Coding

Data analysis

Use the code interpreter to analyse files and data.

Knowledge cards
Workflow
Ask for the Cleaning Steps as a Reusable Script
A workflow move: once you've cleaned and analysed a dataset interactively, ask ChatGPT to consolidate every step into a single reusable script you can run on next month's file without redoing the conversation.
L3 · Workflows
Knowledge card
Describe Your Columns Before Asking for Analysis
A setup step: give ChatGPT a short data dictionary — what each column means, its units, and any quirks — before asking your analysis question, so it doesn't guess wrong about your data.
L2 · Context engineering
Best practice
Have ChatGPT Show the Code, Not Just the Chart
A verification habit for the code-interpreter tool: always ask to see the Python it ran, not just the resulting chart or number, so you can check how the result was actually produced.
L2 · Context engineering
Knowledge card
Upload the File, Then Ask One Question at a Time
A pattern for ChatGPT's data analysis (code interpreter): upload the raw file, ask it to first describe the data, then pose one analytical question per turn.
L2 · Context engineering
ChatGPT data analysis

It can actually run the numbers

ChatGPT's data-analysis tool — the code interpreter — sets it apart from a plain chatbot: it runs Python in a sandbox on files you upload, so it can genuinely compute rather than estimate. Upload a CSV and it can clean it, calculate, join tables, and produce charts, showing the code it used along the way. That means you can check its working, which matters because a wrong calculation stated confidently is worse than no answer. Treat it as an analyst whose steps you can audit.

One question at a time

The reliable pattern is to upload the file, confirm ChatGPT has read it correctly, then ask one focused question at a time. Piling several analyses into one prompt makes it harder to spot where a result went wrong. Ask it to show the intermediate numbers and the code, and sanity-check totals against something you know. Iterating question by question keeps the analysis auditable and stops small errors compounding into a wrong conclusion.

Frequently asked
Can ChatGPT analyse a spreadsheet or CSV?

Yes. Its code interpreter runs Python on files you upload, so it can clean, calculate, join, and chart real data — and show the code it used, which lets you check the working.

Is ChatGPT's data analysis accurate?

It computes rather than guesses when using the code interpreter, but verify anyway: ask it to show intermediate numbers and code, and sanity-check totals. A confidently stated wrong calculation is the risk to guard against.

How should I structure a data-analysis session?

Upload the file, confirm it read the data correctly, then ask one focused question at a time. Iterating keeps each result auditable and makes it easy to spot where anything went wrong.