Update DiD and RDD Scripts

.github/workflows/did_sim.yml

@@ -52,7 +52,7 @@ jobs:
     - name: Install uv
       uses: astral-sh/setup-uv@v5
       with:
-        version: "0.6.11"
+        version: "0.7.8"
 
     - name: Set up Python
       uses: actions/setup-python@v5

.github/workflows/rdd_sim.yml

@@ -17,8 +17,8 @@ jobs:
     strategy:
       matrix:
         script: [
-          'scripts/rdd/rdd_sharp_coverage.py',
-          'scripts/rdd/rdd_fuzzy_coverage.py',
+          'scripts/rdd/rdd_sharp.py',
+          'scripts/rdd/rdd_fuzzy.py',
         ]
 
     steps:
@@ -48,34 +48,42 @@ jobs:
       with:
         ref: ${{ env.TARGET_BRANCH }}
 
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+      with:
+        version: "0.7.8"
+
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: '3.12'
+        python-version-file: "monte-cover/pyproject.toml"
 
-    - name: Install dependencies
+    - name: Install Monte-Cover
       run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
+        cd monte-cover
+        uv venv
+        uv sync
 
-    - name: Install DoubleML from correct branch
-      run: |
-        pip uninstall -y doubleml
-        pip install "doubleml[rdd] @ git+https://github.com/DoubleML/doubleml-for-py@${{ env.DML_BRANCH }}"
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.12'
 
-    - name: Install RDFlex from main branch
+    - name: Install DoubleML from correct branch
       run: |
-        pip uninstall -y doubleml
-        pip install git+https://github.com/DoubleML/doubleml-rdflex.git@main
-        pip install rdrobust
+        source monte-cover/.venv/bin/activate
+        uv pip uninstall doubleml
+        uv pip install "doubleml[rdd] @ git+https://github.com/DoubleML/doubleml-for-py@${{ env.DML_BRANCH }}"
 
     - name: Set up Git configuration
       run: |
         git config --global user.name 'github-actions'
         git config --global user.email '[email protected]'
 
     - name: Run scripts
-      run: python ${{ matrix.script }}
+      run: |
+        source monte-cover/.venv/bin/activate
+        uv run ${{ matrix.script }}
 
     - name: Commit any existing changes
       run: |

doc/rdd/rdd.qmd

@@ -47,7 +47,7 @@ df_sharp = pd.read_csv("../../results/rdd/rdd_sharp_coverage.csv", index_col=Non
 assert df_sharp["repetition"].nunique() == 1
 n_rep_sharp = df_sharp["repetition"].unique()[0]
 
-display_columns_sharp = ["Method", "Learner g", "fs specification", "Bias", "CI Length", "Coverage"]
+display_columns_sharp = ["Method", "Learner g", "fs_specification", "Bias", "CI Length", "Coverage"]
 ```
 
 ```{python}
@@ -99,7 +99,7 @@ df_fuzzy = pd.read_csv("../../results/rdd/rdd_fuzzy_coverage.csv", index_col=Non
 assert df_fuzzy["repetition"].nunique() == 1
 n_rep_fuzzy = df_fuzzy["repetition"].unique()[0]
 
-display_columns_fuzzy = ["Method", "Learner g", "Learner m", "fs specification", "Bias", "CI Length", "Coverage"]
+display_columns_fuzzy = ["Method", "Learner g", "Learner m", "fs_specification", "Bias", "CI Length", "Coverage"]
 ```
 
 ```{python}

monte-cover/src/montecover/did/did_pa_multi.py

@@ -4,10 +4,9 @@
 import numpy as np
 import pandas as pd
 from doubleml.did.datasets import make_did_CS2021
-from lightgbm import LGBMClassifier, LGBMRegressor
-from sklearn.linear_model import LinearRegression, LogisticRegression
 
 from montecover.base import BaseSimulation
+from montecover.utils import create_learner_from_config
 
 
 class DIDMultiCoverageSimulation(BaseSimulation):
@@ -36,39 +35,13 @@ def __init__(
     def _process_config_parameters(self):
         """Process simulation-specific parameters from config"""
         # Process ML models in parameter grid
+        # Process ML models in parameter grid
+        assert "learners" in self.dml_parameters, "No learners specified in the config file"
 
-        assert (
-            "learners" in self.dml_parameters
-        ), "No learners specified in the config file"
+        required_learners = ["ml_g", "ml_m"]
         for learner in self.dml_parameters["learners"]:
-            assert "ml_g" in learner, "No ml_g specified in the config file"
-            assert "ml_m" in learner, "No ml_m specified in the config file"
-
-            # Convert ml_g strings to actual objects
-            if learner["ml_g"][0] == "Linear":
-                learner["ml_g"] = ("Linear", LinearRegression())
-            elif learner["ml_g"][0] == "LGBM":
-                learner["ml_g"] = (
-                    "LGBM",
-                    LGBMRegressor(
-                        n_estimators=500, learning_rate=0.02, verbose=-1, n_jobs=1
-                    ),
-                )
-            else:
-                raise ValueError(f"Unknown learner type: {learner['ml_g']}")
-
-            # Convert ml_m strings to actual objects
-            if learner["ml_m"][0] == "Linear":
-                learner["ml_m"] = ("Linear", LogisticRegression())
-            elif learner["ml_m"][0] == "LGBM":
-                learner["ml_m"] = (
-                    "LGBM",
-                    LGBMClassifier(
-                        n_estimators=500, learning_rate=0.02, verbose=-1, n_jobs=1
-                    ),
-                )
-            else:
-                raise ValueError(f"Unknown learner type: {learner['ml_m']}")
+            for ml in required_learners:
+                assert ml in learner, f"No {ml} specified in the config file"
 
     def _calculate_oracle_values(self):
         """Calculate oracle values for the simulation."""
@@ -102,8 +75,9 @@ def _calculate_oracle_values(self):
     def run_single_rep(self, dml_data, dml_params) -> Dict[str, Any]:
         """Run a single repetition with the given parameters."""
         # Extract parameters
-        learner_g_name, ml_g = dml_params["learners"]["ml_g"]
-        learner_m_name, ml_m = dml_params["learners"]["ml_m"]
+        learner_config = dml_params["learners"]
+        learner_g_name, ml_g = create_learner_from_config(learner_config["ml_g"])
+        learner_m_name, ml_m = create_learner_from_config(learner_config["ml_m"])
         score = dml_params["score"]
         in_sample_normalization = dml_params["in_sample_normalization"]
 

monte-cover/src/montecover/rdd/__init__.py

@@ -0,0 +1,7 @@
+"""Monte Carlo coverage simulations for RDD."""
+
+from montecover.rdd.rdd import RDDCoverageSimulation
+
+__all__ = [
+    "RDDCoverageSimulation",
+]