Build A Data Validation Framework
Builds a repeatable validation suite for a dataset you'll keep receiving, based on its description, columns, and stated business rules. Produces per-column checks, cross-column business-logic rules, and statistical sanity checks, then wraps them into a Python script that reports failure counts per rule, sample bad rows, an overall quality score, and a priority order for fixes.
Prompt
Build a thorough data validation framework for this dataset: Dataset description: {dataset_description} Columns: {columns} Business rules: {business_rules} Produce: 1. Per-column validation rules (type checks, range checks, pattern checks, referential integrity) 2. Cross-column rules (date ordering, calculated-field consistency, logical constraints) 3. Statistical checks (values within expected distribution, no sudden pattern shifts) 4. A script that runs all validations and returns a report: - Rows failing each rule - Sample failing rows - Overall quality score - Priority order for fixes
