use of org.apache.sysml.runtime.controlprogram.caching.FrameObject in project incubator-systemml by apache.
the class MLContextConversionUtil method javaRDDStringIJVToFrameObject.
/**
* Convert a {@code JavaRDD<String>} in IJV format to a {@code FrameObject}
* . Note that metadata is required for IJV format.
*
* @param variableName
* name of the variable associated with the frame
* @param javaRDD
* the Java RDD of strings
* @param frameMetadata
* frame metadata
* @return the {@code JavaRDD<String>} converted to a {@code FrameObject}
*/
public static FrameObject javaRDDStringIJVToFrameObject(String variableName, JavaRDD<String> javaRDD, FrameMetadata frameMetadata) {
JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
MatrixCharacteristics mc = (frameMetadata != null) ? frameMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
JavaPairRDD<LongWritable, Text> javaPairRDDText = javaPairRDD.mapToPair(new CopyTextInputFunction());
FrameObject frameObject = new FrameObject(OptimizerUtils.getUniqueTempFileName(), new MatrixFormatMetaData(mc, OutputInfo.BinaryBlockOutputInfo, InputInfo.BinaryBlockInputInfo), frameMetadata.getFrameSchema().getSchema().toArray(new ValueType[0]));
JavaPairRDD<Long, FrameBlock> rdd;
try {
ValueType[] lschema = null;
if (lschema == null)
lschema = UtilFunctions.nCopies((int) mc.getCols(), ValueType.STRING);
rdd = FrameRDDConverterUtils.textCellToBinaryBlock(jsc(), javaPairRDDText, mc, lschema);
} catch (DMLRuntimeException e) {
e.printStackTrace();
return null;
}
frameObject.setRDDHandle(new RDDObject(rdd, variableName));
return frameObject;
}
Aggregations