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

Example 51 with MatrixMetadata

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

the class MLContextTest method testOutputBinaryBlocksDML.

@Test
public void testOutputBinaryBlocksDML() {
    System.out.println("MLContextTest - output binary blocks DML");
    String s = "M = matrix('1 2 3 4', rows=2, cols=2);";
    MLResults results = ml.execute(dml(s).out("M"));
    Matrix m = results.getMatrix("M");
    JavaPairRDD<MatrixIndexes, MatrixBlock> binaryBlocks = m.toBinaryBlocks();
    MatrixMetadata mm = m.getMatrixMetadata();
    MatrixCharacteristics mc = mm.asMatrixCharacteristics();
    JavaRDD<String> javaRDDStringIJV = RDDConverterUtils.binaryBlockToTextCell(binaryBlocks, mc);
    List<String> lines = javaRDDStringIJV.collect();
    Assert.assertEquals("1 1 1.0", lines.get(0));
    Assert.assertEquals("1 2 2.0", lines.get(1));
    Assert.assertEquals("2 1 3.0", lines.get(2));
    Assert.assertEquals("2 2 4.0", lines.get(3));
}

Example 52 with MatrixMetadata

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

the class MLContextTest method testDataFrameSumPYDMLMllibVectorWithNoIDColumn.

@Test
public void testDataFrameSumPYDMLMllibVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with no ID column");
    List<org.apache.spark.mllib.linalg.Vector> list = new ArrayList<org.apache.spark.mllib.linalg.Vector>();
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0));
    list.add(org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0));
    JavaRDD<org.apache.spark.mllib.linalg.Vector> javaRddVector = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddVector.map(new MllibVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
    StructType schema = DataTypes.createStructType(fields);
    Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);
    MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}

Example 53 with MatrixMetadata

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

the class MLContextTest method testDataFrameGoodMetadataPYDML.

@Test
public void testDataFrameGoodMetadataPYDML() {
    System.out.println("MLContextTest - DataFrame good metadata PYDML");
    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(3, 3, 9);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 450.0");
    ml.execute(script);
}

Example 54 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata in project 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 55 with MatrixMetadata

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

the class MLContextTest method testDataFrameSumPYDMLDoublesWithIDColumnSortCheck.

@Test
public void testDataFrameSumPYDMLDoublesWithIDColumnSortCheck() {
    System.out.println("MLContextTest - DataFrame sum PYDML ID, doubles with ID column sort check");
    List<String> list = new ArrayList<String>();
    list.add("3,7,8,9");
    list.add("1,1,2,3");
    list.add("2,4,5,6");
    JavaRDD<String> javaRddString = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddString.map(new CommaSeparatedValueStringToDoubleArrayRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    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_WITH_INDEX);
    Script script = pydml("print('M[0,0]: ' + scalar(M[0,0]))").in("M", dataFrame, mm);
    setExpectedStdOut("M[0,0]: 1.0");
    ml.execute(script);
}