The Data Cleaning Advisor

Advise on preparing this messy data before I analyse it.

The dataset: [DESCRIBE — SOURCE, FIELDS, SIZE, KNOWN ISSUES]
The analysis I plan: [DESCRIBE]

Provide:
1. The data quality issues to check for (missing values, duplicates,
   outliers, inconsistent formats, wrong types)
2. How to handle each without distorting the results
3. The transformations the planned analysis needs
4. The sanity checks to confirm the data is trustworthy
5. The issues that would make the analysis unsafe to run at all

Warn me where a cleaning choice (e.g. dropping vs imputing missing data)
could change the conclusion.