Imagine we have 150 apples, randomly divide them into 5 group and randomly pick one group to stat the weight of each and whether each is rotten. When the job is done, we have 30 records of data.

I guess the stats about all 150 apples would be called the "whole data", a record of data that has both the weight and quality is called "complete data", a record of data that lacks the weight, the quality, or both, is called "incomplete data".

Is my understanding right?

Why would I have this question? Because a post says

In this approach we randomly split the complete data into training and test sets.

where the author uses "complete data" to refer to all 150 records of data.

The uses of "complete data" in books.google seem to be the way I use it.

Could someone please give a hint? Thanks in advance.

1 Answer 1


As far as what you are talking about here, both whole and complete mean exactly the same thing. (In other contexts there are very slight difference in nuance.)

As you have effectively said yourself, complete is the more common terminology currently, particularly in more formal contexts, but I believe that whole is in more common usage generally.

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .