Machine Learning pipeline

This example shows how to put together a basic Machine Learning pipeline. It fetches a dataset from OpenML, trains a variety of machine learning models on a prediction target, and selects the best model based on some evaluation criteria.

Try it in your computer

To run this pipeline on your computer, you will need:

Unix-like operating system
Java 11 (or higher)
Docker

Install Nextflow by entering the following command in the terminal:

$ curl -fsSL get.nextflow.io | bash

Then launch the pipeline with this command:

$ nextflow run ml-hyperopt -profile wave

It will automatically download the pipeline GitHub repository and build a Docker image on-the-fly using Wave, thus the first execution may take a few minutes to complete depending on your network connection.

NOTE: Nextflow 22.10.0 or newer is required to run this pipeline with Wave.