add support for pandas version 2

.github/workflows/lint.yml

@@ -15,11 +15,11 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Install dependencies
+      - name: Install
         run: |
-          python -m pip install --upgrade pip
-          pip install pylint pytest pytest-cov
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          pip install --upgrade pip
+          pip install .[test]
+          pip install pylint
 
       - name: pylint
         run: |

.github/workflows/tests.yml

@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
 
     steps:
       - name: Checkout

.github/workflows/tests_python312.yml → .github/workflows/tests_python313.yml

@@ -1,5 +1,5 @@
 ---
-name: Test Python312
+name: Test Python313
 
 on: workflow_dispatch
 
@@ -11,7 +11,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ['3.12']
+        python-version: ['3.13']
 
     steps:
       - name: Checkout

CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## Version 0.4.7 (Oct 22, 2024)
+
+Changes:
+*   Add support for Pandas version 2 ([#237](https://github.com/AI-SDC/ACRO/pull/237))
+
 ## Version 0.4.6 (Jun 25, 2024)
 
 Changes:

CITATION.cff

@@ -1,8 +1,8 @@
 cff-version: 1.2.0
 title: ACRO
-version: 0.4.6
-doi: 10.5281/zenodo.12535291
-date-released: 2024-06-25
+version: 0.4.7
+doi:
+date-released: 2024-10-22
 license: MIT
 repository-code: https://github.com/AI-SDC/ACRO
 languages:
@@ -13,6 +13,7 @@ keywords:
   - privacy
   - privacy tools
   - statistical disclosure control
+  - statistical software
 authors:
   - family-names: Preen
     given-names: Richard John

README.md

@@ -8,22 +8,16 @@
 
 This repository holds the Python ACRO package. An R wrapper package is available: [ACRO-R](https://github.com/AI-SDC/ACRO-R).
 
-ACRO (Automatic Checking of Research Outputs) is an open source
-tool for automating the statistical disclosure control (SDC) of research
-outputs. ACRO assists researchers and output checkers by distinguishing between
-research output that is safe to publish, output that requires further analysis,
-and output that cannot be published because of substantial disclosure risk.
-
-It does this by providing a light-weight 'skin' that sits over well-known
-analysis tools, in a variety of languages researchers might use. This adds
-functionality to:
-
-*   identify potentially disclosive outputs against a range of commonly used
-    disclosure tests;
+A GUI for viewing and approving outputs is also available: [SACRO-Viewer](https://github.com/AI-SDC/SACRO-Viewer)
+
+ACRO (Automatic Checking of Research Outputs) is an open source tool for automating the [statistical disclosure control](https://en.wikipedia.org/wiki/Statistical_disclosure_control) (SDC) of research outputs. ACRO assists researchers and output checkers by distinguishing between research output that is safe to publish, output that requires further analysis, and output that cannot be published because of a substantial risk of disclosing private data.
+
+It does this by providing a lightweight 'skin' that sits over well-known analysis tools, in a variety of languages researchers might use. This adds functionality to:
+
+*   identify potentially disclosive outputs against a range of commonly used disclosure tests;
 *   suppress outputs where required;
 *   report reasons for suppression;
-*   produce simple summary documents TRE staff can use to streamline their
-    workflow.
+*   produce simple summary documents TRE staff can use to streamline their workflow.
 
 ![ACRO workflow and architecture schematic](docs/schematic.png)
 
@@ -37,15 +31,16 @@ If installed in this way, the example [notebooks](notebooks) and the [data](data
 $ pip install acro
 ```
 
-#### Notes for Python 3.12
+#### Notes for Python 3.13
 
-ACRO currently depends on an older version of Pandas (~1.5.0) for which no pre-compiled wheels are available within pip for Python 3.12. Therefore, in this scenario, Pandas must be built from source. This requires the installation of a C++ compiler before pip installing acro.
+ACRO currently depends on numpy version 1.x.x for which no pre-compiled wheels are available within pip for Python 3.13. Therefore, in this scenario, numpy must be built from source. This requires the installation of a C++ compiler before pip installing acro.
 
-For Windows, [Microsoft Visual Studio](https://visualstudio.microsoft.com/downloads/) and the [C++ build tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/) will likely need to be installed first.
+For Windows, the [Microsoft Visual Studio C++ build tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/) will likely need to be installed first.
 
 ### Examples
 
 See the example notebooks for:
+
 * [Python charities dataset](notebooks/test.ipynb)
 * [Python nursery dataset](notebooks/test-nursery.ipynb)
 * [R charities dataset](https://ai-sdc.github.io/ACRO/_static/test.nb.html)

acro/acro_tables.py

@@ -1512,6 +1512,9 @@ def crosstab_with_totals(  # pylint: disable=too-many-arguments,too-many-locals
                 normalize=normalize,
             )
 
+            if table.empty:
+                raise ValueError("empty table")
+
             table, _ = delete_empty_rows_columns(table)
             masks = create_crosstab_masks(
                 index_new,

acro/version.py

@@ -1,3 +1,3 @@
 """ACRO version number."""
 
-__version__ = "0.4.6"
+__version__ = "0.4.7"

docs/source/conf.py

@@ -12,7 +12,7 @@
 # -- Project information -----------------------------------------------------
 
 project = "ACRO"
-copyright = "2023, ACRO Project Team"
+copyright = "2024, ACRO Project Team"
 author = "ACRO Project Team"
 release = __version__
 

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = acro
-version = 0.4.6
+version = 0.4.7
 description = ACRO: Tools for the Automatic Checking of Research Outputs
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -10,16 +10,16 @@ maintainer_email = james.smith@uwe.ac.uk
 license = MIT
 license_files = LICENSE.md
 classifiers =
-    Development Status :: 3 - Alpha
+    Development Status :: 4 - Beta
     Intended Audience :: Developers
     Intended Audience :: Science/Research
     License :: OSI Approved :: MIT License
     Natural Language :: English
-    Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
     Programming Language :: Python :: 3.11
     Programming Language :: Python :: 3.12
+    Programming Language :: Python :: 3.13
     Topic :: Scientific/Engineering
     Topic :: Scientific/Engineering :: Information Analysis
     Operating System :: OS Independent
@@ -29,14 +29,15 @@ keywords =
     privacy
     privacy-tools
     statistical-disclosure-control
+    statistical-software
 project_urls =
     Changelog = https://github.com/AI-SDC/ACRO/CHANGELOG.md
     Documentation = https://github.com/AI-SDC/ACRO/wiki
     Bug Tracker = https://github.com/AI-SDC/ACRO/issues
     Discussions = https://github.com/AI-SDC/ACRO/discussions
 
 [options]
-python_requires = >=3.8
+python_requires = >=3.9
 zip_safe = False
 include_package_data = True
 packages = find:
@@ -45,7 +46,7 @@ install_requires =
     matplotlib
     numpy<2.0.0
     openpyxl
-    pandas~=1.5.0
+    pandas>=1.5.0,<2.3
     PyYAML
     statsmodels
 

test/test_initial.py

@@ -379,7 +379,12 @@ def test_finalise_json(data, acro):
     assert orig.summary == read.summary
     assert orig.comments == read.comments
     assert orig.timestamp == read.timestamp
-    assert (orig.output[0].reset_index()).equals(read.output[0])
+    # check SDC outcome DataFrame
+    orig_df = orig.output[0].reset_index()
+    read_df = read.output[0]
+    pd.testing.assert_frame_equal(
+        orig_df, read_df, check_names=False, check_dtype=False
+    )
     # test reading JSON
     with open(os.path.normpath(f"{PATH}/results.json"), encoding="utf-8") as file:
         json_data = json.load(file)