBlock>) rdd.getRDD();
	InputOutputInfo oinfo = InputOutputInfo.get(DataType.FRAME, fmt);
	
	//convert keys to writables if necessary
	if( fmt == FileFormat.BINARY ) {
		lrdd = ((JavaPairRDD<Long, FrameBlock>)lrdd).mapToPair(
				new LongFrameToLongWritableFrameFunction());
	}

	//save file is an action which also triggers nnz maintenance
	lrdd.saveAsHadoopFile(path,
		oinfo.keyClass,
		oinfo.valueClass,
		oinfo.outputFormatClass);
}
 

protected static void run(JavaSparkContext sparkContext) {
    JavaPairRDD<Text, IntWritable> javaPairRDD = sparkContext.sequenceFile("url", Text.class, IntWritable.class);
    JavaPairRDD<String, Integer> pairRDD = javaPairRDD.mapToPair(new sequenceToConvert());
    //写
    pairRDD.saveAsHadoopFile("url",Text.class,IntWritable.class,SequenceFileOutputFormat.class);
}
 

/**
 * Converts a libsvm text input file into two binary block matrices for features 
 * and labels, and saves these to the specified output files. This call also deletes 
 * existing files at the specified output locations, as well as determines and 
 * writes the meta data files of both output matrices. 
 * <p>
 * Note: We use {@code org.apache.spark.mllib.util.MLUtils.loadLibSVMFile} for parsing 
 * the libsvm input files in order to ensure consistency with Spark.
 * 
 * @param sc java spark context
 * @param pathIn path to libsvm input file
 * @param pathX path to binary block output file of features
 * @param pathY path to binary block output file of labels
 * @param mcOutX matrix characteristics of output matrix X
 */
public static void libsvmToBinaryBlock(JavaSparkContext sc, String pathIn, 
		String pathX, String pathY, DataCharacteristics mcOutX)
{
	if( !mcOutX.dimsKnown() )
		throw new DMLRuntimeException("Matrix characteristics "
			+ "required to convert sparse input representation.");
	try {
		//cleanup existing output files
		HDFSTool.deleteFileIfExistOnHDFS(pathX);
		HDFSTool.deleteFileIfExistOnHDFS(pathY);
		
		//convert libsvm to labeled points
		int numFeatures = (int) mcOutX.getCols();
		int numPartitions = SparkUtils.getNumPreferredPartitions(mcOutX, null);
		JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> lpoints = 
				MLUtils.loadLibSVMFile(sc.sc(), pathIn, numFeatures, numPartitions).toJavaRDD();
		
		//append row index and best-effort caching to avoid repeated text parsing
		JavaPairRDD<org.apache.spark.mllib.regression.LabeledPoint,Long> ilpoints = 
				lpoints.zipWithIndex().persist(StorageLevel.MEMORY_AND_DISK()); 
		
		//extract labels and convert to binary block
		DataCharacteristics mc1 = new MatrixCharacteristics(mcOutX.getRows(), 1, mcOutX.getBlocksize(), -1);
		LongAccumulator aNnz1 = sc.sc().longAccumulator("nnz");
		JavaPairRDD<MatrixIndexes,MatrixBlock> out1 = ilpoints
				.mapPartitionsToPair(new LabeledPointToBinaryBlockFunction(mc1, true, aNnz1));
		int numPartitions2 = SparkUtils.getNumPreferredPartitions(mc1, null);
		out1 = RDDAggregateUtils.mergeByKey(out1, numPartitions2, false);
		out1.saveAsHadoopFile(pathY, MatrixIndexes.class, MatrixBlock.class, SequenceFileOutputFormat.class);
		mc1.setNonZeros(aNnz1.value()); //update nnz after triggered save
		HDFSTool.writeMetaDataFile(pathY+".mtd", ValueType.FP64, mc1, OutputInfo.BinaryBlockOutputInfo);
		
		//extract data and convert to binary block
		DataCharacteristics mc2 = new MatrixCharacteristics(mcOutX.getRows(), mcOutX.getCols(), mcOutX.getBlocksize(), -1);
		LongAccumulator aNnz2 = sc.sc().longAccumulator("nnz");
		JavaPairRDD<MatrixIndexes,MatrixBlock> out2 = ilpoints
				.mapPartitionsToPair(new LabeledPointToBinaryBlockFunction(mc2, false, aNnz2));
		out2 = RDDAggregateUtils.mergeByKey(out2, numPartitions, false);
		out2.saveAsHadoopFile(pathX, MatrixIndexes.class, MatrixBlock.class, SequenceFileOutputFormat.class);
		mc2.setNonZeros(aNnz2.value()); //update nnz after triggered save
		HDFSTool.writeMetaDataFile(pathX+".mtd", ValueType.FP64, mc2, OutputInfo.BinaryBlockOutputInfo);
		
