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

Example 26 with StructField

use of org.apache.spark.sql.types.StructField 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 27 with StructField

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

the class DataFrameVectorFrameConversionTest method createDataFrame.

@SuppressWarnings("resource")
private static Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) {
    // 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.slice(i, i, j, j + colsVector - 1, new MatrixBlock()), false);
                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);
}

Example 28 with StructField

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

the class DataFrameVectorScriptTest method createDataFrame.

@SuppressWarnings("resource")
private static Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) {
    // 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.slice(i, i, j, j + colsVector - 1, new MatrixBlock()), false);
                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);
}

Example 29 with StructField

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

the class MLContextFrameTest method testInputFrameAndMatrixOutputMatrixAndFrame.

@Test
public void testInputFrameAndMatrixOutputMatrixAndFrame() {
    System.out.println("MLContextFrameTest - input frame and matrix, output matrix and frame");
    Row[] rowsA = { RowFactory.create("Doc1", "Feat1", 10), RowFactory.create("Doc1", "Feat2", 20), RowFactory.create("Doc2", "Feat1", 31) };
    JavaRDD<Row> javaRddRowA = sc.parallelize(Arrays.asList(rowsA));
    List<StructField> fieldsA = new ArrayList<StructField>();
    fieldsA.add(DataTypes.createStructField("myID", DataTypes.StringType, true));
    fieldsA.add(DataTypes.createStructField("FeatureName", DataTypes.StringType, true));
    fieldsA.add(DataTypes.createStructField("FeatureValue", DataTypes.IntegerType, true));
    StructType schemaA = DataTypes.createStructType(fieldsA);
    Dataset<Row> dataFrameA = spark.createDataFrame(javaRddRowA, schemaA);
    String dmlString = "[tA, tAM] = transformencode (target = A, spec = \"{ids: false ,recode: [ myID, FeatureName ]}\");";
    Script script = dml(dmlString).in("A", dataFrameA, new FrameMetadata(FrameFormat.CSV, dataFrameA.count(), (long) dataFrameA.columns().length)).out("tA").out("tAM");
    MLResults results = ml.execute(script);
    double[][] matrixtA = results.getMatrixAs2DDoubleArray("tA");
    Assert.assertEquals(10.0, matrixtA[0][2], 0.0);
    Assert.assertEquals(20.0, matrixtA[1][2], 0.0);
    Assert.assertEquals(31.0, matrixtA[2][2], 0.0);
    Dataset<Row> dataFrame_tA = results.getMatrix("tA").toDF();
    System.out.println("Number of matrix tA rows = " + dataFrame_tA.count());
    dataFrame_tA.printSchema();
    dataFrame_tA.show();
    Dataset<Row> dataFrame_tAM = results.getFrame("tAM").toDF();
    System.out.println("Number of frame tAM rows = " + dataFrame_tAM.count());
    dataFrame_tAM.printSchema();
    dataFrame_tAM.show();
}

Example 30 with StructField

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

the class MLContextFrameTest method testTransform.

@Test
public void testTransform() {
    System.out.println("MLContextFrameTest - transform");
    Row[] rowsA = { RowFactory.create("\"`@(\"(!&", 2, "20news-bydate-train/comp.os.ms-windows.misc/9979"), RowFactory.create("\"`@(\"\"(!&\"", 3, "20news-bydate-train/comp.os.ms-windows.misc/9979") };
    JavaRDD<Row> javaRddRowA = sc.parallelize(Arrays.asList(rowsA));
    List<StructField> fieldsA = new ArrayList<StructField>();
    fieldsA.add(DataTypes.createStructField("featureName", DataTypes.StringType, true));
    fieldsA.add(DataTypes.createStructField("featureValue", DataTypes.IntegerType, true));
    fieldsA.add(DataTypes.createStructField("id", DataTypes.StringType, true));
    StructType schemaA = DataTypes.createStructType(fieldsA);
    Dataset<Row> dataFrameA = spark.createDataFrame(javaRddRowA, schemaA);
    String dmlString = "[tA, tAM] = transformencode (target = A, spec = \"{ids: false ,recode: [ featureName, id ]}\");";
    Script script = dml(dmlString).in("A", dataFrameA, new FrameMetadata(FrameFormat.CSV, dataFrameA.count(), (long) dataFrameA.columns().length)).out("tA").out("tAM");
    ml.setExplain(true);
    ml.setExplainLevel(ExplainLevel.RECOMPILE_HOPS);
    MLResults results = ml.execute(script);
    double[][] matrixtA = results.getMatrixAs2DDoubleArray("tA");
    Assert.assertEquals(1.0, matrixtA[0][2], 0.0);
    Dataset<Row> dataFrame_tA = results.getMatrix("tA").toDF();
    System.out.println("Number of matrix tA rows = " + dataFrame_tA.count());
    dataFrame_tA.printSchema();
    dataFrame_tA.show();
    Dataset<Row> dataFrame_tAM = results.getFrame("tAM").toDF();
    System.out.println("Number of frame tAM rows = " + dataFrame_tAM.count());
    dataFrame_tAM.printSchema();
    dataFrame_tAM.show();
}