-
Notifications
You must be signed in to change notification settings - Fork 157
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
[WIP] add decision function to LogisticGAM, for compat with sklearn multiclass #213
base: master
Are you sure you want to change the base?
Conversation
Codecov Report
@@ Coverage Diff @@
## master #213 +/- ##
==========================================
+ Coverage 94.86% 94.92% +0.06%
==========================================
Files 22 22
Lines 3056 3074 +18
==========================================
+ Hits 2899 2918 +19
+ Misses 157 156 -1
Continue to review full report at Codecov.
|
Can't use predict_proba with #196 example |
Predict_proba is now working properly but functional terms is (still) broken. It only returns the predicted class of the first item if a functional term is given. |
@903124 hmm thats interesting, but i dont completely understand. can you please show me an example? |
|
@903124 thanks for the example. |
@903124 thanks for your comments! i took a look inside, and it appears to be a complex fix. scikit-learn defers any processing of arguments until the fixing this is going to require a little bit more effort to defer all processing of arguments to the terms. |
Is this still going to be merged into master? Would love to try it out! |
closes #196
add
decision_function
method to theLogisticGAM
class for compatibility with sklearn'sOneVsRestClassifier
classtest
refactor terms so that all argument processing and sanitation is done during the
fit()
method