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

Example 51 with FrameBlock

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

the class FrameTest method testFrameGeneral.

private void testFrameGeneral(InputInfo iinfo, OutputInfo oinfo, boolean bFromDataFrame, boolean bToDataFrame) throws IOException, DMLException, ParseException {
    boolean oldConfig = DMLScript.USE_LOCAL_SPARK_CONFIG;
    DMLScript.USE_LOCAL_SPARK_CONFIG = true;
    RUNTIME_PLATFORM oldRT = DMLScript.rtplatform;
    DMLScript.rtplatform = RUNTIME_PLATFORM.HYBRID_SPARK;
    int rowstart = 234, rowend = 1478, colstart = 125, colend = 568;
    int bRows = rowend - rowstart + 1, bCols = colend - colstart + 1;
    int rowstartC = 124, rowendC = 1178, colstartC = 143, colendC = 368;
    int cRows = rowendC - rowstartC + 1, cCols = colendC - colstartC + 1;
    HashMap<String, ValueType[]> outputSchema = new HashMap<String, ValueType[]>();
    HashMap<String, MatrixCharacteristics> outputMC = new HashMap<String, MatrixCharacteristics>();
    TestConfiguration config = getTestConfiguration(TEST_NAME);
    loadTestConfiguration(config);
    List<String> proArgs = new ArrayList<String>();
    proArgs.add(input("A"));
    proArgs.add(Integer.toString(rows));
    proArgs.add(Integer.toString(cols));
    proArgs.add(input("B"));
    proArgs.add(Integer.toString(bRows));
    proArgs.add(Integer.toString(bCols));
    proArgs.add(Integer.toString(rowstart));
    proArgs.add(Integer.toString(rowend));
    proArgs.add(Integer.toString(colstart));
    proArgs.add(Integer.toString(colend));
    proArgs.add(output("A"));
    proArgs.add(Integer.toString(rowstartC));
    proArgs.add(Integer.toString(rowendC));
    proArgs.add(Integer.toString(colstartC));
    proArgs.add(Integer.toString(colendC));
    proArgs.add(output("C"));
    fullDMLScriptName = SCRIPT_DIR + TEST_DIR + TEST_NAME + ".dml";
    ValueType[] schema = schemaMixedLarge;
    // initialize the frame data.
    List<ValueType> lschema = Arrays.asList(schema);
    fullRScriptName = SCRIPT_DIR + TEST_DIR + TEST_NAME + ".R";
    rCmd = "Rscript" + " " + fullRScriptName + " " + inputDir() + " " + rowstart + " " + rowend + " " + colstart + " " + colend + " " + expectedDir() + " " + rowstartC + " " + rowendC + " " + colstartC + " " + colendC;
    double sparsity = sparsity1;
    double[][] A = getRandomMatrix(rows, cols, min, max, sparsity, 1111);
    writeInputFrameWithMTD("A", A, true, schema, oinfo);
    sparsity = sparsity2;
    double[][] B = getRandomMatrix((int) (bRows), (int) (bCols), min, max, sparsity, 2345);
    ValueType[] schemaB = new ValueType[bCols];
    for (int i = 0; i < bCols; ++i) schemaB[i] = schema[colstart - 1 + i];
    List<ValueType> lschemaB = Arrays.asList(schemaB);
    writeInputFrameWithMTD("B", B, true, schemaB, oinfo);
    ValueType[] schemaC = new ValueType[colendC - colstartC + 1];
    for (int i = 0; i < cCols; ++i) schemaC[i] = schema[colstartC - 1 + i];
    Dataset<Row> dfA = null, dfB = null;
    if (bFromDataFrame) {
        // Create DataFrame for input A
        StructType dfSchemaA = FrameRDDConverterUtils.convertFrameSchemaToDFSchema(schema, false);
        JavaRDD<Row> rowRDDA = FrameRDDConverterUtils.csvToRowRDD(sc, input("A"), DataExpression.DEFAULT_DELIM_DELIMITER, schema);
        dfA = spark.createDataFrame(rowRDDA, dfSchemaA);
        // Create DataFrame for input B
        StructType dfSchemaB = FrameRDDConverterUtils.convertFrameSchemaToDFSchema(schemaB, false);
        JavaRDD<Row> rowRDDB = FrameRDDConverterUtils.csvToRowRDD(sc, input("B"), DataExpression.DEFAULT_DELIM_DELIMITER, schemaB);
        dfB = spark.createDataFrame(rowRDDB, dfSchemaB);
    }
    try {
        Script script = ScriptFactory.dmlFromFile(fullDMLScriptName);
        String format = "csv";
        if (oinfo == OutputInfo.TextCellOutputInfo)
            format = "text";
        if (bFromDataFrame) {
            script.in("A", dfA);
        } else {
            JavaRDD<String> aIn = sc.textFile(input("A"));
            FrameSchema fs = new FrameSchema(lschema);
            FrameFormat ff = (format.equals("text")) ? FrameFormat.IJV : FrameFormat.CSV;
            FrameMetadata fm = new FrameMetadata(ff, fs, rows, cols);
            script.in("A", aIn, fm);
        }
