Examples with MatrixMetadata org.apache.sysml.api.mlcontext.MatrixMetadata used on opensource projects

Example 16 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata 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 17 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.

the class MLContextOutputBlocksizeTest method runMLContextOutputBlocksizeTest.

private void runMLContextOutputBlocksizeTest(String format) {
    try {
        double[][] A = getRandomMatrix(rows, cols, -10, 10, sparsity, 76543);
        MatrixBlock mbA = DataConverter.convertToMatrixBlock(A);
        int blksz = ConfigurationManager.getBlocksize();
        MatrixCharacteristics mc = new MatrixCharacteristics(rows, cols, blksz, blksz, mbA.getNonZeros());
        // create input dataset
        JavaPairRDD<MatrixIndexes, MatrixBlock> in = SparkExecutionContext.toMatrixJavaPairRDD(sc, mbA, blksz, blksz);
        Matrix m = new Matrix(in, new MatrixMetadata(mc));
        ml.setExplain(true);
        ml.setExplainLevel(ExplainLevel.HOPS);
        // execute script
        String s = "if( sum(X) > 0 )" + "   X = X/2;" + "R = X;" + "write(R, \"/tmp\", format=\"" + format + "\");";
        Script script = dml(s).in("X", m).out("R");
        MLResults results = ml.execute(script);
        // compare output matrix characteristics
        MatrixCharacteristics mcOut = results.getMatrix("R").getMatrixMetadata().asMatrixCharacteristics();
        Assert.assertEquals(blksz, mcOut.getRowsPerBlock());
        Assert.assertEquals(blksz, mcOut.getColsPerBlock());
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new RuntimeException(ex);
    }
}

Example 18 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata 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 19 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata in project systemml by apache.

the class MLContextTest method testDataFrameSumDMLDoublesWithNoIDColumn.

@Test
public void testDataFrameSumDMLDoublesWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum DML, doubles with no ID column");
    List<String> list = new ArrayList<String>();
    list.add("10,20,30");
    list.add("40,50,60");
    list.add("70,80,90");
    JavaRDD<String> javaRddString = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddString.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fields = new ArrayList<StructField>();
    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);
    Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 450.0");
    ml.execute(script);
}

Example 20 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata in project systemml by apache.

the class MLContextTest method testInputTupleSeqWithMetadataPYDML.

@SuppressWarnings({ "rawtypes", "unchecked" })
@Test
public void testInputTupleSeqWithMetadataPYDML() {
    System.out.println("MLContextTest - Tuple sequence with metadata PYDML");
    List<String> list1 = new ArrayList<String>();
    list1.add("1,2");
    list1.add("3,4");
    JavaRDD<String> javaRDD1 = sc.parallelize(list1);
    RDD<String> rdd1 = JavaRDD.toRDD(javaRDD1);
    List<String> list2 = new ArrayList<String>();
    list2.add("5,6");
    list2.add("7,8");
    JavaRDD<String> javaRDD2 = sc.parallelize(list2);
    RDD<String> rdd2 = JavaRDD.toRDD(javaRDD2);
    MatrixMetadata mm1 = new MatrixMetadata(2, 2);
    MatrixMetadata mm2 = new MatrixMetadata(2, 2);
    Tuple3 tuple1 = new Tuple3("m1", rdd1, mm1);
    Tuple3 tuple2 = new Tuple3("m2", rdd2, mm2);
    List tupleList = new ArrayList();
    tupleList.add(tuple1);
    tupleList.add(tuple2);
    Seq seq = JavaConversions.asScalaBuffer(tupleList).toSeq();
    Script script = pydml("print('sums: ' + sum(m1) + ' ' + sum(m2))").in(seq);
    setExpectedStdOut("sums: 10.0 26.0");
    ml.execute(script);
}