bugbug/models/component.py [87:127]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        ]

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

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

        self.clf = Pipeline(
            [
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(min_df=0.0001), "title"),
                            (
                                "comments",
                                self.text_vectorizer(min_df=0.0001),
                                "comments",
                            ),
                        ]
                    ),
                ),
                (
                    "estimator",
                    xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
                ),
            ]
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



bugbug/models/fixtime.py [41:81]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        ]

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

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

        self.clf = Pipeline(
            [
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(min_df=0.0001), "title"),
                            (
                                "comments",
                                self.text_vectorizer(min_df=0.0001),
                                "comments",
                            ),
                        ]
                    ),
                ),
                (
                    "estimator",
                    xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count()),
                ),
            ]
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -