def __init__()

in bugbug/models/tracking.py [0:0]

• 72 lines of code
• 1 McCabe index (conditional complexity)

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

        self.calculate_importance = False

        feature_extractors = [
            bug_features.HasSTR(),
            bug_features.HasRegressionRange(),
            bug_features.Severity(),
            bug_features.Keywords(),
            bug_features.IsCoverityIssue(),
            bug_features.HasCrashSignature(),
            bug_features.HasURL(),
            bug_features.HasW3CURL(),
            bug_features.HasGithubURL(),
            bug_features.Whiteboard(),
            bug_features.Patches(),
            bug_features.Landings(),
            bug_features.Product(),
            bug_features.Component(),
            bug_features.IsMozillian(),
            bug_features.BugReporter(),
            bug_features.BlockedBugsNumber(),
            bug_features.Priority(),
            bug_features.HasCVEInAlias(),
            bug_features.CommentCount(),
            bug_features.CommentLength(),
            bug_features.ReporterExperience(),
            bug_features.NumberOfBugDependencies(),
        ]

        cleanup_functions = [
            feature_cleanup.url(),
            feature_cleanup.fileref(),
            feature_cleanup.hex(),
            feature_cleanup.dll(),
            feature_cleanup.synonyms(),
            feature_cleanup.crash(),
        ]

        self.extraction_pipeline = Pipeline(
            [
                (
                    "bug_extractor",
                    bug_features.BugExtractor(
                        feature_extractors,
                        cleanup_functions,
                        rollback=True,
                        rollback_when=self.rollback,
                    ),
                ),
            ]
        )

        self.clf = ImblearnPipeline(
            [
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(min_df=0.0001), "title"),
                            (
                                "comments",
                                self.text_vectorizer(min_df=0.0001),
                                "comments",
                            ),
                        ]
                    ),
                ),
                ("sampler", InstanceHardnessThreshold(random_state=0)),
                (
                    "estimator",
                    xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
                ),
            ]
        )