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

703 lines
24 KiB
Python

#!/usr/bin/env python3
5 years ago
class KEYS :
logger.write({"module":"bigquery","action":"read","input":{"sql":SQL}})
if 'autopilot' in ( list(args.keys())) :
else:
if df[name].unique().size > 0 :
4 years ago
columns.append(name)
4 years ago
x_cols = []
_columns = None
# 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} )
if 'matrix_size' in args :
else:
agent.train(**args)
#
# If we have any obs we should wait till they finish
#
# jobs = [job for job in jobs if job.is_alive()]