diff --git a/data/maker/__init__.py b/data/maker/__init__.py index cde3928..723991f 100644 --- a/data/maker/__init__.py +++ b/data/maker/__init__.py @@ -218,7 +218,13 @@ class Generator (Learner): for values in batches : index = [ _x not in ['',None,np.nan] for _x in values] - _values = np.random.dirichlet(values[index].astype(_type)) + + if len(index) == len(values): + # + # Sometimes messy data has unpleasant surprises + continue + _values = np.random.dirichlet(values[index].astype(_type)) + values[index] = list(values[index] + _values )if np.random.randint(0,2) else list(values[index] - _values) values[index] = values[index].astype(_type) x += values.tolist() @@ -284,7 +290,7 @@ class Generator (Learner): _df[name] = _df[name].astype('datetime64[ns]') else: _df[name] = _df[name].astype(str) - _df[name] = _df[name].replace('NaT','') + _df = _df.replace('NaT','') if r : self.log(**{'action':'format','input':r}) return _df