There are many ways to deal with missing records. The simplest one is to delete them. This is especially true when we have a relative large dataset. One potential issue is that our final dataset should not be changed in any fundamental way after we delete the missing data. In other words, if the missing records happened in a random way, then simply deleting them would not generate a biased result.
Dealing with missing data
Get Hands-On Data Science with Anaconda now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
