Federated algorithm for a coxph model in Vantage6 v4
Please refer to the Wiki for more information on how to use this algorithm.
This algorithm is designed to be run with the vantage6 infrastructure for distributed analysis and learning.
The base code for this algorithm has been created via the v6-algorithm-template template generator.
To finally run your algorithm on the vantage6 infrastructure, you need to create a Docker image of your algorithm.
The easiest way to create a Docker image is to use the GitHub Actions pipeline to
automatically build and push the Docker image. All that you need to do is push a
commit to the main branch.
A Docker image can be created by executing the following command in the root of your algorithm directory:
docker build -t [my_docker_image_name] .where you should provide a sensible value for the Docker image name. The
docker build command will create a Docker image that contains your algorithm.
You can create an additional tag for it by running
docker tag [my_docker_image_name] [another_image_name]This way, you can e.g. do
docker tag local_average_algorithm harbor2.vantage6.ai/algorithms/average to
make the algorithm available on a remote Docker registry (in this case
harbor2.vantage6.ai).
Finally, you need to push the image to the Docker registry. This can be done by running
docker push [my_docker_image_name]Note that you need to be logged in to the Docker registry before you can push
the image. You can do this by running docker login and providing your
credentials. Check this page
For more details on sharing images on Docker Hub. If you are using a different
Docker registry, check the documentation of that registry and be sure that you
have sufficient permissions.