Add Python 3.12 support (#550)

.github/workflows/integration.yml

@@ -10,12 +10,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.github/workflows/lint.yml

@@ -9,9 +9,9 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python 3.9
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5
       with:
         python-version: 3.9
     - name: Install dependencies

.github/workflows/minimum.yml

@@ -10,12 +10,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.github/workflows/readme.yml

@@ -10,12 +10,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-latest, macos-latest]   # skip windows bc rundoc fails
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.github/workflows/unit.yml

@@ -10,12 +10,12 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
@@ -26,4 +26,4 @@ jobs:
       run: invoke unit
     - if: matrix.os == 'ubuntu-latest' && matrix.python-version == 3.8
       name: Upload codecov report
-      uses: codecov/codecov-action@v2
+      uses: codecov/codecov-action@v4

INSTALL.md

@@ -2,7 +2,7 @@
 
 ## Requirements
 
-**SDMetrics** has been developed and tested on [Python 3.8, 3.9, 3.10 and 3.11](https://www.python.org/downloads/)
+**SDMetrics** has been developed and tested on [Python 3.8, 3.9, 3.10, 3.11 and 3.12](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

pyproject.toml

@@ -12,25 +12,29 @@ classifiers = [
     'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: 3.10',
     'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
 ]
 keywords = ['sdmetrics', 'sdmetrics', 'SDMetrics']
 dynamic = ['version']
 license = { text = 'MIT license' }
-requires-python = ">=3.8,<3.12"
+requires-python = ">=3.8,<3.13"
 readme = 'README.md'
 dependencies = [
     "numpy>=1.20.0;python_version<'3.10'",
-    "numpy>=1.23.3;python_version>='3.10'",
+    "numpy>=1.23.3;python_version>='3.10' and python_version<'3.12'",
+    "numpy>=1.26.0;python_version>='3.12'",
     "pandas>=1.1.3;python_version<'3.10'",
     "pandas>=1.3.4;python_version>='3.10' and python_version<'3.11'",
     "pandas>=1.5.0;python_version>='3.11'",
     "scikit-learn>=0.24;python_version<'3.10'",
-    "scikit-learn>=1.1.3;python_version>='3.10'",
+    "scikit-learn>=1.1.3;python_version>='3.10' and python_version<'3.12'",
+    "scikit-learn>=1.3.0;python_version>='3.12'",
     "scipy>=1.5.4;python_version<'3.10'",
-    "scipy>=1.9.2;python_version>='3.10'",
-    'copulas>=0.10.0',
-    'tqdm>=4.15',
-    'plotly>=5.10.0',
+    "scipy>=1.9.2;python_version>='3.10' and python_version<'3.12'",
+    "scipy>=1.12.0;python_version>='3.12'",
+    'copulas @ git+https://github.com/sdv-dev/Copulas@main',
+    'tqdm>=4.29',
+    'plotly>=5.19.0',
 ]
 
 [project.urls]
@@ -46,15 +50,15 @@ sdmetrics = { main = 'sdmetrics.cli.__main__:main' }
 [project.optional-dependencies]
 torch = [
     "torch>=1.8.0;python_version<'3.10'",
-    "torch>=1.11.0;python_version>='3.10' and python_version<'3.11'",
-    "torch>=2.0.0;python_version>='3.11'",
+    "torch>=2.0.0;python_version>='3.10' and python_version<'3.12'",
+    "torch>=2.2.0;python_version>='3.12'",
 ]
 pomegranate = ['pomegranate>=0.14.1,<0.14.7']
 test = [
     'sdmetrics[torch]',
     'pytest>=6.2.5,<7',
     'pytest-cov>=2.6.0,<3',
-    'pytest-rerunfailures>=10',
+    'pytest-rerunfailures>=10.3,<15',
     'jupyter>=1.0.0,<2',
     'rundoc>=0.4.3,<0.5',
     'tomli>=2.0.0,<3',
@@ -68,7 +72,7 @@ dev = [
     'build>=1.0.0,<2',
     'bump-my-version>=0.18.3,<1',
     'pip>=9.0.1',
-    'watchdog>=0.8.3,<0.11',
+    'watchdog>=1.0.1,<5',
 
     # style check
     'flake8>=3.7.7,<4',
@@ -132,7 +136,6 @@ namespaces = false
     '*.gif'
 ]
 'sdmetrics' = ['demos/*/*.json', 'demos/*/*.csv']
-'tests' = ['*']
 
