Home

Welcome to the Causal Inference Pipeline wiki! On this page, you find a general overview of the project. Check out the sidebar to find out how to set it up or extend it with more features.

The pipeline currently includes the following features, which are all accessible via a REST-api:

• Store causal inference ready datasets into our backend
• Set up causal inference experiments for the pcalg algorithm in R with different hyperparameter settings and dataset choice
• Run the experiments as jobs directly in our backend
• Manage all currently running jobs on the backend
• Deliver the results and metainformation of past experiments

The following features are currently under active development and will be added in the following months:

• Receive additional metainformation from past experiments
• Add the choice of additional causal inference algorithms
• Give people the opportunity to extend the pipeline with their own algorithms
• Integrate prior knowledge into the algorithms
• Add additional steps to pre-process datasets

The following image shows the holistic architecture as a FMC diagram:

Additionally, the data model can be seen as ER diagram:

TODO: Update ER diagram

Endpoint Documentation

A Swagger documentation of our REST endpoints is available using http://localhost:5000/static/swagger/index.html given default host and port settings.