def __init__(self, lemmatization=False, interpretable=False):
CommitModel.__init__(self, lemmatization)
self.required_dbs.append(BUG_INTRODUCING_COMMITS_DB)
self.store_dataset = True
self.sampler = RandomUnderSampler(random_state=0)
feature_extractors = [
commit_features.source_code_file_size(),
commit_features.other_file_size(),
commit_features.test_file_size(),
commit_features.source_code_added(),
commit_features.other_added(),
commit_features.test_added(),
commit_features.source_code_deleted(),
commit_features.other_deleted(),
commit_features.test_deleted(),
commit_features.author_experience(),
commit_features.reviewer_experience(),
commit_features.reviewers_num(),
commit_features.component_touched_prev(),
commit_features.directory_touched_prev(),
commit_features.file_touched_prev(),
commit_features.types(),
commit_features.files(),
commit_features.components(),
commit_features.components_modified_num(),
commit_features.directories(),
commit_features.directories_modified_num(),
commit_features.source_code_files_modified_num(),
commit_features.other_files_modified_num(),
commit_features.test_files_modified_num(),
commit_features.functions_touched_num(),
commit_features.functions_touched_size(),
]
cleanup_functions = [
feature_cleanup.fileref(),
feature_cleanup.url(),
feature_cleanup.synonyms(),
]
column_transformers = [("data", DictVectorizer(), "data")]
if not interpretable:
column_transformers.append(
("desc", self.text_vectorizer(min_df=0.0001), "desc"))
self.extraction_pipeline = Pipeline([
(
"commit_extractor",
commit_features.CommitExtractor(feature_extractors,
cleanup_functions),
),
("union", ColumnTransformer(column_transformers)),
])
self.clf = xgboost.XGBClassifier(n_jobs=16)
self.clf.set_params(predictor="cpu_predictor")
def __init__(self, lemmatization: bool = False) -> None:
CommitModel.__init__(self, lemmatization)
self.calculate_importance = False
self.training_dbs += [bugzilla.BUGS_DB]
self.sampler = RandomUnderSampler(random_state=0)
feature_extractors = [
commit_features.source_code_file_size(),
commit_features.other_file_size(),
commit_features.test_file_size(),
commit_features.source_code_added(),
commit_features.other_added(),
commit_features.test_added(),
commit_features.source_code_deleted(),
commit_features.other_deleted(),
commit_features.test_deleted(),
commit_features.reviewers_num(),
commit_features.types(),
commit_features.files(),
commit_features.components(),
commit_features.components_modified_num(),
commit_features.directories(),
commit_features.directories_modified_num(),
commit_features.source_code_files_modified_num(),
commit_features.other_files_modified_num(),
commit_features.test_files_modified_num(),
commit_features.functions_touched_num(),
commit_features.functions_touched_size(),
commit_features.source_code_file_metrics(),
]
cleanup_functions = [
feature_cleanup.fileref(),
feature_cleanup.url(),
feature_cleanup.synonyms(),
]
self.extraction_pipeline = Pipeline([
(
"commit_extractor",
commit_features.CommitExtractor(feature_extractors,
cleanup_functions),
),
(
"union",
ColumnTransformer([
("data", DictVectorizer(), "data"),
("desc", self.text_vectorizer(min_df=0.0001), "desc"),
]),
),
])
self.clf = xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count())
self.clf.set_params(predictor="cpu_predictor")
def __init__(
self,
lemmatization: bool = False,
interpretable: bool = True,
use_finder: bool = False,
exclude_finder: bool = True,
finder_regressions_only: bool = False,
) -> None:
CommitModel.__init__(self, lemmatization)
self.training_dbs += [BUG_INTRODUCING_COMMITS_DB, bugzilla.BUGS_DB]
if finder_regressions_only:
self.training_dbs.append(BUG_FIXING_COMMITS_DB)
self.store_dataset = True
self.sampler = RandomUnderSampler(random_state=0)
self.use_finder = use_finder
self.exclude_finder = exclude_finder
assert (
use_finder ^ exclude_finder
), "Using both use_finder and exclude_finder option does not make a lot of sense"
self.finder_regressions_only = finder_regressions_only
feature_extractors = [
commit_features.source_code_file_size(),
commit_features.other_file_size(),
commit_features.test_file_size(),
commit_features.source_code_added(),
commit_features.other_added(),
commit_features.test_added(),
commit_features.source_code_deleted(),
commit_features.other_deleted(),
commit_features.test_deleted(),
commit_features.author_experience(),
commit_features.reviewer_experience(),
commit_features.reviewers_num(),
commit_features.component_touched_prev(),
commit_features.directory_touched_prev(),
commit_features.file_touched_prev(),
commit_features.types(),
commit_features.files(),
commit_features.components(),
commit_features.components_modified_num(),
commit_features.directories(),
commit_features.directories_modified_num(),
commit_features.source_code_files_modified_num(),
commit_features.other_files_modified_num(),
commit_features.test_files_modified_num(),
commit_features.functions_touched_num(),
commit_features.functions_touched_size(),
commit_features.source_code_file_metrics(),
]
cleanup_functions = [
feature_cleanup.fileref(),
feature_cleanup.url(),
feature_cleanup.synonyms(),
]
column_transformers = [("data", DictVectorizer(), "data")]
if not interpretable:
column_transformers.append(
("desc", self.text_vectorizer(min_df=0.0001), "desc")
)
self.extraction_pipeline = Pipeline(
[
(
"commit_extractor",
commit_features.CommitExtractor(
feature_extractors, cleanup_functions
),
),
("union", ColumnTransformer(column_transformers)),
]
)
self.clf = xgboost.XGBClassifier(n_jobs=utils.get_physical_cpu_count())
self.clf.set_params(predictor="cpu_predictor")