Search in sources :

Example 1 with LongWritableFrameToLongFrameFunction

use of org.apache.sysml.runtime.instructions.spark.utils.FrameRDDConverterUtils.LongWritableFrameToLongFrameFunction in project incubator-systemml by apache.

the class FrameConverterTest method runConverter.

/**
	 * @param oinfo 
	 * @param frame1
	 * @param frame2
	 * @param fprop
	 * @param schema
	 * @return 
	 * @throws DMLRuntimeException, IOException
	 */
@SuppressWarnings("unchecked")
private void runConverter(ConvType type, MatrixCharacteristics mc, MatrixCharacteristics mcMatrix, List<ValueType> schema, String fnameIn, String fnameOut) throws DMLRuntimeException, 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();
}
Also used : MatrixBlock(org.apache.sysml.runtime.matrix.data.MatrixBlock) CSVFileFormatProperties(org.apache.sysml.runtime.matrix.data.CSVFileFormatProperties) SparkSession(org.apache.spark.sql.SparkSession) StructType(org.apache.spark.sql.types.StructType) ValueType(org.apache.sysml.parser.Expression.ValueType) MatrixIndexes(org.apache.sysml.runtime.matrix.data.MatrixIndexes) Dataset(org.apache.spark.sql.Dataset) Text(org.apache.hadoop.io.Text) JavaRDD(org.apache.spark.api.java.JavaRDD) OutputInfo(org.apache.sysml.runtime.matrix.data.OutputInfo) InputInfo(org.apache.sysml.runtime.matrix.data.InputInfo) DMLRuntimeException(org.apache.sysml.runtime.DMLRuntimeException) FrameBlock(org.apache.sysml.runtime.matrix.data.FrameBlock) JavaPairRDD(org.apache.spark.api.java.JavaPairRDD) LongWritableFrameToLongFrameFunction(org.apache.sysml.runtime.instructions.spark.utils.FrameRDDConverterUtils.LongWritableFrameToLongFrameFunction) SparkExecutionContext(org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext) JavaSparkContext(org.apache.spark.api.java.JavaSparkContext) LongWritable(org.apache.hadoop.io.LongWritable) LongFrameToLongWritableFrameFunction(org.apache.sysml.runtime.instructions.spark.utils.FrameRDDConverterUtils.LongFrameToLongWritableFrameFunction) CopyFrameBlockPairFunction(org.apache.sysml.runtime.instructions.spark.functions.CopyFrameBlockPairFunction)

Aggregations

LongWritable (org.apache.hadoop.io.LongWritable)1 Text (org.apache.hadoop.io.Text)1 JavaPairRDD (org.apache.spark.api.java.JavaPairRDD)1 JavaRDD (org.apache.spark.api.java.JavaRDD)1 JavaSparkContext (org.apache.spark.api.java.JavaSparkContext)1 Dataset (org.apache.spark.sql.Dataset)1 SparkSession (org.apache.spark.sql.SparkSession)1 StructType (org.apache.spark.sql.types.StructType)1 ValueType (org.apache.sysml.parser.Expression.ValueType)1 DMLRuntimeException (org.apache.sysml.runtime.DMLRuntimeException)1 SparkExecutionContext (org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext)1 CopyFrameBlockPairFunction (org.apache.sysml.runtime.instructions.spark.functions.CopyFrameBlockPairFunction)1 LongFrameToLongWritableFrameFunction (org.apache.sysml.runtime.instructions.spark.utils.FrameRDDConverterUtils.LongFrameToLongWritableFrameFunction)1 LongWritableFrameToLongFrameFunction (org.apache.sysml.runtime.instructions.spark.utils.FrameRDDConverterUtils.LongWritableFrameToLongFrameFunction)1 CSVFileFormatProperties (org.apache.sysml.runtime.matrix.data.CSVFileFormatProperties)1 FrameBlock (org.apache.sysml.runtime.matrix.data.FrameBlock)1 InputInfo (org.apache.sysml.runtime.matrix.data.InputInfo)1 MatrixBlock (org.apache.sysml.runtime.matrix.data.MatrixBlock)1 MatrixIndexes (org.apache.sysml.runtime.matrix.data.MatrixIndexes)1 OutputInfo (org.apache.sysml.runtime.matrix.data.OutputInfo)1