Update pre-commit repositories

.pre-commit-config.yaml

@@ -1,10 +1,10 @@
 repos:
   - repo: https://github.com/PyCQA/isort
-    rev: 5.10.1
+    rev: 5.12.0
     hooks:
       - id: isort
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.1.0
     hooks:
       - id: black
   - repo: https://github.com/pre-commit/mirrors-prettier
@@ -22,7 +22,7 @@ repos:
           - "flake8-debugger==4.1.2"
           - "flake8-mypy==17.8.0"
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.4.0
     hooks:
       - id: check-ast
       - id: check-docstring-first
@@ -41,7 +41,7 @@ repos:
       - id: requirements-txt-fixer
       - id: check-vcs-permalinks
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.1.0
+    rev: v2.2.2
     hooks:
       - id: codespell
         exclude_types: [json]
@@ -50,7 +50,7 @@ repos:
     hooks:
       - id: taskcluster_yml
   - repo: https://github.com/asottile/yesqa
-    rev: v1.3.0
+    rev: v1.4.0
     hooks:
       - id: yesqa
   - repo: https://github.com/pre-commit/mirrors-mypy

bugbug/bug_features.py

@@ -731,7 +731,6 @@ class BugExtractor(BaseEstimator, TransformerMixin):
         already_rollbacked = set()
 
         def apply_transform(bug):
-
             is_couple = isinstance(bug, tuple)
 
             if not is_couple:

bugbug/issue_features.py

@@ -49,7 +49,6 @@ class IssueExtractor(BaseEstimator, TransformerMixin):
         results = []
 
         for issue in issues():
-
             if self.rollback:
                 issue = issue_snapshot.rollback(issue, self.rollback_when)
 

bugbug/models/component.py

@@ -258,7 +258,6 @@ class ComponentModel(BugModel):
         # than 0 bugs
 
         for conflated_component in self.CONFLATED_COMPONENTS:
-
             matching_components = [
                 full_comp
                 for full_comp in bugs_number
@@ -286,7 +285,6 @@ class ComponentModel(BugModel):
         # still exist as components and have more than 0 bugs
 
         for full_comp in self.CONFLATED_COMPONENTS_MAPPING.values():
-
             if full_comp not in bugs_number:
                 print(
                     f"{full_comp} from conflated component mapping doesn't exists, failure"
@@ -302,7 +300,6 @@ class ComponentModel(BugModel):
         # exist as components or are in CONFLATED_COMPONENTS_MAPPING
 
         for conflated_component in self.CONFLATED_COMPONENTS:
-
             in_mapping = conflated_component in self.CONFLATED_COMPONENTS_MAPPING
 
             matching_components = [

bugbug/models/component_nn.py

@@ -66,7 +66,7 @@ class ComponentNNClassifier(KerasClassifier):
         self.long_desc_emb_sz = kwargs.pop("long_desc_emb_sz")
         self.model_params = kwargs.pop("params")
 
-        for (k, v) in self.model_params.items():
+        for k, v in self.model_params.items():
             setattr(self, k, v)
 
         return self

bugbug/models/duplicate.py

@@ -76,7 +76,6 @@ class DuplicateModel(BugCoupleModel):
         self.clf = XGBClassifier(n_jobs=utils.get_physical_cpu_count())
 
     def get_labels(self):
-
         random.seed(4)
 
         all_ids = set(

bugbug/models/spambug.py

@@ -130,7 +130,7 @@ class SpamBugModel(BugModel):
         return self.extraction_pipeline.named_steps["union"].get_feature_names()
 
     def overwrite_classes(self, bugs, classes, probabilities):
-        for (i, bug) in enumerate(bugs):
+        for i, bug in enumerate(bugs):
             if "@mozilla" in bug["creator"]:
                 if probabilities:
                     classes[i] = [1.0, 0.0]

bugbug/nlp.py

@@ -48,7 +48,6 @@ def spacy_token_lemmatizer(text):
 
 class SpacyVectorizer(TfidfVectorizer):
     def __init__(self, *args, **kwargs):
-
         # Detect when the Spacy optional dependency is missing
         if not HAS_OPTIONAL_DEPENDENCIES:
             raise NotImplementedError(OPT_MSG_MISSING)

bugbug/nn.py

@@ -45,7 +45,7 @@ class KerasClassifier(BaseEstimator, ClassifierMixin):
 
         self.model = self.model_creator(X_dict, y)
 
-        for (epochs, batch_size) in self.fit_params:
+        for epochs, batch_size in self.fit_params:
             self.model.fit(X_dict, y, epochs=epochs, batch_size=batch_size, verbose=1)
 
         return self

bugbug/similarity.py

@@ -138,7 +138,6 @@ class BaseSimilarity(abc.ABC):
         return similar_bug_ids
 
     def text_preprocess(self, text, stemming=True, lemmatization=False, join=False):
-
         for func in self.cleanup_functions:
             text = func(text)
 
