Clean repository

.github/workflows/iivm_sim.yml

@@ -17,7 +17,7 @@ jobs:
     strategy:
       matrix:
         script: [
-          'scripts/irm/iivm_late_coverage.py',
+          'scripts/irm/iivm_late.py',
         ]
 
     steps:
@@ -47,28 +47,37 @@ 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 @ git+https://github.com/DoubleML/doubleml-for-py@${{ env.DML_BRANCH }}"
+        source monte-cover/.venv/bin/activate
+        uv pip uninstall doubleml
+        uv pip install "doubleml @ git+https://github.com/DoubleML/doubleml-for-py@${{ 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: |

.github/workflows/ssm_sim.yml

@@ -48,28 +48,37 @@ 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 @ git+https://github.com/DoubleML/doubleml-for-py@${{ env.DML_BRANCH }}"
+        source monte-cover/.venv/bin/activate
+        uv pip uninstall doubleml
+        uv pip install "doubleml @ git+https://github.com/DoubleML/doubleml-for-py@${{ 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/irm/iivm.qmd

@@ -30,7 +30,7 @@ The simulations are based on the  the [make_iivm_data](https://docs.doubleml.org
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/irm/iivm_late_coverage_metadata.csv'
+metadata_file = '../../results/irm/iivm_late_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```
@@ -46,7 +46,7 @@ df = pd.read_csv("../../results/irm/iivm_late_coverage.csv", index_col=None)
 assert df["repetition"].nunique() == 1
 n_rep = df["repetition"].unique()[0]
 
-display_columns = ["Learner g", "Learner m", "Bias", "CI Length", "Coverage"]
+display_columns = ["Learner g", "Learner m", "Learner r", "Bias", "CI Length", "Coverage"]
 ```
 
 

doc/irm/irm.qmd

@@ -30,7 +30,7 @@ The simulations are based on the  the [make_irm_data](https://docs.doubleml.org/
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/irm/irm_ate_coverage_metadata.csv'
+metadata_file = '../../results/irm/irm_ate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/irm/irm_cate.qmd

@@ -32,7 +32,7 @@ The non-uniform results (coverage, ci length and bias) refer to averaged values
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/irm/irm_cate_coverage_metadata.csv'
+metadata_file = '../../results/irm/irm_cate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/irm/irm_gate.qmd

@@ -32,7 +32,7 @@ The non-uniform results (coverage, ci length and bias) refer to averaged values
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/irm/irm_gate_coverage_metadata.csv'
+metadata_file = '../../results/irm/irm_gate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/plm/pliv.qmd

@@ -30,7 +30,7 @@ The simulations are based on the  the [make_pliv_CHS2015](https://docs.doubleml.
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/plm/pliv_late_coverage_metadata.csv'
+metadata_file = '../../results/plm/pliv_late_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/plm/plr.qmd

@@ -30,7 +30,7 @@ The simulations are based on the  the [make_plr_CCDDHNR2018](https://docs.double
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/plm/plr_ate_coverage_metadata.csv'
+metadata_file = '../../results/plm/plr_ate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/plm/plr_cate.qmd

@@ -32,7 +32,7 @@ The non-uniform results (coverage, ci length and bias) refer to averaged values
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/plm/plr_cate_coverage_metadata.csv'
+metadata_file = '../../results/plm/plr_cate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```
@@ -116,4 +116,4 @@ generate_and_show_styled_table(
     rename_map={"Learner g": "Learner l"},
     coverage_highlight_cols=["Coverage", "Uniform Coverage"]
 )
-```
+```

doc/plm/plr_gate.qmd

@@ -32,7 +32,7 @@ The non-uniform results (coverage, ci length and bias) refer to averaged values
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/plm/plr_gate_coverage_metadata.csv'
+metadata_file = '../../results/plm/plr_gate_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

doc/rdd/rdd.qmd

@@ -31,7 +31,7 @@ The simulations are based on the [make_simple_rdd_data](https://docs.doubleml.or
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/rdd/rdd_sharp_coverage_metadata.csv'
+metadata_file = '../../results/rdd/rdd_sharp_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```
@@ -83,7 +83,7 @@ The simulations are based on the [make_simple_rdd_data](https://docs.doubleml.or
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/rdd/rdd_fuzzy_coverage_metadata.csv'
+metadata_file = '../../results/rdd/rdd_fuzzy_metadata.csv'
 metadata_df = pd.read_csv(metadata_file)
 print(metadata_df.T.to_string(header=False))
 ```

