fix formatting and type issues

rasa/nlu/classifiers/logistic_regression_classifier.py

@@ -1,7 +1,6 @@
 import logging
 from typing import Any, Text, Dict, List, Type, Tuple
 
-import structlog
 from scipy.sparse import hstack, vstack, csr_matrix
 from sklearn.linear_model import LogisticRegression
 
@@ -184,7 +183,8 @@ def load(
 
                 if unknown_types:
                     logger.debug(
-                        f"Untrusted types ({unknown_types}) found when loading {classifier_file}!",
+                        f"Untrusted types ({unknown_types}) found when "
+                        f"loading {classifier_file}!",
                     )
                     raise ValueError()
 

rasa/nlu/extractors/crf_entity_extractor.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
-from collections import OrderedDict
-from enum import Enum
 import logging
 import typing
+from collections import OrderedDict
+from enum import Enum
 from typing import Any, Dict, List, Optional, Text, Tuple, Callable, Type
 
 import numpy as np
@@ -15,13 +15,12 @@
 from rasa.engine.recipes.default_recipe import DefaultV1Recipe
 from rasa.engine.storage.resource import Resource
 from rasa.engine.storage.storage import ModelStorage
+from rasa.nlu.constants import TOKENS_NAMES
+from rasa.nlu.extractors.extractor import EntityExtractorMixin
 from rasa.nlu.test import determine_token_labels
 from rasa.nlu.tokenizers.spacy_tokenizer import POS_TAG_KEY
-from rasa.nlu.extractors.extractor import EntityExtractorMixin
 from rasa.nlu.tokenizers.tokenizer import Token, Tokenizer
-from rasa.shared.nlu.training_data.training_data import TrainingData
-from rasa.shared.nlu.training_data.message import Message
-from rasa.nlu.constants import TOKENS_NAMES
+from rasa.shared.constants import DOCS_URL_COMPONENTS
 from rasa.shared.nlu.constants import (
     TEXT,
     ENTITIES,
@@ -32,7 +31,8 @@
     SPLIT_ENTITIES_BY_COMMA,
     SPLIT_ENTITIES_BY_COMMA_DEFAULT_VALUE,
 )
-from rasa.shared.constants import DOCS_URL_COMPONENTS
+from rasa.shared.nlu.training_data.message import Message
+from rasa.shared.nlu.training_data.training_data import TrainingData
 from rasa.utils.tensorflow.constants import BILOU_FLAG, FEATURIZERS
 
 logger = logging.getLogger(__name__)
@@ -116,7 +116,7 @@ class CRFEntityExtractor(GraphComponent, EntityExtractorMixin):
 
     CONFIG_FEATURES = "features"
 
-    function_dict: Dict[Text, Callable[[CRFToken], Any]] = {  # noqa: RUF012
+    function_dict: Dict[Text, Callable[[CRFToken], Any]] = {
         CRFEntityExtractorOptions.LOW: lambda crf_token: crf_token.text.lower(),
         CRFEntityExtractorOptions.TITLE: lambda crf_token: crf_token.text.istitle(),
         CRFEntityExtractorOptions.PREFIX5: lambda crf_token: crf_token.text[:5],

rasa/nlu/featurizers/sparse_featurizer/count_vectors_featurizer.py

@@ -6,22 +6,13 @@
 
 import numpy as np
 import scipy.sparse
-from sklearn.exceptions import NotFittedError
 from sklearn.feature_extraction.text import CountVectorizer
 
 import rasa.shared.utils.io
 from rasa.engine.graph import GraphComponent, ExecutionContext
 from rasa.engine.recipes.default_recipe import DefaultV1Recipe
 from rasa.engine.storage.resource import Resource
 from rasa.engine.storage.storage import ModelStorage
-from rasa.nlu.featurizers.sparse_featurizer.sparse_featurizer import SparseFeaturizer
-from rasa.nlu.utils.spacy_utils import SpacyModel
-from rasa.shared.constants import DOCS_URL_COMPONENTS
-import rasa.utils.io as io_utils
-from sklearn.feature_extraction.text import CountVectorizer
-from rasa.shared.nlu.training_data.training_data import TrainingData
-from rasa.shared.nlu.training_data.message import Message
-from rasa.shared.exceptions import RasaException, FileIOException
 from rasa.nlu.constants import (
     TOKENS_NAMES,
     MESSAGE_ATTRIBUTES,

rasa/utils/io.py

@@ -2,12 +2,13 @@
 import filecmp
 import logging
 import os
+import re
 import tempfile
 import warnings
-import re
 from asyncio import AbstractEventLoop
 from pathlib import Path
-from typing import Text, Any, Union, List, Type, Callable, TYPE_CHECKING, Pattern
+from typing import Text, Any, List, Type, Callable, TYPE_CHECKING, Pattern
+
 from typing_extensions import Protocol
 
 import rasa.shared.constants
@@ -100,7 +101,6 @@ def create_temporary_directory() -> Text:
 
 def create_path(file_path: Text) -> None:
     """Makes sure all directories in the 'file_path' exists."""
-
     parent_dir = os.path.dirname(os.path.abspath(file_path))
     if not os.path.exists(parent_dir):
         os.makedirs(parent_dir)
@@ -136,8 +136,8 @@ def create_validator(
     function: Callable[[Text], bool], error_message: Text
 ) -> Type["Validator"]:
     """Helper method to create `Validator` classes from callable functions. Should be
-    removed when questionary supports `Validator` objects."""
-
+    removed when questionary supports `Validator` objects.
+    """
     from prompt_toolkit.validation import Validator, ValidationError
     from prompt_toolkit.document import Document
 

rasa/utils/tensorflow/feature_array.py

@@ -1,9 +1,9 @@
 from typing import Dict, Any, List, Tuple, Optional, Union
 
-from safetensors.numpy import save_file
 import numpy as np
-from safetensors.numpy import load_file
 import scipy.sparse
+from safetensors.numpy import load_file
+from safetensors.numpy import save_file
 
 import rasa.shared.utils.io
 
@@ -77,9 +77,9 @@ def _serialize_nested_data(
                     array_metadata["features"],
                 )
 
-            inner_metadata["components"].append(
+            inner_metadata["components"].append(  # type:ignore[attr-defined]
                 array_metadata
-            )  # type:ignore[attr-defined]
+            )
 
         metadata.append(inner_metadata)
 
@@ -236,7 +236,9 @@ def __array_finalize__(self, obj: Optional[np.ndarray]) -> None:
             return
 
         self.units = getattr(obj, "units", None)
-        self.number_of_dimensions = getattr(obj, "number_of_dimensions", None)  # type: ignore[assignment]
+        self.number_of_dimensions = getattr(
+            obj, "number_of_dimensions", None
+        )  # type: ignore[assignment]
         self.is_sparse = getattr(obj, "is_sparse", None)
 
         default_attributes = {

tests/utils/test_io.py

@@ -1,5 +1,3 @@
-from pathlib import Path
-
 import pytest
 from _pytest.tmpdir import TempPathFactory
 from prompt_toolkit.document import Document