Plan an exploratory data analysis from scratch
Generate a practical exploratory data analysis plan when starting with unfamiliar data. Frame key business questions, data hygiene checks, and visualization priorities.
Prompt
Act as a principal data analyst. Help me design a complete exploratory data analysis plan for a raw dataset.
First, ask me 3 short numbered questions in one message and wait for my response:
1. What is the business context or core question you want this data to answer?
2. What are the main columns or fields available, and roughly how many rows are there?
3. What tool or environment will you use to inspect the data (such as Excel, SQL, Python, or a BI tool)?
Once I answer, produce a clear execution plan following this format:
1. Data Hygiene Checklist: 4 specific sanity checks for missing values, duplicates, and outliers
2. Core Analysis Questions: 3 high-impact questions to investigate
3. Visualization Plan: 3 charts to construct, naming the X-axis, Y-axis, and target insight
4. Risk Warnings: 2 common biases or pitfalls to avoid with this specific data structureExample output
Paste the prompt into Gemini, ChatGPT, or Claude. Answer the three questions the model asks, then ask it to supply the exact formulas or queries for your chosen software tool.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Separate true anomalies from pipeline data errors
Classify extreme values as either legitimate business events or pipeline errors. Use it when high or low metrics distort downstream reporting.
Map and inspect an unfamiliar data export
Quickly understand the purpose, column types, and data quality risks of a messy raw CSV export. Ideal when inheriting unfamiliar operations sheets.
Differentiate structural null values from missing data
Identify whether null values represent expected business logic or export dropouts. Use it when auditing schema quality or preparing datasets for modeling.
Check survey sample size for decision confidence
Find out if your survey response count is reliable enough to make business decisions or if the margin of error is too wide.
Stress test data conclusions with counterarguments
Challenge data findings and business recommendations before presenting them. Use this to catch false correlations, survivorship bias, and hidden assumptions.
Create an anomaly investigation checklist for analytics teams
Run a disciplined diagnostic process before investigating metric shifts. Use this checklist whenever unexpected data spikes or drops appear in reports.
- Map inconsistent export columns to target schemas
- Rank survey satisfaction drivers by loyalty impact
- Sanity check revenue projections against past baselines
- Screen survey data for duplicate and low-effort responses
- Summarize weekly metric anomalies into executive briefings
- Translate statistical model outputs into plain business decisions