Examples with JavaPairRDD org.apache.spark.api.java.JavaPairRDD used on opensource projects

Example 91 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class MultiReturnParameterizedBuiltinSPInstruction method processInstruction.

@Override
@SuppressWarnings("unchecked")
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    try {
        // get input RDD and meta data
        FrameObject fo = sec.getFrameObject(input1.getName());
        FrameObject fometa = sec.getFrameObject(_outputs.get(1).getName());
        JavaPairRDD<Long, FrameBlock> in = (JavaPairRDD<Long, FrameBlock>) sec.getRDDHandleForFrameObject(fo, InputInfo.BinaryBlockInputInfo);
        String spec = ec.getScalarInput(input2.getName(), input2.getValueType(), input2.isLiteral()).getStringValue();
        MatrixCharacteristics mcIn = sec.getMatrixCharacteristics(input1.getName());
        MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
        String[] colnames = !TfMetaUtils.isIDSpec(spec) ? in.lookup(1L).get(0).getColumnNames() : null;
        // step 1: build transform meta data
        Encoder encoderBuild = EncoderFactory.createEncoder(spec, colnames, fo.getSchema(), (int) fo.getNumColumns(), null);
        MaxLongAccumulator accMax = registerMaxLongAccumulator(sec.getSparkContext());
        JavaRDD<String> rcMaps = in.mapPartitionsToPair(new TransformEncodeBuildFunction(encoderBuild)).distinct().groupByKey().flatMap(new TransformEncodeGroupFunction(accMax));
        if (containsMVImputeEncoder(encoderBuild)) {
            EncoderMVImpute mva = getMVImputeEncoder(encoderBuild);
            rcMaps = rcMaps.union(in.mapPartitionsToPair(new TransformEncodeBuild2Function(mva)).groupByKey().flatMap(new TransformEncodeGroup2Function(mva)));
        }
        // trigger eval
        rcMaps.saveAsTextFile(fometa.getFileName());
        // consolidate meta data frame (reuse multi-threaded reader, special handling missing values)
        FrameReader reader = FrameReaderFactory.createFrameReader(InputInfo.TextCellInputInfo);
        FrameBlock meta = reader.readFrameFromHDFS(fometa.getFileName(), accMax.value(), fo.getNumColumns());
        // recompute num distinct items per column
        meta.recomputeColumnCardinality();
        meta.setColumnNames((colnames != null) ? colnames : meta.getColumnNames());
        // step 2: transform apply (similar to spark transformapply)
        // compute omit offset map for block shifts
        TfOffsetMap omap = null;
        if (TfMetaUtils.containsOmitSpec(spec, colnames)) {
            omap = new TfOffsetMap(SparkUtils.toIndexedLong(in.mapToPair(new RDDTransformApplyOffsetFunction(spec, colnames)).collect()));
        }
        // create encoder broadcast (avoiding replication per task)
        Encoder encoder = EncoderFactory.createEncoder(spec, colnames, fo.getSchema(), (int) fo.getNumColumns(), meta);
        mcOut.setDimension(mcIn.getRows() - ((omap != null) ? omap.getNumRmRows() : 0), encoder.getNumCols());
        Broadcast<Encoder> bmeta = sec.getSparkContext().broadcast(encoder);
        Broadcast<TfOffsetMap> bomap = (omap != null) ? sec.getSparkContext().broadcast(omap) : null;
        // execute transform apply
        JavaPairRDD<Long, FrameBlock> tmp = in.mapToPair(new RDDTransformApplyFunction(bmeta, bomap));
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = FrameRDDConverterUtils.binaryBlockToMatrixBlock(tmp, mcOut, mcOut);
        // set output and maintain lineage/output characteristics
        sec.setRDDHandleForVariable(_outputs.get(0).getName(), out);
        sec.addLineageRDD(_outputs.get(0).getName(), input1.getName());
        sec.setFrameOutput(_outputs.get(1).getName(), meta);
    } catch (IOException ex) {
        throw new RuntimeException(ex);
    }
}

Example 92 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class ReblockSPInstruction method processMatrixReblockInstruction.

