Блог

Эта проблема возникает при запуске множественной регрессии в цикле for. Один из примеров этого представлен ниже: переменная y выглядит следующим образом:

 0         NaN
1         NaN
2         3
3         NaN
4         2
5         NaN
6         NaN
7         NaN
8         4
9         NaN
Name: 1794, dtype: float64
 

переменная x

      0   1   2     3         4
0   NaN NaN NaN 24.1071 -143.421717
1   NaN NaN NaN 18.1163 -144.781828
2   NaN NaN NaN 19.2395 -138.566242
3   3   0.0 0.0 21.2295 -153.737705
4   NaN NaN NaN 21.1719 -163.109375
5   2   0.0 0.0 23.6562 -168.140625
6   NaN NaN NaN 26.9867 -125.666667
7   NaN NaN NaN 28.1184 -107.486842
8   NaN NaN NaN 30.5556 -125.416667
9   4   0.0 0.0 28.0714 -136.071429
 

Код регрессии:

 reg = sm.OLS(y, sm.add_constant(x, has_constant = "add"), missing="drop").fit()
 

Сообщение об ошибке:

 ValueError                                Traceback (most recent call last)
<ipython-input-186-ff72de5301d3> in <module>
----> 1 reg = sm.OLS(y, sm.add_constant(x, has_constant = "add"), missing="drop").fit()

C:ProgramDataAnaconda3libsite-packagesstatsmodelsregressionlinear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
    870     def __init__(self, endog, exog=None, missing='none', hasconst=None,
    871                  **kwargs):
--> 872         super(OLS, self).__init__(endog, exog, missing=missing,
    873                                   hasconst=hasconst, **kwargs)
    874         if "weights" in self._init_keys:

C:ProgramDataAnaconda3libsite-packagesstatsmodelsregressionlinear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
    701         else:
    702             weights = weights.squeeze()
--> 703         super(WLS, self).__init__(endog, exog, missing=missing,
    704                                   weights=weights, hasconst=hasconst, **kwargs)
    705         nobs = self.exog.shape[0]

C:ProgramDataAnaconda3libsite-packagesstatsmodelsregressionlinear_model.py in __init__(self, endog, exog, **kwargs)
    188     """
    189     def __init__(self, endog, exog, **kwargs):
--> 190         super(RegressionModel, self).__init__(endog, exog, **kwargs)
    191         self._data_attr.extend(['pinv_wexog', 'weights'])
    192 

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasemodel.py in __init__(self, endog, exog, **kwargs)
    235 
    236     def __init__(self, endog, exog=None, **kwargs):
--> 237         super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
    238         self.initialize()
    239 

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasemodel.py in __init__(self, endog, exog, **kwargs)
     75         missing = kwargs.pop('missing', 'none')
     76         hasconst = kwargs.pop('hasconst', None)
---> 77         self.data = self._handle_data(endog, exog, missing, hasconst,
     78                                       **kwargs)
     79         self.k_constant = self.data.k_constant

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasemodel.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
     99 
    100     def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 101         data = handle_data(endog, exog, missing, hasconst, **kwargs)
    102         # kwargs arrays could have changed, easier to just attach here
    103         for key in kwargs:

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasedata.py in handle_data(endog, exog, missing, hasconst, **kwargs)
    670 
    671     klass = handle_data_class_factory(endog, exog)
--> 672     return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
    673                  **kwargs)

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasedata.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
     85         self.const_idx = None
     86         self.k_constant = 0
---> 87         self._handle_constant(hasconst)
     88         self._check_integrity()
     89         self._cache = {}

C:ProgramDataAnaconda3libsite-packagesstatsmodelsbasedata.py in _handle_constant(self, hasconst)
    129             # detect where the constant is
    130             check_implicit = False
--> 131             exog_max = np.max(self.exog, axis=0)
    132             if not np.isfinite(exog_max).all():
    133                 raise MissingDataError('exog contains inf or nans')

<__array_function__ internals> in amax(*args, **kwargs)

C:ProgramDataAnaconda3libsite-packagesnumpycorefromnumeric.py in amax(a, axis, out, keepdims, initial, where)
   2703     5
   2704     """
-> 2705     return _wrapreduction(a, np.maximum, 'max', axis, None, out,
   2706                           keepdims=keepdims, initial=initial, where=where)
   2707 

C:ProgramDataAnaconda3libsite-packagesnumpycorefromnumeric.py in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs)
     85                 return reduction(axis=axis, out=out, **passkwargs)
     86 
---> 87     return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
     88 
     89 

ValueError: zero-size array to reduction operation maximum which has no identity
 

Я знаю, что есть похожие сообщения об этой ошибке, но я не смог найти точный случай, и все, что было предложено в других сообщениях, не помогло.