I am new to data science. I was looking into some datasets and I saw some values like -99, which I discovered later that it means that there is a missing value. Does this mean the same thing as NaN? If it is the same thing, why do we use -99 instead of NaN?

  • $\begingroup$ Maybe, the datset values do not/ rarely turn negative - and even then the abs(num_val) is pretty small. If so, -99 is an sort of numerical identifier for 'wrong' values. Meanwhile, you can refer this wiki page. $\endgroup$ – Continue2Learn Jul 18 '19 at 2:14

No, it is not the same. It may have that meaning in that particular dataframe, but don't take that as a rule.

I'd recommend you replace that magic number with actual NaNs, and then try to find the best possible way of filling up the missing values.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.