@SuppressWarnings("unchecked")
protected void processMatrixReblockInstruction(SparkExecutionContext sec, InputInfo iinfo) {
    MatrixObject mo = sec.getMatrixObject(input1.getName());
    MatrixCharacteristics mc = sec.getMatrixCharacteristics(input1.getName());
    MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
    if (iinfo == InputInfo.TextCellInputInfo || iinfo == InputInfo.MatrixMarketInputInfo) {
        // get the input textcell rdd
        JavaPairRDD<LongWritable, Text> lines = (JavaPairRDD<LongWritable, Text>) sec.getRDDHandleForVariable(input1.getName(), iinfo);
        // convert textcell to binary block
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = RDDConverterUtils.textCellToBinaryBlock(sec.getSparkContext(), lines, mcOut, outputEmptyBlocks);
        // put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else if (iinfo == InputInfo.CSVInputInfo) {
        // HACK ALERT: Until we introduces the rewrite to insert csvrblock for non-persistent read
        // throw new DMLRuntimeException("CSVInputInfo is not supported for ReblockSPInstruction");
        CSVReblockSPInstruction csvInstruction = null;
        boolean hasHeader = false;
        String delim = ",";
        boolean fill = false;
        double fillValue = 0;
        if (mo.getFileFormatProperties() instanceof CSVFileFormatProperties && mo.getFileFormatProperties() != null) {
            CSVFileFormatProperties props = (CSVFileFormatProperties) mo.getFileFormatProperties();
            hasHeader = props.hasHeader();
            delim = props.getDelim();
            fill = props.isFill();
            fillValue = props.getFillValue();
        }
        csvInstruction = new CSVReblockSPInstruction(null, input1, output, mcOut.getRowsPerBlock(), mcOut.getColsPerBlock(), hasHeader, delim, fill, fillValue, "csvrblk", instString);
        csvInstruction.processInstruction(sec);
        return;
    } else if (iinfo == InputInfo.BinaryCellInputInfo) {
        JavaPairRDD<MatrixIndexes, MatrixCell> binaryCells = (JavaPairRDD<MatrixIndexes, MatrixCell>) sec.getRDDHandleForVariable(input1.getName(), iinfo);
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = RDDConverterUtils.binaryCellToBinaryBlock(sec.getSparkContext(), binaryCells, mcOut, outputEmptyBlocks);
        // put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else if (iinfo == InputInfo.BinaryBlockInputInfo) {
        // BINARY BLOCK <- BINARY BLOCK (different sizes)
        JavaPairRDD<MatrixIndexes, MatrixBlock> in1 = sec.getBinaryBlockRDDHandleForVariable(input1.getName());
        boolean shuffleFreeReblock = mc.dimsKnown() && mcOut.dimsKnown() && (mc.getRows() < mcOut.getRowsPerBlock() || mc.getRowsPerBlock() % mcOut.getRowsPerBlock() == 0) && (mc.getCols() < mcOut.getColsPerBlock() || mc.getColsPerBlock() % mcOut.getColsPerBlock() == 0);
        JavaPairRDD<MatrixIndexes, MatrixBlock> out = in1.flatMapToPair(new ExtractBlockForBinaryReblock(mc, mcOut));
        if (!shuffleFreeReblock)
            out = RDDAggregateUtils.mergeByKey(out, false);
        // put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
    } else {
        throw new DMLRuntimeException("The given InputInfo is not implemented " + "for ReblockSPInstruction:" + InputInfo.inputInfoToString(iinfo));
    }
}

Example 93 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class FrameIndexingSPInstruction method processInstruction.

