Examples with InputInfo org.apache.sysml.runtime.matrix.data.InputInfo used on opensource projects

Example 26 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo in project incubator-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();
}

Example 27 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo in project incubator-systemml by apache.

the class MatrixObject method readBlobFromRDD.

@Override
protected MatrixBlock readBlobFromRDD(RDDObject rdd, MutableBoolean writeStatus) throws IOException {
    // note: the read of a matrix block from an RDD might trigger
    // lazy evaluation of pending transformations.
    RDDObject lrdd = rdd;
    // prepare return status (by default only collect)
    writeStatus.setValue(false);
    MetaDataFormat iimd = (MetaDataFormat) _metaData;
    MatrixCharacteristics mc = iimd.getMatrixCharacteristics();
    InputInfo ii = iimd.getInputInfo();
    MatrixBlock mb = null;
    try {
        // prevent unnecessary collect through rdd checkpoint
        if (rdd.allowsShortCircuitCollect()) {
            lrdd = (RDDObject) rdd.getLineageChilds().get(0);
        }
        // obtain matrix block from RDD
        int rlen = (int) mc.getRows();
        int clen = (int) mc.getCols();
        int brlen = (int) mc.getRowsPerBlock();
        int bclen = (int) mc.getColsPerBlock();
        long nnz = mc.getNonZerosBound();
        // guarded rdd collect
        if (// guarded collect not for binary cell
        ii == InputInfo.BinaryBlockInputInfo && !OptimizerUtils.checkSparkCollectMemoryBudget(mc, getPinnedSize() + getBroadcastSize(), true)) {
            // note: lazy, partition-at-a-time collect (toLocalIterator) was significantly slower
            if (!MapReduceTool.existsFileOnHDFS(_hdfsFileName)) {
                // prevent overwrite existing file
                long newnnz = SparkExecutionContext.writeRDDtoHDFS(lrdd, _hdfsFileName, iimd.getOutputInfo());
                _metaData.getMatrixCharacteristics().setNonZeros(newnnz);
                // mark rdd as non-pending (for export)
                ((RDDObject) rdd).setPending(false);
                // mark rdd as hdfs file (for restore)
                ((RDDObject) rdd).setHDFSFile(true);
                // mark for no cache-write on read
                writeStatus.setValue(true);
            // note: the flag hdfsFile is actually not entirely correct because we still hold an rdd
            // reference to the input not to an rdd of the hdfs file but the resulting behavior is correct
            }
            mb = readBlobFromHDFS(_hdfsFileName);
        } else if (ii == InputInfo.BinaryCellInputInfo) {
            // collect matrix block from binary block RDD
            mb = SparkExecutionContext.toMatrixBlock(lrdd, rlen, clen, nnz);
        } else {
            // collect matrix block from binary cell RDD
            mb = SparkExecutionContext.toMatrixBlock(lrdd, rlen, clen, brlen, bclen, nnz);
        }
    } catch (DMLRuntimeException ex) {
        throw new IOException(ex);
    }
    // sanity check correct output
    if (mb == null)
        throw new IOException("Unable to load matrix from rdd.");
    return mb;
}

Example 28 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo in project incubator-systemml by apache.

the class SparkExecutionContext method getRDDHandleForFrameObject.

/**
 * FIXME: currently this implementation assumes matrix representations but frame signature
 * in order to support the old transform implementation.
 *
 * @param fo frame object
 * @param inputInfo input info
 * @return JavaPairRDD handle for a frame object
 */
@SuppressWarnings("unchecked")
public JavaPairRDD<?, ?> getRDDHandleForFrameObject(FrameObject fo, InputInfo inputInfo) {
    // NOTE: MB this logic should be integrated into FrameObject
    // However, for now we cannot assume that spark libraries are
    // always available and hence only store generic references in
    // matrix object while all the logic is in the SparkExecContext
    InputInfo inputInfo2 = (inputInfo == InputInfo.BinaryBlockInputInfo) ? InputInfo.BinaryBlockFrameInputInfo : inputInfo;
    JavaSparkContext sc = getSparkContext();
    JavaPairRDD<?, ?> rdd = null;
    // rdd operations if already executed and cached
    if (fo.getRDDHandle() != null && (fo.getRDDHandle().isCheckpointRDD() || !fo.isCached(false))) {
        // return existing rdd handling (w/o input format change)
        rdd = fo.getRDDHandle().getRDD();
    } else // CASE 2: dirty in memory data or cached result of rdd operations
    if (fo.isDirty() || fo.isCached(false)) {
        // get in-memory matrix block and parallelize it
        // w/ guarded parallelize (fallback to export, rdd from file if too large)
        MatrixCharacteristics mc = fo.getMatrixCharacteristics();
        boolean fromFile = false;
        if (!OptimizerUtils.checkSparkCollectMemoryBudget(mc, 0) || !_parRDDs.reserve(OptimizerUtils.estimatePartitionedSizeExactSparsity(mc))) {
            if (fo.isDirty()) {
                // write only if necessary
                fo.exportData();
            }
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, FrameBlock>) rdd).mapToPair(new CopyFrameBlockPairFunction());
            fromFile = true;
        } else {
            // default case
            // pin frame in memory
            FrameBlock fb = fo.acquireRead();
            rdd = toFrameJavaPairRDD(sc, fb);
            // unpin frame
            fo.release();
            _parRDDs.registerRDD(rdd.id(), OptimizerUtils.estimatePartitionedSizeExactSparsity(mc), true);
        }
        // keep rdd handle for future operations on it
        RDDObject rddhandle = new RDDObject(rdd);
        rddhandle.setHDFSFile(fromFile);
        fo.setRDDHandle(rddhandle);
    } else // CASE 3: non-dirty (file exists on HDFS)
    {
        // For binary block, these are: SequenceFileInputFormat.class, MatrixIndexes.class, MatrixBlock.class
        if (inputInfo2 == InputInfo.BinaryBlockFrameInputInfo) {
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // note: this copy is still required in Spark 1.4 because spark hands out whatever the inputformat
            // recordreader returns; the javadoc explicitly recommend to copy all key/value pairs
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, FrameBlock>) rdd).mapToPair(new CopyFrameBlockPairFunction());
        } else if (inputInfo2 == InputInfo.TextCellInputInfo || inputInfo2 == InputInfo.CSVInputInfo || inputInfo2 == InputInfo.MatrixMarketInputInfo) {
            rdd = sc.hadoopFile(fo.getFileName(), inputInfo2.inputFormatClass, inputInfo2.inputKeyClass, inputInfo2.inputValueClass);
            // cp is workaround for read bug
            rdd = ((JavaPairRDD<LongWritable, Text>) rdd).mapToPair(new CopyTextInputFunction());
        } else if (inputInfo2 == InputInfo.BinaryCellInputInfo) {
            throw new DMLRuntimeException("Binarycell not supported for frames.");
        } else {
            throw new DMLRuntimeException("Incorrect input format in getRDDHandleForVariable");
        }
        // keep rdd handle for future operations on it
        RDDObject rddhandle = new RDDObject(rdd);
        rddhandle.setHDFSFile(true);
        fo.setRDDHandle(rddhandle);
    }
    return rdd;
}

