Exercise 2: Which Workflow Stage Is Out of Scope, and Why Explore Gets the Most Chapters — Possible Solution
====================================================================

THE FIVE STAGES, PER THIS CHAPTER
------------------------------
Per this chapter's own flow-steps: Collect, Clean, Explore, Model,
Communicate — with Model marked visually and explicitly as
"deliberately out of scope for this course — this is ml1's entire job,
start to finish."

WHY MODEL IS THE STAGE MARKED OUT OF SCOPE
------------------------------
This directly matches this chapter's own earlier distinction between
data science (the broad discipline) and machine learning (model-
building specifically). Since this course scopes itself around data
science minus machine learning, and per the chapter "Model" is defined
as "build a predictive or classification model" — exactly the
definition given for machine learning earlier in the chapter — it
follows necessarily that Model is the one stage this course excludes.

WHICH STAGE GETS THE MOST CHAPTERS, PER THIS CHAPTER'S OWN TABLE
------------------------------
Per this chapter, "Explore... Covered in ds1-5 through ds1-9 — the
largest share of this course by chapter count, because it's the largest
share of real data science work." Counting the chapters explicitly
named: ds1-5, ds1-6, ds1-7, ds1-8, and ds1-9 — five chapters devoted to
the Explore stage alone, out of the course's own ten total chapters
(not counting ds1-1's own introductory chapter or ds1-10's capstone).

WHY THIS ALLOCATION MATCHES THE CHAPTER'S OWN STATED REASONING
------------------------------
The chapter states its reasoning for this allocation directly: chapter
count tracks how much real, everyday data science work each stage
actually represents, not an arbitrary or evenly-spread division. Given
the chapter's own earlier warn-box — "a huge amount of real, valuable
data science work... happens before any model gets built" — it follows
that a course scoped specifically around the pre-modeling stages would
naturally spend most of its length on the stage (Explore) that
represents the largest share of that pre-modeling work, exactly as the
chapter states outright rather than leaving the reader to infer it.

WHY THIS WORKS AS AN ANSWER
------------------------------
It identifies Model as the excluded stage using the chapter's own
explicit marking and definitional overlap with "machine learning,"
counts the specific chapters the chapter itself assigns to Explore, and
ties the resulting five-chapter concentration directly back to the
chapter's own stated rationale (chapter count reflecting real-world
work distribution) rather than treating the allocation as arbitrary.