Assess Dataset Quality Before Analysis
Audits a dataset's health before analysis starts, using its columns, row count, source, time range, and a sample of rows to spot missing values, type mismatches, likely outliers, duplicate rows, and inconsistent categorical entries. Returns a 1-10 quality score with reasoning and a concrete cleaning step for every issue found, making it a natural first pass before writing any cleaning script.
Prompt
I have a dataset structured as follows: Columns: {columns} Row count: {row_count} Source: {source} Time range: {time_range} Sample rows: {sample_rows} Evaluate the data quality: 1. Spot columns likely to have null or missing values and propose ways to handle them (impute, drop, flag) 2. Highlight possible data type problems (numbers stored as strings, inconsistent date formats) 3. Point out likely outliers and note whether each is an error or a genuine extreme value 4. Look for duplicate or near-duplicate rows 5. Flag inconsistencies within categorical columns (capitalization, spelling variants, abbreviations) 6. Score the overall data quality from 1 to 10 with your reasoning For every issue you find, describe the exact cleaning step required.