Example 29 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo in project incubator-systemml by apache.

the class ProgramConverter method parseDataObject.

/**
 * NOTE: MRJobConfiguration cannot be used for the general case because program blocks and
 * related symbol tables can be hierarchically structured.
 *
 * @param in data object as string
 * @return array of objects
 */
public static Object[] parseDataObject(String in) {
    Object[] ret = new Object[2];
    StringTokenizer st = new StringTokenizer(in, DATA_FIELD_DELIM);
    String name = st.nextToken();
    DataType datatype = DataType.valueOf(st.nextToken());
    ValueType valuetype = ValueType.valueOf(st.nextToken());
    String valString = st.hasMoreTokens() ? st.nextToken() : "";
    Data dat = null;
    switch(datatype) {
        case SCALAR:
            {
                switch(valuetype) {
                    case INT:
                        dat = new IntObject(Long.parseLong(valString));
                        break;
                    case DOUBLE:
                        dat = new DoubleObject(Double.parseDouble(valString));
                        break;
                    case BOOLEAN:
                        dat = new BooleanObject(Boolean.parseBoolean(valString));
                        break;
                    case STRING:
                        dat = new StringObject(valString);
                        break;
                    default:
                        throw new DMLRuntimeException("Unable to parse valuetype " + valuetype);
                }
                break;
            }
        case MATRIX:
            {
                MatrixObject mo = new MatrixObject(valuetype, valString);
                long rows = Long.parseLong(st.nextToken());
                long cols = Long.parseLong(st.nextToken());
                int brows = Integer.parseInt(st.nextToken());
                int bcols = Integer.parseInt(st.nextToken());
                long nnz = Long.parseLong(st.nextToken());
                InputInfo iin = InputInfo.stringToInputInfo(st.nextToken());
                OutputInfo oin = OutputInfo.stringToOutputInfo(st.nextToken());
                PartitionFormat partFormat = PartitionFormat.valueOf(st.nextToken());
                UpdateType inplace = UpdateType.valueOf(st.nextToken());
                MatrixCharacteristics mc = new MatrixCharacteristics(rows, cols, brows, bcols, nnz);
                MetaDataFormat md = new MetaDataFormat(mc, oin, iin);
                mo.setMetaData(md);
                if (partFormat._dpf != PDataPartitionFormat.NONE)
                    mo.setPartitioned(partFormat._dpf, partFormat._N);
                mo.setUpdateType(inplace);
                dat = mo;
                break;
            }
        default:
            throw new DMLRuntimeException("Unable to parse datatype " + datatype);
    }
    ret[0] = name;
    ret[1] = dat;
    return ret;
}

Example 30 with InputInfo

use of org.apache.sysml.runtime.matrix.data.InputInfo in project incubator-systemml by apache.

the class ResultMergeLocalFile method createNewMatrixObject.

private MatrixObject createNewMatrixObject(MatrixObject output, ArrayList<MatrixObject> inMO) {
    MetaDataFormat metadata = (MetaDataFormat) _output.getMetaData();
    MatrixObject moNew = new MatrixObject(_output.getValueType(), _outputFName);
    // create deep copy of metadata obj
    MatrixCharacteristics mcOld = metadata.getMatrixCharacteristics();
    OutputInfo oiOld = metadata.getOutputInfo();
    InputInfo iiOld = metadata.getInputInfo();
    MatrixCharacteristics mc = new MatrixCharacteristics(mcOld);
    mc.setNonZeros(_isAccum ? -1 : computeNonZeros(output, inMO));
    MetaDataFormat meta = new MetaDataFormat(mc, oiOld, iiOld);
    moNew.setMetaData(meta);
    return moNew;
}