-
Notifications
You must be signed in to change notification settings - Fork 2
Releases: Trybnetic/paat
v1.0.0b10
f9863d6 What's Changed
- Update docs by @Trybnetic in #46
- Update readme by @Trybnetic in #47
- Fixes returning correct vector length in
detect_time_in_bed_weitz2024by @Trybnetic - Adds JOSS paper by @Trybnetic in #54
Full Changelog: v1.0.0b9...v1.0.0b10
Assets 4
v1.0.0
8ad4b2b The Physical Activity Analysis Toolbox (PAAT) is a versatile Python package designed to analyze physical activity
data. It is used in research and health-related fields to process raw acceleration data collected from the hip. It
supports importing, cleaning, and preprocessing raw data, and includes algorithms to classify time in bed and non wear
time. Furthermore, it supports estimating various physical activity levels such as moderate-to-vigorous physical
activity or sedentary behavior, with customizable thresholds from multiple metrics. These estimates can be aggregated
and used for further statistical analysis or be used directly for more sophisticated physical activity pattern analysis.
Additionally, PAAT is extensible, allowing users to add custom algorithms or modules, and it integrates well with
other data analysis tools within the Python ecosystem.
Assets 4
v1.0.0b9
f2bf96b What's Changed
- adds requirements.txt for Binder builts by @Trybnetic in #41
- Ports code and models to keras3 by @Trybnetic in #45
Full Changelog: v1.0.0b8...v1.0.0b9
Assets 4
v1.0.0b8
3fd21c2 What's Changed
- fixes DeprecationWarnings by @Trybnetic in #37
- fixes python 3.12 error by @Trybnetic in #38
- adds MAD function by @Trybnetic in #30
- adds option to use pygt3x to read gt3x files by @Trybnetic in #29
- improves documentation by @Trybnetic in #39
- registers pytest slow marker by @Trybnetic in #40
Full Changelog: v1.0.0b7...v1.0.0b8
Assets 4
v1.0.0b7
095935f What's Changed
- Fix broken doi/zenodo link by @freddie-freeloader in #32
- Update io.py to change metadata dates into a more readable format by @claaslendt in #33
- fixes PerformanceWarning in detect_non_wear_time_syed2021 by @Trybnetic in #34
New Contributors
- @freddie-freeloader made their first contribution in #32
- @claaslendt made their first contribution in #33
Full Changelog: v1.0.0b6...v1.0.0b7
Contributors
Assets 4
paat v1.0.0b6
The physical activity analysis toolbox (PAAT) is a comprehensive toolbox to analyze raw acceleration data. We developed all code mainly for analyzing ActiGraph data (GT3X files) in large sample study settings where manual annotation and analysis is not feasible. Most functions come along with scientific papers describing the methodology in detail. Even though, the package was and is primarily develop for analyzing ActiGraph data, we warmly welcome contributions for other clinical sensors as well!
This is the first more or less stable release which will be uploaded to zenodo. This is still a beta release which might be subject to changes, but it is uploaded to allow reproducible usage nonetheless.