This commit is contained in:
Ayush Shridhar 2019-05-18 04:03:57 -07:00 коммит произвёл Marco
Родитель 33f6ae83ce
Коммит 24c805e64e
3 изменённых файлов: 93 добавлений и 0 удалений

Просмотреть файл

@ -21,6 +21,7 @@ MODELS = {
"stepstoreproduce": "bugbug.models.stepstoreproduce.StepsToReproduceModel",
"tracking": "bugbug.models.tracking.TrackingModel",
"uplift": "bugbug.models.uplift.UpliftModel",
"regressionrange": "bugbug.models.regressionrange.RegressionRangeModel",
}

Просмотреть файл

@ -0,0 +1,91 @@
# -*- coding: utf-8 -*-
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this file,
# You can obtain one at http://mozilla.org/MPL/2.0/.
import xgboost
from imblearn.under_sampling import RandomUnderSampler
from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction import DictVectorizer
from sklearn.pipeline import Pipeline
from bugbug import bug_features, bugzilla, feature_cleanup
from bugbug.model import BugModel
class RegressionRangeModel(BugModel):
def __init__(self, lemmatization=False):
BugModel.__init__(self, lemmatization)
self.sampler = RandomUnderSampler(random_state=0)
feature_extractors = [
bug_features.has_str(),
bug_features.severity(),
bug_features.keywords({"regression", "regressionwindow-wanted"}),
bug_features.is_coverity_issue(),
bug_features.has_crash_signature(),
bug_features.has_url(),
bug_features.has_w3c_url(),
bug_features.has_github_url(),
bug_features.whiteboard(),
bug_features.patches(),
bug_features.landings(),
bug_features.title(),
]
cleanup_functions = [
feature_cleanup.fileref(),
feature_cleanup.url(),
feature_cleanup.synonyms(),
]
self.extraction_pipeline = Pipeline(
[
(
"bug_extractor",
bug_features.BugExtractor(feature_extractors, cleanup_functions),
),
(
"union",
ColumnTransformer(
[
("data", DictVectorizer(), "data"),
("title", self.text_vectorizer(), "title"),
("comments", self.text_vectorizer(), "comments"),
]
),
),
]
)
self.clf = xgboost.XGBClassifier(n_jobs=16)
self.clf.set_params(predictor="cpu_predictor")
def get_labels(self):
classes = {}
for bug_data in bugzilla.get_bugs():
bug_id = int(bug_data["id"])
if "regressionwindow-wanted" in bug_data["keywords"]:
classes[bug_id] = 0
elif "cf_has_regression_range" in bug_data:
if bug_data["cf_has_regression_range"] == "yes":
classes[bug_id] = 1
elif bug_data["cf_has_regression_range"] == "no":
classes[bug_id] = 0
print(
"{} bugs have regression range".format(
sum(1 for label in classes.values() if label == 1)
)
)
print(
"{} bugs don't have a regression range".format(
sum(1 for label in classes.values() if label == 0)
)
)
return classes, [0, 1]
def get_feature_names(self):
return self.extraction_pipeline.named_steps["union"].get_feature_names()

1
run.py
Просмотреть файл

@ -38,6 +38,7 @@ if __name__ == "__main__":
"assignee",
"bugtype",
"stepstoreproduce",
"regressionrange",
# commit classifiers
"backout",
],