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

542 lines
17 KiB
Python

#!/usr/bin/env python3
5 years ago
@staticmethod
df = pd.read_gbq(SQL,credentials=credentials,dialect='standard')
else :
4 years ago
4 years ago
4 years ago
"io":{"min":_df[_col].min(),"max":_df[_col].max(),"mean":_df[_col].mean(),"sd":_df[_col].values.std(),"missing": _df[_col].where(_df[_col] == -1).dropna().count(),"zeros":_df[_col].where(_df[_col] == 0).dropna().count()},
# 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 :