Fix code quality

.github/workflows/ci.yml

@@ -20,15 +20,15 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: "3.11"
 
       - name: Install uv
         uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
 
       - name: Install dependencies
-        run: uv sync --extra dev
+        run: uv sync --all-extras
 
       - name: Run ty type checking
         run: uv run ty check
@@ -86,7 +86,7 @@ jobs:
         # Patch coverage (new/changed lines ≥ 80%) is enforced by Codecov below.
         run: |
           EXTRA_ARGS=""
-          if [ "${{ matrix.python-version }}" = "3.12" ]; then
+          if [ "${{ matrix.python-version }}" = "3.11" ]; then
             EXTRA_ARGS="--cov=src/risk_assessment --cov-report=xml --cov-report=html --cov-report=term-missing"
           fi
           uv run pytest tests/ -v --tb=short --maxfail=5 \
@@ -102,7 +102,7 @@ jobs:
           retention-days: 7
 
       - name: Upload coverage to Codecov
-        if: matrix.python-version == '3.12'
+        if: matrix.python-version == '3.11'
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -111,7 +111,7 @@ jobs:
           verbose: true
 
       - name: Upload HTML coverage report as artifact
-        if: always() && matrix.python-version == '3.12'
+        if: always() && matrix.python-version == '3.11'
         uses: actions/upload-artifact@v4
         with:
           name: coverage-html-report

pyproject.toml

@@ -48,7 +48,7 @@ dependencies = [
     "word2number==1.1",
 
     # To fix dependabot
-    "setuptools>=83.0.0",
+    # "setuptools>=83.0.0",
 ]
 [project.optional-dependencies]
 rest = [

src/risk_assessment/anonymization/mondrian.py

@@ -29,6 +29,7 @@
 
 from __future__ import annotations
 
+from contextlib import suppress
 from dataclasses import dataclass
 from enum import Enum, auto
 from typing import Any
@@ -112,12 +113,10 @@ def _find_common_ancestor(values: npt.NDArray[Any], hierarchy: GeneralizationHie
                 node = node.parent
         else:
             while node is not None:
-                try:
+                with suppress(ValueError):
                     index = ancestors.index(node)
                     ancestors = ancestors[index:]
                     break
-                except ValueError:
-                    pass
                 node = node.parent
 
     if ancestors is None:

src/risk_assessment/anonymization/optimal_lattice_anonymization.py

@@ -148,7 +148,7 @@ def _check_constraints(self, dataset: DataFrame) -> bool:
         return True
 
 
-@dataclass(eq=True)
+@dataclass
 class LatticeNode:
     """A single node in the generalization lattice.
 
@@ -189,6 +189,12 @@ def __str__(self) -> str:
     def __hash__(self) -> int:
         return hash(str(self.values))
 
+    def __eq__(self, other: Any) -> bool:
+        if isinstance(other, LatticeNode):
+            return self.__hash__() == other.__hash__()
+
+        return False
+
 
 def _calculate_product(levels: list[list[int]]) -> list[list[int]]:
     product_result: list[list[int]] = []

src/risk_assessment/classification/unstructured/nltk.py

@@ -8,7 +8,8 @@
 
 
 class NLTKPoSTagger(EntityExtractor):
-    def __init__(self, tokenizer: TokenizerI, tagger: TaggerI) -> None:
+    def __init__(self, tokenizer: TokenizerI, tagger: TaggerI, type_mapping: dict[str, str] | None = None) -> None:
+        super().__init__(type_mapping if type_mapping is not None else {})
         self.tokenizer = tokenizer
         self.tagger = tagger
 

src/risk_assessment/metrics/informationloss/__init__.py

@@ -199,8 +199,8 @@ def _get_loss_categorical(value: Any, column_information: ColumnInformation) ->
 def _report_for_column_without_transformation_level(
     original: Series | DataFrame, anonymized: Series | DataFrame, column_information: ColumnInformation
 ) -> float:
-    # if column_information.column_class != ColumnClass.CATEGORICAL:
-    #     raise ValueError("Cannot process non categorical colums")
+    if column_information.column_class != ColumnClass.CATEGORICAL:
+        raise ValueError("Cannot process non categorical colums")
 
     weight = column_information.weight
     precision = 0.0
@@ -241,7 +241,7 @@ def _categorical_precision_report_per_quasi_column(
         if c_i.column_type == ColumnType.QUASI:
             report: float = _report_for_column(
                 original.iloc[:, index], anonymized.iloc[:, index], column_information[index], transformation_levels
-            )  # for index, c_i in enumerate(column_information) if c_i.column_type == ColumnType.QUASI
+            )
             results.append(report)
 
     return results

src/risk_assessment/readi/text_tokenizer.py

@@ -158,6 +158,7 @@ def __init__(self, model_name: str = "FacebookAI/roberta-base", device: str = "c
         )
 
     def span_tokenize(self, text: str) -> list[tuple[int, int]]:
+        assert self.tokenizer is not None
         tokenized_text = self.tokenizer(text)
         num_of_tokens = len(tokenized_text["input_ids"])
         token_spans: list[tuple[int, int]] = []

tests/anonymization/test_anonymity_checker.py

@@ -1,8 +1,6 @@
-import importlib.resources
 import math
 
 import pandas as pd
-import pytest
 
 from risk_assessment.anonymization import KAnonymity, PrivacyConstraint
 from risk_assessment.anonymization.optimal_lattice_anonymization import AnonymityChecker, LatticeNode

tests/anonymization/test_privacy_constraints.py

@@ -6,7 +6,6 @@
 from risk_assessment.anonymization import DistinctLDiversity, EntropyLDiversity, KAnonymity, TCloseness
 from risk_assessment.metrics.informationloss import ColumnClass, ColumnInformation, ColumnType
 from risk_assessment.utility import extract_histograms
-from risk_assessment.utility.hierarchy import MaterializedHierarchy
 
 
 def test_kanonymity():

tests/classification/unstructured/test_presidio.py

@@ -76,7 +76,10 @@ def _make_extractor(**kwargs) -> PresidioEntityExtractor:
     return PresidioEntityExtractor(type_mapping=TYPE_MAPPING, **kwargs)
 
 
-def _stub_result(entity_type: str, start: int, end: int, score: float = 0.85) -> _RecognizerResult:
+RecognizerResult = _RecognizerResult
+
+
+def _stub_result(entity_type: str, start: int, end: int, score: float = 0.85) -> RecognizerResult:
     return _RecognizerResult(entity_type=entity_type, start=start, end=end, score=score)
 
 
@@ -255,7 +258,7 @@ def test_empty_type_mapping_returns_raw_types():
 def test_build_entity_returns_entity_dataclass():
     extractor = _make_extractor()
     result = _stub_result("PERSON", 3, 11, score=0.88)
-    entity = extractor._build_entity(result)
+    entity = extractor._build_entity(result)  # ty: ignore[invalid-argument-type]
     assert isinstance(entity, Entity)
     assert entity.start == 3
     assert entity.end == 11
@@ -267,7 +270,7 @@ def test_build_entity_returns_entity_dataclass():
 def test_build_entity_score_zero():
     extractor = _make_extractor()
     result = _stub_result("PERSON", 0, 4, score=0.0)
-    entity = extractor._build_entity(result)
+    entity = extractor._build_entity(result)  # ty: ignore[invalid-argument-type]
     assert entity.confidence == pytest.approx(0.0)