3.6 Exploratory data analysis as a discipline
You can walk into a new dataset and produce a one-page summary.
Before:01. Mathematics for Machine Learning02. Python — Basics to AdvancedUnlocks:05. Classical Machine Learning
Exploratory data analysis is a repeatable checklist, not a vibe: univariate, bivariate and segment-level passes that surface problems before production surfaces them for you. It is also where most genuine insight comes from. It sits after cleaning because exploration of dirty data explores the dirt. The standard it sets is findings, not plots — an EDA that ends without written findings, each attached to evidence, was scrolling with extra steps.
Work through these
A repeatable EDA checklist
A written checklist you follow on every new dataset, so nothing is skipped because it felt fine. Repeatability is what turns exploration from wandering into a method.
Univariate, bivariate, multivariate passes
Looking at one variable, then pairs, then several at once, in that order. Going straight to the complicated view is how obvious problems get missed.
Segment analysis and cohort views
Splitting the data by a meaningful group, or by when each record entered, frequently reveals patterns that the whole-dataset view hides. Simpson's paradox lives here.
Writing findings, not just plots
The output of exploration is a written statement of what you found, not a folder of charts. A chart without a sentence leaves the reader to do the analysis themselves.
Sign in to keep your progress.
Free resources
We haven't checked most of these for screen reader use yet.
These videos are on YouTube. Opening the link takes you to YouTube's page. Pressing "Watch here" loads YouTube's player into this page — nothing loads from YouTube until you do. Either way the video comes from Google and uses much more mobile data than a page of text. Something wrong with a link here?
Links last checked 29 Aug 2026.
Stuck here?
Ask a mentor. A real person answers, and they can see exactly which topic you're on. Usually within a couple of working days.
Checking your session…
Topics shown in module order.