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

rwedge · rwedge · commit b1d545afd4f2 · 2025-11-03T15:36:49.000-06:00
diff --git a/.github/workflows/install.yml b/.github/workflows/install.yml
@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        python_version: ["3.8", "3.13"]
+        python_version: ["3.9", "3.13"]
     runs-on: ubuntu-latest
     steps:
       - name: Set up python ${{ matrix.python_version }}
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 +1,19 @@
 # History
 
+## v0.24.0 - 2025-11-03
+
+### New Features
+
+* Update `InterRowMSAS` to compare the overall distributions between row `n` and `n+1` (not the average) - Issue [#800](https://github.com/sdv-dev/SDMetrics/issues/800) by @sarahmish
+
+### Bugs Fixed
+
+* Minimum tests failing - OSError: [WinError 1114] A dynamic link library (DLL) initialization routine failed - Issue [#802](https://github.com/sdv-dev/SDMetrics/issues/802) by @sarahmish
+
+### Maintenance
+
+* Remove support for Python 3.8 - Issue [#801](https://github.com/sdv-dev/SDMetrics/issues/801) by @fealho
+
 ## v0.23.0 - 2025-08-14
 
 ### New Features
diff --git a/INSTALL.md b/INSTALL.md
@@ -2,7 +2,7 @@
 
 ## Requirements
 
-**SDMetrics** 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/)
+**SDMetrics** has been developed and tested on [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
@@ -1,7 +1,7 @@
 copulas==0.12.3
-numpy==2.2.6
-pandas==2.3.1
-plotly==6.2.0
-scikit-learn==1.7.1
-scipy==1.16.1
+numpy==2.3.4
+pandas==2.3.3
+plotly==6.3.1
+scikit-learn==1.7.2
+scipy==1.16.3
 tqdm==4.67.1
diff --git a/pyproject.toml b/pyproject.toml
@@ -8,7 +8,6 @@ classifiers = [
     'License :: OSI Approved :: MIT License',
     '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',
@@ -18,7 +17,7 @@ classifiers = [
 keywords = ['sdmetrics', 'sdmetrics', 'SDMetrics']
 dynamic = ['version']
 license = { text = 'MIT license' }
-requires-python = ">=3.8,<3.14"
+requires-python = ">=3.9,<3.14"
 readme = 'README.md'
 dependencies = [
     "numpy>=1.22.2;python_version<'3.10'",
@@ -140,7 +139,7 @@ convention = 'google'
 add-ignore = ['D107', 'D407', 'D417']
 
 [tool.bumpversion]
-current_version = "0.23.0"
+current_version = "0.24.0.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/sdmetrics/__init__.py b/sdmetrics/__init__.py
@@ -4,7 +4,7 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = 'dailabmit@gmail.com'
-__version__ = '0.23.0'
+__version__ = '0.24.0.dev0'
 
 import sys
 import warnings as python_warnings
diff --git a/sdmetrics/column_pairs/statistical/inter_row_msas.py b/sdmetrics/column_pairs/statistical/inter_row_msas.py
@@ -85,13 +85,11 @@ def diff_func(group):
             if len(group) <= n_rows_diff:
                 return np.nan
             group = group.to_numpy()
-            with warnings.catch_warnings():
-                warnings.filterwarnings('ignore', message='Mean of empty slice')
-                return np.nanmean(group[n_rows_diff:] - group[:-n_rows_diff])
+            return (group[n_rows_diff:] - group[:-n_rows_diff]).flatten()
 
         with warnings.catch_warnings():
             warnings.filterwarnings('ignore', message='invalid value encountered in.*')
-            return grouped.apply(diff_func)
+            return grouped.apply(diff_func).explode().astype(float)
 
     @classmethod
     def compute(cls, real_data, synthetic_data, n_rows_diff=1, apply_log=False):
diff --git a/sdmetrics/single_table/new_row_synthesis.py b/sdmetrics/single_table/new_row_synthesis.py
@@ -148,8 +148,8 @@ def compute_breakdown(
             except TypeError:
                 if len(real_data) > 10000:
                     warnings.warn(
-                        'Unable to optimize query. For better formance, set the '
-                        '`synthetic_sample_size` parameter or upgrade to Python 3.8'
+                        'Unable to optimize query. For better performance, set the '
+                        '`synthetic_sample_size` parameter.'
                     )
 
                 matches = real_data.query(' and '.join(row_filter), engine='python')
diff --git a/static_code_analysis.txt b/static_code_analysis.txt
@@ -1,4 +1,4 @@
-Run started:2025-08-13 23:11:12.422595
+Run started:2025-11-03 20:45:24.062021
 
 Test results:
 >> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
@@ -117,7 +117,7 @@ Test results:
 --------------------------------------------------
 
 Code scanned:
-	Total lines of code: 11839
+	Total lines of code: 11842
 	Total lines skipped (#nosec): 0
 	Total potential issues skipped due to specifically being disabled (e.g., #nosec BXXX): 0
 
diff --git a/tasks.py b/tasks.py
@@ -14,6 +14,9 @@
 
 COMPARISONS = {'>=': operator.ge, '>': operator.gt, '<': operator.lt, '<=': operator.le}
 
+EXTERNAL_DEPENDENCY_CAPS = {
+    'torch': '2.9.0'
+}
 
 if not hasattr(inspect, 'getargspec'):
     inspect.getargspec = inspect.getfullargspec
@@ -87,7 +90,8 @@ def install_minimum(c):
     if minimum_versions:
         install_deps = ' '.join(minimum_versions)
         c.run(f'python -m pip install {install_deps}')
-
+        for dep, cap in EXTERNAL_DEPENDENCY_CAPS.items():
+            c.run(f'python -m pip install "{dep}<{cap}"')
 
 @task
 def minimum(c):
diff --git a/tests/unit/column_pairs/statistical/test_inter_row_msas.py b/tests/unit/column_pairs/statistical/test_inter_row_msas.py
@@ -24,7 +24,7 @@ def test_compute_breakdown(self):
         )
 
         # Assert
-        assert result == {'score': 0.5}
+        assert result == {'score': 0.25}
 
     def test_compute(self):
         """Test it runs."""
@@ -40,7 +40,7 @@ def test_compute(self):
         )
 
         # Assert
-        assert score == 0.5
+        assert score == 0.25
 
     def test_compute_nans(self):
         """Test it runs with nans."""
