Ошибка Azure ML: объект TimeSeriesImputer не имеет атрибута '_known_df'

Question

Запуская этот блокнот по продажам апельсинового сока, я получаю следующую ошибку:.forecast() метод.

код

# The featurized data, aligned to y, will also be returned.
# This contains the assumptions that were made in the forecast
# and helps align the forecast to the original data
y_predictions, X_trans = fitted_model.forecast(X_test)

Ошибка (полная трассировка стека):

**AttributeError: 'TimeSeriesImputer' object has no attribute '_known_df'**

Answer 1

This is commonly fixed by upgrading to the latest SDK. You can do this by running pip install --upgrade azureml-sdk[explain,automl].

Thanks, Sabina