Compile, Deploy and Run Kubeflow Pipeline

Automatically Dockerize A Data-Science Repo As A Jupyter Server

A GitHub action to build data science environment images with repo2docker and push them to registries.

Azure Machine Learning With GitHub Actions

Template for getting started with automated ML Ops on Azure Machine Learning

Run Parameterized Jupyter Notebooks

Run Notebook is a GitHub Action designed to automate the execution of Jupyter notebooks within CI/CD workflows. It leverages Papermill to inject parameters into notebooks and enables the upload of generated outputs as artifacts, facilitating reproducible data analysis and reporting. ## Key Features - **Parameterized Execution** — Injects parameters into Jupyter notebooks using Papermill, supporting dynamic inputs for flexible workflows. - **Artifact Upload** — Integrates with GitHub's upload-artifact action to save notebook outputs, making results easily accessible. - **Secrets Management** — Automatically provides a JSON file containing GitHub secrets, allowing secure access to sensitive data within notebooks. - **Notebook Chaining** — Supports sequential execution of multiple notebooks, enabling complex, multi-step data pipelines. - **Output Polling** — Offers an optional polling mechanism to display live output from long-running cells, improving visibility in GitHub Actions logs. ## Philosophy Run Notebook emphasizes automation and reproducibility, aiming to seamlessly integrate interactive Jupyter notebooks into automated workflows while maintaining security and flexibility.

Query Experiment Tracking Results From Weights & Biases

GitHub Action That Retrieves Model Runs From Weights & Biases