Fine tuning model parameters for a new dataset.

WenjieDu / PyPOTS

A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputation/classification/clustering/forecasting/anomaly detection/cleaning on incomplete industrial (irregularly-sampled) multivariate TS with NaN missing values

https://pypots.com

BSD 3-Clause "New" or "Revised" License

965 stars 92 forks source link

Fine tuning model parameters for a new dataset. #488

Closed jovidsilva closed 1 week ago

jovidsilva commented 1 month ago

Issue description

I have a question regarding using PyPOTS (SAITS or other DL Models) for my own multivariate time series. On the GitHub homepage example the entire dataset was used with 10% missing data to evaluate. Can this approach be used to find the optimal parameters for the model? Or do i consider splitting the my Time series into samples ( I have Daily data so 365 or 366 Values per Year will be one sample) and then do a Train-Validation split to find optimal parameters. Please Help.

github-actions[bot] commented 1 month ago

Hi there 👋,

Thank you so much for your attention to PyPOTS! You can follow me on GitHub to receive the latest news of PyPOTS. If you find PyPOTS helpful to your work, please star⭐️ this repository. Your star is your recognition, which can help more people notice PyPOTS and grow PyPOTS community. It matters and is definitely a kind of contribution to the community.

I have received your message and will respond ASAP. Thank you for your patience! 😃

Best, Wenjie

github-actions[bot] commented 2 weeks ago

This issue had no activity for 14 days. It will be closed in 1 week unless there is some new activity. Is this issue already resolved?