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

Example 21 with StructField

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

the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumnSortCheck.

@Test
public void testDataFrameSumDMLDoublesWithIDColumnSortCheck() {
    System.out.println("MLContextTest - DataFrame sum DML, doubles with ID column sort check");
    List<String> list = new ArrayList<String>();
    list.add("3,7,8,9");
    list.add("1,1,2,3");
    list.add("2,4,5,6");
    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);
    MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_DOUBLES_WITH_INDEX);
    Script script = dml("print('M[1,1]: ' + as.scalar(M[1,1]));").in("M", dataFrame, mm);
    setExpectedStdOut("M[1,1]: 1.0");
    ml.execute(script);
}

Example 22 with StructField

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

the class MLContextTest method testDataFrameGoodMetadataDML.

@Test
public void testDataFrameGoodMetadataDML() {
    System.out.println("MLContextTest - DataFrame good metadata DML");
    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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 450.0");
    ml.execute(script);
}

Example 23 with StructField

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

the class MLContextTest method testDataFrameSumPYDMLVectorWithNoIDColumn.

@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column");
    List<Vector> list = new ArrayList<Vector>();
    list.add(Vectors.dense(1.0, 2.0, 3.0));
    list.add(Vectors.dense(4.0, 5.0, 6.0));
    list.add(Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", new 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 24 with StructField

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

the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumDMLDoublesWithIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('sum: ' + sum(M));").in("M", dataFrame);
    setExpectedStdOut("sum: 27.0");
    ml.execute(script);
}

Example 25 with StructField

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

the class MLContextTest method testDataFrameToBinaryBlocks.

@Test
public void testDataFrameToBinaryBlocks() {
    System.out.println("MLContextTest - DataFrame to binary blocks");
    List<String> list = new ArrayList<String>();
    list.add("1,2,3");
    list.add("4,5,6");
    list.add("7,8,9");
    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);
    JavaPairRDD<MatrixIndexes, MatrixBlock> binaryBlocks = MLContextConversionUtil.dataFrameToMatrixBinaryBlocks(dataFrame);
    Tuple2<MatrixIndexes, MatrixBlock> first = binaryBlocks.first();
    MatrixBlock mb = first._2();
    double[][] matrix = DataConverter.convertToDoubleMatrix(mb);
    Assert.assertArrayEquals(new double[] { 1.0, 2.0, 3.0 }, matrix[0], 0.0);
    Assert.assertArrayEquals(new double[] { 4.0, 5.0, 6.0 }, matrix[1], 0.0);
    Assert.assertArrayEquals(new double[] { 7.0, 8.0, 9.0 }, matrix[2], 0.0);
}