        if (bFromDataFrame) {
            script.in("B", dfB);
        } else {
            JavaRDD<String> bIn = sc.textFile(input("B"));
            FrameSchema fs = new FrameSchema(lschemaB);
            FrameFormat ff = (format.equals("text")) ? FrameFormat.IJV : FrameFormat.CSV;
            FrameMetadata fm = new FrameMetadata(ff, fs, bRows, bCols);
            script.in("B", bIn, fm);
        }
        // Output one frame to HDFS and get one as RDD //TODO HDFS input/output to do
        script.out("A", "C");
        // set positional argument values
        for (int argNum = 1; argNum <= proArgs.size(); argNum++) {
            script.in("$" + argNum, proArgs.get(argNum - 1));
        }
        MLResults results = ml.execute(script);
        format = "csv";
        if (iinfo == InputInfo.TextCellInputInfo)
            format = "text";
        String fName = output("AB");
        try {
            MapReduceTool.deleteFileIfExistOnHDFS(fName);
        } catch (IOException e) {
            throw new DMLRuntimeException("Error: While deleting file on HDFS");
        }
        if (!bToDataFrame) {
            if (format.equals("text")) {
                JavaRDD<String> javaRDDStringIJV = results.getJavaRDDStringIJV("A");
                javaRDDStringIJV.saveAsTextFile(fName);
            } else {
                JavaRDD<String> javaRDDStringCSV = results.getJavaRDDStringCSV("A");
                javaRDDStringCSV.saveAsTextFile(fName);
            }
        } else {
            Dataset<Row> df = results.getDataFrame("A");
            // Convert back DataFrame to binary block for comparison using original binary to converted DF and back to binary
            MatrixCharacteristics mc = new MatrixCharacteristics(rows, cols, -1, -1, -1);
            JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.dataFrameToBinaryBlock(sc, df, mc, bFromDataFrame).mapToPair(new LongFrameToLongWritableFrameFunction());
            rddOut.saveAsHadoopFile(output("AB"), LongWritable.class, FrameBlock.class, OutputInfo.BinaryBlockOutputInfo.outputFormatClass);
        }
        fName = output("C");
        try {
            MapReduceTool.deleteFileIfExistOnHDFS(fName);
        } catch (IOException e) {
            throw new DMLRuntimeException("Error: While deleting file on HDFS");
        }
        if (!bToDataFrame) {
            if (format.equals("text")) {
                JavaRDD<String> javaRDDStringIJV = results.getJavaRDDStringIJV("C");
                javaRDDStringIJV.saveAsTextFile(fName);
            } else {
                JavaRDD<String> javaRDDStringCSV = results.getJavaRDDStringCSV("C");
                javaRDDStringCSV.saveAsTextFile(fName);
            }
        } else {
            Dataset<Row> df = results.getDataFrame("C");
            // Convert back DataFrame to binary block for comparison using original binary to converted DF and back to binary
            MatrixCharacteristics mc = new MatrixCharacteristics(cRows, cCols, -1, -1, -1);
            JavaPairRDD<LongWritable, FrameBlock> rddOut = FrameRDDConverterUtils.dataFrameToBinaryBlock(sc, df, mc, bFromDataFrame).mapToPair(new LongFrameToLongWritableFrameFunction());
            rddOut.saveAsHadoopFile(fName, LongWritable.class, FrameBlock.class, OutputInfo.BinaryBlockOutputInfo.outputFormatClass);
        }
        runRScript(true);
        outputSchema.put("AB", schema);
        outputMC.put("AB", new MatrixCharacteristics(rows, cols, -1, -1));
        outputSchema.put("C", schemaC);
        outputMC.put("C", new MatrixCharacteristics(cRows, cCols, -1, -1));
        for (String file : config.getOutputFiles()) {
            MatrixCharacteristics md = outputMC.get(file);
            FrameBlock frameBlock = readDMLFrameFromHDFS(file, iinfo, md);
            FrameBlock frameRBlock = readRFrameFromHDFS(file + ".csv", InputInfo.CSVInputInfo, md);
            ValueType[] schemaOut = outputSchema.get(file);
            verifyFrameData(frameBlock, frameRBlock, schemaOut);
            System.out.println("File " + file + " processed successfully.");
        }
        System.out.println("Frame MLContext test completed successfully.");
    } finally {
        DMLScript.rtplatform = oldRT;
        DMLScript.USE_LOCAL_SPARK_CONFIG = oldConfig;
    }
}