@Override
public void processInstruction(ExecutionContext ec) {
    SparkExecutionContext sec = (SparkExecutionContext) ec;
    String opcode = getOpcode();
    // get indexing range
    long rl = ec.getScalarInput(rowLower.getName(), rowLower.getValueType(), rowLower.isLiteral()).getLongValue();
    long ru = ec.getScalarInput(rowUpper.getName(), rowUpper.getValueType(), rowUpper.isLiteral()).getLongValue();
    long cl = ec.getScalarInput(colLower.getName(), colLower.getValueType(), colLower.isLiteral()).getLongValue();
    long cu = ec.getScalarInput(colUpper.getName(), colUpper.getValueType(), colUpper.isLiteral()).getLongValue();
    IndexRange ixrange = new IndexRange(rl, ru, cl, cu);
    // right indexing
    if (opcode.equalsIgnoreCase(RightIndex.OPCODE)) {
        // update and check output dimensions
        MatrixCharacteristics mcIn = sec.getMatrixCharacteristics(input1.getName());
        MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
        mcOut.set(ru - rl + 1, cu - cl + 1, mcIn.getRowsPerBlock(), mcIn.getColsPerBlock());
        checkValidOutputDimensions(mcOut);
        // execute right indexing operation (partitioning-preserving if possible)
        JavaPairRDD<Long, FrameBlock> in1 = sec.getFrameBinaryBlockRDDHandleForVariable(input1.getName());
        JavaPairRDD<Long, FrameBlock> out = null;
        if (isPartitioningPreservingRightIndexing(mcIn, ixrange)) {
            out = in1.mapPartitionsToPair(new SliceBlockPartitionFunction(ixrange, mcOut), true);
        } else {
            out = in1.filter(new IsFrameBlockInRange(rl, ru, mcOut)).mapToPair(new SliceBlock(ixrange, mcOut));
        }
        // put output RDD handle into symbol table
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
        // update schema of output with subset of input schema
        sec.getFrameObject(output.getName()).setSchema(sec.getFrameObject(input1.getName()).getSchema((int) cl, (int) cu));
    } else // left indexing
    if (opcode.equalsIgnoreCase(LeftIndex.OPCODE) || opcode.equalsIgnoreCase("mapLeftIndex")) {
        JavaPairRDD<Long, FrameBlock> in1 = sec.getFrameBinaryBlockRDDHandleForVariable(input1.getName());
        PartitionedBroadcast<FrameBlock> broadcastIn2 = null;
        JavaPairRDD<Long, FrameBlock> in2 = null;
        JavaPairRDD<Long, FrameBlock> out = null;
        // update and check output dimensions
        MatrixCharacteristics mcOut = sec.getMatrixCharacteristics(output.getName());
        MatrixCharacteristics mcLeft = ec.getMatrixCharacteristics(input1.getName());
        mcOut.set(mcLeft.getRows(), mcLeft.getCols(), mcLeft.getRowsPerBlock(), mcLeft.getColsPerBlock());
        checkValidOutputDimensions(mcOut);
        // note: always frame rhs, scalars are preprocessed via cast to 1x1 frame
        MatrixCharacteristics mcRight = ec.getMatrixCharacteristics(input2.getName());
        // sanity check matching index range and rhs dimensions
        if (!mcRight.dimsKnown()) {
            throw new DMLRuntimeException("The right input frame dimensions are not specified for FrameIndexingSPInstruction");
        }
        if (!(ru - rl + 1 == mcRight.getRows() && cu - cl + 1 == mcRight.getCols())) {
            throw new DMLRuntimeException("Invalid index range of leftindexing: [" + rl + ":" + ru + "," + cl + ":" + cu + "] vs [" + mcRight.getRows() + "x" + mcRight.getCols() + "].");
        }
        if (opcode.equalsIgnoreCase("mapLeftIndex")) {
            broadcastIn2 = sec.getBroadcastForFrameVariable(input2.getName());
            // partitioning-preserving mappartitions (key access required for broadcast loopkup)
            out = in1.mapPartitionsToPair(new LeftIndexPartitionFunction(broadcastIn2, ixrange, mcOut), true);
        } else {
            // general case
            // zero-out lhs
            in1 = in1.flatMapToPair(new ZeroOutLHS(false, ixrange, mcLeft));
            // slice rhs, shift and merge with lhs
            in2 = sec.getFrameBinaryBlockRDDHandleForVariable(input2.getName()).flatMapToPair(new SliceRHSForLeftIndexing(ixrange, mcLeft));
            out = FrameRDDAggregateUtils.mergeByKey(in1.union(in2));
        }
        sec.setRDDHandleForVariable(output.getName(), out);
        sec.addLineageRDD(output.getName(), input1.getName());
        if (broadcastIn2 != null)
            sec.addLineageBroadcast(output.getName(), input2.getName());
        if (in2 != null)
            sec.addLineageRDD(output.getName(), input2.getName());
    } else
        throw new DMLRuntimeException("Invalid opcode (" + opcode + ") encountered in FrameIndexingSPInstruction.");
}

Example 94 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class MatrixIndexingSPInstruction method createPartitionPruningRDD.

