Examples with VectorUDT org.apache.spark.ml.linalg.VectorUDT used on opensource projects

Example 1 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class MLContextConversionUtil method determineMatrixFormatIfNeeded.

/**
	 * If the MatrixFormat of the DataFrame has not been explicitly specified,
	 * attempt to determine the proper MatrixFormat.
	 * 
	 * @param dataFrame
	 *            the Spark {@code DataFrame}
	 * @param matrixMetadata
	 *            the matrix metadata, if available
	 */
public static void determineMatrixFormatIfNeeded(Dataset<Row> dataFrame, MatrixMetadata matrixMetadata) {
    MatrixFormat matrixFormat = matrixMetadata.getMatrixFormat();
    if (matrixFormat != null) {
        return;
    }
    StructType schema = dataFrame.schema();
    boolean hasID = false;
    try {
        schema.fieldIndex(RDDConverterUtils.DF_ID_COLUMN);
        hasID = true;
    } catch (IllegalArgumentException iae) {
    }
    StructField[] fields = schema.fields();
    MatrixFormat mf = null;
    if (hasID) {
        if (fields[1].dataType() instanceof VectorUDT) {
            mf = MatrixFormat.DF_VECTOR_WITH_INDEX;
        } else {
            mf = MatrixFormat.DF_DOUBLES_WITH_INDEX;
        }
    } else {
        if (fields[0].dataType() instanceof VectorUDT) {
            mf = MatrixFormat.DF_VECTOR;
        } else {
            mf = MatrixFormat.DF_DOUBLES;
        }
    }
    if (mf == null) {
        throw new MLContextException("DataFrame format not recognized as an accepted SystemML MatrixFormat");
    }
    matrixMetadata.setMatrixFormat(mf);
}

Example 2 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT 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 3 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT 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 4 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT 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);
}

Example 5 with VectorUDT

use of org.apache.spark.ml.linalg.VectorUDT in project incubator-systemml by apache.

the class DataFrameVectorFrameConversionTest method createDataFrame.

@SuppressWarnings("resource")
private Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) throws DMLRuntimeException {
    //create in-memory list of rows
    List<Row> list = new ArrayList<Row>();
    int off = (containsID ? 1 : 0);
    int clen = mb.getNumColumns() + off - colsVector + 1;
    for (int i = 0; i < mb.getNumRows(); i++) {
        Object[] row = new Object[clen];
        if (containsID)
            row[0] = (double) i + 1;
        for (int j = 0, j2 = 0; j < mb.getNumColumns(); j++, j2++) {
            if (schema[j2] != ValueType.OBJECT) {
                row[j2 + off] = UtilFunctions.doubleToObject(schema[j2], mb.quickGetValue(i, j));
            } else {
                double[] tmp = DataConverter.convertToDoubleVector(mb.sliceOperations(i, i, j, j + colsVector - 1, new MatrixBlock()));
                row[j2 + off] = new DenseVector(tmp);
                j += colsVector - 1;
            }
        }
        list.add(RowFactory.create(row));
    }
    //create data frame schema
    List<StructField> fields = new ArrayList<StructField>();
    if (containsID)
        fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    for (int j = 0; j < schema.length; j++) {
        DataType dt = null;
        switch(schema[j]) {
            case STRING:
                dt = DataTypes.StringType;
                break;
            case DOUBLE:
                dt = DataTypes.DoubleType;
                break;
            case INT:
                dt = DataTypes.LongType;
                break;
            case OBJECT:
                dt = new VectorUDT();
                break;
            default:
                throw new RuntimeException("Unsupported value type.");
        }
        fields.add(DataTypes.createStructField("C" + (j + 1), dt, true));
    }
    StructType dfSchema = DataTypes.createStructType(fields);
    //create rdd and data frame
    JavaSparkContext sc = new JavaSparkContext(sparkSession.sparkContext());
    JavaRDD<Row> rowRDD = sc.parallelize(list);
    return sparkSession.createDataFrame(rowRDD, dfSchema);
}