[Repo Assist] fix: correct categorical groupby KeyError and pandas FutureWarning in dummy_outcome_refuter

dowhy/causal_refuters/dummy_outcome_refuter.py

@@ -757,14 +757,13 @@ def preprocess_data_by_treatment(
         std_dev = data[treatment_variable_name].std()
         num_bins = (data.max() - data.min()) / (bucket_size_scale_factor * std_dev)
         data["bins"] = pd.cut(data[treatment_variable_name], num_bins)
-        groups = data.groupby("bins")
+        groups = data.groupby("bins", observed=False)
         data.drop("bins", axis=1, inplace=True)
         return groups
 
     elif "categorical" in variable_type.name:
         # Action for categorical variables
-        groups = data.groupby(treatment_variable_name)
-        groups = data.groupby("bins")
+        groups = data.groupby(treatment_variable_name, observed=False)
         return groups
     else:
         raise ValueError("Passed {}. Expected bool, float, int or categorical.".format(variable_type.name))

tests/causal_refuters/test_dummy_outcome_refuter.py

@@ -25,6 +25,18 @@ def test_refutation_dummy_outcome_refuter_default_binary_treatment(
         refuter_tester = SimpleRefuter(error_tolerence, estimator_method, "dummy_outcome_refuter")
         refuter_tester.binary_treatment_testsuite(tests_to_run="atleast-one-common-cause", num_samples=num_samples)
 
+    @mark.parametrize(
+        ["error_tolerance", "estimator_method", "num_samples"],
+        [(0.1, "backdoor.propensity_score_matching", 1000)],
+    )
+    def test_refutation_dummy_outcome_refuter_default_categorical_treatment(
+        self, error_tolerance, estimator_method, num_samples
+    ):
+        # Regression test for #1316: the categorical branch had a copy-paste error that tried to
+        # groupby("bins") which doesn't exist for categorical treatments, raising KeyError.
+        refuter_tester = SimpleRefuter(error_tolerance, estimator_method, "dummy_outcome_refuter")
+        refuter_tester.categorical_treatment_testsuite(tests_to_run="atleast-one-common-cause", num_samples=num_samples)
+
     @mark.parametrize(
         ["error_tolerence", "estimator_method", "transformations"],
         [(0.05, "iv.instrumental_variable", [("zero", ""), ("noise", {"std_dev": 1})])],