Update rules for linting

.pre-commit-config.yaml

@@ -19,4 +19,4 @@ repos:
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
-      - id: trailing-whitespace
+      - id: trailing-whitespace

README.md

@@ -19,7 +19,7 @@ Concepts have to be identifiable by `rdf:type`.
 The training of the predictor requires annotated text.
 Each training sample should be annotated with one or more concepts from the thesaurus.
 
-## Installation 
+## Installation
 
 ### Requirements
 
@@ -32,7 +32,7 @@ stwfsapy is available on [PyPI](pypi.org) . You can install stwfsapy using pip:
 
 This will install a python package called `stwfsapy`.
 
-Note that it is generally recommended to use a [virtual environment](https://docs.python.org/3/tutorial/venv.html) to avoid 
+Note that it is generally recommended to use a [virtual environment](https://docs.python.org/3/tutorial/venv.html) to avoid
  conflicting behaviour with the system package manager.
 
 ### From source
@@ -41,7 +41,7 @@ You also have the option to checkout the repository and install the packages fro
 
 ```shell
 # call inside the project directory
-poetry install --without ci 
+poetry install --without ci
 ```
 
 ## Usage
@@ -105,15 +105,15 @@ Afterwards it can be loaded as follows:
 from stwfsapy.predictor import StwfsapyPredictor
 
 StwfsapyPredictor.load('/path/to/storage/location')
-``` 
+```
 
 ## Contribute
 
 Contributions via pull requests are welcome. Please create an issue beforehand
 to explain and discuss the reasons for the respective contribution. We recommend
 [forking](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo) the repository, if you have not already done so, before working on any possible pull request.
 
-`stwfsapy` code should follow the [Black style] (https://black.readthedocs.io/en/stable/). The Black tool is included as a development dependency; you can run `black .` in the project root to autoformat code. There is also the possibility of doing linting and code formatting with a Git Pre-Commit hook script. To this end a  `.pre-commit-config.yaml` configuration file has been added. The [pre-commit](https://pre-commit.com/) tool has been included as a development dependency. You would have to run the command `pre-commit install` inside your local virtual environment. Subsequently, the Black and Ruff tools will automatically check the linting and formatting of modified or new scripts after each time a `git commit` command is executed.
+`stwfsapy` code should follow the [Black style](https://black.readthedocs.io/en/stable/). The Black tool is included as a development dependency; you can run `black .` in the project root to autoformat code. There is also the possibility of doing linting and code formatting with a Git Pre-Commit hook script. To this end a  `.pre-commit-config.yaml` configuration file has been added. The [pre-commit](https://pre-commit.com/) tool has been included as a development dependency. You would have to run the command `pre-commit install` inside your local virtual environment. Subsequently, the Black and Ruff tools will automatically check the linting and formatting of modified or new scripts after each time a `git commit` command is executed.
 
 ## References
 [1] [Toepfer, Martin, and Christin Seifert. "Fusion architectures for automatic subject indexing under concept drift" International Journal on Digital Libraries (IJDL), 2018.](https://ris.utwente.nl/ws/portalfiles/portal/248044709/Toepfer2018fusion.pdf)

pyproject.toml

@@ -34,6 +34,16 @@ bandit = "~1.8"
 [tool.ruff]
 target-version = "py310"
 
+[tool.ruff.lint]
+select = [
+    # pycodestyle
+    "E",
+    # Pyflakes
+    "F",
+    # isort
+    "I"
+]
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

stwfsapy/automata/construction.py

@@ -14,6 +14,7 @@
 
 
 from typing import List
+
 from stwfsapy.automata import nfa
 
 

stwfsapy/automata/conversion.py

@@ -14,10 +14,10 @@
 
 
 from collections import defaultdict
-from typing import Tuple, Set, Dict, FrozenSet, Iterable, List
-from stwfsapy.automata import dfa
-from stwfsapy.automata import nfa
 from queue import Queue
+from typing import Dict, FrozenSet, Iterable, List, Set, Tuple
+
+from stwfsapy.automata import dfa, nfa
 
 
 class NfaToDfaConverter:

stwfsapy/automata/dfa.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-from typing import List, Dict, Iterable, Tuple, Any, Callable, Optional
+from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple
 
 _KEY_STATE_SYMBOL_TRANSITIONS = "symbol_transitions"
 _KEY_STATE_NON_WORD_CHAR_TRANSITION = "non_word_char_transitions"

stwfsapy/automata/heap.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 
-from typing import List, Dict, Tuple, Any, SupportsFloat
+from typing import Any, Dict, List, SupportsFloat, Tuple
 
 
 class BinaryMinHeap:

stwfsapy/automata/nfa.py

@@ -14,7 +14,8 @@
 
 
 from collections import defaultdict
-from typing import Set, List, Any, DefaultDict
+from typing import Any, DefaultDict, List, Set
+
 from stwfsapy.automata.heap import BinaryMinHeap
 
 

stwfsapy/expansion.py

@@ -13,9 +13,8 @@
 # limitations under the License.
 
