search

Nixtla / neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.
https://nixtlaverse.nixtla.io/neuralforecast
Apache License 2.0
3.02k stars 348 forks source link

'NeuralForecast' object has no attribute 'dataset' #798

Closed wwulfric closed 11 months ago

wwulfric commented 12 months ago

What happened + What you expected to happen

The example for transfer learning cannot work

AttributeError Traceback (most recent call last) in <cell line: 1>() ----> 1 Y_hat_df = fcst2.predict(df=Y_train_df).reset_index() 2 Y_hat_df.head()

/usr/local/lib/python3.10/dist-packages/neuralforecast/core.py in predict(self, df, static_df, futr_df, sort_df, verbose, **data_kwargs) 338 df=df, static_df=static_df, sort_df=sort_df, scalertype=None 339 ) --> 340 dataset.scalers = self.dataset.scalers_ 341 dataset._transform_temporal() 342 else:

AttributeError: 'NeuralForecast' object has no attribute 'dataset'

https://colab.research.google.com/github/Nixtla/neuralforecast/blob/main/nbs/examples/Transfer_Learning.ipynb#scrollTo=5eLU1eusHM5n

image

Versions / Dependencies

neuralforecast-1.6.4 datasetsforecast-0.0.8 python 3.10

Reproduction script

https://colab.research.google.com/github/Nixtla/neuralforecast/blob/main/nbs/examples/Transfer_Learning.ipynb#scrollTo=RgNGBUbfHM5j

uncomment 

!pip install neuralforecast 
!pip install datasetsforecast

and execute all

Issue Severity

None

jmoralez commented 12 months ago

Hey @wwulfric, thanks for using neuralforecast. This bug was introduced recently, we'll work on it. In the meantime you can change the save method to use save_dataset=True and you should be able to run it. Sorry for the troubles.