Chore: Add CI/CD for tests

.github/workflows/test.yml

@@ -0,0 +1,46 @@
+name: Tests & checks
+
+on:
+  pull_request:
+  workflow_dispatch: # allow running manually from the Actions tab
+
+# cancel previous runs on a new commit
+concurrency:
+  group: ${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  ci:
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+        os: [macos-latest, ubuntu-latest, windows-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - uses: actions/cache@v4
+        name: Cache venv
+        with:
+          path: ./.venv
+          key: ${{ matrix.os }}-venv-${{ matrix.python-version }}-${{ hashFiles('**/uv.lock') }}
+
+      - name: Install the project dependencies
+        run: uv sync --group test --python "$(python -c 'import sys; print(sys.executable)')"
+        shell: bash
+
+      - name: Check pre-commit
+        run: uv run pre-commit run --all-files
+
+      - name: Run tests with pytest
+        run: uv run make test

.gitignore

@@ -6,6 +6,9 @@ dist/
 wheels/
 *.egg-info
 
+# Dev cache
+.ruff_cache/
+
 # Virtual environments
 .venv
 

Makefile

@@ -9,5 +9,8 @@ setup:  ## Install development dependencies
 	uv sync --group dev
 	uv run pre-commit install
 
+test:
+	uv run ruff check
+
 help:
 	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'

bbttest/__init__.py

@@ -1,13 +1,13 @@
 """bbt-test: Bayesian Bradley-Terry model for algorithm comparison."""
 
+from .const import HyperPrior, ReportedProperty, TieSolver
 from .py_bbt import PyBBT
 from .utils import multiple_ropes_control_table
-from .const import TieSolver, ReportedProperty, HyperPrior
 
 __all__ = [
+    "HyperPrior",
     "PyBBT",
-    "multiple_ropes_control_table",
-    "TieSolver",
     "ReportedProperty",
-    "HyperPrior",
+    "TieSolver",
+    "multiple_ropes_control_table",
 ]

bbttest/py_bbt.py

@@ -1,3 +1,5 @@
+from collections.abc import Sequence
+
 import numpy as np
 import pandas as pd
 
@@ -139,7 +141,7 @@ def posterior_table(
         rope_value: tuple[float, float] = (0.45, 0.55),
         control_model: str | None = None,
         selected_models: list[str] | None = None,
-        columns: list[ReportedProperty] = DEFAULT_PROPERTIES,
+        columns: Sequence[ReportedProperty | str] = DEFAULT_PROPERTIES,
         hdi_proba: float = 0.89,
         round_ndigits: int | None = 2,
     ) -> pd.DataFrame:
@@ -196,7 +198,11 @@ def posterior_table(
         out_table["strong_interpretation_raw"] = np.where(
             out_table["mean"] > self._STRONG_INTERPRETATION_BETTER_THRESHOLD,
             out_table["left_model"] + ">",
-            np.where(out_table["mean"] <= self._STRONG_INTERPRETATION_EQUAL_THRESHOLD, "=", "?"),
+            np.where(
+                out_table["mean"] <= self._STRONG_INTERPRETATION_EQUAL_THRESHOLD,
+                "=",
+                "?",
+            ),
         )
         out_table["strong_interpretation"] = np.where(
             out_table["strong_interpretation_raw"].str.endswith(">"),

bbttest/utils.py

@@ -1,7 +1,9 @@
+from typing import Literal
+
 import pandas as pd
 
 from .py_bbt import PyBBT
-from typing import Literal
+
 
 def multiple_ropes_control_table(
     model: PyBBT,
@@ -66,12 +68,22 @@ def multiple_ropes_control_table(
             else:
                 unknown_models.append(row["left_model"])
 
-        rows.append({
-            "rope": rope,
-            "better_models": better_models if return_as_array else join_char.join(better_models),
-            "equivalent_models": equivalent_models if return_as_array else join_char.join(equivalent_models),
-            "worse_models": worse_models if return_as_array else join_char.join(worse_models),
-            "unknown_models": unknown_models if return_as_array else join_char.join(unknown_models),
-        })
+        rows.append(
+            {
+                "rope": rope,
+                "better_models": better_models
+                if return_as_array
+                else join_char.join(better_models),
+                "equivalent_models": equivalent_models
+                if return_as_array
+                else join_char.join(equivalent_models),
+                "worse_models": worse_models
+                if return_as_array
+                else join_char.join(worse_models),
+                "unknown_models": unknown_models
+                if return_as_array
+                else join_char.join(unknown_models),
+            }
+        )
 
     return pd.DataFrame(rows)

pyproject.toml

@@ -29,13 +29,28 @@ dependencies = [
 
 [dependency-groups]
 dev = [
-    "coverage>=7.12.0",
-    "jupyter>=1.1.1",
-    "mypy>=1.18.2",
-    "pre-commit>=4.5.0",
-    "ruff>=0.14.6",
-    "seaborn>=0.13.2",
+    "coverage",
+    "jupyter",
+    "mypy",
+    "pre-commit",
+    "ruff",
+    "seaborn",
 ]
+test = [
+    "pre-commit",
+    "pytest",
+    "ruff",
+    "mypy",
+]
+
+[tool.mypy]
+python_version = "3.11"
+check_untyped_defs = true  # check all functions, this fixes some tests
+allow_redefinition = true  # we redefine variables a lot for efficiency
+# most libraries used are not properly typed in Python, particularly RDKit
+ignore_missing_imports = true
+disable_error_code = ["import-untyped"]
+no_site_packages = true
 
 [tool.uv.build-backend]
 module-name = "bbttest"

ruff.toml

@@ -1,9 +1,6 @@
 include = [
     "pyproject.toml",
-    "benchmarking/**/*.ipynb",
-    "examples/**/*.py",
-    "skfp/**/*.py",
-    "tests/**/*.py",
+    "bbttest/**"
 ]
 exclude = [
     "docs/**"