 
-from typing import Callable, Pattern, List
 import re
-
+from typing import Callable, List, Pattern
 
 _symbol_base_expression = re.compile(r"([\[\]()\{\}*?])")
 

stwfsapy/frequency_features.py

@@ -13,11 +13,12 @@
 # limitations under the License.
 
 
-from collections import defaultdict, OrderedDict
-from sklearn.base import BaseEstimator, TransformerMixin
-from sklearn.exceptions import NotFittedError
+from collections import OrderedDict, defaultdict
 from math import log
+
 import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.exceptions import NotFittedError
 
 
 class FrequencyFeatures(BaseEstimator, TransformerMixin):

stwfsapy/position_features.py

@@ -13,8 +13,8 @@
 # limitations under the License.
 
 
-from sklearn.base import BaseEstimator, TransformerMixin
 import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin
 
 
 class PositionFeatures(BaseEstimator, TransformerMixin):

stwfsapy/predictor.py

@@ -13,33 +13,32 @@
 # limitations under the License.
 
 
-from stwfsapy.util.passthrough_transformer import PassthroughTransformer
-from stwfsapy.frequency_features import FrequencyFeatures
-from stwfsapy.position_features import PositionFeatures
+import pickle as pkl
 from collections import defaultdict
-from typing import Dict, FrozenSet, List, Iterable, Container, Tuple, TypeVar, Union
-from scipy.sparse import spmatrix
-from numpy import array
+from json import dumps, loads
 from logging import getLogger
-from rdflib.term import URIRef
+from typing import Container, Dict, FrozenSet, Iterable, List, Tuple, TypeVar, Union
+from zipfile import ZipFile
+
+from numpy import array
 from rdflib import Graph
+from rdflib.term import URIRef
+from scipy.sparse import csr_matrix, spmatrix
 from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.pipeline import Pipeline
 from sklearn.compose import ColumnTransformer
-from sklearn.tree import DecisionTreeClassifier
 from sklearn.feature_extraction.text import TfidfVectorizer
-from scipy.sparse import csr_matrix
+from sklearn.pipeline import Pipeline
+from sklearn.tree import DecisionTreeClassifier
+
+from stwfsapy import case_handlers, expansion
 from stwfsapy import thesaurus as t
-from stwfsapy.automata import nfa, construction, conversion, dfa
-from stwfsapy.thesaurus_features import ThesaurusFeatureTransformation
+from stwfsapy.automata import construction, conversion, dfa, nfa
+from stwfsapy.frequency_features import FrequencyFeatures
+from stwfsapy.position_features import PositionFeatures
 from stwfsapy.text_features import mk_text_features
+from stwfsapy.thesaurus_features import ThesaurusFeatureTransformation
 from stwfsapy.util.input_handler import get_input_handler
-from stwfsapy import case_handlers
-from stwfsapy import expansion
-import pickle as pkl
-from json import dumps, loads
-from zipfile import ZipFile
-
+from stwfsapy.util.passthrough_transformer import PassthroughTransformer
 
 T = TypeVar("T")
 N = TypeVar("N", int, float)
@@ -273,7 +272,8 @@ def fit(self, X, y=None, **kwargs):
         Fits the classifier to the given training data.
 
         :params  X: Iterable of text inputs.
-        :params  y: Iterable of correct concepts given by their URI for supervised training.
+        :params  y: Iterable of correct concepts given by their URI for supervised
+        training.
 
         Returns:
             self: The fitted StwfsapyPredictor instance.
@@ -295,7 +295,8 @@ def predict_proba(self, X) -> csr_matrix:
         :params  X: Iterable of input texts.
 
         Returns:
-            A sparse matrix of shape (n_samples, n_concepts) with concept match probabilities.
+            A sparse matrix of shape (n_samples, n_concepts) with concept match
+            probabilities.
         """
         match_X, doc_counts = self.match_and_extend(X)
         if match_X:
@@ -314,7 +315,8 @@ def suggest_proba(self, texts) -> List[List[Tuple[str, float]]]:
         :params  texts: Iterable of strings (documents).
 
         Returns:
-            A list of lists, where each inner list contains tuples of (concept, probability).
+            A list of lists, where each inner list contains tuples of
+            (concept, probability).
         """
         match_X, doc_counts = self.match_and_extend(texts)
         if match_X:
@@ -336,7 +338,8 @@ def predict(self, X) -> csr_matrix:
         :params  X: Iterable of input strings.
 
