This tutorial is an introduction to machine learning in Python. We will rely heavily on the scikit-learn and numpy packages. Scikit-learn will be used for implementing machine learning protocols and learning algorithms, and numpy will be used to manipulate matrices of data.
Clone the GitHub repository for the tutorial:
git clone https://github.com/aldro61/microbiome-summer-school-2017.git microbiome-ml-tutorial
Then, go to the exercise directory:
cd microbiome-ml-tutorial/exercises
Install the dependencies for the tutorial by running the following command:
make install.dependencies
After completing this tutorial, you should have acquired the following skills:
- Understanding the various types of learning problems (regression, classification, etc.)
- Performing machine learning experiments using correct protocols
- Interpreting the results of machine learning experiments
- Using Python to apply machine learning algorithms to biological datasets