fraunhoferportugal/tsfel

Health v2 · maintenance only

Adoption not part of the score

1098 stars · 156 forks observed · 2026-08-28

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

TSFEL is an open-source Python library for extracting features from time series signals across statistical, temporal, spectral, and fractal domains. It provides configurable feature extraction pipelines with reproducible configuration files and extensive documentation.

Use cases

• extract features from time series for machine learning
• compute statistical and spectral features from sensor signals
• feature engineering for human activity recognition
• extract features from ECG or physiological signals
• build reproducible time series feature extraction pipelines
• prepare time series data for classification models

When to choose

• you need a broad, ready-made set of time series features in Python
• you want configurable, reproducible feature extraction with saved config files
• you work with sensor, ECG, or accelerometer data for classification
• you need documented, unit-tested feature implementations

When to avoid

• you need streaming or real-time feature extraction at scale
• you work outside Python or need deep learning end-to-end models
• you only need simple rolling statistics already available in pandas

Facets

library · maturity active

machine-learning data-science etl data-science machine-learning time-series python cross-platform feature-extraction time-series feature-engineering signal-processing spectral-features statistical-features

Member repositories

For agents

markdown · JSON · MCP: product_card(name="fraunhoferportugal/tsfel")