SKIP docstring test output for model classes, adjust optuna tuning

JanTeichertKluge · JanTeichertKluge · commit e283e85e6415 · 2025-11-13T18:13:16.000+01:00
diff --git a/doubleml/did/did.py b/doubleml/did/did.py
@@ -71,7 +71,7 @@ class DoubleMLDID(LinearScoreMixin, DoubleML):
     >>> data = make_did_SZ2020(n_obs=500, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLDIDData(data, 'y', 'd')
     >>> dml_did_obj = dml.DoubleMLDID(obj_dml_data, ml_g, ml_m)
-    >>> dml_did_obj.fit().summary
+    >>> dml_did_obj.fit().summary # doctest: +SKIP
            coef   std err         t     P>|t|     2.5 %    97.5 %
     d -2.840718  1.760386 -1.613691  0.106595 -6.291011  0.609575
 
diff --git a/doubleml/did/did_cs.py b/doubleml/did/did_cs.py
@@ -70,7 +70,7 @@ class DoubleMLDIDCS(LinearScoreMixin, DoubleML):
     >>> data = make_did_SZ2020(n_obs=500, cross_sectional_data=True, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLDIDData(data, 'y', 'd', t_col='t')
     >>> dml_did_obj = dml.DoubleMLDIDCS(obj_dml_data, ml_g, ml_m)
-    >>> dml_did_obj.fit().summary
+    >>> dml_did_obj.fit().summary # doctest: +SKIP
          coef   std err         t     P>|t|      2.5 %    97.5 %
     d -4.9944  7.561785 -0.660479  0.508947 -19.815226  9.826426
     """
diff --git a/doubleml/did/did_multi.py b/doubleml/did/did_multi.py
@@ -140,7 +140,7 @@ class DoubleMLDIDMulti:
     ...     gt_combinations="standard",
     ...     control_group="never_treated",
     ... )
-    >>> print(dml_did_obj.fit().summary)
+    >>> print(dml_did_obj.fit().summary) # doctest: +SKIP
                                       coef   std err  ...     2.5 %    97.5 %
     ATT(2025-03,2025-01,2025-02) -0.797617  0.459617  ... -1.698450  0.103215
     ATT(2025-03,2025-02,2025-03)  0.270311  0.456453  ... -0.624320  1.164941
diff --git a/doubleml/double_ml.py b/doubleml/double_ml.py
@@ -14,7 +14,7 @@
 from doubleml.utils._checks import _check_external_predictions
 from doubleml.utils._estimation import _aggregate_coefs_and_ses, _rmse, _set_external_predictions, _var_est
 from doubleml.utils._sensitivity import _compute_sensitivity_bias
-from doubleml.utils._tune_optuna import OPTUNA_GLOBAL_SETTING_KEYS, _join_param_spaces, resolve_optuna_cv
+from doubleml.utils._tune_optuna import OPTUNA_GLOBAL_SETTING_KEYS, resolve_optuna_cv
 from doubleml.utils.gain_statistics import gain_statistics
 
 _implemented_data_backends = ["DoubleMLData", "DoubleMLClusterData", "DoubleMLDIDData", "DoubleMLSSMData", "DoubleMLRDDData"]
@@ -1236,10 +1236,7 @@ def _validate_optuna_param_space(self, ml_param_space):
                 final_param_space[param_key] = ml_param_space[learner_name]
         # Override if param_name specific space is provided
         for param_key in [pk for pk in self.params_names if pk in ml_param_space.keys()]:
-            if final_param_space[param_key] is None:
-                final_param_space[param_key] = ml_param_space[param_key]
-            else:
-                final_param_space[param_key] = _join_param_spaces(final_param_space[param_key], ml_param_space[param_key])
+            final_param_space[param_key] = ml_param_space[param_key]
 
         return requested_learners, final_param_space
 
diff --git a/doubleml/irm/cvar.py b/doubleml/irm/cvar.py
@@ -98,7 +98,7 @@ class DoubleMLCVAR(LinearScoreMixin, DoubleML):
     >>> data = make_irm_data(theta=0.5, n_obs=500, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd')
     >>> dml_cvar_obj = dml.DoubleMLCVAR(obj_dml_data, ml_g, ml_m, treatment=1, quantile=0.5)
-    >>> dml_cvar_obj.fit().summary
+    >>> dml_cvar_obj.fit().summary # doctest: +SKIP
            coef   std err         t         P>|t|     2.5 %    97.5 %
     d  1.588364  0.096616  16.43989  9.909942e-61  1.398999  1.777728
 
