Create beginner Works with: Any AI

Project Folder Structure for Analysis Work

Table output Has example

Organize files so others can follow.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Design a folder structure for my analysis project. Project type and size: [PROJECT_TYPE_AND_SIZE]. Tools: [TOOLS]. Team: [TEAM].

Produce:
1. A tree in text with a short comment on each folder: data/raw (never edited), data/interim, data/processed, notebooks, src (functions), reports/figures, config, tests, docs.
2. Naming conventions: dated and ordered notebook names (01_load.ipynb), versioned outputs, no spaces, no "final_final2".
3. Rules for what goes where, with a decision list for ambiguous files.
4. A README outline with the five questions it must answer: what is this, how do I run it, where is the data, what are the outputs, who do I ask.
5. A data dictionary template: Column | Meaning | Type | Unit | Source | Notes.
6. A .gitignore starter and a rule for large files.
7. A migration plan to reorganize an existing messy project in one hour, as numbered steps.
8. A short checklist to hand over the project to a colleague.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

project/
 README.md (purpose, how to run)
 environment.yml (pinned packages)
 data/
  raw/ (never edited)
  interim/
  processed/
 notebooks/ (01_explore, 02_model)
 src/ (cleaning.py, features.py)
 tests/
 reports/ (figures, final report)
 config/ (settings.yaml)
Rules: raw data read-only; one command (make all) rebuilds processed data; notebooks import from src.
Naming: date-prefixed reports; version tags for data snapshots.
Do not commit secrets or personal data.
Onboarding: a new person should be able to clone, create the environment, run make all, and reproduce the reports within an hour. Add a CHANGELOG for data snapshot updates and keep the README short.

• project-structure