An introduction on how to use the Machine Learning package Scikit-learn to perform feature selection on input data. This jupyter notebook (hosted on Google Colab) shows Feature Selection example using statistical measures, based on 3 scenarios:
- Numerical Input, Numerical Output using f_regression()_
- Numerical Input, Categorical Output using f_classif()
- Categorical Input, Categorical Output using chi2() and mutual_info_classif()
For full coverage on the content of this jupyter notebook, please visit the Medium article.