Search in sources :

Example 41 with MatrixMetadata

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

the class MLContextTest method testDataFrameSumPYDMLMllibVectorWithIDColumn.

@Test
public void testDataFrameSumPYDMLMllibVectorWithIDColumn() {
    System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with ID column");
    List<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> list = new ArrayList<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>>();
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(1.0, org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0)));
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(2.0, org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0)));
    list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(3.0, org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0)));
    JavaRDD<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> javaRddTuple = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleMllibVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    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_WITH_INDEX);
    Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}
Also used : Script(org.apache.sysml.api.mlcontext.Script) VectorUDT(org.apache.spark.ml.linalg.VectorUDT) StructType(org.apache.spark.sql.types.StructType) ArrayList(java.util.ArrayList) StructField(org.apache.spark.sql.types.StructField) Tuple2(scala.Tuple2) Row(org.apache.spark.sql.Row) MatrixMetadata(org.apache.sysml.api.mlcontext.MatrixMetadata) Vector(org.apache.spark.ml.linalg.Vector) DenseVector(org.apache.spark.ml.linalg.DenseVector) Test(org.junit.Test)

Example 42 with MatrixMetadata

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

the class MLContextTest method testDataFrameSumDMLVectorWithNoIDColumn.

@Test
public void testDataFrameSumDMLVectorWithNoIDColumn() {
    System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}
Also used : Script(org.apache.sysml.api.mlcontext.Script) VectorUDT(org.apache.spark.ml.linalg.VectorUDT) StructType(org.apache.spark.sql.types.StructType) ArrayList(java.util.ArrayList) StructField(org.apache.spark.sql.types.StructField) Row(org.apache.spark.sql.Row) MatrixMetadata(org.apache.sysml.api.mlcontext.MatrixMetadata) Vector(org.apache.spark.ml.linalg.Vector) DenseVector(org.apache.spark.ml.linalg.DenseVector) Test(org.junit.Test)

Example 43 with MatrixMetadata

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

the class MLContextTest method testJavaRDDGoodMetadataDML.

@Test
public void testJavaRDDGoodMetadataDML() {
    System.out.println("MLContextTest - JavaRDD<String> good metadata DML");
    List<String> list = new ArrayList<String>();
    list.add("1,2,3");
    list.add("4,5,6");
    list.add("7,8,9");
    JavaRDD<String> javaRDD = sc.parallelize(list);
    MatrixMetadata mm = new MatrixMetadata(3, 3, 9);
    Script script = dml("print('sum: ' + sum(M));").in("M", javaRDD, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}
Also used : Script(org.apache.sysml.api.mlcontext.Script) ArrayList(java.util.ArrayList) MatrixMetadata(org.apache.sysml.api.mlcontext.MatrixMetadata) Test(org.junit.Test)

Example 44 with MatrixMetadata

use of org.apache.sysml.api.mlcontext.MatrixMetadata in project incubator-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);
}
Also used : Script(org.apache.sysml.api.mlcontext.Script) StructType(org.apache.spark.sql.types.StructType) ArrayList(java.util.ArrayList) StructField(org.apache.spark.sql.types.StructField) Row(org.apache.spark.sql.Row) MatrixMetadata(org.apache.sysml.api.mlcontext.MatrixMetadata) Test(org.junit.Test)

Example 45 with MatrixMetadata

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

the class MLContextTest method testDataFrameSumDMLVectorWithIDColumn.

@Test
public void testDataFrameSumDMLVectorWithIDColumn() {
    System.out.println("MLContextTest - DataFrame sum DML, vector with ID column");
    List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
    list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
    list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
    list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
    JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);
    JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
    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_WITH_INDEX);
    Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
    setExpectedStdOut("sum: 45.0");
    ml.execute(script);
}
Also used : Script(org.apache.sysml.api.mlcontext.Script) VectorUDT(org.apache.spark.ml.linalg.VectorUDT) StructType(org.apache.spark.sql.types.StructType) ArrayList(java.util.ArrayList) StructField(org.apache.spark.sql.types.StructField) Tuple2(scala.Tuple2) Row(org.apache.spark.sql.Row) MatrixMetadata(org.apache.sysml.api.mlcontext.MatrixMetadata) Vector(org.apache.spark.ml.linalg.Vector) DenseVector(org.apache.spark.ml.linalg.DenseVector) Test(org.junit.Test)

Aggregations

MatrixMetadata (org.apache.sysml.api.mlcontext.MatrixMetadata)72 Script (org.apache.sysml.api.mlcontext.Script)68 Test (org.junit.Test)68 ArrayList (java.util.ArrayList)60 Row (org.apache.spark.sql.Row)36 StructField (org.apache.spark.sql.types.StructField)34 StructType (org.apache.spark.sql.types.StructType)34 DenseVector (org.apache.spark.ml.linalg.DenseVector)16 Vector (org.apache.spark.ml.linalg.Vector)16 VectorUDT (org.apache.spark.ml.linalg.VectorUDT)16 MLResults (org.apache.sysml.api.mlcontext.MLResults)12 MatrixCharacteristics (org.apache.sysml.runtime.matrix.MatrixCharacteristics)10 MatrixBlock (org.apache.sysml.runtime.matrix.data.MatrixBlock)10 MatrixIndexes (org.apache.sysml.runtime.matrix.data.MatrixIndexes)10 Matrix (org.apache.sysml.api.mlcontext.Matrix)8 Tuple2 (scala.Tuple2)8 URL (java.net.URL)4 List (java.util.List)4 Tuple3 (scala.Tuple3)4 Seq (scala.collection.Seq)4