/**
 * Wraps the input RDD into a PartitionPruningRDD, which acts as a filter
 * of required partitions. The distinct set of required partitions is determined
 * via the partitioner of the input RDD.
 *
 * @param in input matrix as {@code JavaPairRDD<MatrixIndexes,MatrixBlock>}
 * @param filter partition filter
 * @return matrix as {@code JavaPairRDD<MatrixIndexes,MatrixBlock>}
 */
private static JavaPairRDD<MatrixIndexes, MatrixBlock> createPartitionPruningRDD(JavaPairRDD<MatrixIndexes, MatrixBlock> in, List<MatrixIndexes> filter) {
    // build hashset of required partition ids
    HashSet<Integer> flags = new HashSet<>();
    Partitioner partitioner = in.rdd().partitioner().get();
    for (MatrixIndexes key : filter) flags.add(partitioner.getPartition(key));
    // create partition pruning rdd
    Function1<Object, Object> f = new PartitionPruningFunction(flags);
    PartitionPruningRDD<Tuple2<MatrixIndexes, MatrixBlock>> ppRDD = PartitionPruningRDD.create(in.rdd(), f);
    // wrap output into java pair rdd
    return new JavaPairRDD<>(ppRDD, ClassManifestFactory.fromClass(MatrixIndexes.class), ClassManifestFactory.fromClass(MatrixBlock.class));
}

Example 95 with JavaPairRDD

use of org.apache.spark.api.java.JavaPairRDD in project systemml by apache.

the class FrameConverterTest method runConverter.

