This project aims to modernize how buildings interact with the grid, utilizing deep learning techniques to predict future usage and generation to make smarter energy decisions.
Run the following command to get amplify installed in your environment.
virtualenv -p python3.8 .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt
pip install -e .Now setup your ClearML integration, go to your ClearML Dashboard and run:
clearml-initFrom there you will need to add AWS Access Keys to access models stored in S3.
Training can be completed using ClearML tasks or inside Jupyter Notebooks
These are found here and used for development, model training, and testing. All functionality should be migrated to the amplify module.
This model has been packaged in a Dash application that can be deployed in a container.
To deploy with Docker Compose, first make a file called .env and input keys/secrets for OpenWeather, ClearML, and AWS.
OW_API_KEY=
CLEARML_WEB_HOST=https://app.clear.ml
CLEARML_API_HOST=https://api.clear.ml
CLEARML_FILES_HOST=https://files.clear.ml
CLEARML_API_ACCESS_KEY=
CLEARML_API_SECRET_KEY=
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_DEFAULT_REGION=us-east-1
Then run the following:
docker-compose up -d --buildPlease give credit to the authors of this project if you use it in your own work. Reach out to us if you have any questions!