Merge branch 'main' into uml-autoupdate

Author: drbenvincent

.github/workflows/release.yml

@@ -1,4 +1,5 @@
 name: PyPI release
+
 on:
   workflow_dispatch:
   pull_request:
@@ -23,28 +24,30 @@ jobs:
         run: |
           pip install build
           python -m build
+          ls dist  # List the contents of the dist directory
       - name: Check the sdist installs and imports
         run: |
           mkdir -p test-sdist
           cd test-sdist
           python -m venv venv-sdist
           venv-sdist/bin/python -m pip install ../dist/causalpy*.tar.gz
           echo "Checking import and version number (on release)"
-          venv-sdist/bin/python -c "import causalpy; assert causalpy.__version__ == '${{  github.ref_name }}' if '${{ github.ref_type }}' == 'tag' else causalpy.__version__; print(causalpy.__version__)"
+          venv-sdist/bin/python -c "import causalpy; assert causalpy.__version__ == '${{ github.ref_name }}' if '${{ github.ref_type }}' == 'tag' else causalpy.__version__; print(causalpy.__version__)"
           cd ..
       - name: Check the bdist installs and imports
         run: |
           mkdir -p test-bdist
           cd test-bdist
           python -m venv venv-bdist
-          venv-bdist/bin/python -m pip install ../dist/CausalPy*.whl
+          venv-bdist/bin/python -m pip install ../dist/causalpy*.whl
           echo "Checking import and version number (on release)"
-          venv-bdist/bin/python -c "import causalpy; assert causalpy.__version__ == '${{  github.ref_name }}' if '${{ github.ref_type }}' == 'tag' else causalpy.__version__; print(causalpy.__version__)"
+          venv-bdist/bin/python -c "import causalpy; assert causalpy.__version__ == '${{ github.ref_name }}' if '${{ github.ref_type }}' == 'tag' else causalpy.__version__; print(causalpy.__version__)"
           cd ..
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
           name: artifact
           path: dist/*
+
   test:
     name: Upload to Test PyPI
     permissions:
@@ -72,7 +75,7 @@ jobs:
           python -m venv venv-test-pypi
           venv-test-pypi/bin/python -m pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple causalpy
           echo "Checking import and version number"
-          venv-test-pypi/bin/python -c "import causalpy; assert causalpy.__version__ == '${{  github.ref_name }}'"
+          venv-test-pypi/bin/python -c "import causalpy; assert causalpy.__version__ == '${{ github.ref_name }}'"
 
   publish:
     environment: release

.pre-commit-config.yaml

@@ -25,7 +25,7 @@ repos:
         exclude: &exclude_pattern 'iv_weak_instruments.ipynb'
         args: ["--maxkb=1500"]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.4
+    rev: v0.9.8
     hooks:
       # Run the linter
       - id: ruff
@@ -42,7 +42,7 @@ repos:
         # see here https://github.com/econchick/interrogate/issues/60#issuecomment-735436566
         pass_filenames: false
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
       - id: codespell
         additional_dependencies:

causalpy/pymc_models.py

@@ -164,7 +164,7 @@ def print_row(
         ) -> None:
             """Print one row of the coefficient table"""
             formatted_name = f"  {name: <{max_label_length}}"
-            formatted_val = f"{round_num(coeff_samples.mean().data, round_to)}, 94% HDI [{round_num(coeff_samples.quantile(0.03).data, round_to)}, {round_num(coeff_samples.quantile(1-0.03).data, round_to)}]"  # noqa: E501
+            formatted_val = f"{round_num(coeff_samples.mean().data, round_to)}, 94% HDI [{round_num(coeff_samples.quantile(0.03).data, round_to)}, {round_num(coeff_samples.quantile(1 - 0.03).data, round_to)}]"  # noqa: E501
             print(f"  {formatted_name}  {formatted_val}")
 
         print("Model coefficients:")

causalpy/tests/test_api_stability.py

@@ -36,9 +36,9 @@ def test_causal_inference_and_discovery_with_python_example():
 
     # Build the model
     model = cp.pymc_models.WeightedSumFitter(sample_kwargs=sample_kwargs)
-    assert isinstance(
-        model, WeightedSumFitter
-    ), "model is not an instance of WeightedSumFitter"
+    assert isinstance(model, WeightedSumFitter), (
+        "model is not an instance of WeightedSumFitter"
+    )
 
     formula = "twitter ~ 0 + tiktok + linkedin + instagram"
 
