Y

Library · practice

Data cleaning and quality

Find what is wrong with a dataset before it reaches a report, and write checks that catch it automatically next time.

Analysts often say most of their time goes on cleaning. The skill is not only fixing problems; it is finding them systematically, deciding which ones matter, and documenting the decisions.

Examples use the NYC TLC trip records and the UCI Online Retail II data, both of which contain real, instructive problems.

  1. 1A data quality checklistA data quality checklist you can run in ten minutes3 min read

Data cleaning and quality lessons

Loading lessons…