def __init__()

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

• 65 lines of code
• 2 McCabe index (conditional complexity)

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

        feature_extractors = [
            bug_features.HasSTR(),
            bug_features.Severity(),
            # Ignore keywords that would make the ML completely skewed
            # (we are going to use them as 100% rules in the evaluation phase).
            bug_features.Keywords({"regression", "talos-regression", "feature"}),
            bug_features.IsCoverityIssue(),
            bug_features.HasCrashSignature(),
            bug_features.HasURL(),
            bug_features.HasW3CURL(),
            bug_features.HasGithubURL(),
            bug_features.Whiteboard(),
            bug_features.BlockedBugsNumber(),
            bug_features.EverAffected(),
            bug_features.AffectedThenUnaffected(),
            bug_features.Product(),
            bug_features.Component(),
        ]

        if historical:
            feature_extractors += [
                bug_features.HadSeverityEnhancement(),
                bug_features.Patches(),
                bug_features.Landings(),
            ]

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

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

        self.clf = ImblearnPipeline(
            [
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(min_df=0.001), "title"),
                            (
                                "first_comment",
                                self.text_vectorizer(min_df=0.001),
                                "first_comment",
                            ),
                            (
                                "comments",
                                self.text_vectorizer(min_df=0.001),
                                "comments",
                            ),
                        ]
                    ),
                ),
                ("sampler", BorderlineSMOTE(random_state=0)),
                (
                    "estimator",
                    xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
                ),
            ]
        )