add warnings for did benchmark and experimental score

Author: SvenKlaassen

doubleml/did/did.py

@@ -433,3 +433,31 @@ def _nuisance_tuning(
         res = {"params": params, "tune_res": tune_res}
 
         return res
+
+    def sensitivity_benchmark(self, benchmarking_set, fit_args=None):
+        """
+        Computes a benchmark for a given set of features.
+        Returns a DataFrame containing the corresponding values for cf_y, cf_d, rho and the change in estimates.
+
+        Parameters
+        ----------
+        benchmarking_set : list
+            List of features to be used for benchmarking.
+
+        fit_args : dict, optional
+            Additional arguments for the fit method.
+            Default is None.
+
+        Returns
+        -------
+        benchmark_results : pandas.DataFrame
+            Benchmark results.
+        """
+        if self.score == "experimental":
+            warnings.warn(
+                "Sensitivity benchmarking for experimental score may not be meaningful. "
+                "Consider using score='observational' for conditional treatment assignment.",
+                UserWarning,
+            )
+
+        return super().sensitivity_benchmark(benchmarking_set, fit_args)

doubleml/did/did_cs.py

@@ -664,3 +664,31 @@ def _nuisance_tuning(
         res = {"params": params, "tune_res": tune_res}
 
         return res
+
+    def sensitivity_benchmark(self, benchmarking_set, fit_args=None):
+        """
+        Computes a benchmark for a given set of features.
+        Returns a DataFrame containing the corresponding values for cf_y, cf_d, rho and the change in estimates.
+
+        Parameters
+        ----------
+        benchmarking_set : list
+            List of features to be used for benchmarking.
+
+        fit_args : dict, optional
+            Additional arguments for the fit method.
+            Default is None.
+
+        Returns
+        -------
+        benchmark_results : pandas.DataFrame
+            Benchmark results.
+        """
+        if self.score == "experimental":
+            warnings.warn(
+                "Sensitivity benchmarking for experimental score may not be meaningful. "
+                "Consider using score='observational' for conditional treatment assignment.",
+                UserWarning,
+            )
+
+        return super().sensitivity_benchmark(benchmarking_set, fit_args)