Chris Gervais
10/04/2022, 7:41 PMv1.0.0
? it looks like we should always be using the core.NeuralForecast
wrapper now instead of using the model predict methods directly - is that correct?Max (Nixtla)
10/04/2022, 10:30 PMkushagra kumar
10/13/2022, 2:14 PMvirgilio espina
10/18/2022, 4:31 AMMuhammad Hasnain Khan
11/07/2022, 12:36 PMChris Gervais
11/08/2022, 11:18 AMValeriy
11/08/2022, 11:22 AMChris Gervais
11/08/2022, 11:26 AMEric Braun
11/21/2022, 5:32 PMJ T
11/23/2022, 2:31 PMJ T
11/23/2022, 2:32 PMMuhammad Hasnain Khan
12/07/2022, 10:40 AMChris Gervais
12/13/2022, 9:05 PMneuralforecast
consistently outperforming NHiTS from pytorch-forecasting
in the wild lolTomasz
12/20/2022, 1:18 PMEric Braun
12/27/2022, 9:43 PMArona Ben Cherif DIATTA
12/30/2022, 5:34 PMMads Jensen
01/04/2023, 6:56 PMAndrei Tulbure
01/04/2023, 10:01 PMMads Jensen
01/05/2023, 11:13 AMChris Gervais
01/06/2023, 2:19 PMsktime
) with the neuralforecast
native cross-validation but we're running into a merge issue. The culprit seems to be in the core NeuralForecast
class here:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[56], line 1
----> 1 nf.cross_validation(df=df, static_df=static_df, val_size=val_size)
File ~/Desktop/rtobots/.venv/lib/python3.9/site-packages/neuralforecast/core.py:386, in NeuralForecast.cross_validation(self, df, static_df, n_windows, step_size, val_size, test_size, sort_df, verbose, **data_kwargs)
383 fcsts_df = pd.concat([fcsts_df, fcsts], axis=1)
385 # Add original input df's y to forecasts DataFrame
--> 386 fcsts_df = fcsts_df.merge(df, how="left", on=["unique_id", "ds"])
387 return fcsts_df
and the actual error appears to be related to index types that don't match:
ValueError: You are trying to merge on datetime64[ns] and object columns. If you wish to proceed you should use pd.concat
Replication:
• using the exogenous tutorial here https://nixtla.github.io/neuralforecast/examples/exogenous_variables.html
• replacing the .fit()
code chunk with .cross_validation(df=df, static_df=static_df, val_size=int(len(df) * .2))
Arona Ben Cherif DIATTA
01/08/2023, 1:27 PMvirgilio espina
01/18/2023, 9:15 AMVishwa Brungi
01/19/2023, 6:01 PMneuralforecast
to forecast into the future/unseen/out-sample dates?Majid Yazdani
01/27/2023, 2:44 PMVishwa Brungi
01/31/2023, 4:32 PM.predict()
, it's forecasting into the future. I also want to look at the historical predictions of the model.kushagra kumar
02/04/2023, 9:59 AMkushagra kumar
02/04/2023, 10:24 AMpip install neuralforecast statsforecast s3fs fastparquet
cmd. I am getting the below error:
from neuralforecast.losses.pytorch import DistributionLoss
ImportError: cannot import name 'DistributionLoss' from 'neuralforecast.losses.pytorch' (E:\MT\code\env\lib\site-packages\neuralforecast\losses\pytorch.py)
Can someone please help. python version is 3.10.9
Chris Gervais
02/07/2023, 5:20 PMweekday
column doesn't get hot encoded when passing to futur_exog_list = [..., 'weekday']
- was that intentional? we're trying to integrate tsfresh features but seem to be running into issues when we hot encode - still investigating but thought it might be related to exogenous scalingMarcello Infantino
02/08/2023, 8:48 PMChris Gervais
02/08/2023, 8:52 PMy
values?