         Returns:
-            A sparse matrix of shape (n_samples, n_concepts) indicating predicted concept matches.
+            A sparse matrix of shape (n_samples, n_concepts) indicating predicted
+            concept matches.
         """
         match_X, doc_counts = self.match_and_extend(X)
         if match_X:

stwfsapy/tests/automata/construction_test.py

@@ -13,9 +13,8 @@
 # limitations under the License.
 
 
-from stwfsapy.automata import nfa
 from stwfsapy.automata import construction as c
-
+from stwfsapy.automata import nfa
 from stwfsapy.tests.automata.data import accept
 
 expression = "test"

stwfsapy/tests/automata/data.py

@@ -14,8 +14,8 @@
 
 
 import pytest
-from stwfsapy.automata import nfa
 
+from stwfsapy.automata import nfa
 
 symbol0 = "s"
 symbol1 = "t"

stwfsapy/tests/automata/heap_test.py

@@ -13,9 +13,10 @@
 # limitations under the License.
 
 
-from stwfsapy.automata import heap
 import pytest
 
+from stwfsapy.automata import heap
+
 
 def check_heap(queue):
     for i in range(1, len(queue.heap)):

stwfsapy/tests/automata/integration_test.py

@@ -13,9 +13,9 @@
 # limitations under the License.
 
 
-from stwfsapy.automata import nfa
 from stwfsapy.automata import construction as const
 from stwfsapy.automata import conversion as conv
+from stwfsapy.automata import nfa
 from stwfsapy.tests.automata.data import accept
 
 

stwfsapy/tests/automata/nfa_test.py

@@ -14,6 +14,7 @@
 
 
 import pytest
+
 from stwfsapy.automata import nfa
 from stwfsapy.tests.automata.data import symbol0
 

stwfsapy/tests/automata/search_overlap_regression_test.py

@@ -14,11 +14,11 @@
 
 """The tests in this file compare the behaviors of
 stwfsapy and zaptain-stwfsa regarding overlap of potential matches."""
-from stwfsapy.automata import nfa
-import stwfsapy.automata.construction as const
-import stwfsapy.automata.conversion as conv
 import pytest
 
+import stwfsapy.automata.construction as const
+import stwfsapy.automata.conversion as conv
+from stwfsapy.automata import nfa
 
 label_global = "global"
 id_global = "id_global"

stwfsapy/tests/common.py

@@ -15,7 +15,6 @@
 from rdflib import URIRef
 from rdflib.term import Literal
 
-
 test_type_thesaurus = URIRef("http://type.org/thesaurus")
 test_type_concept = URIRef("http://type.org/concept")
 

stwfsapy/tests/conftest.py

@@ -15,6 +15,7 @@
 from pytest import fixture
 from rdflib.graph import Graph
 from rdflib.namespace import RDF, SKOS
+
 from stwfsapy.tests import common as c
 
 

stwfsapy/tests/expansion/any_case_from_braces_test.py

@@ -13,9 +13,10 @@
 # limitations under the License.
 
 
-from stwfsapy import expansion as e
 import common as c
 
+from stwfsapy import expansion as e
+
 replacement_fun_any = e._replace_by_pattern_fun(e._any_case_from_braces_expression)
 
 

stwfsapy/tests/expansion/collect_test.py

@@ -13,9 +13,10 @@
 # limitations under the License.
 
 
-import stwfsapy.expansion as e
 from inspect import signature
 
+import stwfsapy.expansion as e
+
 _name_abbreviation_fun = e._expand_abbreviation_with_punctuation_fun.__name__
 _name_ampersand_fun = e._expand_ampersand_with_spaces_fun.__name__
 _name_replacer = "replacer"

stwfsapy/tests/expansion/upper_case_abbreviations_from_braces_test.py

@@ -13,9 +13,10 @@
 # limitations under the License.
 
 
-from stwfsapy import expansion as e
 import common as c
 
+from stwfsapy import expansion as e
+
 replacement_fun_upper = e._replace_by_pattern_fun(
     e._upper_case_abbreviation_from_braces_expression
 )

stwfsapy/tests/frequency_features_test.py

@@ -13,12 +13,13 @@
 # limitations under the License.
 
 
-from stwfsapy.frequency_features import FrequencyFeatures
-from sklearn.exceptions import NotFittedError
-import numpy as np
 from math import log
 
+import numpy as np
 import pytest
+from sklearn.exceptions import NotFittedError
+
+from stwfsapy.frequency_features import FrequencyFeatures
 
 frequency_input = [
     ("cncpt_1", [3, 4, 0, 2], 0),

stwfsapy/tests/position_features_test.py

@@ -13,9 +13,9 @@
 # limitations under the License.
 
 
-from stwfsapy.position_features import PositionFeatures
 import numpy as np
 
+from stwfsapy.position_features import PositionFeatures
 
 position_feature_data = [
     (3, [3, 4, 0, 2]),