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

Example 11 with StructType

use of org.apache.spark.sql.types.StructType 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 12 with StructType

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

Example 13 with StructType

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

the class MLContextTest method testDataFrameSumPYDMLVectorWithNoIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column, no format specified");
    List<Vector> list = new ArrayList<Vector>();
    list.add(Vectors.dense(1.0, 2.0, 3.0));
    list.add(Vectors.dense(4.0, 5.0, 6.0));
    list.add(Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    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 14 with StructType

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

Example 15 with StructType

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

the class MLContextTest method testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified.

@Test
public void testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified() {
    System.out.println("MLContextTest - DataFrame sum DML, vector with no ID column, no format specified");
    List<Vector> list = new ArrayList<Vector>();
    list.add(Vectors.dense(1.0, 2.0, 3.0));
    list.add(Vectors.dense(4.0, 5.0, 6.0));
    list.add(Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    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);
}