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
This project helps scientists, operations engineers, and other practitioners analyze real-world time series data that often has gaps or missing values. It takes your raw, incomplete time series data and can fill in the missing parts, predict future trends, classify patterns, group similar sequences, or detect unusual events. The result is clean, actionable insights from your time-based measurements.
1,965 stars. Used by 1 other package. Actively maintained with 16 commits in the last 30 days. Available on PyPI.
Use this if you need to perform advanced analysis like forecasting or anomaly detection on industrial or scientific time series data that frequently contains missing observations.
Not ideal if your time series data is always complete and perfectly regularly sampled, as it specifically addresses challenges with partially-observed data.
Stars
1,965
Forks
180
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 12, 2026
Commits (30d)
16
Dependencies
16
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/WenjieDu/PyPOTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
sktime/sktime
A unified framework for machine learning with time series
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
tslearn-team/tslearn
The machine learning toolkit for time series analysis in Python
Nixtla/mlforecast
Scalable machine 🤖 learning for time series forecasting.