コード例 #1
0
ファイル: devdocneeded.py プロジェクト: yuyan9/bugbug
    def __init__(self, lemmatization=False):
        BugModel.__init__(self, lemmatization, commit_data=True)

        self.cross_validation_enabled = False

        self.sampler = RandomUnderSampler(random_state=0)

        feature_extractors = [
            bug_features.has_str(),
            bug_features.has_regression_range(),
            bug_features.severity(),
            bug_features.keywords({"dev-doc-needed", "dev-doc-complete"}),
            bug_features.is_coverity_issue(),
            bug_features.has_crash_signature(),
            bug_features.has_url(),
            bug_features.has_w3c_url(),
            bug_features.has_github_url(),
            bug_features.whiteboard(),
            bug_features.patches(),
            bug_features.landings(),
            bug_features.product(),
            bug_features.component(),
            bug_features.commit_added(),
            bug_features.commit_deleted(),
            bug_features.commit_types(),
        ]

        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,
                        rollback_when=self.rollback,
                        commit_data=True,
                    ),
                ),
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(), "title"),
                            ("comments", self.text_vectorizer(), "comments"),
                        ]
                    ),
                ),
            ]
        )

        self.clf = xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count())
        self.clf.set_params(predictor="cpu_predictor")
コード例 #2
0
ファイル: devdocneeded.py プロジェクト: mythmon/bugbug
    def __init__(self, lemmatization=False):
        BugModel.__init__(self, lemmatization)

        self.sampler = RandomUnderSampler(random_state=0)

        feature_extractors = [
            bug_features.has_str(),
            bug_features.has_regression_range(),
            bug_features.severity(),
            bug_features.keywords({"dev-doc-needed", "dev-doc-complete"}),
            bug_features.is_coverity_issue(),
            bug_features.has_crash_signature(),
            bug_features.has_url(),
            bug_features.has_w3c_url(),
            bug_features.has_github_url(),
            bug_features.whiteboard(),
            bug_features.patches(),
            bug_features.landings(),
            bug_features.title(),
            bug_features.product(),
            bug_features.component(),
            bug_features.commit_added(),
            bug_features.commit_deleted(),
            bug_features.commit_types(),
        ]

        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,
                        rollback_when=self.rollback,
                        commit_data=True,
                    ),
                ),
                (
                    "union",
                    ColumnTransformer(
                        [
                            ("data", DictVectorizer(), "data"),
                            ("title", self.text_vectorizer(), "title"),
                            ("comments", self.text_vectorizer(), "comments"),
                        ]
                    ),
                ),
            ]
        )

        self.clf = xgboost.XGBClassifier(n_jobs=16)
        self.clf.set_params(predictor="cpu_predictor")
コード例 #3
0
    def __init__(self, lemmatization=False):
        Model.__init__(self, lemmatization)

        feature_extractors = [
            bug_features.has_str(),
            bug_features.has_regression_range(),
            bug_features.severity(),
            bug_features.keywords({'dev-doc-needed', 'dev-doc-complete'}),
            bug_features.is_coverity_issue(),
            bug_features.has_crash_signature(),
            bug_features.has_url(),
            bug_features.has_w3c_url(),
            bug_features.has_github_url(),
            bug_features.whiteboard(),
            bug_features.patches(),
            bug_features.landings(),
            bug_features.title(),
            bug_features.product(),
            bug_features.component(),
            bug_features.commit_added(),
            bug_features.commit_deleted(),
            bug_features.commit_types(),
        ]

        cleanup_functions = [
            bug_features.cleanup_fileref,
            bug_features.cleanup_url,
            bug_features.cleanup_synonyms,
        ]

        self.extraction_pipeline = Pipeline([
            ('bug_extractor',
             bug_features.BugExtractor(feature_extractors,
                                       cleanup_functions,
                                       rollback=True,
                                       rollback_when=self.rollback,
                                       commit_data=True)),
            ('union',
             ColumnTransformer([
                 ('data', DictVectorizer(), 'data'),
                 ('title', self.text_vectorizer(stop_words='english'),
                  'title'),
                 ('comments', self.text_vectorizer(stop_words='english'),
                  'comments'),
             ])),
        ])

        self.clf = xgboost.XGBClassifier(n_jobs=16)
        self.clf.set_params(predictor='cpu_predictor')