Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

Z-Score to absolute anomaly score value #157

Open
mr-price opened this issue Aug 1, 2023 · 0 comments
Open

Z-Score to absolute anomaly score value #157

mr-price opened this issue Aug 1, 2023 · 0 comments

Comments

@mr-price
Copy link
Contributor

mr-price commented Aug 1, 2023

Hi,
I am building an app with merlion backend and have trained an isolation forest model on multivariate data. Now i want to provide my users a visual representation of my anomlay score. With a marker separating scores before the threshold and scores after the threshold.
for this I create a PDF plot representation of anomaly scores provided by my Isolation Forest model ( model.get_anomaly_score(data) ) and now i want create marker represent threshold. But my threshold is in Zscore value and to create a marker i would have to convert it into absolute score value. so that i am able to plot.

Since the score are processed using a calibrator i am unable to convert z-score to absolute score value. A guidance on how can i obtain this conversion would be helpful.

I have already tried getting the mean and standard deviation from the score data and then trying to convert z score to an absolute value using : Z = (x-μ)/σ

i want to achieve something like this :
Screenshot 2023-08-01 at 1 06 21 PM

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant