use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.
the class DataFrameVectorFrameConversionTest method createDataFrame.
@SuppressWarnings("resource")
private Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) throws DMLRuntimeException {
//create in-memory list of rows
List<Row> list = new ArrayList<Row>();
int off = (containsID ? 1 : 0);
int clen = mb.getNumColumns() + off - colsVector + 1;
for (int i = 0; i < mb.getNumRows(); i++) {
Object[] row = new Object[clen];
if (containsID)
row[0] = (double) i + 1;
for (int j = 0, j2 = 0; j < mb.getNumColumns(); j++, j2++) {
if (schema[j2] != ValueType.OBJECT) {
row[j2 + off] = UtilFunctions.doubleToObject(schema[j2], mb.quickGetValue(i, j));
} else {
double[] tmp = DataConverter.convertToDoubleVector(mb.sliceOperations(i, i, j, j + colsVector - 1, new MatrixBlock()));
row[j2 + off] = new DenseVector(tmp);
j += colsVector - 1;
}
}
list.add(RowFactory.create(row));
}
//create data frame schema
List<StructField> fields = new ArrayList<StructField>();
if (containsID)
fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
for (int j = 0; j < schema.length; j++) {
DataType dt = null;
switch(schema[j]) {
case STRING:
dt = DataTypes.StringType;
break;
case DOUBLE:
dt = DataTypes.DoubleType;
break;
case INT:
dt = DataTypes.LongType;
break;
case OBJECT:
dt = new VectorUDT();
break;
default:
throw new RuntimeException("Unsupported value type.");
}
fields.add(DataTypes.createStructField("C" + (j + 1), dt, true));
}
StructType dfSchema = DataTypes.createStructType(fields);
//create rdd and data frame
JavaSparkContext sc = new JavaSparkContext(sparkSession.sparkContext());
JavaRDD<Row> rowRDD = sc.parallelize(list);
return sparkSession.createDataFrame(rowRDD, dfSchema);
}
use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.
the class DataFrameVectorScriptTest method createDataFrame.
@SuppressWarnings("resource")
private Dataset<Row> createDataFrame(SparkSession sparkSession, MatrixBlock mb, boolean containsID, ValueType[] schema) throws DMLRuntimeException {
//create in-memory list of rows
List<Row> list = new ArrayList<Row>();
int off = (containsID ? 1 : 0);
int clen = mb.getNumColumns() + off - colsVector + 1;
for (int i = 0; i < mb.getNumRows(); i++) {
Object[] row = new Object[clen];
if (containsID)
row[0] = (double) i + 1;
for (int j = 0, j2 = 0; j < mb.getNumColumns(); j++, j2++) {
if (schema[j2] != ValueType.OBJECT) {
row[j2 + off] = UtilFunctions.doubleToObject(schema[j2], mb.quickGetValue(i, j));
} else {
double[] tmp = DataConverter.convertToDoubleVector(mb.sliceOperations(i, i, j, j + colsVector - 1, new MatrixBlock()));
row[j2 + off] = new DenseVector(tmp);
j += colsVector - 1;
}
}
list.add(RowFactory.create(row));
}
//create data frame schema
List<StructField> fields = new ArrayList<StructField>();
if (containsID)
fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
for (int j = 0; j < schema.length; j++) {
DataType dt = null;
switch(schema[j]) {
case STRING:
dt = DataTypes.StringType;
break;
case DOUBLE:
dt = DataTypes.DoubleType;
break;
case INT:
dt = DataTypes.LongType;
break;
case OBJECT:
dt = new VectorUDT();
break;
default:
throw new RuntimeException("Unsupported value type.");
}
fields.add(DataTypes.createStructField("C" + (j + 1), dt, true));
}
StructType dfSchema = DataTypes.createStructType(fields);
//create rdd and data frame
JavaSparkContext sc = new JavaSparkContext(sparkSession.sparkContext());
JavaRDD<Row> rowRDD = sc.parallelize(list);
return sparkSession.createDataFrame(rowRDD, dfSchema);
}
use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumDMLVectorWithIDColumnNoFormatSpecified.
@Test
public void testDataFrameSumDMLVectorWithIDColumnNoFormatSpecified() {
System.out.println("MLContextTest - DataFrame sum DML, vector with ID column, no format specified");
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);
Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame);
setExpectedStdOut("sum: 45.0");
ml.execute(script);
}
use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumDMLMllibVectorWithNoIDColumn.
@Test
public void testDataFrameSumDMLMllibVectorWithNoIDColumn() {
System.out.println("MLContextTest - DataFrame sum DML, 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 = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
setExpectedStdOut("sum: 45.0");
ml.execute(script);
}
use of org.apache.spark.sql.types.StructType in project incubator-systemml by apache.
the class MLContextTest method testDataFrameSumDMLDoublesWithIDColumnNoFormatSpecified.
@Test
public void testDataFrameSumDMLDoublesWithIDColumnNoFormatSpecified() {
System.out.println("MLContextTest - DataFrame sum DML, doubles with ID column, no format specified");
List<String> list = new ArrayList<String>();
list.add("1,2,2,2");
list.add("2,3,3,3");
list.add("3,4,4,4");
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);
Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame);
setExpectedStdOut("sum: 27.0");
ml.execute(script);
}
Aggregations