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

Example 51 with StructType

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

the class MLContextFrameTest method testFrame.

public void testFrame(FrameFormat format, SCRIPT_TYPE script_type, IO_TYPE inputType, IO_TYPE outputType) {
    System.out.println("MLContextTest - Frame JavaRDD<String> for format: " + format + " Script: " + script_type);
    List<String> listA = new ArrayList<String>();
    List<String> listB = new ArrayList<String>();
    FrameMetadata fmA = null, fmB = null;
    Script script = null;
    ValueType[] schemaA = { ValueType.INT, ValueType.STRING, ValueType.DOUBLE, ValueType.BOOLEAN };
    List<ValueType> lschemaA = Arrays.asList(schemaA);
    FrameSchema fschemaA = new FrameSchema(lschemaA);
    ValueType[] schemaB = { ValueType.STRING, ValueType.DOUBLE, ValueType.BOOLEAN };
    List<ValueType> lschemaB = Arrays.asList(schemaB);
    FrameSchema fschemaB = new FrameSchema(lschemaB);
    if (inputType != IO_TYPE.FILE) {
        if (format == FrameFormat.CSV) {
            listA.add("1,Str2,3.0,true");
            listA.add("4,Str5,6.0,false");
            listA.add("7,Str8,9.0,true");
            listB.add("Str12,13.0,true");
            listB.add("Str25,26.0,false");
            fmA = new FrameMetadata(FrameFormat.CSV, fschemaA, 3, 4);
            fmB = new FrameMetadata(FrameFormat.CSV, fschemaB, 2, 3);
        } else if (format == FrameFormat.IJV) {
            listA.add("1 1 1");
            listA.add("1 2 Str2");
            listA.add("1 3 3.0");
            listA.add("1 4 true");
            listA.add("2 1 4");
            listA.add("2 2 Str5");
            listA.add("2 3 6.0");
            listA.add("2 4 false");
            listA.add("3 1 7");
            listA.add("3 2 Str8");
            listA.add("3 3 9.0");
            listA.add("3 4 true");
            listB.add("1 1 Str12");
            listB.add("1 2 13.0");
            listB.add("1 3 true");
            listB.add("2 1 Str25");
            listB.add("2 2 26.0");
            listB.add("2 3 false");
            fmA = new FrameMetadata(FrameFormat.IJV, fschemaA, 3, 4);
            fmB = new FrameMetadata(FrameFormat.IJV, fschemaB, 2, 3);
        }
        JavaRDD<String> javaRDDA = sc.parallelize(listA);
        JavaRDD<String> javaRDDB = sc.parallelize(listB);
        if (inputType == IO_TYPE.DATAFRAME) {
            JavaRDD<Row> javaRddRowA = FrameRDDConverterUtils.csvToRowRDD(sc, javaRDDA, CSV_DELIM, schemaA);
            JavaRDD<Row> javaRddRowB = FrameRDDConverterUtils.csvToRowRDD(sc, javaRDDB, CSV_DELIM, schemaB);
            // Create DataFrame
            StructType dfSchemaA = FrameRDDConverterUtils.convertFrameSchemaToDFSchema(schemaA, false);
            Dataset<Row> dataFrameA = spark.createDataFrame(javaRddRowA, dfSchemaA);
            StructType dfSchemaB = FrameRDDConverterUtils.convertFrameSchemaToDFSchema(schemaB, false);
            Dataset<Row> dataFrameB = spark.createDataFrame(javaRddRowB, dfSchemaB);
            if (script_type == SCRIPT_TYPE.DML)
                script = dml("A[2:3,2:4]=B;C=A[2:3,2:3]").in("A", dataFrameA, fmA).in("B", dataFrameB, fmB).out("A").out("C");
            else if (script_type == SCRIPT_TYPE.PYDML)
                // DO NOT USE ; at the end of any statment, it throws NPE
                script = pydml("A[$X:$Y,$X:$Z]=B\nC=A[$X:$Y,$X:$Y]").in("A", dataFrameA, fmA).in("B", dataFrameB, fmB).in("$X", 1).in("$Y", 3).in("$Z", 4).out("A").out("C");
        } else {
            if (inputType == IO_TYPE.JAVA_RDD_STR_CSV || inputType == IO_TYPE.JAVA_RDD_STR_IJV) {
                if (script_type == SCRIPT_TYPE.DML)
                    script = dml("A[2:3,2:4]=B;C=A[2:3,2:3]").in("A", javaRDDA, fmA).in("B", javaRDDB, fmB).out("A").out("C");
                else if (script_type == SCRIPT_TYPE.PYDML)
                    // DO NOT USE ; at the end of any statment, it throws
                    // NPE
                    script = pydml("A[$X:$Y,$X:$Z]=B\nC=A[$X:$Y,$X:$Y]").in("A", javaRDDA, fmA).in("B", javaRDDB, fmB).in("$X", 1).in("$Y", 3).in("$Z", 4).out("A").out("C");
            } else if (inputType == IO_TYPE.RDD_STR_CSV || inputType == IO_TYPE.RDD_STR_IJV) {
                RDD<String> rddA = JavaRDD.toRDD(javaRDDA);
                RDD<String> rddB = JavaRDD.toRDD(javaRDDB);
