def __init__()

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

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

    def __init__(self, lemmatization: bool = False) -> None:
        CommitModel.__init__(self, lemmatization)

        self.calculate_importance = False
        self.cross_validation_enabled = False

        self.training_dbs += [bugzilla.BUGS_DB]

        feature_extractors = [
            commit_features.SourceCodeFileSize(),
            commit_features.OtherFileSize(),
            commit_features.TestFileSize(),
            commit_features.SourceCodeAdded(),
            commit_features.OtherAdded(),
            commit_features.TestAdded(),
            commit_features.SourceCodeDeleted(),
            commit_features.OtherDeleted(),
            commit_features.TestDeleted(),
            commit_features.ReviewersNum(),
            commit_features.Types(),
            commit_features.Files(),
            commit_features.Components(),
            commit_features.ComponentsModifiedNum(),
            commit_features.Directories(),
            commit_features.DirectoriesModifiedNum(),
            commit_features.SourceCodeFilesModifiedNum(),
            commit_features.OtherFilesModifiedNum(),
            commit_features.TestFilesModifiedNum(),
            commit_features.FunctionsTouchedNum(),
            commit_features.FunctionsTouchedSize(),
            commit_features.SourceCodeFileMetrics(),
        ]

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

        self.extraction_pipeline = Pipeline(
            [
                (
                    "commit_extractor",
                    commit_features.CommitExtractor(
                        feature_extractors, cleanup_functions
                    ),
                ),
            ]
        )

        self.clf = ImblearnPipeline(
            [
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("desc", self.text_vectorizer(min_df=0.0001), "desc"),
                            (
                                "files",
                                CountVectorizer(
                                    analyzer=utils.keep_as_is,
                                    lowercase=False,
                                    min_df=0.0014,
                                ),
                                "files",
                            ),
                        ]
                    ),
                ),
                ("sampler", RandomUnderSampler(random_state=0)),
                (
                    "estimator",
                    xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
                ),
            ]
        )