make release-tag: Merge branch 'main' into stable

rwedge · rwedge · commit 66cd118a7f66 · 2026-01-02T15:08:39.000-06:00
diff --git a/.github/workflows/integration.yml b/.github/workflows/integration.yml
@@ -14,11 +14,11 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
         os: [ubuntu-latest, windows-latest]
         include:
           - os: macos-latest
-            python-version: '3.8'
+            python-version: '3.9'
           - os: macos-latest
             python-version: '3.13'
     steps:
diff --git a/.github/workflows/minimum.yml b/.github/workflows/minimum.yml
@@ -14,11 +14,11 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
         os: [ubuntu-latest, windows-latest]
         include:
           - os: macos-latest
-            python-version: '3.8'
+            python-version: '3.9'
           - os: macos-latest
             python-version: '3.13'
     steps:
diff --git a/.github/workflows/readme.yml b/.github/workflows/readme.yml
@@ -14,7 +14,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
         os: [ubuntu-latest, macos-latest]   # skip windows bc rundoc fails
     steps:
     - uses: actions/checkout@v4
diff --git a/.github/workflows/unit.yml b/.github/workflows/unit.yml
@@ -14,11 +14,11 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
         os: [ubuntu-latest, windows-latest]
         include:
           - os: macos-latest
-            python-version: '3.8'
+            python-version: '3.9'
           - os: macos-latest
             python-version: '3.13'
     steps:
diff --git a/HISTORY.md b/HISTORY.md
@@ -1,5 +1,15 @@
 # History
 
+## v1.19.0 - 2026-01-02
+
+### Internal
+
+* Faker `40.1.0` Breaks Backward Compatibility in `AnonymizedFaker` - Issue [#1057](https://github.com/sdv-dev/RDT/issues/1057) by @pvk-developer
+
+### Maintenance
+
+* Remove support for Python 3.8 - Issue [#1048](https://github.com/sdv-dev/RDT/issues/1048) by @fealho
+
 ## v1.18.2 - 2025-10-15
 
 ### Bugs Fixed
diff --git a/INSTALL.md b/INSTALL.md
@@ -3,7 +3,7 @@
 ## Requirements
 
 **RDT** has been developed and tested on
-[Python 3.8, 3.9, 3.10, 3.11, 3.12, and 3.13](https://www.python.org/downloads/)
+[Python 3.9, 3.10, 3.11, 3.12, and 3.13](https://www.python.org/downloads/)
 
 Also, although it is not strictly required, the usage of a [virtualenv](
 https://virtualenv.pypa.io/en/latest/) is highly recommended in order to avoid
diff --git a/latest_requirements.txt b/latest_requirements.txt
@@ -1,6 +1,6 @@
-Faker==37.8.0
+Faker==39.0.0
 copulas==0.12.3
-numpy==2.3.3
+numpy==2.4.0
 pandas==2.3.3
-scikit-learn==1.7.2
-scipy==1.16.2
+scikit-learn==1.8.0
+scipy==1.16.3
diff --git a/pyproject.toml b/pyproject.toml
@@ -8,7 +8,6 @@ classifiers = [
     'License :: Free for non-commercial use',
     'Natural Language :: English',
     'Programming Language :: Python :: 3',
-    'Programming Language :: Python :: 3.8',
     'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: 3.10',
     'Programming Language :: Python :: 3.11',
@@ -19,7 +18,7 @@ classifiers = [
 keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
 dynamic = ['version']
 license = { text = 'BSL-1.1' }
-requires-python = '>=3.8,<3.14'
+requires-python = '>=3.9,<3.14'
 readme = 'README.md'
 dependencies = [
     "numpy>=1.21.0;python_version<'3.10'",
@@ -144,7 +143,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.18.2"
+current_version = "1.19.0.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',
diff --git a/rdt/__init__.py b/rdt/__init__.py
@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.18.2'
+__version__ = '1.19.0.dev0'
 
 
 import sys
diff --git a/rdt/transformers/pii/anonymizer.py b/rdt/transformers/pii/anonymizer.py
@@ -196,6 +196,12 @@ def reset_randomization(self):
 
     def _function(self):
         """Return the result of calling the ``faker`` function."""
+        if not hasattr(self.faker.unique, '_excluded_types'):
+            # Faker v40.1.0 changed its uniqueness logic to rely on _excluded_types.
+            # Instances created before v40.1.0 don’t initialize this attribute,
+            # so accessing it can raise runtime errors.
+            setattr(self.faker.unique, '_excluded_types', ())
+
         try:
             if self.cardinality_rule in {'unique', 'match', 'scale'}:
                 faker_attr = self.faker.unique
diff --git a/static_code_analysis.txt b/static_code_analysis.txt
@@ -1,10 +1,10 @@
-Run started:2025-10-15 16:09:17.276277
+Run started:2026-01-02 20:43:58.943401
 
 Test results:
 	No issues identified.
 
 Code scanned:
-	Total lines of code: 6333
+	Total lines of code: 6335
 	Total lines skipped (#nosec): 0
 	Total potential issues skipped due to specifically being disabled (e.g., #nosec BXXX): 0
 
diff --git a/tests/unit/transformers/pii/test_anonymizer.py b/tests/unit/transformers/pii/test_anonymizer.py
@@ -101,7 +101,7 @@ def test__function_cardinality_rule_none(self):
             - The returned function, when called, has to call the `faker.<function_name>` function
               with the provided kwargs.
         """
-        # setup
+        # Setup
         instance = Mock()
         function = Mock()
         unique_function = Mock()
@@ -147,7 +147,7 @@ def test__function_cardinality_rule_unique(self):
             - The returned function, when called, has to call the ``faker.unique.<function_name>``
               function with the provided kwargs.
         """
-        # setup
+        # Setup
         instance = Mock()
         function = Mock()
         unique_function = Mock()
@@ -169,7 +169,7 @@ def test__function_cardinality_rule_unique(self):
 
     def test__function_cardinality_rule_match(self):
         """Test it when 'cardinality_rule' is 'match'."""
-        # setup
+        # Setup
         instance = Mock()
         function = Mock()
         unique_function = Mock()
@@ -191,7 +191,7 @@ def test__function_cardinality_rule_match(self):
 
     def test__function_cardinality_rule_missing_attribute(self):
         """Test it when ``cardinality_rule`` attribute is missing."""
-        # setup
+        # Setup
         instance = Mock()
         function = Mock()
         unique_function = Mock()
@@ -214,11 +214,36 @@ def test__function_cardinality_rule_missing_attribute(self):
 
     def test__function_with_iterables_return(self):
         """Test that ``_function`` returns the values of the iterable."""
-        # setup
+        # Setup
+        instance = Mock()
+        instance.cardinality_rule = None
+        function = Mock()
+        function.return_value = ('value_1', 'value_2')
+
+        instance.faker.number = function
+        instance.function_name = 'number'
+        instance.function_kwargs = {'type': 'int'}
+
+        # Run
+        result = AnonymizedFaker._function(instance)
+
+        # Assert
+        function.assert_called_once_with(type='int')
+        assert result == 'value_1, value_2'
+
+    def test__function_sets__excluded_types(self):
+        """Test that ``_function`` will set the `_excluded_types` attribute to `faker`."""
+
+        # Setup
+        class Dummy:
+            pass
+
         instance = Mock()
         instance.cardinality_rule = None
         function = Mock()
         function.return_value = ('value_1', 'value_2')
+        instance.faker.unique = Dummy()
+        assert hasattr(instance.faker.unique, '_excluded_types') is False
 
         instance.faker.number = function
         instance.function_name = 'number'
@@ -230,6 +255,7 @@ def test__function_with_iterables_return(self):
         # Assert
         function.assert_called_once_with(type='int')
         assert result == 'value_1, value_2'
+        assert hasattr(instance.faker.unique, '_excluded_types')
 
     @patch('rdt.transformers.pii.anonymizer.importlib')
     @patch('rdt.transformers.pii.anonymizer.warnings')
