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

Example 26 with Row

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

the class MLContextTest method testOutputJavaRDDStringIJVFromMatrixDML.

@Test
public void testOutputJavaRDDStringIJVFromMatrixDML() {
    System.out.println("MLContextTest - output Java RDD String IJV from matrix DML");
    String s = "M = matrix('1 2 3 4', rows=2, cols=2);";
    Script script = dml(s).out("M");
    MLResults results = ml.execute(script);
    JavaRDD<String> javaRDDStringIJV = results.getJavaRDDStringIJV("M");
    List<String> lines = javaRDDStringIJV.sortBy(row -> row, true, 1).collect();
    Assert.assertEquals("1 1 1.0", lines.get(0));
    Assert.assertEquals("1 2 2.0", lines.get(1));
    Assert.assertEquals("2 1 3.0", lines.get(2));
    Assert.assertEquals("2 2 4.0", lines.get(3));
}

Example 27 with Row

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

the class MLContextTest method testDataFrameSumDMLMllibVectorWithNoIDColumn.

@Test
public void testDataFrameSumDMLMllibVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum DML, mllib vector with no ID column");
    List<org.apache.spark.mllib.linalg.Vector> list = new ArrayList<org.apache.spark.mllib.linalg.Vector>();
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<org.apache.spark.mllib.linalg.Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new MllibVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    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);
    Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 28 with Row

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

the class MLContextTest method testOutputDataFramePYDMLVectorWithIDColumn.

@Test
public void testOutputDataFramePYDMLVectorWithIDColumn() {
    System.out.println("MLContextTest - output DataFrame PYDML, vector with 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.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 29 with Row

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

the class MLContextTest method testDataFrameSumPYDMLDoublesWithNoIDColumnNoFormatSpecified.

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

Example 30 with Row

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

the class MLContextTest method testDataFrameSumPYDMLDoublesWithIDColumn.

@Test
public void testDataFrameSumPYDMLDoublesWithIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, doubles with ID column");
    List<String> list = new ArrayList<String>();
    list.add("1,1,2,3");
    list.add("2,4,5,6");
    list.add("3,7,8,9");
    JavaRDD<String> javaRddString = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddString.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(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('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}