Exploratory Plot Sequence for a New Dataset
See the data before modelling it.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Plan the first hour of exploratory plotting for a new dataset. Dataset description and columns: [DATASET_DESCRIPTION]. The question or goal: [GOAL]. Plotting library: [PLOTTING_LIBRARY]. Produce a sequence of ten plots in order, each with: the question it answers, the code, what a healthy result looks like, and what each unexpected pattern would suggest. 1. Row count, missingness map. 2. Distribution of each numeric column (histogram and box plot). 3. Counts of each categorical column (sorted bars). 4. Time series of record counts to spot gaps. 5. Pairwise relationships among key numeric columns. 6. Target versus each predictor, if there is a target. 7. Group comparisons (small multiples). 8. Correlation heatmap with a caution that correlation is not causation. 9. Outlier inspection with the rows shown. 10. A summary plot per hypothesis you form. Add a rule to write one sentence of interpretation under each plot and a list of data cleaning actions that emerge. Warn about overplotting, binning choices that change the story, and drawing conclusions from small groups.
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.