Merged CSV Data Quality Report: Duplicates and Gaps
Create a data quality report for a merged CSV: duplicate rows, missing values, type mismatches and a 1 to 5 trust score with fixes to try.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Write a pandas script that checks a merged CSV file for quality and prints a plain-English report. The merged file: [MERGED_FILE_PATH]. Columns and what each should contain: [COLUMN_DEFINITIONS]. Key columns that should be unique together: [UNIQUE_KEY_COLUMNS]. Allowed values or ranges for important columns: [ALLOWED_VALUES]. The source file name column is called [SOURCE_COLUMN]. The report should include, as printed tables: row and column counts; missing values per column (count and percentage); duplicate rows and duplicate keys, with the source files involved; values outside the allowed list or range; columns with mixed types; dates that cannot be parsed; and rows per source file compared to what I expect: [EXPECTED_ROWS_PER_FILE]. Then add a scoring step. Score each area from 1 to 5 (completeness, uniqueness, validity, consistency, traceability) with a short threshold rule written in the code, and print a total out of 25 with a label: Trusted, Use with care, Fix first. Explain how each score was calculated, showing the arithmetic for one example. Provide the code with comments, then a short guide to reading the report and the five most common fixes. Do not change or delete data in the file; the script only reads and reports. Do not claim it was run. Ask me about any column rule I left unclear.
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.