Phase 2: Ensembles & Evaluation · ~90 minutes · Python

Feature Engineering & Selection

A good feature is worth a thousand data points.

What you will learn

Implement numerical transforms (standardization, min-max scaling, log transform, binning) and explain when each is appropriate
Build one-hot, label, and target encoding for categorical features and identify the data leakage risk in target encoding
Construct a TF-IDF vectorizer from scratch and explain why it outperforms raw word counts for text classification
Apply filter-based feature selection (variance threshold, correlation, mutual information) to reduce dimensionality

Introduction

Type: Build
Languages: Python
Prerequisites: the Math for AI & ML course
Time: ~90 minutes

Objective

Learning objectives

Implement numerical transforms (standardization, min-max scaling, log transform, binning) and explain when each is appropriate
Build one-hot, label, and target encoding for categorical features and identify the data leakage risk in target encoding
Construct a TF-IDF vectorizer from scratch and explain why it outperforms raw word counts for text classification
Apply filter-based feature selection (variance threshold, correlation, mutual information) to reduce dimensionality

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.