Examples with Row org.apache.spark.sql.Row used on opensource projects

Example 86 with Row

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

the class MLContextTest method testDataFrameSumDMLDoublesWithNoIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumDMLDoublesWithNoIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum DML, doubles with no ID column, no format specified");
    List<String> list = new ArrayList<String>();
    list.add("2,2,2");
    list.add("3,3,3");
    list.add("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("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 87 with Row

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

the class MLContextTest method testOutputDataFrameDoublesNoIDColumnFromMatrixDML.

@Test
public void testOutputDataFrameDoublesNoIDColumnFromMatrixDML() {
    System.out.println("MLContextTest - output DataFrame of doubles with no ID column from matrix DML");
    String s = "M = matrix('1 2 3 4', rows=1, cols=4);";
    Script script = dml(s).out("M");
    Dataset<Row> df = ml.execute(script).getMatrix("M").toDFDoubleNoIDColumn();
    List<Row> list = df.collectAsList();
    Row row = list.get(0);
    Assert.assertEquals(1.0, row.getDouble(0), 0.0);
    Assert.assertEquals(2.0, row.getDouble(1), 0.0);
    Assert.assertEquals(3.0, row.getDouble(2), 0.0);
    Assert.assertEquals(4.0, row.getDouble(3), 0.0);
}

Example 88 with Row

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

the class MLContextTest method testOutputDataFrameDMLVectorNoIDColumn.

@Test
public void testOutputDataFrameDMLVectorNoIDColumn() {
    System.out.println("MLContextTest - output DataFrame DML, vector no ID column");
    String s = "M = matrix('1 2 3 4', rows=2, cols=2);";
    Script script = dml(s).out("M");
    MLResults results = ml.execute(script);
    Dataset<Row> dataFrame = results.getDataFrameVectorNoIDColumn("M");
    List<Row> list = dataFrame.collectAsList();
    Row row1 = list.get(0);
    Assert.assertArrayEquals(new double[] { 1.0, 2.0 }, ((Vector) row1.get(0)).toArray(), 0.0);
    Row row2 = list.get(1);
    Assert.assertArrayEquals(new double[] { 3.0, 4.0 }, ((Vector) row2.get(0)).toArray(), 0.0);
}

Example 89 with Row

use of org.apache.spark.sql.Row 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 90 with Row

use of org.apache.spark.sql.Row 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);
}