Example 52 with FrameBlock

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

the class JMLCInputStreamReadTest method runJMLCInputStreamReadTest.

private void runJMLCInputStreamReadTest(DataType dt, boolean sparse, String format, boolean metaData) throws IOException {
    TestConfiguration config = getTestConfiguration(TEST_NAME);
    loadTestConfiguration(config);
    // generate inputs
    OutputInfo oinfo = format.equals("csv") ? OutputInfo.CSVOutputInfo : OutputInfo.TextCellOutputInfo;
    double[][] data = TestUtils.round(getRandomMatrix(rows, cols, 0.51, 7.49, sparse ? sparsity2 : sparsity1, 7));
    Connection conn = new Connection();
    try {
        if (dt == DataType.MATRIX) {
            // write input matrix
            MatrixBlock mb = DataConverter.convertToMatrixBlock(data);
            MatrixWriter writer = MatrixWriterFactory.createMatrixWriter(oinfo);
            writer.writeMatrixToHDFS(mb, output("X"), rows, cols, -1, -1, -1);
            // read matrix from input stream
            FileInputStream fis = new FileInputStream(output("X"));
            double[][] data2 = conn.convertToDoubleMatrix(fis, rows, cols, format);
            fis.close();
            // compare matrix result
            TestUtils.compareMatrices(data, data2, rows, cols, 0);
        } else if (dt == DataType.FRAME) {
            // write input frame
            String[][] fdata = FrameTransformTest.createFrameData(data, "V");
            // test quoted tokens w/ inner quotes
            fdata[3][1] = "\"ab\"\"cdef\"";
            if (format.equals("csv"))
                // test delimiter and space tokens
                fdata[7][2] = "\"a,bc def\"";
            FrameBlock fb = DataConverter.convertToFrameBlock(fdata);
            if (metaData) {
                fb.setColumnNames(IntStream.range(0, cols).mapToObj(i -> "CC" + i).collect(Collectors.toList()).toArray(new String[0]));
            }
            FrameWriter writer = FrameWriterFactory.createFrameWriter(oinfo);
            writer.writeFrameToHDFS(fb, output("X"), rows, cols);
            // read frame from input stream
            FileInputStream fis = new FileInputStream(output("X"));
            String[][] fdata2 = conn.convertToStringFrame(fis, rows, cols, format);
            fis.close();
            // compare frame result
            TestUtils.compareFrames(fdata, fdata2, rows, cols);
        } else {
            throw new IOException("Unsupported data type: " + dt.name());
        }
    } catch (Exception ex) {
        throw new RuntimeException(ex);
    } finally {
        MapReduceTool.deleteFileIfExistOnHDFS(output("X"));
        IOUtilFunctions.closeSilently(conn);
    }
}

Example 53 with FrameBlock

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

the class FrameAppendDistTest method commonAppendTest.

