Introduction
  • Introduction
  • Course Curriculum Overview
  • Course requirements
  • Course Aim
  • Optional: How to approach this course
  • Course Material
  • The code | Jupyter notebooks
  • Presentations covered in this course
  • Download the data sets
  • FAQ: Data Science and Python programming
Feature Selection
  • What is feature selection?
  • Feature selection methods | Overview
  • Filter Methods
  • Wrapper methods
  • Embedded Methods
  • Moving Forward
  • Open-source packages for feature selection
Filter Methods | Basics
  • Constant, quasi constant, and duplicated features – Intro
  • Constant features
  • Quasi-constant features
  • Duplicated features
  • Install Feature-engine
  • Drop constant and quasi-constant with Feature-engine
  • Drop duplicates with Feature-engine
Filter methods | Correlation
  • Correlation - Intro
  • Correlation Feature Selection
  • Correlation procedures to select features
  • Correlation | Notebook demo
  • Basic methods plus Correlation pipeline
  • Correlation with Feature-engine
  • Feature Selection Pipeline with Feature-engine
  • Additional reading resources
Filter methods | Statistical measures
  • Statistical methods – Intro
  • Mutual information
  • Mutual information demo
  • Chi-square
  • Chi-square | Demo
  • Anova
  • Anova | Demo
  • Basic methods + Correlation + Filter with stats pipeline
Filter Methods | Other methods and metrics
  • Filter Methods with other metrics
  • Univariate model performance metrics
  • Univariate model performance metrics | Demo
  • KDD 2009: Select features by target mean encoding
  • KDD 2009: Select features by mean encoding | Demo
  • Univariate model performance with Feature-engine
  • Target Mean Encoding Selection with Feature-engine
Wrapper methods
  • Wrapper methods – Intro
  • MLXtend
  • Step forward feature selection
  • Step forward feature selection | Demo
  • Step backward feature selection
  • Step backward feature selection | Demo
  • Exhaustive search
  • Exhaustive search | Demo
Embedded methods | Linear models
  • Regression Coefficients – Intro
  • Selection by Logistic Regression Coefficients
  • Selection by Linear Regression Coefficients
  • Coefficients change with penalty
  • Basic methods + Correlation + Embedded method using coefficients
Embedded methods – Lasso regularisation
  • Regularisation – Intro
  • Lasso
  • A note on SelectFromModel
  • Basic filter methods + LASSO pipeline
Embedded methods | Trees
  • Feature Selection by Tree importance | Intro
  • Feature Selection by Tree importance | Demo
  • Feature Selection by Tree importance | Recursively
  • Feature selection with decision trees | review
Hybrid feature selection methods
  • Introduction to hybrid methods
  • Feature Shuffling - Intro
  • Shuffling features | Demo
  • Recursive feature elimination - Intro
  • Recursive feature elimination | Demo
  • Recursive feature addition - Intro
  • Recursive feature addition | Demo
  • Feature Shuffling with Feature-engine
  • Recursive feature elimination with Feature-engine
  • Recursive feature addition with Feature-engine
Final section | Next steps
  • THERE IS MORE...
  • Additional reading resources