# fraunhoferportugal/tsfel

An intuitive library to extract features from time series.

Repository: https://github.com/fraunhoferportugal/tsfel
Canonical: https://ross.abutalabs.com/products/tsfel
Homepage: https://tsfel.readthedocs.io
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: feature-extraction, classification, time-series, colab-notebook, data-science, feature-engineering
Last push: 2026-01-30T16:06:10+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 12, longevity 100
- inputs: {"age_days": 2793, "days_push": 215, "days_rel": 378, "gap_med": 342, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1098, forks 156 (observed 2026-08-28T04:03:34.809907+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, data-science, etl
- domain: data-science, machine-learning, time-series
- platform: python, cross-platform
- tags: feature-extraction, time-series, feature-engineering, signal-processing, spectral-features, statistical-features

## Member repositories
- fraunhoferportugal/tsfel (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.809907+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:46:18.890982+00:00, confidence not recorded.
  - readme: https://github.com/fraunhoferportugal/tsfel (fetched 2026-08-28T04:03:34.809907+00:00, sha 9e02e64f065a)
  - registry_pypi: https://pypi.org/pypi/tsfel/json (fetched 2026-08-29T12:50:13.699827+00:00, sha cf0a4fd79a31)
- Data as of 2026-08-30T08:39:29.467469+00:00.