Scikit-Survival выдает AttributeError: объект float не имеет атрибута exp при вызове numpy.exp

Question

Я получаю следующее сообщение об ошибке:

AttributeError: 'float' object has no attribute 'exp'


The above exception was the direct cause of the following exception:

Traceback (most recent call last):

  File "/Users/herman/Documents/epistats/hw/hw4/hw4p2.py", line 125, in <module>
    chf_funcs = model.predict_cumulative_hazard_function(exposure3[:5])

  File "/opt/anaconda3/lib/python3.8/site-packages/sksurv/linear_model/coxph.py", line 527, in predict_cumulative_hazard_function
    return self._baseline_model.get_cumulative_hazard_function(self.predict(X))

  File "/opt/anaconda3/lib/python3.8/site-packages/sksurv/linear_model/coxph.py", line 97, in get_cumulative_hazard_function
    risk_score = numpy.exp(linear_predictor)

TypeError: loop of ufunc does not support argument 0 of type float which has no callable exp method

Означает ли это, что в какой-то момент переменная numpy установлен на поплавок?

Вот мой код:

exposure3 = data[['Height0', 'Weight0', 'Sbp0', 'Chol0', 'Dibpat0']]
validValues = np.argwhere(data['Chol0'].to_numpy() != '.')[:,0]
exposure3 = exposure3.iloc[validValues]
data_y3 = data_y[validValues]

dtypes = {'Height0': 'int64',
          'Weight0': 'int64',
          'Sbp0': 'int64',
          'Chol0': 'int64',
          'Dibpat0': 'category'}
exposure3 = exposure3.astype(dtypes)

model = CoxPHSurvivalAnalysis().fit(exposure3, data_y3)
chf_funcs = model.predict_cumulative_hazard_function(exposure3[:5])
# error