The Jupyter notebooks in this project are intended to be comprehensive, end-to-end notebooks, going through each phase of the machine learning workflow - data understanding and exploration, data cleaning, feature engineering, model training, and model interpretation. So going through these notebooks is a great way to get started with the project.
To make the notebooks reproducible and executable by everyone, we have containerized and deployed them on the public JupyterHub instance on the Massachusetts Open Cloud (MOC). So you can get access to a Jupyter environment and run our notebooks in just a few clicks! To do so, please follow the steps below:
- Visit our JupyterHub, click on
Log in with moc-ssoand sign in using your Google Account.
- On the spawner page, select
OpenShift Anomaly Detection Notebook Imagefor notebook image,
Large - Memory Intensivefor container size, and then click
Start serverto spawn your server.
- Once your server has spawned, you should see a directory titled
openshift-anomaly-detection-<current-timestamp>. All the notebooks should be available inside the
notebooksdirectory in it for you to explore.
Note: When you’re done running the notebooks, please go to
Hub Control Panel and click
Stop My Server to shut down your JupyterHub pod.
In addition to exploring the notebooks, you can also read our blog post to get a brief overview of the diagnosis discovery project. Additionally, you can also check out our conference talk at DevConf.CZ 2021 for an in-depth presentation and discussion.