Understand basic principles of underfitting and overfitting and why you should use particular techniques to deal with them.
You can read detailed article on Towards Data Science.
See Jupiter notebooks, that contain all examples from article:
- bias_variance.ipynb, which contains Python code to plot bias-variance plots from article
- underfitting_vs_overfitting.ipynb, which contains all other materials
Open them with Jupyter or see directly in a browser.
To run this code, you must have numpy, sklearn, matplotlib and seaborn libraries installed.
You should create virtual environment, activate it and run pip install -r requirements.txt
or run following command:
pip install numpy scikit-learn matplotlib seaborn