Examples with StructType org.apache.spark.sql.types.StructType used on opensource projects

Example 46 with StructType

use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.

the class MLContextTest method testDataFrameSumPYDMLVectorWithIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumPYDMLVectorWithIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum PYDML, vector with ID column, no format specified");
    List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
    list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
    list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
    list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
    JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    Script script = dml("print('sum: ' + sum(M))").in("M", dataFrame);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 47 with StructType

use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.

the class MLContextTest method testDataFrameSumPYDMLDoublesWithIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumPYDMLDoublesWithIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum PYDML, doubles with ID column, no format specified");
    List<String> list = new ArrayList<String>();
    list.add("1,2,2,2");
    list.add("2,3,3,3");
    list.add("3,4,4,4");
    JavaRDD<String> javaRddString = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddString.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C1", DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C2", DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C3", DataTypes.DoubleType, true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame);
    setExpectedStdOut("sum: 27.0");
    ml.execute(script);
}

Example 48 with StructType

use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.

the class MLContextTest method testDataFrameSumPYDMLMllibVectorWithNoIDColumn.

@Test
public void testDataFrameSumPYDMLMllibVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with no ID column");
    List<org.apache.spark.mllib.linalg.Vector> list = new ArrayList<org.apache.spark.mllib.linalg.Vector>();
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<org.apache.spark.mllib.linalg.Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new MllibVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 49 with StructType

use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.

the class MLContextTest method testDataFrameGoodMetadataPYDML.

@Test
public void testDataFrameGoodMetadataPYDML() {
    System.out.println("MLContextTest - DataFrame good metadata PYDML");
    List<String> list = new ArrayList<String>();
    list.add("10,20,30");
    list.add("40,50,60");
    list.add("70,80,90");
    JavaRDD<String> javaRddString = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddString.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C2", DataTypes.DoubleType, true));
    fields.add(DataTypes.createStructField("C3", DataTypes.DoubleType, true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    MatrixMetadata mm = new MatrixMetadata(3, 3, 9);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 450.0");
    ml.execute(script);
}

Example 50 with StructType

use of org.apache.spark.sql.types.StructType 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();
}