 [tool.setuptools.exclude-package-data]
 '*' = [

sdmetrics/__init__.py

@@ -8,11 +8,11 @@
 
 import sys
 import warnings as python_warnings
+from importlib.metadata import entry_points
 from operator import attrgetter
 from types import ModuleType
 
 import pandas as pd
-from pkg_resources import iter_entry_points
 
 from sdmetrics import (
     column_pairs, demos, goal, multi_table, reports, single_column, single_table, timeseries)
@@ -134,7 +134,13 @@ def _find_addons():
     from top_module.addon_module import x
     """
     group = 'sdmetrics_modules'
-    for entry_point in iter_entry_points(group=group):
+    try:
+        eps = entry_points(group=group)
+    except TypeError:
+        # Load-time selection requires Python >= 3.10 or importlib_metadata >= 3.6
+        eps = entry_points().get(group, [])
+
+    for entry_point in eps:
         try:
             addon = entry_point.load()
         except Exception:  # pylint: disable=broad-exception-caught

sdmetrics/reports/base_report.py

@@ -1,4 +1,5 @@
 """Single table base report."""
+import importlib.metadata
 import pickle
 import sys
 import time
@@ -9,7 +10,6 @@
 
 import numpy as np
 import pandas as pd
-import pkg_resources
 import tqdm
 
 from sdmetrics.reports.utils import convert_datetime_columns
@@ -287,7 +287,7 @@ def save(self, filepath):
             filepath (str):
                 The path to the file where the report instance will be serialized.
         """
-        self._package_version = pkg_resources.get_distribution('sdmetrics').version
+        self._package_version = importlib.metadata.version('sdmetrics')
 
         with open(filepath, 'wb') as output:
             pickle.dump(self, output)
@@ -304,7 +304,7 @@ def load(cls, filepath):
             SDMetrics Report:
                 The loaded report instance.
         """
-        current_version = pkg_resources.get_distribution('sdmetrics').version
+        current_version = importlib.metadata.version('sdmetrics')
 
         with open(filepath, 'rb') as f:
             report = pickle.load(f)

sdmetrics/single_table/table_structure.py

@@ -39,7 +39,7 @@ def compute_breakdown(cls, real_data, synthetic_data):
         real_columns = set(real_data.columns)
         intersection_columns = real_columns & synthetic_columns
         union_columns = real_columns | synthetic_columns
-        score = len(intersection_columns)/len(union_columns)
+        score = len(intersection_columns) / len(union_columns)
 
         return {'score': score}
 

tasks.py

@@ -44,7 +44,7 @@ def _get_minimum_versions(dependencies, python_version):
     for dependency in dependencies:
         if '@' in dependency:
             name, url = dependency.split(' @ ')
-            min_versions[name] = f'{name} @ {url}'
+            min_versions[name] = f'{url}#egg={name}'
             continue
 
         req = Requirement(dependency)

tests/unit/column_pairs/statistical/test_correlation_similarity.py

@@ -44,10 +44,10 @@ def test_compute_breakdown(self, pearson_mock):
         result = metric.compute_breakdown(real_data, synthetic_data, coefficient='Pearson')
 
         # Assert
-        assert pearson_mock.has_calls(
+        pearson_mock.assert_has_calls([
             call(SeriesMatcher(real_data['col1']), SeriesMatcher(real_data['col2'])),
             call(SeriesMatcher(synthetic_data['col1']), SeriesMatcher(synthetic_data['col2'])),
-        )
+        ])
         assert result == expected_score_breakdown
 
     @patch('sdmetrics.column_pairs.statistical.correlation_similarity.pearsonr')
@@ -89,10 +89,16 @@ def test_compute_breakdown_datetime(self, pearson_mock):
         result = metric.compute_breakdown(real_data, synthetic_data, coefficient='Pearson')
 
         # Assert
-        assert pearson_mock.has_calls(
-            call(SeriesMatcher(real_data['col1']), SeriesMatcher(real_data['col2'])),
-            call(SeriesMatcher(synthetic_data['col1']), SeriesMatcher(synthetic_data['col2'])),
-        )
+        pearson_mock.assert_has_calls([
+            call(
+                SeriesMatcher(
+                    real_data['col1'].astype('int64')), SeriesMatcher(
+                    real_data['col2'].astype('int64'))),
+            call(
+                SeriesMatcher(
+                    synthetic_data['col1'].astype('int64')), SeriesMatcher(
+                    synthetic_data['col2'].astype('int64'))),
+        ])
         assert result == expected_score_breakdown
 
     def test_compute_breakdown_constant_input(self):

tests/unit/reports/test_base_report.py

@@ -669,7 +669,7 @@ def test_get_details(self):
         base_report._properties['Property 1'].details.copy.assert_called_once()
         base_report._properties['Property 2'].details.copy.assert_called_once()
 
