Navigation: <-- Part II: Data-Science Projects | Main Index | Part IV: Data Preparation -->

Part III: Data Understanding

Before you can train a model, you need to understand what you have. This part builds the exploratory data analysis (EDA) vocabulary and habits that let you assess any dataset's structure, quality, and distributions. This corresponds to the CRISP-DM Data Understanding phase. The skills you develop here are prerequisites for every modeling task that follows.

Nuggets in This Part

#	Nugget	Prerequisites
1	Why Data Work Dominates	CRISP-DM
2	Data Types and Measurement Scales	Why Data Work Dominates
3	Datasets	Data Types and Measurement Scales
4	EDA: Descriptive Statistics	Datasets
5	EDA: Data Quality	EDA: Descriptive Statistics
6	EDA: Distributions	EDA: Descriptive Statistics
7	EDA: Correlations	EDA: Distributions
8	Data Understanding: Best Practices	--

Script v1.4 (2026-06-10) · FGN