def __init__()

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

• 70 lines of code
• 3 McCabe index (conditional complexity)

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

        self.calculate_importance = False

        self.le = LabelBinarizer()

        self.bug_type_extractors = bug_features.BugTypes.bug_type_extractors

        label_keyword_prefixes = {
            keyword
            for extractor in self.bug_type_extractors
            for keyword in extractor.keyword_prefixes
        }

        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(prefixes_to_ignore=label_keyword_prefixes),
            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.BlockedBugsNumber(),
            bug_features.EverAffected(),
            bug_features.AffectedThenUnaffected(),
            bug_features.Product(),
            bug_features.Component(),
        ]

        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 = Pipeline(
            [
                (
                    "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",
                            ),
                        ]
                    ),
                ),
                (
                    "estimator",
                    OneVsRestClassifier(
                        xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count())
                    ),
                ),
            ]
        )