End-to-End Learning for Partially-Observed Time Series with PyPOTS

TL;DR

PyPOTS is an open-source Python toolkit enabling end-to-end data mining and machine learning on partially-observed time series, covering tasks from imputation to anomaly detection.

Contribution

It introduces a comprehensive, unified framework for handling POTS with practical workflows and extensibility for research and production use.

Findings

Provides practical workflows for POTS tasks

Enables end-to-end pipeline construction

Open-source at https://github.com/WenjieDu/PyPOTS

Abstract

Partially-observed time series (POTS) is ubiquitous in real-world applications, yet most existing toolchains separate missing-value handling from downstream learning, which limits reproducibility and overall performance. This tutorial introduces PyPOTS, an open-source Python ecosystem for end-to-end data mining and machine learning on POTS. We present practical workflows spanning missingness simulation, data preprocessing, model training, and evaluation across core tasks, including imputation, forecasting, classification, clustering, and anomaly detection. The tutorial consists of two parts: Part I emphasizes hands-on application for practitioners through unified APIs and benchmark-oriented experiments. Part II targets developers and researchers, focusing on extending PyPOTS with custom models, domain-specific constraints, and contribution-ready engineering practices. Participants will gain both conceptual understanding and implementation experience for building robust, transparent, and reusable POTS pipelines in research and production settings. PyPOTS is publicly available at https://github.com/WenjieDu/PyPOTS