add ssm models to monte cover

Author: SvenKlaassen

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

@@ -0,0 +1,9 @@
+"""Monte Carlo coverage simulations for SSM."""
+
+from montecover.ssm.ssm_mar_ate import SSMMarATECoverageSimulation
+from montecover.ssm.ssm_nonig_ate import SSMNonIgnorableATECoverageSimulation
+
+__all__ = [
+    "SSMMarATECoverageSimulation",
+    "SSMNonIgnorableATECoverageSimulation",
+]

monte-cover/src/montecover/ssm/ssm_mar_ate.py

@@ -0,0 +1,123 @@
+from typing import Any, Dict, Optional
+
+import doubleml as dml
+from doubleml.datasets import make_ssm_data
+
+from montecover.base import BaseSimulation
+from montecover.utils import create_learner_from_config
+
+
+class SSMMarATECoverageSimulation(BaseSimulation):
+    """Simulation class for coverage properties of DoubleMLSSM with missing at random for ATE 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_pi"]
+        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_pi_name, ml_pi = create_learner_from_config(learner_config["ml_pi"])
+
+        # Model
+        dml_model = dml.DoubleMLSSM(
+            obj_dml_data=dml_data,
+            ml_g=ml_g,
+            ml_m=ml_m,
+            ml_pi=ml_pi,
+            score="missing-at-random",
+        )
+        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 pi": learner_pi_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 pi", "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_ssm_data(
+            theta=dgp_params["theta"],
+            n_obs=dgp_params["n_obs"],
+            dim_x=dgp_params["dim_x"],
+            mar=True,
+            return_type="DataFrame",
+        )
+        dml_data = dml.DoubleMLData(data, "y", "d", s_col="s")
+        return dml_data

monte-cover/src/montecover/ssm/ssm_nonig_ate.py

@@ -0,0 +1,125 @@
+from typing import Any, Dict, Optional
+
+import doubleml as dml
+from doubleml.datasets import make_ssm_data
+
+from montecover.base import BaseSimulation
+from montecover.utils import create_learner_from_config
+
+
+class SSMNonIgnorableATECoverageSimulation(BaseSimulation):
+    """
+    Simulation class for coverage properties of DoubleMLSSM with nonignorable nonresponse for ATE 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_pi"]
+        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_pi_name, ml_pi = create_learner_from_config(learner_config["ml_pi"])
+
+        # Model
+        dml_model = dml.DoubleMLSSM(
+            obj_dml_data=dml_data,
+            ml_g=ml_g,
+            ml_m=ml_m,
+            ml_pi=ml_pi,
+            score="nonignorable",
+        )
+        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 pi": learner_pi_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 pi", "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_ssm_data(
+            theta=dgp_params["theta"],
+            n_obs=dgp_params["n_obs"],
+            dim_x=dgp_params["dim_x"],
+            mar=False,
+            return_type="DataFrame",
+        )
+        dml_data = dml.DoubleMLData(data, "y", "d", z_cols="z", s_col="s")
+        return dml_data