in benchmarking/pipemode_benchmark/dataset.py [0:0]
def build(self, overwrite=False):
"""Build the dataset and upload to s3.
Args:
overwrite (bool): If true will overwrite the dataset if it exists already.
"""
if self._exists() and not overwrite:
return
self.root_dir = tempfile.mkdtemp()
self._make_benchmark_files()
self._upload_to_s3()
self._cleanup()