Skip to content

Calibrate component model #5183

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

Open
marco-c wants to merge 1 commit into
base: master
Choose a base branch
from
+9 −2
Open

Calibrate component model #5183

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 9 additions & 2 deletions bugbug/models/component.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
from bugbug import bug_features, bugzilla, feature_cleanup, utils
from bugbug.bugzilla import get_product_component_count
from bugbug.model import BugModel
from bugbug.model_calibration import IsotonicRegressionCalibrator

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -67,7 +68,7 @@ class ComponentModel(BugModel):
"Firefox for Android": "Firefox for Android::General",
}

def __init__(self, lemmatization=False):
def __init__(self, calibration=True, lemmatization=False):
BugModel.__init__(self, lemmatization)

self.cross_validation_enabled = False
Expand Down Expand Up @@ -103,6 +104,12 @@ def __init__(self, lemmatization=False):
]
)

estimator = xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count())
if calibration:
estimator = IsotonicRegressionCalibrator(estimator)
# This is a temporary workaround for the error : "Model type not yet supported by TreeExplainer"
self.calculate_importance = False

self.clf = Pipeline(
[
(
Expand All @@ -121,7 +128,7 @@ def __init__(self, lemmatization=False):
),
(
"estimator",
xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
estimator,
),
]
)
Expand Down