A tutorial for the development of regression models in machine learning

Objectives

1. How to define your problem
2. How to choose a appropriate model
3. How to evaluate the model performance
4. How to save your model for re-use

We are not going to cover

1. classification problem
2. deep learning models

In this tutorial, we are going to use the case from Li, G., et al (2019) (https://doi.org/10.1021/acssynbio.9b00099), which tried to predict optimal growth temperature of microoganisms from their proteomes.

Dependences

• sklearn
• seaborn
• pandas
• Python 3

Jupyter notebook:
https://github.com/Gangl2016/Machine_Learning_On_OGT/tree/master/scripts/Tutorial.ipynb

HTML version: (open with chrome) https://github.com/Gangl2016/Machine_Learning_On_OGT/tree/master/scripts/Tutorial.html