User Guide

USER GUIDE for Pre-processing module

All you need to do is, clone the github repository and get the code on your personal computer.

$ git clone https://github.com/DigitalBiomarkerDiscoveryPipeline/Pre-process.git

In your local machine go to :

$ cd /Pre-process/pipeline

Run 'Complete - Browse file' file or 'Complete - User path

If you prefer using the terminal to run the code, please follow the following steps after you clone the repository

jupyter nbconvert --to python Complete\ -\ Browse\ file.ipynb or jupyter nbconvert --to python Complete\ -\ User\ path.ipynb

Then run the file from terminal using:

python Complete\ -\ Browse\ file.py or python Complete\ -\ User\ path.py

After the code is run, you would be prompted to browse an Apple Watch file or if you choose a wearable device with multiple input files (example: Biovotion), you would be prompted to give the path to the folder that has all the Biovotion files stored and the device ID, please find the details in the README. Once you upload the file/s, a new .csv file would be created in my current folder containing Actual time of measurement, elapsed time of measurement and all the physiological measurements that were available in the original raw dataset. Behind the scene, the code jumps to the code block dedicated for the selected wearable device and does the necessary processing for you.

Next, go ahead and use a visualization package of your choice (matplotlib, seaborn or plotly) and plot the actual time vs the heart rate or elapsed time vs heart rate for the apple watch data. Similarly, for biovotion, you can just use simple commands to plot actual time vs temperature. It’s that easy! No converting dates to python datetime data type, no need of calculating elapsed time, it’s all done for you.