@@ -274,7 +273,6 @@ class LSISimilarity(BaseSimilarity):
         self.corpus = []
 
         for bug in bugzilla.get_bugs():
-
             textual_features = self.text_preprocess(self.get_text(bug))
             self.corpus.append([bug["id"], textual_features])
 
@@ -349,7 +347,6 @@ class NeighborsSimilarity(BaseSimilarity):
         self.similarity_calculator.fit(self.vectorizer.transform(text))
 
     def search_similar_bugs(self, query):
-
         processed_query = self.vectorizer.transform([self.get_text(query)])
         _, indices = self.similarity_calculator.kneighbors(processed_query)
 
@@ -466,7 +463,6 @@ class Word2VecWmdSimilarity(Word2VecSimilarityBase):
         )
 
     def search_similar_bugs(self, query):
-
         words = self.text_preprocess(self.get_text(query))
         words = [word for word in words if word in self.w2vmodel.wv.vocab]
 
@@ -493,7 +489,6 @@ class Word2VecWmdSimilarity(Word2VecSimilarityBase):
         confirmed_distances = []
 
         for i, (doc_id, rwmd_distance) in enumerate(distances):
-
             if (
                 len(confirmed_distances) >= 10
                 and rwmd_distance > confirmed_distances[10 - 1]
@@ -520,7 +515,6 @@ class Word2VecWmdSimilarity(Word2VecSimilarityBase):
         ]
 
     def get_distance(self, query1, query2):
-
         words1 = self.text_preprocess(self.get_text(query1))
         words1 = [word for word in words1 if word in self.w2vmodel.wv.vocab]
         words2 = self.text_preprocess(self.get_text(query2))
@@ -550,7 +544,6 @@ class Word2VecWmdRelaxSimilarity(Word2VecSimilarityBase):
         self.tfidf = TfidfModel(dictionary=self.dictionary)
 
     def search_similar_bugs(self, query):
-
         query = self.text_preprocess(self.get_text(query))
         words = [
             word for word in set(chain(query, *self.corpus)) if word in self.w2vmodel.wv

scripts/analyze_training_metrics.py

@@ -121,7 +121,6 @@ def analyze_metrics(
 
     # First process the metrics JSON files
     for metric_file_path in root.glob("metric*.json"):
-
         date, model_name, metric = parse_metric_file(metric_file_path)
 
         # Then process the report
@@ -151,7 +150,6 @@ def analyze_metrics(
     # Then analyze them
     for model_name in metrics:
         for metric_name, values in metrics[model_name].items():
-
             if metric_name.endswith("_std"):
                 LOGGER.info(
                     "Skipping analysis of %r, analysis is not efficient on standard deviation",

scripts/get_untriaged.py

@@ -47,7 +47,7 @@ def run_untriaged(untriaged_bugs):
         (ComponentModel, "../componentmodel"),
         (ComponentNNModel, "../componentnnmodel"),
     ]
-    for (model_class, model_file_name) in models:
+    for model_class, model_file_name in models:
         rows = []
         model = model_class.load(model_file_name)
         for bug in untriaged_bugs:

scripts/github_issue_classifier.py

@@ -19,7 +19,6 @@ logger = getLogger(__name__)
 def classify_issues(
     owner: str, repo: str, retrieve_events: bool, model_name: str, issue_number: int
 ) -> None:
-
     model_file_name = f"{model_name}model"
 
     if not os.path.exists(model_file_name):

scripts/github_issue_retriever.py

@@ -70,7 +70,6 @@ class Retriever(object):
         return updated_issues, updated_ids
 
     def retrieve_issues(self) -> None:
-
         last_modified = None
         db.download(self.github.db_path)
 

scripts/similarity_query.py

@@ -31,7 +31,6 @@ def parse_args(args):
 
 
 def main(args):
-
     if args.algorithm == "elasticsearch":
         model = similarity.model_name_to_class[args.algorithm]()
     else:

tests/test_bugtype.py

@@ -9,7 +9,6 @@ from bugbug.models.bugtype import BugTypeModel
 
 
 def test_get_bugtype_labels():
-
     model = BugTypeModel()
     classes, keyword_list = model.get_labels()
 

tests/test_testselect.py

@@ -186,7 +186,9 @@ def test_reduce4(failing_together: LMDBDict) -> None:
         },
         1.0,
     )
-    assert result == {"windows10/opt-e",} or result == {
+    assert result == {
+        "windows10/opt-e",
+    } or result == {
         "windows10/opt-b",
     }