                if (script_type == SCRIPT_TYPE.DML)
                    script = dml("A[2:3,2:4]=B;C=A[2:3,2:3]").in("A", rddA, fmA).in("B", rddB, fmB).out("A").out("C");
                else if (script_type == SCRIPT_TYPE.PYDML)
                    // DO NOT USE ; at the end of any statment, it throws
                    // NPE
                    script = pydml("A[$X:$Y,$X:$Z]=B\nC=A[$X:$Y,$X:$Y]").in("A", rddA, fmA).in("B", rddB, fmB).in("$X", 1).in("$Y", 3).in("$Z", 4).out("A").out("C");
            }
        }
    } else {
        // Input type is file
        String fileA = null, fileB = null;
        if (format == FrameFormat.CSV) {
            fileA = baseDirectory + File.separator + "FrameA.csv";
            fileB = baseDirectory + File.separator + "FrameB.csv";
        } else if (format == FrameFormat.IJV) {
            fileA = baseDirectory + File.separator + "FrameA.ijv";
            fileB = baseDirectory + File.separator + "FrameB.ijv";
        }
        if (script_type == SCRIPT_TYPE.DML)
            script = dml("A=read($A); B=read($B);A[2:3,2:4]=B;C=A[2:3,2:3];A[1,1]=234").in("$A", fileA, fmA).in("$B", fileB, fmB).out("A").out("C");
        else if (script_type == SCRIPT_TYPE.PYDML)
            // DO NOT USE ; at the end of any statment, it throws NPE
            script = pydml("A=load($A)\nB=load($B)\nA[$X:$Y,$X:$Z]=B\nC=A[$X:$Y,$X:$Y]").in("$A", fileA).in("$B", fileB).in("$X", 1).in("$Y", 3).in("$Z", 4).out("A").out("C");
    }
    MLResults mlResults = ml.execute(script);
    // Validate output schema
    List<ValueType> lschemaOutA = Arrays.asList(mlResults.getFrameObject("A").getSchema());
    List<ValueType> lschemaOutC = Arrays.asList(mlResults.getFrameObject("C").getSchema());
    Assert.assertEquals(ValueType.INT, lschemaOutA.get(0));
    Assert.assertEquals(ValueType.STRING, lschemaOutA.get(1));
    Assert.assertEquals(ValueType.DOUBLE, lschemaOutA.get(2));
    Assert.assertEquals(ValueType.BOOLEAN, lschemaOutA.get(3));
    Assert.assertEquals(ValueType.STRING, lschemaOutC.get(0));
    Assert.assertEquals(ValueType.DOUBLE, lschemaOutC.get(1));
    if (outputType == IO_TYPE.JAVA_RDD_STR_CSV) {
        JavaRDD<String> javaRDDStringCSVA = mlResults.getJavaRDDStringCSV("A");
        List<String> linesA = javaRDDStringCSVA.collect();
        Assert.assertEquals("1,Str2,3.0,true", linesA.get(0));
        Assert.assertEquals("4,Str12,13.0,true", linesA.get(1));
        Assert.assertEquals("7,Str25,26.0,false", linesA.get(2));
        JavaRDD<String> javaRDDStringCSVC = mlResults.getJavaRDDStringCSV("C");
        List<String> linesC = javaRDDStringCSVC.collect();
        Assert.assertEquals("Str12,13.0", linesC.get(0));
        Assert.assertEquals("Str25,26.0", linesC.get(1));
    } else if (outputType == IO_TYPE.JAVA_RDD_STR_IJV) {
        JavaRDD<String> javaRDDStringIJVA = mlResults.getJavaRDDStringIJV("A");
        List<String> linesA = javaRDDStringIJVA.collect();
        Assert.assertEquals("1 1 1", linesA.get(0));
        Assert.assertEquals("1 2 Str2", linesA.get(1));
        Assert.assertEquals("1 3 3.0", linesA.get(2));
        Assert.assertEquals("1 4 true", linesA.get(3));
        Assert.assertEquals("2 1 4", linesA.get(4));
        Assert.assertEquals("2 2 Str12", linesA.get(5));
        Assert.assertEquals("2 3 13.0", linesA.get(6));
        Assert.assertEquals("2 4 true", linesA.get(7));
        JavaRDD<String> javaRDDStringIJVC = mlResults.getJavaRDDStringIJV("C");
        List<String> linesC = javaRDDStringIJVC.collect();
        Assert.assertEquals("1 1 Str12", linesC.get(0));
        Assert.assertEquals("1 2 13.0", linesC.get(1));
        Assert.assertEquals("2 1 Str25", linesC.get(2));
        Assert.assertEquals("2 2 26.0", linesC.get(3));
    } else if (outputType == IO_TYPE.RDD_STR_CSV) {
        RDD<String> rddStringCSVA = mlResults.getRDDStringCSV("A");
        Iterator<String> iteratorA = rddStringCSVA.toLocalIterator();
        Assert.assertEquals("1,Str2,3.0,true", iteratorA.next());
        Assert.assertEquals("4,Str12,13.0,true", iteratorA.next());
        Assert.assertEquals("7,Str25,26.0,false", iteratorA.next());
        RDD<String> rddStringCSVC = mlResults.getRDDStringCSV("C");
        Iterator<String> iteratorC = rddStringCSVC.toLocalIterator();
