RJT1990/pyflux

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2134 stars · 244 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PyFlux is an open source Python library for time series analysis and forecasting, offering a broad range of models such as ARIMA, GARCH, GAS, and state space models. It supports both frequentist and Bayesian inference options, enabling a probabilistic approach to time series modelling.

Use cases

• forecast future values of a time series with ARIMA models
• model volatility in financial returns using GARCH or EGARCH
• fit Bayesian time series models with variational inference
• analyze multivariate time series with VAR models
• fit non-Gaussian state space models to count data
• run probabilistic forecasting with uncertainty estimates

When to avoid

• you need actively maintained software with recent bug fixes and dependency updates
• you require production-grade stability, as the library is alpha software with limited test coverage
• you need deep learning based forecasting such as neural networks or transformers
• you need a library with strong community support and ongoing development

Facets

library · maturity maintenance

data-science machine-learning time-series data-science python time-series-analysis bayesian-inference arima garch state-space-models forecasting statistics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="RJT1990/pyflux")