-
Notifications
You must be signed in to change notification settings - Fork 856
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
More sklearn-compatible algorithms #318
Conversation
hoffmansc
commented
Jun 28, 2022
- RejectOptionClassification (Port post-processing algorithms to sklearn-compatible API #151)
- LearnedFairRepresentations (Port pre-processing algorithms to sklearn-compatible API #154)
- option to suppress zero division warnings in metrics
- consolidate dataset loading in conftest.py
* dataset loading is more similar to sklearn.datasets * label binarization is now done outside standardize_dataset * metrics use 'groups' and 'priv_group' to signify priv/unpriv split
removed Reweighing.sample_weight_ attribute
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
* postprocessors need 'requires_proba' tag * no default postprocessor * fix prefit, score PostProcessingMeta bugs Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
* add fit_predict * add sample_weight warning Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
This pull request introduces 1 alert and fixes 1 when merging f978b5f into 89f700b - view on LGTM.com new alerts:
fixed alerts:
|
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.
both notebooks (LFR and ROC) look good to go :)
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>
This pull request introduces 1 alert and fixes 1 when merging 35f87a7 into 38368c5 - view on LGTM.com new alerts:
fixed alerts:
|
* new ROC and LFR implementations * allow prot_attr/target input to be Series * LFR uses pytorch to calculate grad * change defaults in metaestimators * clean up tests * infer proba behavior for PostProcessingMeta from estimator 'requires_proba' tag * fix prefit, score PostProcessingMeta bugs * propagate classes_ in metaestimators Signed-off-by: Samuel Hoffman <hoffman.sc@gmail.com>