First look at a dataset

I have a dataset and want to answer: {{question}}.

Schema / columns:
{{schema}}

Give me:
1. The first 5 checks I should run (data quality, distributions, missingness).
2. The 3 most relevant columns for my question and why.
3. Two plausible hypotheses and how to test each.
4. Traps specific to this kind of data (leakage, confounders, seasonality).
Where useful, give the analysis as steps I could run in SQL or pandas.

Variables to customize

{{question}}

What you want to learn

{{schema}}

Columns or schema

Good follow-ups

• Write the SQL for the first quality checks.
• What visualization would best communicate the main finding?