# What is the correct way to compute Mean F1 score?

I have a set of 10 experiments that compute precision, recall and f1-score for each experiment. Now, average precision & average recall is easy to compute. I have some confusion regarding average f1-score.

There are 2 ways on how i can compute mean f1-score:

1. Take f1 scores for each of the 10 experiments and compute their average.
2. Take average precision & average recall and then compute f1-score using the formula f1 = 2*p*r/(p+r)

I could not find any strong reference to support any of the arguments. The closest document i could find is this: https://www.kaggle.com/wiki/MeanFScore

Can anyone explain with some reference (if possible) which of the methods is correct and why?

EDIT: One of the members suggested this source. Though, i still suspect the reliability of the source. I have seen people not using the method explained above in their research publications. (Even i would be using it in one of my publications) I would expect some more opinions from the community to verify this idea.

• You might find this useful. Jan 9, 2017 at 6:42
• How are you calculating the average precision/recall? Micro or macro? Jan 9, 2017 at 11:43
• @HimaVarsha I calculate using macro. Jan 9, 2017 at 18:09
• @Kiritee From that reference it looks like in both the methods(micro/macro) the method used is HM of average-precision & average-recall. One of my professors also suggested this. So i guess this should be correct. Jan 9, 2017 at 18:13
• @oW_ That is a good idea only when i am absolutely sure about the answer. I would still expect a few more suggestions. Jan 10, 2017 at 21:08