segment-profilelisted

# Segment Profile Goal: Characterize the **subgroup** described in the user's request with data and **contrast it against the rest of the sample** — a basis for personas/audiences. Result as Markdown in `reports/`. ## Tool ``` python3 scripts/survey.py <cmd> [...] [--file CSV] ``` Run these from the project root. If `scripts/survey.py` is not there, check `.claude/scripts/survey.py` or locate `survey.py` in the project. - `profile` — column overview (always first). - `freq COL [--filter "COL=VALUE"]` — distribution within the segment (filter) vs. overall. - `freq COL --by SEGMENT_COLUMN --sig` — segment as a column against a trait, with the significance test, to separate real differences from noise. - `text COL [--filter ...] [--sample N]` — verbatims from the segment. `COL` = index (from `profile`) or an unambiguous name part. ## Survey context If a context document sits next to the CSV (`<name>.context.md`, or `survey-context.md` when the folder holds exactly one CSV), read it before defining the segment. Its **column notes** often name the segments the business actually cares about and which column carries them — check there before inventing your own cut. The glossary keeps the profile in the organization's own vocabulary. Figures still come only from the engine. The **"Who is missing"** section matters doubly here: a segment profile describes a subgroup *of the respondents*, and if the recruiting route already excluded a group, the profile silently describes a f