4.49 out of 5
4.49
413 reviews on Udemy

Feature Selection for Machine Learning

From beginner to advanced
Instructor:
Soledad Galli
2,832 students enrolled
English
Understand different methods of feature selection
Implement different methods of feature selection
Reduce feature space in a dataset
Build simpler, faster and more reliable machine learning models
Analyse and understand the selected features

Learn how to select features and build simpler, faster and more reliable machine learning models.

This is the most comprehensive, yet easy to follow, course for feature selection available online. Throughout this course you will learn a variety of techniques used worldwide for variable selection, gathered from data competition websites and white papers, blogs and forums, and from the instructor’s experience as a Data Scientist.

You will have at your fingertips, altogether in one place, multiple methods that you can apply to select features from your data set.

The course starts describing simple and fast methods to quickly screen the data set and remove redundant and irrelevant features. Then it describes more complex techniques that select variables taking into account variable interaction, the feature importance and its interaction with the machine learning algorithm. Finally, it describes specific techniques used in data competitions and the industry. 

The lectures include an explanation of the feature selection technique, the rationale to use it, and the advantages and limitations of the procedure. It also includes full code that you can take home and apply to your own data sets.

This course is therefore suitable for complete beginners in data science looking to learn how to go about to select features from a data set, as well as for intermediate and even advanced data scientists seeking to level up their skills.

With more than 50 lectures and 8 hours of video this comprehensive course covers every aspect of variable selection. Throughout the course you will use python as your main language.

So what are you waiting for? Enrol today, learn how to select variables for machine learning, and build simpler, faster and more reliable learning models.

Introduction

1
Introduction
2
Course Curriculum Overview
3
Course requirements
4
Additional Requirements | Nice to have
5
How to approach this course
6
Guide to setting up your computer
7
Installing XGBoost in windows
8
Presentations covered in this course
9
Jupyter notebooks covered in this course
10
FAQ: Data Science and Python programming

Feature Selection

1
What is feature selection?
2
Feature selection methods | Overview
3
Filter Methods
4
Wrapper methods
5
Embedded Methods

Filter Methods | Basics

1
Constant, quasi constant, and duplicated features – Intro
2
Constant features
3
Quasi-constant features
4
Duplicated features
5
Basic methods | review

Filter methods | Correlation

1
Correlation – Intro
2
Correlation
3
Basic methods plus Correlation pipeline

Filter methods | Statistical measures

1
Statistical methods – Intro
2
Mutual information
3
Chi-square for categorical variables | Fisher score
4
Univariate approaches
5
Univariate ROC-AUC
6
Basic methods + Correlation + univariate ROC-AUC pipeline
7
BONUS: select features by mean encoding | KDD 2009

Wrapper methods

1
Wrapper methods – Intro
2
Step forward feature selection
3
Step backward feature selection
4
Exhaustive search

Embedded methods – Lasso regularisation

1
Regularisation – Intro
2
Lasso
3
Basic filter methods + LASSO pipeline

Embedded methods | Linear models

1
Regression Coefficients – Intro
2
Selection by Logistic Regression Coefficients
3
Coefficients change with penalty
4
Selection by Linear Regression Coefficients
5
Feature selection with linear models | review

Embedded methods | Trees

1
Selecting Features by Tree importance – Intro
2
Select by model importance random forests |embedded
3
Select by model importance random forests | recursively
4
Select by model importance gradient boosted machines
5
Feature selection with decision trees | review

Reading Resources

1
Additional reading resources

Hybrid feature selection methods

1
BONUS: Shuffling features
2
BONUS: Hybrid method: Recursive feature elimination
3
BONUS: Hybrid method: Recursive feature addition

Final section | Next steps

1
Bonus Lecture: Discounts on my other courses!
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.5
4.5 out of 5
413 Ratings

Detailed Rating

Stars 5
226
Stars 4
146
Stars 3
31
Stars 2
6
Stars 1
4
6fbd449c3679bc111bd5ad2f62510705
30-Day Money-Back Guarantee

Includes

3 hours on-demand video
22 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion