You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
data-maker/pipeline.py

504 lines
16 KiB
Python

#!/usr/bin/env python3
5 years ago
@staticmethod
df = pd.read_gbq(SQL,credentials=credentials,dialect='standard')
else :
4 years ago
if 'ignore' in args and 'columns' in args['ignore'] :
else :
4 years ago
# _pname = os.sep.join([folder,table+'.csv'])
# _fname = table.replace('_io','_full_io')
# partial = '.'.join(['io',args['context']+'_partial_io'])
# complete= '.'.join(['io',args['context']+'_full_io'])
# data_comp.to_csv(_pname,index=False)
# if 'dump' in args :
# print (_args['data'].head())
# else:
# Components.lock.acquire()
# data_comp.to_gbq(if_exists='append',destination_table=partial,credentials=credentials,chunksize=90000)
# _args['data'].to_gbq(if_exists='append',destination_table=complete,credentials=credentials,chunksize=90000)
# Components.lock.release()
# _id = 'dataset'
# info = {"full":{_id:_fname,"rows":_args['data'].shape[0]},"partial":{"path":_pname,"rows":data_comp.shape[0]} }
# if partition :
# info ['partition'] = int(partition)
# logger.write({"module":"generate","action":"write","input":info} )
5 years ago
generator.generate(args)