/**
 * @param platform
 * @param rows
 * @param cols1
 * @param cols2
 * @param sparse
 */
public void commonAppendTest(RUNTIME_PLATFORM platform, int rows1, int rows2, int cols1, int cols2, boolean sparse, AppendMethod forcedAppendMethod, boolean rbind) {
    TestConfiguration config = getAndLoadTestConfiguration(TEST_NAME);
    RUNTIME_PLATFORM prevPlfm = rtplatform;
    double sparsity = (sparse) ? sparsity2 : sparsity1;
    boolean sparkConfigOld = DMLScript.USE_LOCAL_SPARK_CONFIG;
    try {
        if (forcedAppendMethod != null) {
            BinaryOp.FORCED_APPEND_METHOD = forcedAppendMethod;
        }
        rtplatform = platform;
        if (rtplatform == RUNTIME_PLATFORM.SPARK)
            DMLScript.USE_LOCAL_SPARK_CONFIG = true;
        config.addVariable("rows", rows1);
        config.addVariable("cols", cols1);
        /* This is for running the junit test the new way, i.e., construct the arguments directly */
        String RI_HOME = SCRIPT_DIR + TEST_DIR;
        fullDMLScriptName = RI_HOME + TEST_NAME + ".dml";
        programArgs = new String[] { "-explain", "-args", input("A"), Long.toString(rows1), Long.toString(cols1), input("B"), Long.toString(rows2), Long.toString(cols2), output("C"), (rbind ? "rbind" : "cbind") };
        fullRScriptName = RI_HOME + TEST_NAME + ".R";
        rCmd = "Rscript" + " " + fullRScriptName + " " + inputDir() + " " + expectedDir() + " " + (rbind ? "rbind" : "cbind");
        // initialize the frame data.
        ValueType[] lschemaA = genMixSchema(cols1);
        double[][] A = getRandomMatrix(rows1, cols1, min, max, sparsity, 1111);
        writeInputFrameWithMTD("A", A, true, lschemaA, OutputInfo.BinaryBlockOutputInfo);
        ValueType[] lschemaB = genMixSchema(cols2);
        double[][] B = getRandomMatrix(rows2, cols2, min, max, sparsity, 2345);
        writeInputFrameWithMTD("B", B, true, lschemaB, OutputInfo.BinaryBlockOutputInfo);
        boolean exceptionExpected = false;
        int expectedNumberOfJobs = -1;
        runTest(true, exceptionExpected, null, expectedNumberOfJobs);
        runRScript(true);
        ValueType[] lschemaAB = UtilFunctions.copyOf(lschemaA, lschemaB);
        for (String file : config.getOutputFiles()) {
            FrameBlock frameBlock = readDMLFrameFromHDFS(file, InputInfo.BinaryBlockInputInfo);
            MatrixCharacteristics md = new MatrixCharacteristics(frameBlock.getNumRows(), frameBlock.getNumColumns(), -1, -1);
            FrameBlock frameRBlock = readRFrameFromHDFS(file + ".csv", InputInfo.CSVInputInfo, md);
            verifyFrameData(frameBlock, frameRBlock, (ValueType[]) lschemaAB);
            System.out.println("File processed is " + file);
        }
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new RuntimeException(ex);
    } finally {
        // reset execution platform
        rtplatform = prevPlfm;
        DMLScript.USE_LOCAL_SPARK_CONFIG = sparkConfigOld;
        BinaryOp.FORCED_APPEND_METHOD = null;
    }
}

Example 54 with FrameBlock

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

the class FrameAppendTest method runFrameAppendTest.

/**
 * @param sparseM1
 * @param sparseM2
 * @param instType
 */
private void runFrameAppendTest(ValueType[] schema1, ValueType[] schema2, AppendType atype) {
    try {
        // data generation
        double[][] A = getRandomMatrix(rows, schema1.length, -10, 10, 0.9, 2373);
        double[][] B = getRandomMatrix(rows, schema2.length, -10, 10, 0.9, 129);
        // init data frame 1
        FrameBlock frame1 = new FrameBlock(schema1);
        Object[] row1 = new Object[schema1.length];
        for (int i = 0; i < rows; i++) {
            for (int j = 0; j < schema1.length; j++) A[i][j] = UtilFunctions.objectToDouble(schema1[j], row1[j] = UtilFunctions.doubleToObject(schema1[j], A[i][j]));
            frame1.appendRow(row1);
        }
        // init data frame 2
        FrameBlock frame2 = new FrameBlock(schema2);
        Object[] row2 = new Object[schema2.length];
        for (int i = 0; i < rows; i++) {
            for (int j = 0; j < schema2.length; j++) B[i][j] = UtilFunctions.objectToDouble(schema2[j], row2[j] = UtilFunctions.doubleToObject(schema2[j], B[i][j]));
            frame2.appendRow(row2);
        }
        // core append operations matrix blocks
        MatrixBlock mbA = DataConverter.convertToMatrixBlock(A);
        MatrixBlock mbB = DataConverter.convertToMatrixBlock(B);
        MatrixBlock mbC = mbA.append(mbB, new MatrixBlock(), atype == AppendType.CBIND);
        // core append operations frame blocks
        FrameBlock frame3 = frame1.append(frame2, new FrameBlock(), atype == AppendType.CBIND);
        // check basic meta data
        if (frame3.getNumRows() != mbC.getNumRows())
            Assert.fail("Wrong number of rows: " + frame3.getNumRows() + ", expected: " + mbC.getNumRows());
        // check correct values
        ValueType[] lschema = frame3.getSchema();
        for (int i = 0; i < rows; i++) for (int j = 0; j < lschema.length; j++) {
            double tmp = UtilFunctions.objectToDouble(lschema[j], frame3.get(i, j));
            if (tmp != mbC.quickGetValue(i, j))
                Assert.fail("Wrong get value for cell (" + i + "," + j + "): " + tmp + ", expected: " + mbC.quickGetValue(i, j));
        }
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new RuntimeException(ex);
    }
}

Example 55 with FrameBlock

use of org.apache.sysml.runtime.matrix.data.FrameBlock 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();
}