-
Notifications
You must be signed in to change notification settings - Fork 9
feat(RHOAIENG-21045): Add fairness metrics and tests #5
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
base: main
Are you sure you want to change the base?
feat(RHOAIENG-21045): Add fairness metrics and tests #5
Conversation
def filter_rows_by_inputs(data, filter_func): | ||
return data[np.apply_along_axis(filter_func, 1, data)] | ||
|
||
def calculate_confusion_matrix(test: np.array, truth: np.array, positive_class: int) -> dict: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@staticmethod | ||
def calculate_model( | ||
samples: np.ndarray, | ||
model: Any, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we have a structure/planned datatype for this yet? While I like this idea, I fear it could run into the same security issues as we've been seeing with the explainers in the Java service
tests/metrics/data/data.csv
Outdated
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Are these to test parity against the existing Java service? I wonder if we might want to use synthetically generated data to avoid storing a lot of raw datasets in the repo
49ef199
to
407f057
Compare
b83a31e
to
1e28682
Compare
No description provided.