use of org.apache.spark.sql.Row in project incubator-systemml by apache.
the class MLContextTest method testOutputDataFramePYDMLVectorNoIDColumn.
@Test
public void testOutputDataFramePYDMLVectorNoIDColumn() {
System.out.println("MLContextTest - output DataFrame PYDML, vector no ID column");
String s = "M = full('1 2 3 4', rows=2, cols=2)";
Script script = pydml(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);
}
use of org.apache.spark.sql.Row 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);
}
use of org.apache.spark.sql.Row 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);
}
use of org.apache.spark.sql.Row in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumDMLVectorWithIDColumn.
@Test
public void testDataFrameSumDMLVectorWithIDColumn() {
System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
setExpectedStdOut("sum: 45.0");
ml.execute(script);
}
use of org.apache.spark.sql.Row in project incubator-systemml by apache.
the class MLContextTest method testOutputDataFrameDMLDoublesNoIDColumn.
@Test
public void testOutputDataFrameDMLDoublesNoIDColumn() {
System.out.println("MLContextTest - output DataFrame DML, doubles 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.getDataFrameDoubleNoIDColumn("M");
List<Row> list = dataFrame.collectAsList();
Row row1 = list.get(0);
Assert.assertEquals(1.0, row1.getDouble(0), 0.0);
Assert.assertEquals(2.0, row1.getDouble(1), 0.0);
Row row2 = list.get(1);
Assert.assertEquals(3.0, row2.getDouble(0), 0.0);
Assert.assertEquals(4.0, row2.getDouble(1), 0.0);
}
Aggregations