DataCareerHubLearn · Practice · Progress
Explore learning
DataCareerHub
Explore learning
Learning/Data Processing & Preparation
Module 02 · Free practice

Clean data without losing evidence

Resolve defensible defects, quarantine uncertainty and keep a traceable record of every correction.

3 published lessons2h 55m suggestedGuided practiceFiles + exercises + worked solutions
Start the first lesson →Download the practice pack ↓
Turn knowledge into practice

A method you can explain.

Work through the reasoning, attempt the task and compare the separate solution. Keep your source copy unchanged and save your own evidence locally.

Before you start: Basic spreadsheet skills; complete the earlier modules in this track. Python exercises introduce each operation and include a separate worked script.

The suggested study time includes exercises. Use a spreadsheet or text editor for introductory tasks; code lessons use a local Python environment with the supplied setup guide. This website does not run arbitrary Python or upload your files.

The complete module

Three lessons. One connected workflow.

Learn + practise + review
01

Missing values and duplicate records

Detailed explanation, practical exercise and worked solution.

55 min02

Inconsistent categories and safe corrections

Detailed explanation, practical exercise and worked solution.

55 min03

Document corrections and reconcile the result

Detailed explanation, practical exercise and worked solution.

65 min
Your local practice desk

Real tasks.
Inspectable evidence.

Download the complete pack or choose individual files. Start with the dictionary and worksheet. Templates are deliberately unfinished; the separate worked reference contains explanations and solutions.

All data are fictional. Downloadable code uses local files and fresh output paths. Read the setup guide before running it. The offline HTML reference is static and does not execute Python or save progress.

Open the worked reference ↗
Complete offline practice pack13 files: sources, worksheet, templates, explained solutions and reference.
Download ↓
Orders rawFictional unchanged source; inspect the supplied dictionary before use.
Download ↓
ProductsFictional unchanged source; inspect the supplied dictionary before use.
Download ↓
Plan wideFictional unchanged source; inspect the supplied dictionary before use.
Download ↓
Source dictionary & timingGrain, units, validity rules, missingness and interpretation limits.
Download ↓
Three practical exercisesAttempt each task before comparing the separate worked solution.
Download ↓
Worked solutions with reasoningExplained answers and independently checked counts or evaluation measures.
Download ↓
Quality log templateEditable prompts for your own evidence; intentionally unfinished.
Download ↓
Checked reference resultsBaseline counts and cent totals; changed sources require fresh results.
Download ↓
Local setup and reproductionmacOS/Windows working-copy instructions, exact command and output behaviour.
Download ↓
Evidence-based self-reviewFive dimensions with an artifact supporting each score.
Download ↓
Complete offline worked referenceDetailed explanations, exercises and expandable solutions; static local HTML.
Download ↓
Start here and file guideComplete local workflow, intended use and file descriptions.
Download ↓
File provenanceHashes of the supplied reference files before ZIP packaging.
Download ↓
Before moving on

Can someone reproduce your work?

Use the evidence-based self-review to check your method, validation and explanation. Keep unresolved questions visible. This is guided practice, not certification or production approval.

Begin Module 02 →

Return to the complete course ↗

Next module: Processing data with Python →

Explore practical lessons, worked examples and projects. Follow a published path, practise the method and build work you can explain.