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

Example 46 with Row

use of org.apache.spark.sql.Row 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();
}

Example 47 with Row

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

the class MLContextFrameTest method testInputFrameAndMatrixOutputMatrix.

@Test
public void testInputFrameAndMatrixOutputMatrix() {
    System.out.println("MLContextFrameTest - input frame and matrix, output matrix");
    List<String> dataA = new ArrayList<String>();
    dataA.add("Test1,4.0");
    dataA.add("Test2,5.0");
    dataA.add("Test3,6.0");
    JavaRDD<String> javaRddStringA = sc.parallelize(dataA);
    ValueType[] schema = { ValueType.STRING, ValueType.DOUBLE };
    List<String> dataB = new ArrayList<String>();
    dataB.add("1.0");
    dataB.add("2.0");
    JavaRDD<String> javaRddStringB = sc.parallelize(dataB);
    JavaRDD<Row> javaRddRowA = FrameRDDConverterUtils.csvToRowRDD(sc, javaRddStringA, CSV_DELIM, schema);
    JavaRDD<Row> javaRddRowB = javaRddStringB.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fieldsA = new ArrayList<StructField>();
    fieldsA.add(DataTypes.createStructField("1", DataTypes.StringType, true));
    fieldsA.add(DataTypes.createStructField("2", DataTypes.DoubleType, true));
    StructType schemaA = DataTypes.createStructType(fieldsA);
    Dataset<Row> dataFrameA = spark.createDataFrame(javaRddRowA, schemaA);
    List<StructField> fieldsB = new ArrayList<StructField>();
    fieldsB.add(DataTypes.createStructField("1", DataTypes.DoubleType, true));
    StructType schemaB = DataTypes.createStructType(fieldsB);
    Dataset<Row> dataFrameB = spark.createDataFrame(javaRddRowB, schemaB);
    String dmlString = "[tA, tAM] = transformencode (target = A, spec = \"{ids: true ,recode: [ 1, 2 ]}\");\n" + "C = tA %*% B;\n" + "M = s * C;";
    Script script = dml(dmlString).in("A", dataFrameA, new FrameMetadata(FrameFormat.CSV, dataFrameA.count(), (long) dataFrameA.columns().length)).in("B", dataFrameB, new MatrixMetadata(MatrixFormat.CSV, dataFrameB.count(), (long) dataFrameB.columns().length)).in("s", 2).out("M");
    MLResults results = ml.execute(script);
    double[][] matrix = results.getMatrixAs2DDoubleArray("M");
    Assert.assertEquals(6.0, matrix[0][0], 0.0);
    Assert.assertEquals(12.0, matrix[1][0], 0.0);
    Assert.assertEquals(18.0, matrix[2][0], 0.0);
}

Example 48 with Row

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

the class MLContextParforDatasetTest method runMLContextParforDatasetTest.

private void runMLContextParforDatasetTest(boolean vector, boolean unknownDims, boolean multiInputs) {
    // modify memory budget to trigger fused datapartition-execute
    long oldmem = InfrastructureAnalyzer.getLocalMaxMemory();
    // 1MB
    InfrastructureAnalyzer.setLocalMaxMemory(1 * 1024 * 1024);
    try {
        double[][] A = getRandomMatrix(rows, cols, -10, 10, sparsity, 76543);
        MatrixBlock mbA = DataConverter.convertToMatrixBlock(A);
        int blksz = ConfigurationManager.getBlocksize();
        MatrixCharacteristics mc1 = new MatrixCharacteristics(rows, cols, blksz, blksz, mbA.getNonZeros());
        MatrixCharacteristics mc2 = unknownDims ? new MatrixCharacteristics() : new MatrixCharacteristics(mc1);
        // create input dataset
        SparkSession sparkSession = SparkSession.builder().sparkContext(sc.sc()).getOrCreate();
        JavaPairRDD<MatrixIndexes, MatrixBlock> in = SparkExecutionContext.toMatrixJavaPairRDD(sc, mbA, blksz, blksz);
        Dataset<Row> df = RDDConverterUtils.binaryBlockToDataFrame(sparkSession, in, mc1, vector);
        MatrixMetadata mm = new MatrixMetadata(vector ? MatrixFormat.DF_VECTOR_WITH_INDEX : MatrixFormat.DF_DOUBLES_WITH_INDEX);
        mm.setMatrixCharacteristics(mc2);
        String s1 = "v = matrix(0, rows=nrow(X), cols=1)" + "parfor(i in 1:nrow(X), log=DEBUG) {" + "   v[i, ] = sum(X[i, ]);" + "}" + "r = sum(v);";
        String s2 = "v = matrix(0, rows=nrow(X), cols=1)" + "Y = X;" + "parfor(i in 1:nrow(X), log=DEBUG) {" + "   v[i, ] = sum(X[i, ]+Y[i, ]);" + "}" + "r = sum(v);";
        String s = multiInputs ? s2 : s1;
        ml.setExplain(true);
        ml.setExplainLevel(ExplainLevel.RUNTIME);
        ml.setStatistics(true);
        Script script = dml(s).in("X", df, mm).out("r");
        MLResults results = ml.execute(script);
        // compare aggregation results
        double sum1 = results.getDouble("r");
        double sum2 = mbA.sum() * (multiInputs ? 2 : 1);
        TestUtils.compareScalars(sum2, sum1, 0.000001);
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new RuntimeException(ex);
    } finally {
        InfrastructureAnalyzer.setLocalMaxMemory(oldmem);
    }
}

