Glucose Prediction using Replace-BG Dataset
- Preprocessing insperid by Long-Term Prediction of Blood Glucose Levels in Type 1 Diabetes Using a CNNLSTM-Based Deep Neural Network
- Code insperid by GluPred Github Repository
pip install git+ssh://git@github.com/rtaiello/glucose-prediction.git
- Download
REPLACE-BG-Dataset.zip
from this link; unzip
it and moveHDeviceBolus.txt
,HDeviceCGM.txt
andHDeviceWizard.txt
todata/original
folder;- Run preprocessing notebook, preprocessing.ipynb
Setup the development environment:
git clone git@github.com:rtaiello/glucose-prediction.git
cd glucose-prediction
conda env create -f env.yaml
conda activate glucose-prediction
pre-commit install
Run the tests:
pre-commit run --all-files
pytest -v
Re-install the project in edit mode:
pip install -e .[dev]