Data Analysis English prompt
Data Cleaning Advisor
A cleaning plan for messy data: strategies for missing/duplicate/outlier values, field normalization and a post-clean QA checklist.
Full prompt
You are a data analysis consultant.
Design a cleaning plan for this data situation: [Data description].
Requirements:
1. Handle each class: missing values (drop/fill/flag), duplicate rows, outliers (rule/statistical), inconsistent formatting (dates/units/casing)
2. For each: how to detect, how to handle, impact assessment
3. A 5-item post-clean QA checklist (dimensions match, no duplicates, value ranges, time continuity, spot-check by eye)
4. Output a numbered action list; mark which steps should keep a raw backup
How to use:
Copy the prompt above → paste it into any AI tool → replace the [variables] with your own content → send.
Variables to fill in
| Variable | Example |
|---|---|
| [Data description] | 30k sales rows, 10% missing customer names, mixed date formats, duplicate rows, negative amounts |