Slackbot
01/06/2023, 2:19 PMKin Gtz. Olivares
01/06/2023, 2:25 PMds
columns do not match in their types.
You would need to convert one of them using <http://pd.to|pd.to>_datetime
.Chris Gervais
01/06/2023, 2:39 PMChris Gervais
01/06/2023, 7:17 PMValueError: You are trying to merge on datetime64[ns] and datetime64[ns, tzfile('/usr/share/zoneinfo/US/Eastern')] columns. If you wish to proceed you should use pd.concat
Chris Gervais
01/06/2023, 7:31 PM.cross_validation()
?Kin Gtz. Olivares
01/06/2023, 10:10 PMKin Gtz. Olivares
01/06/2023, 10:10 PMChris Gervais
01/08/2023, 7:57 PM.fit()
method works but .cross_validation()
fails, i think it's when merging the cv forecast dataframes. i can toss up an issue with replication steps if that's helpful?Kin Gtz. Olivares
01/08/2023, 7:57 PMChris Gervais
01/08/2023, 8:00 PMpl.Trainer
kwargs down from either the core NeuralForecast
class or the individual models, ie NHITS
?Chris Gervais
01/08/2023, 8:03 PMpl.Trainer(log_dir=..., auto_lr_find=...)
Chris Gervais
01/10/2023, 5:00 PMmax_steps=1
• init the NeuralForecast
class and run .fit()
• deepcopy nf.models[0].trainer.datamodule
• init your own trainer class and train with pl.Trainer(...).fit(nf.models[0], datamodule=datamodule)