data-maker/data/maker/__main__.py

import pandas as pd
import data.maker
from data.params import SYS_ARGS
import json
from scipy.stats import wasserstein_distance as wd
import risk
import numpy as np
if 'config' in SYS_ARGS :
    ARGS = json.loads(open(SYS_ARGS['config']).read())
    if 'generate' not in SYS_ARGS :
        data.maker.train(**ARGS)    
    else:
        #
        #
        ARGS['no_value'] = ''
        _df = data.maker.generate(**ARGS)
        odf = pd.read_csv (ARGS['data'])
        odf.columns = [name.lower() for name in odf.columns]
        column = ARGS['column']  if isinstance(ARGS['column'],list) else [ARGS['column']]
        # print (odf.head())
        # print (_df.head())
        print(odf.join(_df[column],rsuffix='_io'))
        # print (_df[column].risk.evaluate(flag='synth'))
        # print (odf[column].risk.evaluate(flag='original'))
        # _x = pd.get_dummies(_df[column]).values
        # y  = pd.get_dummies(odf[column]).values
        # N = _df.shape[0]
        # print (np.mean([ wd(_x[i],y[i])for i in range(0,N)]))
        # print (wd(_x[0],y[0]) )
        
        # column = SYS_ARGS['column']
        # odf = open(SYS_ARGS['data'])