Не могли бы вы мне помочь со следующей функцией, где я получил ошибку ValueError: Порядок столбцов должен быть одинаковым для подгонки и для преобразования при использовании ключевого слова остатка
(функция вызывается для маринованного конвейер sklearn, который я сохранил в GCP Storage.)
Ошибка:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-192-c6a8bc0ab221> in <module>
----> 1 safety_project_lite(request)
<ipython-input-190-24c565131f14> in safety_project_lite(request)
31
32 df_resp = pd.DataFrame(data=request_data)
---> 33 response = loaded_model.predict(df_resp)
34
35 output = {"Safety Rating": response[0]}
~/.local/lib/python3.5/site-packages/sklearn/utils/metaestimators.py in <lambda>(*args, **kwargs)
114
115 # lambda, but not partial, allows help() to work with update_wrapper
--> 116 out = lambda *args, **kwargs: self.fn(obj, *args, **kwargs)
117 # update the docstring of the returned function
118 update_wrapper(out, self.fn)
~/.local/lib/python3.5/site-packages/sklearn/pipeline.py in predict(self, X, **predict_params)
417 Xt = X
418 for _, name, transform in self._iter(with_final=False):
--> 419 Xt = transform.transform(Xt)
420 return self.steps[-1][-1].predict(Xt, **predict_params)
421
~/.local/lib/python3.5/site-packages/sklearn/compose/_column_transformer.py in transform(self, X)
581 if (n_cols_transform >= n_cols_fit and
582 any(X.columns[:n_cols_fit] != self._df_columns)):
--> 583 raise ValueError('Column ordering must be equal for fit '
584 'and for transform when using the '
585 'remainder keyword')
ValueError: Column ordering must be equal for fit and for transform when using the remainder keyword
Код:
def safety_project_lite_beta(request):
client = storage.Client(request.GCP_Project)
bucket = client.get_bucket(request.GCP_Bucket)
blob = bucket.blob(request.GCP_Path)
model_file = BytesIO()
blob.download_to_file(model_file)
loaded_model = pickle.loads(model_file.getvalue())
request_data = {'A': [request.A],
'B': [request.B],
'C': [request.C],
'D': [request.D],
'E': [request.E],
'F': [request.F]}
df_resp = pd.DataFrame(data=request_data)
response = loaded_model.predict(df_resp)
output = {"Rating": response[0]}
return output