dev
Steve Nyemba 3 years ago
parent 4aacb74f29
commit 587248c63b

@ -219,7 +219,7 @@ class Generator (Learner):
index = [ _x not in ['',None,np.nan] for _x in values] index = [ _x not in ['',None,np.nan] for _x in values]
if len(index) == len(values): if np.sum(index) == 0:
# #
# Sometimes messy data has unpleasant surprises # Sometimes messy data has unpleasant surprises
continue continue
@ -228,6 +228,7 @@ class Generator (Learner):
values[index] = list(values[index] + _values )if np.random.randint(0,2) else list(values[index] - _values) values[index] = list(values[index] + _values )if np.random.randint(0,2) else list(values[index] - _values)
values[index] = values[index].astype(_type) values[index] = values[index].astype(_type)
x += values.tolist() x += values.tolist()
print (batches)
if x : if x :
_log['input']['identical_percentage'] = 100 * (1 - np.divide( (_df[name].dropna() == x).sum(),_df[name].dropna().size)) _log['input']['identical_percentage'] = 100 * (1 - np.divide( (_df[name].dropna() == x).sum(),_df[name].dropna().size))
_df[name] = x #np.array(x,dtype=np.int64) if 'int' in _type else np.arry(x,dtype=np.float64) _df[name] = x #np.array(x,dtype=np.int64) if 'int' in _type else np.arry(x,dtype=np.float64)

Loading…
Cancel
Save