# PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Series

arXiv: https://arxiv.org/abs/2305.18811 · HTML: https://mlsanity.com/paper/2305.18811/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 3 of 3)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Bayesian Temporal Factorization for Multidimensional Time Series Prediction](https://mlsanity.com/paper/1910.06366/) (2019)
- [Forecasting Loss of Signal in Optical Networks with Machine Learning](https://mlsanity.com/paper/2201.07089/) (2022)

## Built on by (most cited first, 12 of 12)

- [TSI-Bench: Benchmarking Time Series Imputation](https://mlsanity.com/paper/2406.12747/) (2024)
- [Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputation](https://mlsanity.com/paper/2405.17508/) (2024)
- [Task-oriented Time Series Imputation Evaluation via Generalized Representers](https://mlsanity.com/paper/2410.06652/) (2024)
- [TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning](https://mlsanity.com/paper/2606.05878/) (2026)
- [T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation](https://mlsanity.com/paper/2602.21043/) (2026)
- [Are Time-Indexed Foundation Models the Future of Time Series Imputation?](https://mlsanity.com/paper/2511.05980/) (2025)
- [SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting](https://mlsanity.com/paper/2605.00126/) (2026)
- [Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning](https://mlsanity.com/paper/2606.15107/) (2026)
- [Deep Representation Learning-Based Dynamic Trajectory Phenotyping for Acute Respiratory Failure in Medical Intensive Care Units](https://mlsanity.com/paper/2405.02563/) (2024)
- [Closing Gaps: An Imputation Analysis of ICU Vital Signs](https://mlsanity.com/paper/2510.24217/) (2025)
- [End-to-End Learning for Partially-Observed Time Series with PyPOTS](https://mlsanity.com/paper/2604.24041/) (2026)
- [Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random](https://mlsanity.com/paper/2605.25439/) (2026)

## Abstract (arXiv)

PyPOTS is an open-source Python library dedicated to data mining and analysis on multivariate partially-observed time series with missing values. Particularly, it provides easy access to diverse algorithms categorized into five tasks: imputation, forecasting, anomaly detection, classification, and clustering. The included models represent a diverse set of methodological paradigms, offering a unified and well-documented interface suitable for both academic research and practical applications. With robustness and scalability in its design philosophy, best practices of software construction, for example, unit testing, continuous integration and continuous delivery, code coverage, maintainability evaluation, interactive tutorials, and parallelization, are carried out as principles during the development of PyPOTS. The toolbox is available on PyPI, Anaconda, and Docker. PyPOTS is open source and publicly available on GitHub https://github.com/WenjieDu/PyPOTS.