PyPOTS
PyPOTS copied to clipboard
WenjieDu
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,...
### 1. Model description TimesURL should be included in PyPOTS, and could start from the imputation task. ```bibtex @article{liu2024timesurl, title={{TimesURL}: Self-Supervised Contrastive Learning for Universal Time Series Representation Learning}, author={Liu,...
### 1. Model description TimeMixer should be included in PyPOTS, and could start from the imputation task. ```bibtex @inproceedings{wang2024timemixer, title={TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting}, author={Shiyu Wang and...
### 1. Model description UniTS should be included in PyPOTS, and could start from the imputation task. ```bibtex @article{gao2024units, title={{UniTS}: Building a Unified Time Series Model}, author={Gao, Shanghua and Koker,...
### 1. Model description PITS should be included in PyPOTS, and could start from the imputation task. ```bibtex @inproceedings{lee2024pits, title={Learning to Embed Time Series Patches Independently}, author={Seunghan Lee and Taeyoung...
# What does this PR do? 1. fixing #520; ## Before submitting - [x] Was this discussed/approved via a GitHub issue? Please add a link to it if that's the...
### Issue description pypots/nn/modules/reformer/local_attention.py:31: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead May be affected in future versions.
Add CSAI
### 1. Model description CSAI should be included in PyPOTS as an imputation model. ```bibtex @article{qian2023knowledge, title={Knowledge Enhanced Conditional Imputation for Healthcare Time-series}, author={Qian, Linglong and Ibrahim, Zina and Ellis,...
### 1. System Info pypots: 0.8.1 ### 2. Information - [ ] The official example scripts - [X] My own created scripts ### 3. Reproduction Use `dataset_val` in addition to...
### 1. Feature description Nice work with this library! Was wondering what is the best way to use CDSI models, as in the imputation so that I get some 95%...
### 1. Feature description Add arguments to enable user customized training loss function and validation metric ### 2. Motivation Users usually need to customize the training loss function and evaluation...