@@ -49,9 +49,9 @@ def test_causal_inference_and_discovery_with_python_example():
         formula=formula,
         model=model,
     )
-    assert isinstance(
-        results, SyntheticControl
-    ), "results is not an instance of SyntheticControl"
+    assert isinstance(results, SyntheticControl), (
+        "results is not an instance of SyntheticControl"
+    )
 
     fig, ax = results.plot()
     assert isinstance(fig, plt.Figure)

docs/source/index.md

@@ -96,7 +96,7 @@ CausalPy has a broad range of quasi-experimental methods for causal inference:
 | Geographical lift | Measures the impact of an intervention in a specific geographic area by comparing it to similar areas without the intervention. Commonly used in marketing to assess regional campaigns. |
 | ANCOVA | Analysis of Covariance combines ANOVA and regression to control for the effects of one or more quantitative covariates. Used when comparing group means while controlling for other variables. |
 | Differences in Differences | Compares the changes in outcomes over time between a treatment group and a control group. Used in observational studies to estimate causal effects by accounting for time trends. |
-| Regression discontinuity | Identifies causal effects by exploiting a cutoff or threshold in an assignment variable. Used when treatment is assigned based on a threshold value of an observed variable, allowing comparison just above and below the cutoff. |
+|Regression discontinuity | Identifies causal effects by exploiting a sharp cutoff or threshold in an assignment variable. Used when treatment is assigned based on a threshold value of an observed variable, allowing comparison just above and below the cutoff. |
 | Regression kink designs | Focuses on changes in the slope (kinks) of the relationship between variables rather than jumps at cutoff points. Used to identify causal effects when treatment intensity changes at a threshold. |
 | Interrupted time series | Analyzes the effect of an intervention by comparing time series data before and after the intervention. Used when data is collected over time and an intervention occurs at a known point, allowing assessment of changes in level or trend. |
 | Instrumental variable regression | Addresses endogeneity by using an instrument variable that is correlated with the endogenous explanatory variable but uncorrelated with the error term. Used when explanatory variables are correlated with the error term, providing consistent estimates of causal effects. |

docs/source/notebooks/multi_cell_geolift.ipynb

@@ -1099,7 +1099,7 @@
     "unpooled_results = []\n",
     "\n",
     "for i, target_geo in enumerate(treated):\n",
-    "    print(f\"Analyzing test geo: {target_geo} ({i+1} of {len(treated)})\")\n",
+    "    print(f\"Analyzing test geo: {target_geo} ({i + 1} of {len(treated)})\")\n",
     "    formula = f\"{target_geo} ~ 0 + {' + '.join(untreated)}\"\n",
     "    print(formula)\n",
     "\n",

docs/source/notebooks/rd_pymc.ipynb

@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Regression discontinuity with `pymc` models"
+    "# Sharp regression discontinuity with `pymc` models"
    ]
   },
   {

docs/source/notebooks/rd_pymc_drinking.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Drinking age - Bayesian analysis\n",
     "\n",
-    "This example uses the regression discontinuity design to make claims about the causal effects of the minimum legal drinking age (21 in the USA) upon all cause mortality rates. The dataset is from a study by {cite:t}`carpenter2009effect`."
+    "This example uses the sharp regression discontinuity design to make claims about the causal effects of the minimum legal drinking age (21 in the USA) upon all cause mortality rates. The dataset is from a study by {cite:t}`carpenter2009effect`."
    ]
   },
   {

docs/source/notebooks/rd_skl.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Regression discontinuity with sci-kit learn models"
+    "# Sharp regression discontinuity with sci-kit learn models"
    ]
   },
   {

docs/source/notebooks/rd_skl_drinking.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Drinking age with a scikit-learn model\n",
     "\n",
-    "This example uses the regression discontinuity design to make claims about the causal effects of the minimum legal drinking age (21 in the USA) upon all cause mortality rates. The dataset is from a study by {cite:t}`carpenter2009effect`."
+    "This example uses the sharp regression discontinuity design to make claims about the causal effects of the minimum legal drinking age (21 in the USA) upon all cause mortality rates. The dataset is from a study by {cite:t}`carpenter2009effect`."
    ]
   },
   {

docs/source/notebooks/rkink_pymc.ipynb

@@ -108,7 +108,7 @@
     "    beta = rng.random(5)\n",
     "    ax[0, col].plot(x, f(x, beta, kink), lw=3)\n",
     "    ax[1, col].plot(x, np.gradient(f(x, beta, kink), x), lw=3)\n",
-    "    ax[0, col].set(title=f\"Random  {col+1}\")\n",
+    "    ax[0, col].set(title=f\"Random  {col + 1}\")\n",
     "    ax[1, col].set(xlabel=\"x\")\n",
     "\n",
     "ax[0, 0].set(ylabel=\"$y = f(x)$\")\n",