Phase 5: Capstone · ~45 minutes · Python · pandas

Clean

1,178 'missing' bathroom counts weren't actually missing. They were sitting in a different column, as text, the whole time.

Hiring signal: Checks whether a 'missing' value is genuinely absent or just stored somewhere else in a different format, before reaching for fillna or dropna

What you will learn

Distinguish genuinely missing data from data stored in a different column or format
Recover real values from a differently-formatted column, verified against cases where both formats exist
Document a written justification for each data-cleaning decision
Decide when to fill, drop, or leave data as-is, applying Phase 01's judgment discipline

Introduction

Type: Project Languages: Python, pandas Prerequisites: Lesson 01 (Choose and Load) Time: ~45 minutes

Objective

Learning objectives

Distinguish genuinely missing data from data stored in a different column or format
Recover real values from a differently-formatted column, verified against cases where both formats exist
Document a written justification for each data-cleaning decision
Decide when to fill, drop, or leave data as-is, applying Phase 01's judgment discipline

What you're building

A documented cleaning pass over the real New Orleans dataset (cleaning_log.md plus your cleaning script), covering at minimum:

Bathrooms: reproduce the recovery above, with your own verification of the agreement rate
The $2.88 and "Sleeps 44" issues from Lesson 01: for each, a written decision (keep, flag, or exclude from specific analyses) with the real evidence from the row that led to it
host_response_rate: confirm it's fully missing (100%) across the entire dataset, and write one sentence on why this means "exclude from analysis entirely," not "fill with a guess"
At least one more real column with missing or inconsistent data that you find and resolve yourself, with written reasoning

For every decision: state what you did and why, specifically — "dropped rows missing price" is not sufficient; "dropped the 769 rows missing price, since no other real column reliably predicts it, unlike bathrooms" is.

Unlock the full lesson

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

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.