New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

Sweep score calculation for tp and fp #366

Open

szympie opened this issue May 26, 2020 · 1 comment

szympie commented May 26, 2020

During calculation of sweep score, if the anomalyPoint is in the anomaly windows you divide by windowWidth (https://github.com/numenta/NAB/blob/master/nab/sweeper.py#L176) and if the anomalyPoint is outside the anomaly window, you divide by windowWidth - 1 (https://github.com/numenta/NAB/blob/master/nab/sweeper.py#L188) is there any reason for it or is it a bug?

Contributor

markNZed commented Oct 22, 2021

I agree that it seems strange to change the window width. In the window the position formula is

-(curWindowRightIndex - i + 1) / curWindowWidth

After the window the formula is

abs(prevWindowRightIndex - i) / float(prevWindowWidth - 1)

I doubt it makes an important difference to the scores.

# for free to join this conversation on GitHub. Already have an account? # to comment