Merge branch 'development' into new_datasets

Signed-off-by: yolaj-nhs <[email protected]>

.github/workflows/test.yml

@@ -16,11 +16,11 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v3
 
-      - 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 pytest pytest-cov
+          pip install .
 
       - name: pytest and report coverage
         run: |

.github/workflows/tests.yml

@@ -0,0 +1,30 @@
+---
+name: Tests Manually Run
+
+on: workflow_dispatch
+
+jobs:
+  build:
+    name: ${{ matrix.os }}-Python${{ matrix.python-version }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.8", "3.9", "3.10"]
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install and pytest
+        run: pip install . pytest
+
+      - name: Run pytest
+        run: pytest .
+...

.gitignore

@@ -88,6 +88,9 @@ ipython_config.py
 # pyenv
 .python-version
 
+# development files
+development_files/
+
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
 
   # Standard hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: check-added-large-files
       - id: check-merge-conflict
@@ -21,7 +21,7 @@ repos:
 
   # Check for spelling
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.5
+    rev: v2.2.6
     hooks:
       - id: codespell
         args: ["-L", "fpr, tre, sav, provid"]
@@ -33,27 +33,27 @@ repos:
 
   # Autoremoves unused imports
   - repo: https://github.com/hadialqattan/pycln
-    rev: "v2.2.2"
+    rev: "v2.4.0"
     hooks:
       - id: pycln
         stages: [manual]
 
   # Sort includes
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.10.1
+    rev: v3.15.0
     hooks:
       - id: pyupgrade
 
   # Upgrade old Python syntax
   - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
       - id: isort
         args: ["--profile", "black"]
 
   # Black format Python and notebooks
   - repo: https://github.com/psf/black
-    rev: 23.9.1
+    rev: 23.12.1
     hooks:
       - id: black-jupyter
 

CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## Version 1.1.2 (Oct 30, 2023)
+
+Changes:
+*   Fix a bug related to the `rules.json` path when running from package ([#247](https://github.com/AI-SDC/AI-SDC/pull/247))
+*   Update user stories ([#247](https://github.com/AI-SDC/AI-SDC/pull/247))
+
+## Version 1.1.1 (Oct 19, 2023)
+
+Changes:
+*   Update notebook example paths ([#237](https://github.com/AI-SDC/AI-SDC/pull/237))
+*   Fix AdaBoostClassifier structural attack ([#242](https://github.com/AI-SDC/AI-SDC/pull/242))
+*   Move experiments module and configs to separate repository ([#229](https://github.com/AI-SDC/AI-SDC/pull/229))
+
+## Version 1.1.0 (Oct 11, 2023)
+
+Changes:
+*    Add automatic formatting of docstrings ([#210](https://github.com/AI-SDC/AI-SDC/pull/210))
+*    Update user stories ([#217](https://github.com/AI-SDC/AI-SDC/pull/217))
+*    Add module to run experiments with attacks and gather data ([#224](https://github.com/AI-SDC/AI-SDC/pull/224))
+*    Fix bug in report.py: error removing a file that does not exist ([#227](https://github.com/AI-SDC/AI-SDC/pull/227))
+*    Add structural attack for traditional and other risk measures ([#232](https://github.com/AI-SDC/AI-SDC/pull/232))
+*    Fix package installation for Python 3.8, 3.9, 3.10 ([#234](https://github.com/AI-SDC/AI-SDC/pull/234))
+
 ## Version 1.0.6 (Jul 21, 2023)
 
 Changes:

CITATION.cff

@@ -1,8 +1,8 @@
 cff-version: 1.2.0
 title: AI-SDC
-version: 1.0.6
-doi: 10.5281/zenodo.8172371
-date-released: 2023-07-21
+version: 1.1.2
+doi: 10.5281/zenodo.10055182
+date-released: 2023-10-30
 license: MIT
 repository-code: https://github.com/AI-SDC/AI-SDC
 languages:
@@ -74,3 +74,12 @@ identifiers:
   - type: doi
     value: 10.5281/zenodo.8172371
     description: This is the archived snapshot of AI-SDC v.1.0.6.
+  - type: doi
+    value: 10.5281/zenodo.8430143
+    description: This is the archived snapshot of AI-SDC v.1.1.0.
+  - type: doi
+    value: 10.5281/zenodo.10021954
+    description: This is the archived snapshot of AI-SDC v.1.1.1.
+  - type: doi
+    value: 10.5281/zenodo.10055182
+    description: This is the archived snapshot of AI-SDC v.1.1.2.

README.md

@@ -8,6 +8,10 @@
 
 A collection of tools and resources for managing the statistical disclosure control of trained machine learning models. For a brief introduction, see [Smith et al. (2022)](https://doi.org/10.48550/arXiv.2212.01233).
 
+### User Guides
+
+A collection of user guides can be found in the 'user_stories' folder of this repository. These guides include configurable examples from the perspective of both a researcher and a TRE, with separate scripts for each. Instructions on how to use each of these scripts and which scripts to use are included in the README of the [`user_stories`](./user_stories) folder.
+
 ## Content
 
 * `aisdc`
@@ -82,6 +86,7 @@ $ pip install .
 
 ---
 
-This work was funded by UK Research and Innovation Grant Number MC_PC_21033 as part of Phase 1 of the DARE UK (Data and Analytics Research Environments UK) programme (https://dareuk.org.uk/), delivered in partnership with HDR UK and ADRUK. The specific project was Guidelines and Resources for AI Model Access from TrusTEd Research environments (GRAIMATTER).­ This project has also been supported by MRC and EPSRC [grant number MR/S010351/1]: PICTURES.
+
+This work was funded by UK Research and Innovation under Grant Numbers MC_PC_21033  and MC_PC_23006 as part of Phase 1 of the DARE UK (Data and Analytics Research Environments UK) programme (https://dareuk.org.uk/), delivered in partnership with Health Data Research UK (HDR UK) and Administrative Data Research UK (ADR UK). The specific projects were Semi-Automatic checking of Research Outputs (SACRO -MC_PC_23006) and   Guidelines and Resources for AI Model Access from TrusTEd Research environments (GRAIMATTER - MC_PC_21033).­ This project has also been supported by MRC and EPSRC [grant number MR/S010351/1]: PICTURES.
 
 <img src="docs/source/images/UK_Research_and_Innovation_logo.svg" width="20%" height="20%" padding=20/> <img src="docs/source/images/health-data-research-uk-hdr-uk-logo-vector.png" width="10%" height="10%" padding=20/> <img src="docs/source/images/logo_print.png" width="15%" height="15%" padding=20/>

aisdc/attacks/attack_report_formatter.py

@@ -1,7 +1,10 @@
 """Generate report for TREs from JSON file."""
 
+from __future__ import annotations
+
 import json
 import os
+import pathlib
 import pprint
 import shutil
 from datetime import date
@@ -151,7 +154,8 @@ def _is_instance_based_model(self, instance_based_model_score):
 
     def _tree_min_samples_leaf(self, min_samples_leaf_score):
         # Find min samples per leaf requirement
-        risk_appetite_path = "./aisdc/safemodel/rules.json"
+        base_path = pathlib.Path(__file__).parents[1]
+        risk_appetite_path = os.path.join(base_path, "safemodel", "rules.json")
         min_samples_leaf_appetite = None
 
         with open(risk_appetite_path, "r+", encoding="utf-8") as f: