Crossformer VS PyPOTS

Great write up. There were a few grammatical errors - I’d suggest piping it through a LLM prompted to find grammar errors :-)

Another area of interesting research is the use of transformer like models for highly dimensional time series prediction. While language and vision are interesting and have their uses, my opinion is the application of these techniques for multidimensional non linear effects in time series may ultimately have more broad and significant impact. Ex:

https://github.com/Thinklab-SJTU/Crossformer

You're talking about the end-to-end task on partially-observed time series (POTS) like classification. But sometimes people need to know approximated values of missing parts. Imputation works for them. And imputation can help with downstream tasks (e.g. classification) as well, please refer to the section “4.4.2 Downstream Classification Task” in the SAITS paper. BTW, we include end-to-end methods for modeling POTS data in PyPOTS that may interest you, this library supports four tasks of classification, forecasting, clustering, and imputation.

GitHub repo: https://github.com/WenjieDu/PyPOTS

Oh, wow, thanks for sharing it here! PyPOTS still has a long way to go, and I'm making it better. If you have any suggestions for PyPOTS, please let me know. Your feedback is always welcome and means a lot to the community of PyPOTS! If you like PyPOTS, please star 🌟 PyPOTS repo on GitHub and share it with people you know who may need it to help others notice this helpful work. Thank you very much!

Due to all kinds of reasons like failure of collection sensors, communication error, and unexpected malfunction, missing values are common to see in time series from the real-world environment. This makes partially-observed time series (POTS) a pervasive problem in open-world modelling and prevents advanced data analysis. Although this problem is important, the area of data mining on POTS still lacks a dedicated toolkit. PyPOTS is created to fill in this gap. PyPOTS (pronounced "Pie Pots") is the first (and so far the only) Python toolbox/library specifically designed for data mining and machine learning on partially-observed time series (POTS), namely, incomplete time series with missing values, A.K.A. irregularly-sampled time series, supporting tasks of imputation, classification, clustering, and forecasting on POTS datasets. It is born to become a handy toolbox that is going to make data mining on POTS easy rather than tedious, to help engineers and researchers focus more on the core problems in their hands rather than on how to deal with the missing parts in their data. PyPOTS will keep integrating classical and the latest state-of-the-art data mining algorithms for partially-observed multivariate time series. For sure, besides various algorithms, PyPOTS has unified APIs together with detailed documentation and interactive examples across algorithms as tutorials. Feedback and contributions are very welcome! Website: https://pypots.com Paper link: https://arxiv.org/abs/2305.18811 GitHub repo: https://github.com/WenjieDu/PyPOTS

Website: https://pypots.com