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

.github/workflows/dependency_checker.yml

@@ -7,9 +7,9 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python 3.9
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.9
     - name: Install dependencies

.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-20.04
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python 3.9
-      uses: actions/setup-python@v2
+      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/static_code_analysis.yml

@@ -0,0 +1,33 @@
+name: Static Code Analysis
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  code-analysis:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.10'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install bandit==1.7.7
+    - name: Save code analysis
+      run: bandit -r . -x ./tests -f txt -o static_code_analysis.txt --exit-zero
+    - name: Create pull request
+      id: cpr
+      uses: peter-evans/create-pull-request@v4
+      with:
+        token: ${{ secrets.GH_ACCESS_TOKEN }}
+        commit-message: Update static code analysis
+        title: Latest Code Analysis
+        body: "This is an auto-generated PR with the **latest** code analysis results."
+        branch: static-code-analysis
+        branch-suffix: short-commit-hash
+        base: main

.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

HISTORY.md

@@ -1,5 +1,23 @@
 # History
 
+## v0.10.0 - 2024-04-11
+
+This release adds support for Python 3.12!
+
+### Maintenance
+
+* Support Python 3.12 - Issue [#324](https://github.com/sdv-dev/CTGAN/issues/324) by @fealho
+* Remove scikit-learn dependency - Issue [#346](https://github.com/sdv-dev/CTGAN/issues/346) by @R-Palazzo
+* Add bandit workflow - Issue [#353](https://github.com/sdv-dev/CTGAN/issues/353) by @R-Palazzo
+
+### Internal
+
+* Replace integration test that uses the iris demo data - Issue [#352](https://github.com/sdv-dev/CTGAN/issues/352) by @R-Palazzo
+
+### Bugs Fixed
+
+* Fix minimum version workflow when pointing to github branch - Issue [#355](https://github.com/sdv-dev/CTGAN/issues/355) by @R-Palazzo
+
 ## v0.9.1 - 2024-03-14
 
 This release changes the `loss_values` attribute of a CTGAN model to contain floats instead of `torch.Tensors`.

Makefile

@@ -235,5 +235,5 @@ release-major: check-release bumpversion-major release
 
 .PHONY: check-deps
 check-deps:
-	$(eval allow_list='numpy=|pandas=|scikit-learn=|tqdm=|torch=|rdt=')
+	$(eval allow_list='numpy=|pandas=|tqdm=|torch=|rdt=')
 	pip freeze | grep -v "CTGAN.git" | grep -E $(allow_list) > $(OUTPUT_FILEPATH)

ctgan/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = '[email protected]'
-__version__ = '0.9.1'
+__version__ = '0.10.0.dev1'
 
 from ctgan.demo import load_demo
 from ctgan.synthesizers.ctgan import CTGAN

latest_requirements.txt

@@ -1,6 +1,4 @@
 numpy==1.26.4
 pandas==2.2.1
-rdt==1.10.0
-scikit-learn==1.4.1.post1
-torch==2.2.1
+torch==2.2.2
 tqdm==4.66.2

pyproject.toml

@@ -12,26 +12,28 @@ classifiers = [
     'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: 3.10',
     'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
     'Topic :: Scientific/Engineering :: Artificial Intelligence',
 ]
 keywords = ['ctgan', 'CTGAN']
 dynamic = ['version']
 license = { text = 'BSL-1.1' }
-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,<2;python_version>='3.10' and python_version<'3.12'",
+    "numpy>=1.26.0,<2;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'",
+    "pandas>=1.5.0;python_version>='3.11' and python_version<'3.12'",
+    "pandas>=2.1.1;python_version>='3.12'",
     "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'",
-    'tqdm>=4.15',
-    'rdt>=1.6.1',
+    "torch>=2.0.0;python_version>='3.11' and python_version<'3.12'",
+    "torch>=2.2.0;python_version>='3.12'",
+    'tqdm>=4.29,<5',
+    'rdt>=1.11.0',
 ]
 
