wearablevar is a Python package that calculates wearable variability metrics from longitudinal wearable sensors. These features can be used as part of your feature engineering process.
wearblevar is part of the Digital Biomarker Discovery Pipeline, available at dbdp.org.
wearablevar requires the pandas, numpy, and datetime packages.
Recommended: Install via pip:
$ pip install wearablevarInstall via git:
$ pip install git+git://github.com/brinnaebent/wearablevar.git
$ git clone| Plugin | README |
|---|---|
| summarymetrics | interday mean, median, minimum, maximum, Q1, Q3 |
| interdaycv | interday coefficient of variation |
| interdaysd | interday standard deviation |
| intradaycv | intraday coefficient of variation (mean, median, standard deviation) |
| intradaysd | intraday standard deviation (mean, median, standard deviation) |
| intradaymean | intraday mean (mean, median, standard deviation) |
| TIR | Time in Range (SD default=1), *Note time relative to SR |
| TOR | Time outside Range (SD default=1), *Note time relative to SR |
| POR | Percent Outside Range (%) (SD default=1) |
| MASE | Mean Amplitude of Sensor Excursions (SD default=1) |
| importe4 | Import sensor data in 2 columns: datetime type, sensor type |
| importe4acc | Import tri-axial accelerometry data in 4 columns: datetime type, sensor type x,y,z |
We are frequently updating this package with new functions and insights from the DBDP (Digital Biomarker Discovery Pipeline). For more details on contributing your own functions to this package, see dbdp.org.
MIT