|
|
|
"""
|
|
|
|
(c) 2019 Data Maker, hiplab.mc.vanderbilt.edu
|
|
|
|
version 1.0.0
|
|
|
|
|
|
|
|
This package serves as a proxy to the overall usage of the framework.
|
|
|
|
This package is designed to generate synthetic data from a dataset from an original dataset using deep learning techniques
|
|
|
|
|
|
|
|
@TODO:
|
|
|
|
- Make configurable GPU, EPOCHS
|
|
|
|
"""
|
|
|
|
import pandas as pd
|
|
|
|
import numpy as np
|
|
|
|
from multiprocessing import Queue
|
|
|
|
self.logger = None
|
|
|
|
# logger =
|
|
|
|
_args = dict({'ndx':self.ndx,'module':self.name,'table':self.info['from'],'context':_context,'info':_label,**_args})
|
|
|
|
# At this point we apply pre-processing of the data if there were ever a need for it
|
|
|
|
_index = np.random.choice(np.arange(self._df[name].shape[0]),5,False)
|
|
|
|
for values in batches :
|
|
|
|
|
|
|
|
|
|
|
|
self.log(**{"action":"consolidate","input":{"rows":N,"candidate":_candidates.index(_iodf)}})
|
|
|
|
|
|
|
|
_xdf = _xdf.join(_tmpdf)
|
|
|
|
|
|
|
|
_xdf = _xdf[self._df.columns]
|
|
|
|
self._df = _xdf
|
|
|
|
pthread= Trainer(**_args)
|