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

@@ -3,6 +3,7 @@
 from montecover.irm.apo import APOCoverageSimulation
 from montecover.irm.apos import APOSCoverageSimulation
 from montecover.irm.cvar import CVARCoverageSimulation
+from montecover.irm.iivm_late import IIVMLATECoverageSimulation
 from montecover.irm.irm_ate import IRMATECoverageSimulation
 from montecover.irm.irm_ate_sensitivity import IRMATESensitivityCoverageSimulation
 from montecover.irm.irm_atte import IRMATTECoverageSimulation
@@ -17,6 +18,7 @@
     "APOSCoverageSimulation",
     "CVARCoverageSimulation",
     "IRMATECoverageSimulation",
+    "IIVMLATECoverageSimulation",
     "IRMATESensitivityCoverageSimulation",
     "IRMATTECoverageSimulation",
     "IRMATTESensitivityCoverageSimulation",

monte-cover/src/montecover/irm/iivm_late.py

@@ -0,0 +1,122 @@
+from typing import Any, Dict, Optional
+
+import doubleml as dml
+from doubleml.datasets import make_iivm_data
+
+from montecover.base import BaseSimulation
+from montecover.utils import create_learner_from_config
+
+
+class IIVMLATECoverageSimulation(BaseSimulation):
+    """Simulation class for coverage properties of DoubleMLIIVM for LATE estimation."""
+
+    def __init__(
+        self,
+        config_file: str,
+        suppress_warnings: bool = True,
+        log_level: str = "INFO",
+        log_file: Optional[str] = None,
+    ):
+        super().__init__(
+            config_file=config_file,
+            suppress_warnings=suppress_warnings,
+            log_level=log_level,
+            log_file=log_file,
+        )
+
+        # Calculate oracle values
+        self._calculate_oracle_values()
+
+    def _process_config_parameters(self):
+        """Process simulation-specific parameters from config"""
+        # Process ML models in parameter grid
+        assert "learners" in self.dml_parameters, "No learners specified in the config file"
+
+        required_learners = ["ml_g", "ml_m", "ml_r"]
+        for learner in self.dml_parameters["learners"]:
+            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."""
+        self.logger.info("Calculating oracle values")
+
+        self.oracle_values = dict()
+        self.oracle_values["theta"] = self.dgp_parameters["theta"]
+
+    def run_single_rep(self, dml_data: dml.DoubleMLData, dml_params: Dict[str, Any]) -> Dict[str, Any]:
+        """Run a single repetition with the given parameters."""
+        # Extract parameters
+        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"])
+        learner_r_name, ml_r = create_learner_from_config(learner_config["ml_r"])
+
+        # Model
+        dml_model = dml.DoubleMLIIVM(
+            obj_dml_data=dml_data,
+            ml_g=ml_g,
+            ml_m=ml_m,
+            ml_r=ml_r,
+        )
+        dml_model.fit()
+
+        result = {
+            "coverage": [],
+        }
+        for level in self.confidence_parameters["level"]:
+            level_result = dict()
+            level_result["coverage"] = self._compute_coverage(
+                thetas=dml_model.coef,
+                oracle_thetas=self.oracle_values["theta"],
+                confint=dml_model.confint(level=level),
+                joint_confint=None,
+            )
+
+            # add parameters to the result
+            for res_metric in level_result.values():
+                res_metric.update(
+                    {
+                        "Learner g": learner_g_name,
+                        "Learner m": learner_m_name,
+                        "Learner r": learner_r_name,
+                        "level": level,
+                    }
+                )
+            for key, res in level_result.items():
+                result[key].append(res)
+
+        return result
+
+    def summarize_results(self):
+        """Summarize the simulation results."""
+        self.logger.info("Summarizing simulation results")
+
+        # Group by parameter combinations
+        groupby_cols = ["Learner g", "Learner m", "Learner r", "level"]
+        aggregation_dict = {
+            "Coverage": "mean",
+            "CI Length": "mean",
+            "Bias": "mean",
+            "repetition": "count",
+        }
+
+        # Aggregate results (possibly multiple result dfs)
+        result_summary = dict()
+        for result_name, result_df in self.results.items():
+            result_summary[result_name] = result_df.groupby(groupby_cols).agg(aggregation_dict).reset_index()
+            self.logger.debug(f"Summarized {result_name} results")
+
+        return result_summary
+
+    def _generate_dml_data(self, dgp_params: Dict[str, Any]) -> dml.DoubleMLData:
+        """Generate data for the simulation."""
+        data = make_iivm_data(
+            theta=dgp_params["theta"],
+            n_obs=dgp_params["n_obs"],
+            dim_x=dgp_params["dim_x"],
+            alpha_x=dgp_params["alpha_x"],
+            return_type="DataFrame",
+        )
+        dml_data = dml.DoubleMLData(data, "y", "d", z_cols="z")
+        return dml_data

results/did/did_cs_atte_coverage_metadata.csv

@@ -1,2 +1,2 @@
 DoubleML Version,Script,Date,Total Runtime (seconds),Python Version
-0.11.dev0,did_cs_atte_coverage.py,2025-06-02 15:42:26,12669.156663179398,3.12.3
+0.11.dev0,did_cs_atte_coverage.py,2025-06-06 09:10:00,12688.770802021027,3.12.3