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

Example 21 with Row

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

the class MLContextTest method testDataFrameSumDMLMllibVectorWithIDColumn.

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

Example 22 with Row

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

the class MLContextTest method testOutputDataFrameDMLVectorWithIDColumn.

@Test
public void testOutputDataFrameDMLVectorWithIDColumn() {
    System.out.println("MLContextTest - output DataFrame DML, vector with 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.getDataFrameVectorWithIDColumn("M");
    List<Row> list = dataFrame.collectAsList();
    Row row1 = list.get(0);
    Assert.assertEquals(1.0, row1.getDouble(0), 0.0);
    Assert.assertArrayEquals(new double[] { 1.0, 2.0 }, ((Vector) row1.get(1)).toArray(), 0.0);
    Row row2 = list.get(1);
    Assert.assertEquals(2.0, row2.getDouble(0), 0.0);
    Assert.assertArrayEquals(new double[] { 3.0, 4.0 }, ((Vector) row2.get(1)).toArray(), 0.0);
}

Example 23 with Row

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

the class MLContextTest method testOutputDataFrameVectorsNoIDColumnFromMatrixDML.

@Test
public void testOutputDataFrameVectorsNoIDColumnFromMatrixDML() {
    System.out.println("MLContextTest - output DataFrame of vectors 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").toDFVectorNoIDColumn();
    List<Row> list = df.collectAsList();
    Row row = list.get(0);
    Assert.assertArrayEquals(new double[] { 1.0, 2.0, 3.0, 4.0 }, ((Vector) row.get(0)).toArray(), 0.0);
}

Example 24 with Row

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

the class MLContextTest method testOutputDataFrameVectorsWithIDColumnFromMatrixDML.

@Test
public void testOutputDataFrameVectorsWithIDColumnFromMatrixDML() {
    System.out.println("MLContextTest - output DataFrame of vectors with 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").toDFVectorWithIDColumn();
    List<Row> list = df.collectAsList();
    Row row = list.get(0);
    Assert.assertEquals(1.0, row.getDouble(0), 0.0);
    Assert.assertArrayEquals(new double[] { 1.0, 2.0, 3.0, 4.0 }, ((Vector) row.get(1)).toArray(), 0.0);
}

Example 25 with Row

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

the class MLContextTest method testDataFrameSumPYDMLVectorWithIDColumn.

@Test
public void testDataFrameSumPYDMLVectorWithIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, vector with ID column");
    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);
    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);
}