Bike Path Quality (Observatorio)

FastAPI based web service that predicts surface type based on bike activity time series data

About The Project

The aim of this app is to provide REST endpoints which accept bike activity accelerometer measurements and predict the surface type. Therefore it makes use of the results trained by an analytics component.

Built With

• FastAPI

Installation

Initialize the submodules of this repository by running the following commands.

git submodule init
git submodule update

Install the following dependencies to fulfill the requirements for this project to run.

python -m pip install --upgrade pip
pip install flake8 pytest
pip install pandas
pip install matplotlib
pip install sklearn
pip install torch
pip install tqdm
pip install seaborn
pip install telegram-send
pip install fastapi
pip install fastapi_versioning
pip install uvicorn
pip install requests

Usage

Run this command to start the dev server.

python app.py

Usage (local docker)

Run this command to run the docker container locally.

docker build -t bike-path-quality-prediction .
docker run -p 8000:8000 bike-path-quality-prediction

Usage (docker deployment)

Run these commands to deploy the Docker image to Google Cloud.

gcloud auth login
gcloud config set project bike-path-quality-339900
gcloud builds submit --tag eu.gcr.io/bike-path-quality-339900/bike-path-quality-prediction

Roadmap

See the open issues for a list of proposed features (and known issues).

Contributing

Since this project is part of an ongoing Master's thesis contributions are not possible as for now.

License

Distributed under the GPLv3 License. See LICENSE.md for more information.

Contact

Florian Schwanz - florian.schwanz@gmail.com

Acknowledgements

Icon made by Freepik from www.flaticon.com