 [project.urls]
@@ -47,7 +49,7 @@ ctgan = { main = 'ctgan.cli.__main__:main' }
 [project.optional-dependencies]
 test = [
     'pytest>=3.4.2',
-    'pytest-rerunfailures>=9.1.1,<10',
+    'pytest-rerunfailures>=10.3,<15',
     'pytest-cov>=2.6.0',
     'rundoc>=0.4.3,<0.5',
     'pytest-runner >= 2.11.1',
@@ -60,7 +62,7 @@ dev = [
     'pip>=9.0.1',
     'build>=1.0.0,<2',
     'bump-my-version>=0.18.3,<1',
-    'watchdog>=0.8.3,<0.11',
+    'watchdog>=1.0.1,<5',
 
     # style check
     'flake8>=3.7.7,<4',
@@ -123,12 +125,12 @@ namespaces = false
     '*.png',
     '*.gif'
 ]
-'tests' = ['*']
 
 [tool.setuptools.exclude-package-data]
 '*' = [
     '* __pycache__',
     '*.py[co]',
+    'static_code_analysis.txt',
 ]
 
 [tool.setuptools.dynamic]
@@ -150,7 +152,7 @@ add-ignore = ['D107', 'D407', 'D417']
 collect_ignore = ['pyproject.toml']
 
 [tool.bumpversion]
-current_version = "0.9.1"
+current_version = "0.10.0.dev1"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

static_code_analysis.txt

@@ -0,0 +1,101 @@
+Run started:2024-04-10 18:50:03.907830
+
+Test results:
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/__main__.py:88:8
+87	    if args.sample_condition_column is not None:
+88	        assert args.sample_condition_column_value is not None
+89	
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/data.py:53:12
+52	        else:
+53	            assert item[0] == 'D'
+54	            discrete.append(idx)
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/data.py:74:16
+73	            else:
+74	                assert idx in discrete
+75	                row.append(column_info[idx].index(col))
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/data.py:91:20
+90	                else:
+91	                    assert idx in meta['discrete_columns']
+92	                    print(meta['column_info'][idx][int(col)], end=' ', file=f)
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/data_sampler.py:41:8
+40	                st += sum([span_info.dim for span_info in column_info])
+41	        assert st == data.shape[1]
+42	
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/synthesizers/ctgan.py:56:8
+55	        """Apply the Discriminator to the `input_`."""
+56	        assert input_.size()[0] % self.pac == 0
+57	        return self.seq(input_.view(-1, self.pacdim))
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/synthesizers/ctgan.py:148:8
+147	
+148	        assert batch_size % 2 == 0
+149	
+
+--------------------------------------------------
+>> Issue: [B101:assert_used] Use of assert detected. The enclosed code will be removed when compiling to optimised byte code.
+   Severity: Low   Confidence: High
+   CWE: CWE-703 (https://cwe.mitre.org/data/definitions/703.html)
+   More Info: https://bandit.readthedocs.io/en/1.7.7/plugins/b101_assert_used.html
+   Location: ./ctgan/synthesizers/tvae.py:100:4
+99	
+100	    assert st == recon_x.size()[1]
+101	    KLD = -0.5 * torch.sum(1 + logvar - mu**2 - logvar.exp())
+
+--------------------------------------------------
+
+Code scanned:
+	Total lines of code: 1341
+	Total lines skipped (#nosec): 0
+	Total potential issues skipped due to specifically being disabled (e.g., #nosec BXXX): 0
+
+Run metrics:
+	Total issues (by severity):
+		Undefined: 0
+		Low: 8
+		Medium: 0
+		High: 0
+	Total issues (by confidence):
+		Undefined: 0
+		Low: 0
+		Medium: 0
+		High: 8
+Files skipped (0):

tasks.py

@@ -57,7 +57,7 @@ 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)