        Assert.assertEquals("Str12,13.0", iteratorC.next());
        Assert.assertEquals("Str25,26.0", iteratorC.next());
    } else if (outputType == IO_TYPE.RDD_STR_IJV) {
        RDD<String> rddStringIJVA = mlResults.getRDDStringIJV("A");
        Iterator<String> iteratorA = rddStringIJVA.toLocalIterator();
        Assert.assertEquals("1 1 1", iteratorA.next());
        Assert.assertEquals("1 2 Str2", iteratorA.next());
        Assert.assertEquals("1 3 3.0", iteratorA.next());
        Assert.assertEquals("1 4 true", iteratorA.next());
        Assert.assertEquals("2 1 4", iteratorA.next());
        Assert.assertEquals("2 2 Str12", iteratorA.next());
        Assert.assertEquals("2 3 13.0", iteratorA.next());
        Assert.assertEquals("2 4 true", iteratorA.next());
        Assert.assertEquals("3 1 7", iteratorA.next());
        Assert.assertEquals("3 2 Str25", iteratorA.next());
        Assert.assertEquals("3 3 26.0", iteratorA.next());
        Assert.assertEquals("3 4 false", iteratorA.next());
        RDD<String> rddStringIJVC = mlResults.getRDDStringIJV("C");
        Iterator<String> iteratorC = rddStringIJVC.toLocalIterator();
        Assert.assertEquals("1 1 Str12", iteratorC.next());
        Assert.assertEquals("1 2 13.0", iteratorC.next());
        Assert.assertEquals("2 1 Str25", iteratorC.next());
        Assert.assertEquals("2 2 26.0", iteratorC.next());
    } else if (outputType == IO_TYPE.DATAFRAME) {
        Dataset<Row> dataFrameA = mlResults.getDataFrame("A").drop(RDDConverterUtils.DF_ID_COLUMN);
        StructType dfschemaA = dataFrameA.schema();
        StructField structTypeA = dfschemaA.apply(0);
        Assert.assertEquals(DataTypes.LongType, structTypeA.dataType());
        structTypeA = dfschemaA.apply(1);
        Assert.assertEquals(DataTypes.StringType, structTypeA.dataType());
        structTypeA = dfschemaA.apply(2);
        Assert.assertEquals(DataTypes.DoubleType, structTypeA.dataType());
        structTypeA = dfschemaA.apply(3);
        Assert.assertEquals(DataTypes.BooleanType, structTypeA.dataType());
        List<Row> listAOut = dataFrameA.collectAsList();
        Row row1 = listAOut.get(0);
        Assert.assertEquals("Mismatch with expected value", Long.valueOf(1), row1.get(0));
        Assert.assertEquals("Mismatch with expected value", "Str2", row1.get(1));
        Assert.assertEquals("Mismatch with expected value", 3.0, row1.get(2));
        Assert.assertEquals("Mismatch with expected value", true, row1.get(3));
        Row row2 = listAOut.get(1);
        Assert.assertEquals("Mismatch with expected value", Long.valueOf(4), row2.get(0));
        Assert.assertEquals("Mismatch with expected value", "Str12", row2.get(1));
        Assert.assertEquals("Mismatch with expected value", 13.0, row2.get(2));
        Assert.assertEquals("Mismatch with expected value", true, row2.get(3));
        Dataset<Row> dataFrameC = mlResults.getDataFrame("C").drop(RDDConverterUtils.DF_ID_COLUMN);
        StructType dfschemaC = dataFrameC.schema();
        StructField structTypeC = dfschemaC.apply(0);
        Assert.assertEquals(DataTypes.StringType, structTypeC.dataType());
        structTypeC = dfschemaC.apply(1);
        Assert.assertEquals(DataTypes.DoubleType, structTypeC.dataType());
        List<Row> listCOut = dataFrameC.collectAsList();
        Row row3 = listCOut.get(0);
        Assert.assertEquals("Mismatch with expected value", "Str12", row3.get(0));
        Assert.assertEquals("Mismatch with expected value", 13.0, row3.get(1));
        Row row4 = listCOut.get(1);
        Assert.assertEquals("Mismatch with expected value", "Str25", row4.get(0));
        Assert.assertEquals("Mismatch with expected value", 26.0, row4.get(1));
    } else {
        String[][] frameA = mlResults.getFrameAs2DStringArray("A");
        Assert.assertEquals("Str2", frameA[0][1]);
        Assert.assertEquals("3.0", frameA[0][2]);
        Assert.assertEquals("13.0", frameA[1][2]);
        Assert.assertEquals("true", frameA[1][3]);
        Assert.assertEquals("Str25", frameA[2][1]);
        String[][] frameC = mlResults.getFrameAs2DStringArray("C");
        Assert.assertEquals("Str12", frameC[0][0]);
        Assert.assertEquals("Str25", frameC[1][0]);
        Assert.assertEquals("13.0", frameC[0][1]);
        Assert.assertEquals("26.0", frameC[1][1]);
    }
}

