def run(self):
harmonized_file = self.input()[0].path
parallel.mapreduce(
parallel.Collection.from_sharded(self.input()[1].path),
annotate.AnnotateMapper(harmonized_file),
parallel.IdentityReducer(),
self.output().path)
def run(self):
harmonized_file = self.input()[0].path
parallel.mapreduce(glob.glob(self.input()[1].path + '*-of-*'),
annotate.AnnotateMapper(harmonized_file),
parallel.identity_reducer,
self.output().path,
num_shards=10,
map_workers=2)