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

Example 16 with StructType

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

the class MLContextTest method testInputBinaryBlockMatrixPYDML.

@Test
public void testInputBinaryBlockMatrixPYDML() {
    System.out.println("MLContextTest - input BinaryBlockMatrix 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);
    BinaryBlockMatrix binaryBlockMatrix = new BinaryBlockMatrix(dataFrame);
    Script script = pydml("avg = avg(M)").in("M", binaryBlockMatrix).out("avg");
    double avg = ml.execute(script).getDouble("avg");
    Assert.assertEquals(50.0, avg, 0.0);
}

Example 17 with StructType

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

the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumn.

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

Example 18 with StructType

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

the class MLContextTest method testDataFrameGoodMetadataDML.

@Test
public void testDataFrameGoodMetadataDML() {
    System.out.println("MLContextTest - DataFrame good metadata DML");
    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 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);
    MatrixMetadata mm = new MatrixMetadata(3, 3, 9);
    Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 450.0");
    ml.execute(script);
}

Example 19 with StructType

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

the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumnSortCheck.

@Test
public void testDataFrameSumDMLDoublesWithIDColumnSortCheck() {
    System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('M[1,1]: ' + as.scalar(M[1,1]));").in("M", dataFrame, mm);
    setExpectedStdOut("M[1,1]: 1.0");
    ml.execute(script);
}

Example 20 with StructType

use of org.apache.spark.sql.types.StructType 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);
}