Example 52 with StructType

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

the class FrameRDDConverterUtils method binaryBlockToDataFrame.

public static Dataset<Row> binaryBlockToDataFrame(SparkSession sparkSession, JavaPairRDD<Long, FrameBlock> in, MatrixCharacteristics mc, ValueType[] schema) {
    if (!mc.colsKnown())
        throw new RuntimeException("Number of columns needed to convert binary block to data frame.");
    // convert binary block to rows rdd
    JavaRDD<Row> rowRDD = in.flatMap(new BinaryBlockToDataFrameFunction());
    // create data frame schema
    if (schema == null)
        schema = UtilFunctions.nCopies((int) mc.getCols(), ValueType.STRING);
    StructType dfSchema = convertFrameSchemaToDFSchema(schema, true);
    // rdd to data frame conversion
    return sparkSession.createDataFrame(rowRDD, dfSchema);
}

Example 53 with StructType

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

the class CsvWithDoubleHeaderToDataset method start.

private void start() {
    SparkSession spark = SparkSession.builder().appName("CSV to Dataset").master("local").getOrCreate();
    String filename = "data/csv-double-header.txt";
    // TODO
    StructType schema = buildSchemaFromCsvDefinition("1st line of file", "2nd line of file");
    // I use a dirty comment trick to avoid manipulating the data file, but
    // one could build the method...
    Dataset<Row> df = spark.read().schema(schema).option("inferSchema", "false").option("comment", "#").option("header", "true").option("mode", "DROPMALFORMED").csv(filename);
    df.show();
    df.printSchema();
}

Example 54 with StructType

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

the class RowProcessor method call.

@Override
public void call(JavaRDD<String> rdd) throws Exception {
    JavaRDD<Row> rowRDD = rdd.map(new Function<String, Row>() {

        private static final long serialVersionUID = 5167089361335095997L;

        @Override
        public Row call(String msg) {
            Row row = RowFactory.create(msg);
            return row;
        }
    });
    // Create Schema
    StructType schema = DataTypes.createStructType(new StructField[] { DataTypes.createStructField("Message", DataTypes.StringType, true) });
    // Get Spark 2.0 session
    SparkSession spark = JavaSparkSessionSingleton.getInstance(rdd.context().getConf());
    Dataset<Row> msgDataFrame = spark.createDataFrame(rowRDD, schema);
    msgDataFrame.show();
}

Example 55 with StructType

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

the class BuildDataFrameFromScratch method start.

private void start() {
    SparkSession spark = SparkSession.builder().appName("Build a DataFrame from Scratch").master("local[*]").getOrCreate();
    List<String> stringAsList = new ArrayList<>();
    stringAsList.add("bar");
    JavaSparkContext sparkContext = new JavaSparkContext(spark.sparkContext());
    JavaRDD<Row> rowRDD = sparkContext.parallelize(stringAsList).map((String row) -> RowFactory.create(row));
    // Creates schema
    StructType schema = DataTypes.createStructType(new StructField[] { DataTypes.createStructField("foe", DataTypes.StringType, false) });
    Dataset<Row> df = spark.sqlContext().createDataFrame(rowRDD, schema).toDF();
    log.debug("** Schema: ");
    df.printSchema();
    log.debug("** Data: ");
    df.show();
    sparkContext.close();
}