Scikit-learn on Argo Observations

This Project Pythia Cookbook covers two objectives:

1. Accessing publicly available, quality-controlled Biogeochemical-Argo ocean observations
2. Demonstrating uses of scikit-learn, a powerful Python package for machine learning.

Motivation

This cookbook provides an overview of how to use python to access Argo oceanographic data and how to use sklearn to perform machine learning analyses. Argo is a global observatory of in situ robots that autonomously sample the ocean interior. It is an international collaborative effort, and provides a treasure trove of high quality, open-source data. However, there are many different ways to access Argo data, which can get confusing for users. This cookbook highlights some basic workflows to access and work with Argo data.

Authors

Song Sangmin, Michael Chen.

Contributors

Structure

This cookbook is broken up into two main sections.

1. Argo Foundations
2. Scikit-learn Workflows

Section 1: Argo Foundations

This section contains two notebooks. argo-introductions.ipynb provides an overview of the Argo program, what kind of data are available, and how the data are structured. The argo-access.ipynb provides an overview of several methods to retrieve Argo data.

Section 2: Scikit-learn Workflows

This section provides an overview of workflows using the sklearn package to conduct machine learning analyses on Argo data. The notebooks provide workflows on running regression and clustering (under construction) analyses.

Running the Notebooks

You can either run the notebook using Binder or on your local machine.

Running on Binder

The simplest way to interact with a Jupyter Notebook is through Binder, which enables the execution of a Jupyter Book in the cloud. The details of how this works are not important for now. All you need to know is how to launch a Pythia Cookbooks chapter via Binder. Simply navigate your mouse to the top right corner of the book chapter you are viewing and click on the rocket ship icon, (see figure below), and be sure to select “launch Binder”. After a moment you should be presented with a notebook that you can interact with. I.e. you’ll be able to execute and even change the example programs. You’ll see that the code cells have no output at first, until you execute them by pressing {kbd}Shift+{kbd}Enter. Complete details on how to interact with a live Jupyter notebook are described in Getting Started with Jupyter.

Running on Your Own Machine

If you are interested in running this material locally on your computer, you will need to follow this workflow:

(Replace "cookbook-example" with the title of your cookbooks)

1. Clone the https://github.com/ProjectPythia/cookbook-example repository:

    git clone https://github.com/ProjectPythia/cookbook-example.git

2. Move into the cookbook-example directory

   cd cookbook-example

3. Create and activate your conda environment from the environment.yml file

   conda env create -f environment.yml
   conda activate cookbook-example

4. Move into the notebooks directory and start up Jupyterlab

   cd notebooks/
   jupyter lab