-    @patch('sdmetrics.reports.base_report.pkg_resources.get_distribution')
+    @patch('sdmetrics.reports.base_report.importlib.metadata.version')
     @patch('sdmetrics.reports.base_report.pickle')
     def test_save(self, pickle_mock, get_distribution_mock):
         """Test the ``save`` method.
@@ -694,9 +694,9 @@ def test_save(self, pickle_mock, get_distribution_mock):
         get_distribution_mock.assert_called_once_with('sdmetrics')
         open_mock.assert_called_once_with('test-file.pkl', 'wb')
         pickle_mock.dump.assert_called_once_with(report, open_mock())
-        assert report._package_version == get_distribution_mock.return_value.version
+        assert report._package_version == get_distribution_mock.return_value
 
-    @patch('sdmetrics.reports.base_report.pkg_resources.get_distribution')
+    @patch('sdmetrics.reports.base_report.importlib.metadata.version')
     @patch('sdmetrics.reports.base_report.pickle')
     def test_load(self, pickle_mock, get_distribution_mock):
         """Test the ``load`` method.
@@ -727,7 +727,7 @@ def test_load(self, pickle_mock, get_distribution_mock):
         assert loaded == pickle_mock.load.return_value
 
     @patch('sdmetrics.reports.base_report.warnings')
-    @patch('sdmetrics.reports.base_report.pkg_resources.get_distribution')
+    @patch('sdmetrics.reports.base_report.importlib.metadata.version')
     @patch('sdmetrics.reports.base_report.pickle')
     def test_load_mismatched_versions(self, pickle_mock, get_distribution_mock, warnings_mock):
         """Test the ``load`` method with mismatched sdmetrics versions.
@@ -748,7 +748,7 @@ def test_load_mismatched_versions(self, pickle_mock, get_distribution_mock, warn
         report = Mock()
         pickle_mock.load.return_value = report
         report._package_version = 'previous_version'
-        get_distribution_mock.return_value.version = 'new_version'
+        get_distribution_mock.return_value = 'new_version'
 
         # Run
         with patch('sdmetrics.reports.base_report.open', open_mock):

tests/unit/test___init__.py

@@ -18,7 +18,7 @@ def mock_sdmetrics():
     sys.modules['sdmetrics'] = sdmetrics_module
 
 
-@patch.object(sdmetrics, 'iter_entry_points')
+@patch.object(sdmetrics, 'entry_points')
 def test__find_addons_module(entry_points_mock, mock_sdmetrics):
     """Test loading an add-on."""
     # Setup
@@ -37,7 +37,7 @@ def test__find_addons_module(entry_points_mock, mock_sdmetrics):
     assert sys.modules['sdmetrics.submodule.entry_name'] == add_on_mock
 
 
-@patch.object(sdmetrics, 'iter_entry_points')
+@patch.object(sdmetrics, 'entry_points')
 def test__find_addons_object(entry_points_mock, mock_sdmetrics):
     """Test loading an add-on."""
     # Setup
@@ -55,7 +55,7 @@ def test__find_addons_object(entry_points_mock, mock_sdmetrics):
 
 
 @patch('warnings.warn')
-@patch('sdmetrics.iter_entry_points')
+@patch('sdmetrics.entry_points')
 def test__find_addons_bad_addon(entry_points_mock, warning_mock):
     """Test failing to load an add-on generates a warning."""
     # Setup
@@ -78,7 +78,7 @@ def entry_point_error():
 
 
 @patch('warnings.warn')
-@patch('sdmetrics.iter_entry_points')
+@patch('sdmetrics.entry_points')
 def test__find_addons_wrong_base(entry_points_mock, warning_mock):
     """Test incorrect add-on name generates a warning."""
     # Setup
@@ -99,7 +99,7 @@ def test__find_addons_wrong_base(entry_points_mock, warning_mock):
 
 
 @patch('warnings.warn')
-@patch('sdmetrics.iter_entry_points')
+@patch('sdmetrics.entry_points')
 def test__find_addons_missing_submodule(entry_points_mock, warning_mock):
     """Test incorrect add-on name generates a warning."""
     # Setup
@@ -120,7 +120,7 @@ def test__find_addons_missing_submodule(entry_points_mock, warning_mock):
 
 
 @patch('warnings.warn')
-@patch('sdmetrics.iter_entry_points')
+@patch('sdmetrics.entry_points')
 def test__find_addons_module_and_object(entry_points_mock, warning_mock):
     """Test incorrect add-on name generates a warning."""
     # Setup
@@ -141,7 +141,7 @@ def test__find_addons_module_and_object(entry_points_mock, warning_mock):
 
 
 @patch('warnings.warn')
-@patch.object(sdmetrics, 'iter_entry_points')
+@patch.object(sdmetrics, 'entry_points')
 def test__find_addons_missing_object(entry_points_mock, warning_mock, mock_sdmetrics):
     """Test incorrect add-on name generates a warning."""
     # Setup