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

Example 36 with StructField

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

the class MLContextTest method testDataFrameSumPYDMLMllibVectorWithIDColumn.

@Test
public void testDataFrameSumPYDMLMllibVectorWithIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with ID column");
    List<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> list = new ArrayList<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>>();
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(1.0, org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0)));
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(2.0, org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0)));
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(3.0, org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0)));
    JavaRDD<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> javaRddTuple = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleMllibVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    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_WITH_INDEX);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 37 with StructField

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

the class MLContextTest method testInputMatrixBlockPYDML.

@Test
public void testInputMatrixBlockPYDML() {
    System.out.println("MLContextTest - input MatrixBlock 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 CommaSeparatedValueStringToRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", DataTypes.StringType, true));
    fields.add(DataTypes.createStructField("C2", DataTypes.StringType, true));
    fields.add(DataTypes.createStructField("C3", DataTypes.StringType, true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    Matrix m = new Matrix(dataFrame);
    MatrixBlock matrixBlock = m.toMatrixBlock();
    Script script = pydml("avg = avg(M)").in("M", matrixBlock).out("avg");
    double avg = ml.execute(script).getDouble("avg");
    Assert.assertEquals(50.0, avg, 0.0);
}

Example 38 with StructField

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

the class MLContextTest method testDataFrameSumDMLVectorWithNoIDColumn.

@Test
public void testDataFrameSumDMLVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 39 with StructField

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

the class MLContextTest method testDataFrameSumPYDMLDoublesWithIDColumnSortCheck.

@Test
public void testDataFrameSumPYDMLDoublesWithIDColumnSortCheck() {
    System.out.println("MLContextTest - DataFrame sum PYDML ID, 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 = pydml("print('M[0,0]: ' + scalar(M[0,0]))").in("M", dataFrame, mm);
    setExpectedStdOut("M[0,0]: 1.0");
    ml.execute(script);
}

Example 40 with StructField

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

the class MLContextTest method testGetTuple1DML.

@Test
public void testGetTuple1DML() {
    System.out.println("MLContextTest - Get Tuple1<Matrix> DML");
    JavaRDD<String> javaRddString = sc.parallelize(Stream.of("1,2,3", "4,5,6", "7,8,9").collect(Collectors.toList()));
    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> df = spark.createDataFrame(javaRddRow, schema);
    Script script = dml("N=M*2").in("M", df).out("N");
    Tuple1<Matrix> tuple = ml.execute(script).getTuple("N");
    double[][] n = tuple._1().to2DDoubleArray();
    Assert.assertEquals(2.0, n[0][0], 0);
    Assert.assertEquals(4.0, n[0][1], 0);
    Assert.assertEquals(6.0, n[0][2], 0);
    Assert.assertEquals(8.0, n[1][0], 0);
    Assert.assertEquals(10.0, n[1][1], 0);
    Assert.assertEquals(12.0, n[1][2], 0);
    Assert.assertEquals(14.0, n[2][0], 0);
    Assert.assertEquals(16.0, n[2][1], 0);
    Assert.assertEquals(18.0, n[2][2], 0);
}