Jupyter Notebook Analysis Plan
By Mo · Published · Updated
A plan for a notebook analysis that states the question first, checks the data, picks a method, plans the charts and ends with caveats.
Prompt template
## Jupyter Notebook Analysis Plan Plan a notebook analysis before any code is written. - Question to answer: [textarea: The decision this analysis supports] - Data sources: [textarea: Tables or files and what each row represents] - Known data issues: [textarea: Gaps or duplicates or odd values you already know about] - Audience: [dropdown: Executives, Analysts, Engineers, Customers] - Tooling: [dropdown: pandas, polars, SQL plus Python, R] - Time budget: [dropdown: One hour, Half a day, One day, A week] Structure the notebook as numbered sections. Section 1 restates the question as something measurable, with the metric and the comparison. Section 2 lists data checks to run first: row counts, missing values, duplicates, date ranges, units and join keys, each with the result that would stop the analysis. Section 3 chooses a method and says why it fits the question and the data size, plus one simpler baseline to compare with. Section 4 names each chart, the exact question it answers and the axis choices. Section 5 holds the conclusion template: the answer in one sentence, the evidence and the confidence. Section 6 lists caveats and what would change the conclusion. Fit the scope to the time budget.