Machine Learning Feature Selection in Python

4.0
stars
58 ratings
Offered By
Coursera Project Network
3,575 already enrolled
In this Guided Project, you will:

Demonstrate univariate filtering methods of feature selection such as SelectKBest

Demonstrate wrapper-based feature selection methods such as Recursive Feature Elimination

Demonstrate feature importance estimation, dimensionality reduction, and lasso regularization techniques

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 1-hour long project-based course, you will learn basic principles of feature selection and extraction, and how this can be implemented in Python. Together, we will explore basic Python implementations of Pearson correlation filtering, Select-K-Best knn-based filtering, backward sequential filtering, recursive feature elimination (RFE), estimating feature importance using bagged decision trees, lasso regularization, and reducing dimensionality using Principal Component Analysis (PCA). We will focus on the simplest implementation, usually using Scikit-Learn functions. All of this will be done on Ubuntu Linux, but can be accomplished using any Python I.D.E. on any operating system. We will be using the IDLE development environment to demonstrate several feature selection techniques using the publicly available Pima Diabetes dataset. I would encourage learners to experiment using these techniques not only for feature selection, but hyperparameter tuning as well. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Data SciencePython ProgrammingScikit-Learn

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Defining Terms relating to Feature Selection and Dimensionality Reduction

  2. Introduce Algorithms with Embedded Feature Selection

  3. Demonstrate two Univariate Selection Methods: Pearson Correlation Filtering and SelectKBest f_classif

  4. Demonstrate two Wrapper Methods: Backward Sequential and RFE

  5. Demonstrate Feature Importance Estimation using Bagged Decision Trees

  6. Dimensionality Reduction using Principal Component Analysis

  7. Demonstrate Lasso Regularization

  8. Expanding concepts to hyperparameter optimization and model selection

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.