		//asynchronous cleanup of cached intermediates
		ilpoints.unpersist(false);
	}
	catch(IOException ex) {
		throw new DMLRuntimeException(ex);
	}
}
 

/**
 * Converts a libsvm text input file into two binary block matrices for features 
 * and labels, and saves these to the specified output files. This call also deletes 
 * existing files at the specified output locations, as well as determines and 
 * writes the meta data files of both output matrices. 
 * <p>
 * Note: We use {@code org.apache.spark.mllib.util.MLUtils.loadLibSVMFile} for parsing 
 * the libsvm input files in order to ensure consistency with Spark.
 * 
 * @param sc java spark context
 * @param pathIn path to libsvm input file
 * @param pathX path to binary block output file of features
 * @param pathY path to binary block output file of labels
 * @param mcOutX matrix characteristics of output matrix X
 */
public static void libsvmToBinaryBlock(JavaSparkContext sc, String pathIn, 
		String pathX, String pathY, DataCharacteristics mcOutX)
{
	if( !mcOutX.dimsKnown() )
		throw new DMLRuntimeException("Matrix characteristics "
			+ "required to convert sparse input representation.");
	try {
		//cleanup existing output files
		HDFSTool.deleteFileIfExistOnHDFS(pathX);
		HDFSTool.deleteFileIfExistOnHDFS(pathY);
		
		//convert libsvm to labeled points
		int numFeatures = (int) mcOutX.getCols();
		int numPartitions = SparkUtils.getNumPreferredPartitions(mcOutX, null);
		JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> lpoints = 
				MLUtils.loadLibSVMFile(sc.sc(), pathIn, numFeatures, numPartitions).toJavaRDD();
		
		//append row index and best-effort caching to avoid repeated text parsing
		JavaPairRDD<org.apache.spark.mllib.regression.LabeledPoint,Long> ilpoints = 
				lpoints.zipWithIndex().persist(StorageLevel.MEMORY_AND_DISK()); 
		
		//extract labels and convert to binary block
		DataCharacteristics mc1 = new MatrixCharacteristics(mcOutX.getRows(), 1, mcOutX.getBlocksize(), -1);
		LongAccumulator aNnz1 = sc.sc().longAccumulator("nnz");
		JavaPairRDD<MatrixIndexes,MatrixBlock> out1 = ilpoints
				.mapPartitionsToPair(new LabeledPointToBinaryBlockFunction(mc1, true, aNnz1));
		int numPartitions2 = SparkUtils.getNumPreferredPartitions(mc1, null);
		out1 = RDDAggregateUtils.mergeByKey(out1, numPartitions2, false);
		out1.saveAsHadoopFile(pathY, MatrixIndexes.class, MatrixBlock.class, SequenceFileOutputFormat.class);
		mc1.setNonZeros(aNnz1.value()); //update nnz after triggered save
		HDFSTool.writeMetaDataFile(pathY+".mtd", ValueType.FP64, mc1, FileFormat.BINARY);
		
		//extract data and convert to binary block
		DataCharacteristics mc2 = new MatrixCharacteristics(mcOutX.getRows(), mcOutX.getCols(), mcOutX.getBlocksize(), -1);
		LongAccumulator aNnz2 = sc.sc().longAccumulator("nnz");
		JavaPairRDD<MatrixIndexes,MatrixBlock> out2 = ilpoints
				.mapPartitionsToPair(new LabeledPointToBinaryBlockFunction(mc2, false, aNnz2));
		out2 = RDDAggregateUtils.mergeByKey(out2, numPartitions, false);
		out2.saveAsHadoopFile(pathX, MatrixIndexes.class, MatrixBlock.class, SequenceFileOutputFormat.class);
		mc2.setNonZeros(aNnz2.value()); //update nnz after triggered save
		HDFSTool.writeMetaDataFile(pathX+".mtd", ValueType.FP64, mc2, FileFormat.BINARY);
		
		//asynchronous cleanup of cached intermediates
		ilpoints.unpersist(false);
	}
	catch(IOException ex) {
		throw new DMLRuntimeException(ex);
	}
}