@SuppressWarnings("unchecked")
private static void runConverter(ConvType type, MatrixCharacteristics mc, MatrixCharacteristics mcMatrix, List<ValueType> schema, String fnameIn, String fnameOut) throws IOException {
    SparkExecutionContext sec = (SparkExecutionContext) ExecutionContextFactory.createContext();
    JavaSparkContext sc = sec.getSparkContext();
    ValueType[] lschema = schema.toArray(new ValueType[0]);
    MapReduceTool.deleteFileIfExistOnHDFS(fnameOut);
    switch(type) {
        case CSV2BIN:
            {
                InputInfo iinfo = InputInfo.CSVInputInfo;
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                JavaPairRDD<LongWritable, Text> rddIn = (JavaPairRDD<LongWritable, Text>) sc.hadoopFile(fnameIn, iinfo.inputFormatClass, iinfo.inputKeyClass, iinfo.inputValueClass);
                JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.csvToBinaryBlock(sc, rddIn, mc, null, false, separator, false, 0).mapToPair(new LongFrameToLongWritableFrameFunction());
                rddOut.saveAsHadoopFile(fnameOut, LongWritable.class, FrameBlock.class, oinfo.outputFormatClass);
                break;
            }
        case BIN2CSV:
            {
                InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
                JavaPairRDD<LongWritable, FrameBlock> rddIn = sc.hadoopFile(fnameIn, iinfo.inputFormatClass, LongWritable.class, FrameBlock.class);
                JavaPairRDD<Long, FrameBlock> rddIn2 = rddIn.mapToPair(new CopyFrameBlockPairFunction(false));
                CSVFileFormatProperties fprop = new CSVFileFormatProperties();
                JavaRDD<String> rddOut = FrameRDDConverterUtils.binaryBlockToCsv(rddIn2, mc, fprop, true);
                rddOut.saveAsTextFile(fnameOut);
                break;
            }
        case TXTCELL2BIN:
            {
                InputInfo iinfo = InputInfo.TextCellInputInfo;
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                JavaPairRDD<LongWritable, Text> rddIn = (JavaPairRDD<LongWritable, Text>) sc.hadoopFile(fnameIn, iinfo.inputFormatClass, iinfo.inputKeyClass, iinfo.inputValueClass);
                JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.textCellToBinaryBlock(sc, rddIn, mc, lschema).mapToPair(new LongFrameToLongWritableFrameFunction());
                rddOut.saveAsHadoopFile(fnameOut, LongWritable.class, FrameBlock.class, oinfo.outputFormatClass);
                break;
            }
        case BIN2TXTCELL:
            {
                InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
                JavaPairRDD<LongWritable, FrameBlock> rddIn = sc.hadoopFile(fnameIn, iinfo.inputFormatClass, LongWritable.class, FrameBlock.class);
                JavaPairRDD<Long, FrameBlock> rddIn2 = rddIn.mapToPair(new CopyFrameBlockPairFunction(false));
                JavaRDD<String> rddOut = FrameRDDConverterUtils.binaryBlockToTextCell(rddIn2, mc);
                rddOut.saveAsTextFile(fnameOut);
                break;
            }
        case MAT2BIN:
            {
                InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                JavaPairRDD<MatrixIndexes, MatrixBlock> rddIn = (JavaPairRDD<MatrixIndexes, MatrixBlock>) sc.hadoopFile(fnameIn, iinfo.inputFormatClass, iinfo.inputKeyClass, iinfo.inputValueClass);
                JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.matrixBlockToBinaryBlock(sc, rddIn, mcMatrix);
                rddOut.saveAsHadoopFile(fnameOut, LongWritable.class, FrameBlock.class, oinfo.outputFormatClass);
                break;
            }
        case BIN2MAT:
            {
                InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                JavaPairRDD<Long, FrameBlock> rddIn = sc.hadoopFile(fnameIn, iinfo.inputFormatClass, LongWritable.class, FrameBlock.class).mapToPair(new LongWritableFrameToLongFrameFunction());
                JavaPairRDD<MatrixIndexes, MatrixBlock> rddOut = FrameRDDConverterUtils.binaryBlockToMatrixBlock(rddIn, mc, mcMatrix);
                rddOut.saveAsHadoopFile(fnameOut, MatrixIndexes.class, MatrixBlock.class, oinfo.outputFormatClass);
                break;
            }
        case DFRM2BIN:
            {
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                // Create DataFrame
                SparkSession sparkSession = SparkSession.builder().sparkContext(sc.sc()).getOrCreate();
                StructType dfSchema = FrameRDDConverterUtils.convertFrameSchemaToDFSchema(lschema, false);
                JavaRDD<Row> rowRDD = FrameRDDConverterUtils.csvToRowRDD(sc, fnameIn, separator, lschema);
                Dataset<Row> df = sparkSession.createDataFrame(rowRDD, dfSchema);
                JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.dataFrameToBinaryBlock(sc, df, mc, false).mapToPair(new LongFrameToLongWritableFrameFunction());
                rddOut.saveAsHadoopFile(fnameOut, LongWritable.class, FrameBlock.class, oinfo.outputFormatClass);
                break;
            }
        case BIN2DFRM:
            {
                InputInfo iinfo = InputInfo.BinaryBlockInputInfo;
                OutputInfo oinfo = OutputInfo.BinaryBlockOutputInfo;
                JavaPairRDD<Long, FrameBlock> rddIn = sc.hadoopFile(fnameIn, iinfo.inputFormatClass, LongWritable.class, FrameBlock.class).mapToPair(new LongWritableFrameToLongFrameFunction());
                SparkSession sparkSession = SparkSession.builder().sparkContext(sc.sc()).getOrCreate();
                Dataset<Row> df = FrameRDDConverterUtils.binaryBlockToDataFrame(sparkSession, rddIn, mc, lschema);
                // Convert back DataFrame to binary block for comparison using original binary to converted DF and back to binary
                JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.dataFrameToBinaryBlock(sc, df, mc, true).mapToPair(new LongFrameToLongWritableFrameFunction());
                rddOut.saveAsHadoopFile(fnameOut, LongWritable.class, FrameBlock.class, oinfo.outputFormatClass);
                break;
            }
        default:
            throw new RuntimeException("Unsuported converter type: " + type.toString());
    }
    sec.close();
}