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

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 structure

Example output

Example for: retail customer purchase log containing order dates, basket totals, and store IDs

  1. Data Hygiene Checklist:
  • Check for negative or zero values in basket total and order quantity fields.
  • Identify duplicate transaction IDs across different dates or cashier IDs.
  • Verify date format consistency and confirm no sales dates exist in the future.
  • Review customer ID coverage to quantify what percentage of purchases are guest checkouts.
  1. Core Analysis Questions:
  • What is the distribution of average transaction value by store location and day of the week?
  • Which product categories are most frequently co-purchased in high-value baskets?
  • How does purchase frequency change between first-time buyers and repeat account holders?
  1. Visualization Plan:
  • Box Plot: Store ID on X-axis, Basket Total on Y-axis to uncover store-level performance variance and pricing outliers.
  • Time Series Line Chart: Week of Year on X-axis, Order Volume on Y-axis (segmented by store) to identify seasonal sales spikes.
  • Histogram: Transaction Value on X-axis, Frequency Count on Y-axis with 10-dollar bins to establish standard spend clusters.
  1. Risk Warnings:
  • Bulk commercial buyers may heavily skew average basket sizes, masking retail consumer trends if not isolated.
  • Stores that opened midway through the observation window will artificially deflate annualized revenue comparisons.
Written by AI from this prompt. Your results will vary.

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.

Keep exploring

More in Data Analysis
Data Analysis

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.