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.

Sign up for GitHub

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

Jump to bottom

Fix for SVC fit_proba not using class weights #5912

Merged
merged 7 commits into from
Jun 15, 2024
Merged

Fix for SVC fit_proba not using class weights #5912

Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
29b213a
Pass on sample_weight when fitting svc with proba
pablotanner Jun 1, 2024
277022f
Fix typo in 'sample_weight' param of SVC fit_proba
pablotanner Jun 1, 2024
1813f2b
Init sample_weight variable in _fit_proba so it doesn't crash if not …
pablotanner Jun 2, 2024
12b948d
Merge branch 'branch-24.08' into patch-1
dantegd Jun 3, 2024
9782a8e
Update copyright header year to 2024
pablotanner Jun 4, 2024
584be02
Fix issue where sample_weight is None
pablotanner Jun 6, 2024
9b9810d
Merge branch 'branch-24.08' into patch-1
dantegd Jun 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions python/cuml/svm/svc.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,7 +440,7 @@ class SVC(SVMBase,
self._fit_status_ = 0
return self

def _fit_proba(self, X, y, samle_weight) -> "SVC":
def _fit_proba(self, X, y, sample_weight) -> "SVC":
params = self.get_params()
params["probability"] = False

Expand All @@ -460,8 +460,14 @@ class SVC(SVMBase,
cv=5,
method='sigmoid')

# Apply class weights to sample weights, necessary so it doesn't crash when sample_weight is None
# could also be done in .fit()
sample_weight = apply_class_weight(self.handle, sample_weight, self.class_weight, y, self.verbose,
self.output_type, self.dtype)

with cuml.internals.exit_internal_api():
self.prob_svc.fit(X, y)
# .get() is necessary because sklearn requires explicit conversion to np array
self.prob_svc.fit(X, y, sample_weight=sample_weight.get())
pablotanner marked this conversation as resolved.
Show resolved Hide resolved
self._fit_status_ = 0
return self

Expand Down
Loading