Example 49 with Row

use of org.apache.spark.sql.Row in project ignite by apache.

the class JavaStandaloneIgniteRDDSelfTest method testAllFieldsTypes.

/**
 * @throws Exception If failed.
 */
public void testAllFieldsTypes() throws Exception {
    JavaSparkContext sc = new JavaSparkContext("local[*]", "test");
    final int cnt = 100;
    try {
        JavaIgniteContext<String, EntityTestAllTypeFields> ic = new JavaIgniteContext<>(sc, new IgniteConfigProvider());
        JavaIgniteRDD<String, EntityTestAllTypeFields> cache = ic.fromCache(ENTITY_ALL_TYPES_CACHE_NAME);
        cache.savePairs(sc.parallelize(F.range(0, cnt), 2).mapToPair(INT_TO_ENTITY_ALL_FIELDS_F));
        EntityTestAllTypeFields e = new EntityTestAllTypeFields(cnt / 2);
        for (Field f : EntityTestAllTypeFields.class.getDeclaredFields()) {
            String fieldName = f.getName();
            Object val = GridTestUtils.getFieldValue(e, fieldName);
            Dataset<Row> df = cache.sql(String.format("select %s from EntityTestAllTypeFields where %s = ?", fieldName, fieldName), val);
            if (val instanceof BigDecimal) {
                Object res = ((Row[]) df.collect())[0].get(0);
                assertTrue(String.format("+++ Fail on %s field", fieldName), ((Comparable<BigDecimal>) val).compareTo((BigDecimal) res) == 0);
            } else if (val instanceof java.sql.Date)
                assertEquals(String.format("+++ Fail on %s field", fieldName), val.toString(), ((Row[]) df.collect())[0].get(0).toString());
            else if (val.getClass().isArray())
                assertTrue(String.format("+++ Fail on %s field", fieldName), 1 <= df.count());
            else {
                assertTrue(String.format("+++ Fail on %s field", fieldName), ((Row[]) df.collect()).length > 0);
                assertTrue(String.format("+++ Fail on %s field", fieldName), ((Row[]) df.collect())[0].size() > 0);
                assertEquals(String.format("+++ Fail on %s field", fieldName), val, ((Row[]) df.collect())[0].get(0));
            }
            info(String.format("+++ Query on the filed: %s : %s passed", fieldName, f.getType().getSimpleName()));
        }
    } finally {
        sc.stop();
    }
}

Example 50 with Row

use of org.apache.spark.sql.Row in project net.jgp.labs.spark by jgperrin.

the class CsvToDatasetApp method start.

private void start() {
    SparkSession spark = SparkSession.builder().appName("CSV to Dataset").master("local").getOrCreate();
    String filename = "data/tuple-data-file.csv";
    Dataset<Row> df = spark.read().format("csv").option("inferSchema", "true").option("header", "false").load(filename);
    df.show();
}