use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumnSortCheck.
@Test
public void testDataFrameSumDMLDoublesWithIDColumnSortCheck() {
System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('M[1,1]: ' + as.scalar(M[1,1]));").in("M", dataFrame, mm);
setExpectedStdOut("M[1,1]: 1.0");
ml.execute(script);
}
use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.
the class MLContextTest method testIJVMatrixFromURLSumDML.
@Test
public void testIJVMatrixFromURLSumDML() throws MalformedURLException {
System.out.println("MLContextTest - IJV matrix from URL sum DML");
String ijv = "https://raw.githubusercontent.com/apache/systemml/master/src/test/scripts/org/apache/sysml/api/mlcontext/1234.ijv";
URL url = new URL(ijv);
MatrixMetadata mm = new MatrixMetadata(MatrixFormat.IJV, 2, 2);
Script script = dml("print('sum: ' + sum(M));").in("M", url, mm);
setExpectedStdOut("sum: 10.0");
ml.execute(script);
}
use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.
the class MLContextTest method testOutputBinaryBlocksPYDML.
@Test
public void testOutputBinaryBlocksPYDML() {
System.out.println("MLContextTest - output binary blocks PYDML");
String s = "M = full('1 2 3 4', rows=2, cols=2);";
MLResults results = ml.execute(pydml(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));
}
use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.
the class MLContextTest method testDataFrameGoodMetadataDML.
@Test
public void testDataFrameGoodMetadataDML() {
System.out.println("MLContextTest - DataFrame good metadata DML");
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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
setExpectedStdOut("sum: 450.0");
ml.execute(script);
}
use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumPYDMLVectorWithNoIDColumn.
@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumn() {
System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column");
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);
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);
}
Aggregations