The following records should be marked for review:
These records should be marked for review as duplicates:
Ask the students to disregard their own solutions for Part A and use the Part A Example Solution as a starting point for Part B.
It is recommended to go over the data cleaning plan in class, especially if Part B is not assigned immediately after completion of Part A. The depth and extent of this discussion depends on the quality of students' submissions for Part A of this project.
Tell students that they do not have to follow the order of inconsistencies in the list. For example, one of the approaches is to start the process with structural changes (add and rename columns), and then proceed with actual cleaning. Thoughtful order of cleaning steps can improve the quality of the resulting data. For example, the “Vendor Notes” field is not used...
