Package org.apache.sysds.runtime.instructions.spark.utils

Class RDDConverterUtils

java.lang.Object

org.apache.sysds.runtime.instructions.spark.utils.RDDConverterUtils

public class RDDConverterUtils
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	RDDConverterUtils.BinaryCellToBinaryBlockFunction
static class	RDDConverterUtils.DataFrameExtractIDFunction

Field Summary

Fields

Modifier and Type	Field	Description
static String	DF_ID_COLUMN

Constructor Summary

Constructors

Constructor	Description
RDDConverterUtils()

Method Summary

Modifier and Type	Method	Description
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	binaryBlockToBinaryBlock(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mcIn, DataCharacteristics mcOut)
static org.apache.spark.api.java.JavaRDD<String>	binaryBlockToCsv(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mcIn, FileFormatPropertiesCSV props, boolean strict)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	binaryBlockToDataFrame(org.apache.spark.sql.SparkSession sparkSession, org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mc, boolean toVector)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	binaryBlockToDataFrame(org.apache.spark.sql.SQLContext sqlContext, org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mc, boolean toVector)	Deprecated.
static org.apache.spark.api.java.JavaRDD<org.apache.spark.ml.feature.LabeledPoint>	binaryBlockToLabeledPoints(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in)	Converter from binary block rdd to rdd of labeled points.
static org.apache.spark.api.java.JavaRDD<String>	binaryBlockToLibsvm(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mcIn, FileFormatPropertiesLIBSVM props, boolean strict)
static org.apache.spark.api.java.JavaRDD<String>	binaryBlockToTextCell(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in, DataCharacteristics mc)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	binaryCellToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input, DataCharacteristics mcOut, boolean outputEmptyBlocks)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	csvToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input, DataCharacteristics mc, boolean hasHeader, String delim, boolean fill, double fillValue, Set<String> naStrings)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	csvToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.api.java.JavaRDD<String> input, DataCharacteristics mcOut, boolean hasHeader, String delim, boolean fill, double fillValue, Set<String> naStrings)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	dataFrameToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> df, DataCharacteristics mc, boolean containsID, boolean isVector)
static void	libsvmToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, String pathIn, String pathX, String pathY, DataCharacteristics mcOutX)	Converts a libsvm text input file into two binary block matrices for features and labels, and saves these to the specified output files.
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	libsvmToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input, DataCharacteristics mc, String delim, String indexDelim)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	matrixBlockToAlignedMatrixBlock(org.apache.spark.api.java.JavaPairRDD<Long,MatrixBlock> input, DataCharacteristics mcIn, DataCharacteristics mcOut)
static org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text>	stringToSerializableText(org.apache.spark.api.java.JavaPairRDD<Long,String> in)
static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock>	textCellToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc, org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input, DataCharacteristics mcOut, boolean outputEmptyBlocks, FileFormatPropertiesMM mmProps)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

DF_ID_COLUMN

public static final String DF_ID_COLUMN

See Also:

Constant Field Values

Constructor Detail

RDDConverterUtils

public RDDConverterUtils()

Method Detail

textCellToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> textCellToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                           org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input,
                                                                                                           DataCharacteristics mcOut,
                                                                                                           boolean outputEmptyBlocks,
                                                                                                           FileFormatPropertiesMM mmProps)

binaryCellToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> binaryCellToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                             org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixCell> input,
                                                                                                             DataCharacteristics mcOut,
                                                                                                             boolean outputEmptyBlocks)

binaryBlockToLabeledPoints

public static org.apache.spark.api.java.JavaRDD<org.apache.spark.ml.feature.LabeledPoint> binaryBlockToLabeledPoints(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in)

Converter from binary block rdd to rdd of labeled points. Note that the input needs to be reblocked to satisfy the 'clen <= blen' constraint.

Parameters:

in - matrix as JavaPairRDD<MatrixIndexes, MatrixBlock>

Returns:

JavaRDD of labeled points

binaryBlockToTextCell

public static org.apache.spark.api.java.JavaRDD<String> binaryBlockToTextCell(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                              DataCharacteristics mc)

binaryBlockToCsv

public static org.apache.spark.api.java.JavaRDD<String> binaryBlockToCsv(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                         DataCharacteristics mcIn,
                                                                         FileFormatPropertiesCSV props,
                                                                         boolean strict)

binaryBlockToLibsvm

public static org.apache.spark.api.java.JavaRDD<String> binaryBlockToLibsvm(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                            DataCharacteristics mcIn,
                                                                            FileFormatPropertiesLIBSVM props,
                                                                            boolean strict)

binaryBlockToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> binaryBlockToBinaryBlock(org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                                                              DataCharacteristics mcIn,
                                                                                                              DataCharacteristics mcOut)

csvToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> csvToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                      org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input,
                                                                                                      DataCharacteristics mc,
                                                                                                      boolean hasHeader,
                                                                                                      String delim,
                                                                                                      boolean fill,
                                                                                                      double fillValue,
                                                                                                      Set<String> naStrings)

csvToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> csvToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                      org.apache.spark.api.java.JavaRDD<String> input,
                                                                                                      DataCharacteristics mcOut,
                                                                                                      boolean hasHeader,
                                                                                                      String delim,
                                                                                                      boolean fill,
                                                                                                      double fillValue,
                                                                                                      Set<String> naStrings)

dataFrameToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> dataFrameToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                            org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> df,
                                                                                                            DataCharacteristics mc,
                                                                                                            boolean containsID,
                                                                                                            boolean isVector)

binaryBlockToDataFrame

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> binaryBlockToDataFrame(org.apache.spark.sql.SparkSession sparkSession,
                                                                                            org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                                            DataCharacteristics mc,
                                                                                            boolean toVector)

binaryBlockToDataFrame

@Deprecated
public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> binaryBlockToDataFrame(org.apache.spark.sql.SQLContext sqlContext,
                                                                                            org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> in,
                                                                                            DataCharacteristics mc,
                                                                                            boolean toVector)

Deprecated.

libsvmToBinaryBlock

public static void libsvmToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                       String pathIn,
                                       String pathX,
                                       String pathY,
                                       DataCharacteristics mcOutX)

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.

Note: We use org.apache.spark.mllib.util.MLUtils.loadLibSVMFile for parsing the libsvm input files in order to ensure consistency with Spark.

Parameters:

sc - java spark context

pathIn - path to libsvm input file

pathX - path to binary block output file of features

pathY - path to binary block output file of labels

mcOutX - matrix characteristics of output matrix X

matrixBlockToAlignedMatrixBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> matrixBlockToAlignedMatrixBlock(org.apache.spark.api.java.JavaPairRDD<Long,MatrixBlock> input,
                                                                                                                     DataCharacteristics mcIn,
                                                                                                                     DataCharacteristics mcOut)

stringToSerializableText

public static org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> stringToSerializableText(org.apache.spark.api.java.JavaPairRDD<Long,String> in)

libsvmToBinaryBlock

public static org.apache.spark.api.java.JavaPairRDD<MatrixIndexes,MatrixBlock> libsvmToBinaryBlock(org.apache.spark.api.java.JavaSparkContext sc,
                                                                                                         org.apache.spark.api.java.JavaPairRDD<org.apache.hadoop.io.LongWritable,org.apache.hadoop.io.Text> input,
                                                                                                         DataCharacteristics mc,
                                                                                                         String delim,
                                                                                                         String indexDelim)