diff --git a/doubleml/irm/iivm.py b/doubleml/irm/iivm.py
@@ -96,7 +96,7 @@ class DoubleMLIIVM(LinearScoreMixin, DoubleML):
     >>> data = make_iivm_data(theta=0.5, n_obs=1000, dim_x=20, alpha_x=1.0, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd', z_cols='z')
     >>> dml_iivm_obj = dml.DoubleMLIIVM(obj_dml_data, ml_g, ml_m, ml_r)
-    >>> dml_iivm_obj.fit().summary
+    >>> dml_iivm_obj.fit().summary # doctest: +SKIP
            coef   std err         t     P>|t|     2.5 %    97.5 %
     d  0.362398  0.191578  1.891649  0.058538 -0.013088  0.737884
 
diff --git a/doubleml/irm/irm.py b/doubleml/irm/irm.py
@@ -97,7 +97,7 @@ class DoubleMLIRM(LinearScoreMixin, DoubleML):
     >>> data = make_irm_data(theta=0.5, n_obs=500, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd')
     >>> dml_irm_obj = dml.DoubleMLIRM(obj_dml_data, ml_g, ml_m)
-    >>> dml_irm_obj.fit().summary
+    >>> dml_irm_obj.fit().summary # doctest: +SKIP
            coef   std err         t     P>|t|     2.5 %    97.5 %
     d  0.371972  0.206802  1.798685  0.072069 -0.033353  0.777297
 
diff --git a/doubleml/irm/lpq.py b/doubleml/irm/lpq.py
@@ -100,7 +100,7 @@ class DoubleMLLPQ(NonLinearScoreMixin, DoubleML):
     >>> data = make_iivm_data(theta=0.5, n_obs=1000, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd', z_cols='z')
     >>> dml_lpq_obj = dml.DoubleMLLPQ(obj_dml_data, ml_g, ml_m, treatment=1, quantile=0.5)
-    >>> dml_lpq_obj.fit().summary
+    >>> dml_lpq_obj.fit().summary # doctest: +SKIP
            coef   std err         t    P>|t|    2.5 %    97.5 %
     d  0.217244  0.636453  0.341336  0.73285 -1.03018  1.464668
     """
diff --git a/doubleml/irm/pq.py b/doubleml/irm/pq.py
@@ -106,7 +106,7 @@ class DoubleMLPQ(NonLinearScoreMixin, DoubleML):
     >>> data = make_irm_data(theta=0.5, n_obs=500, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd')
     >>> dml_pq_obj = dml.DoubleMLPQ(obj_dml_data, ml_g, ml_m, treatment=1, quantile=0.5)
-    >>> dml_pq_obj.fit().summary
+    >>> dml_pq_obj.fit().summary # doctest: +SKIP
            coef   std err         t     P>|t|     2.5 %    97.5 %
     d  0.553878  0.149858  3.696011  0.000219  0.260161  0.847595
     """
diff --git a/doubleml/irm/qte.py b/doubleml/irm/qte.py
@@ -88,7 +88,7 @@ class DoubleMLQTE(SampleSplittingMixin):
     >>> data = make_irm_data(theta=0.5, n_obs=500, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd')
     >>> dml_qte_obj = dml.DoubleMLQTE(obj_dml_data, ml_g, ml_m, quantiles=[0.25, 0.5, 0.75])
-    >>> dml_qte_obj.fit().summary
+    >>> dml_qte_obj.fit().summary # doctest: +SKIP
               coef   std err         t     P>|t|     2.5 %    97.5 %
     0.25  0.274825  0.347310  0.791297  0.428771 -0.405890  0.955541
     0.50  0.449150  0.192539  2.332782  0.019660  0.071782  0.826519
diff --git a/doubleml/plm/pliv.py b/doubleml/plm/pliv.py
@@ -74,7 +74,7 @@ class DoubleMLPLIV(LinearScoreMixin, DoubleML):
     >>> data = make_pliv_CHS2015(alpha=0.5, n_obs=500, dim_x=20, dim_z=1, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd', z_cols='Z1')
     >>> dml_pliv_obj = dml.DoubleMLPLIV(obj_dml_data, ml_l, ml_m, ml_r)
-    >>> dml_pliv_obj.fit().summary
+    >>> dml_pliv_obj.fit().summary # doctest: +SKIP
            coef   std err         t         P>|t|     2.5 %  97.5 %
     d  0.511722  0.087184  5.869427  4.373034e-09  0.340844  0.6826
 
diff --git a/doubleml/plm/plr.py b/doubleml/plm/plr.py
@@ -69,7 +69,7 @@ class DoubleMLPLR(LinearScoreMixin, DoubleML):
     >>> ml_m = RandomForestRegressor(n_estimators=100, max_features=20, max_depth=5, min_samples_leaf=2)
     >>> obj_dml_data = make_plr_CCDDHNR2018(alpha=0.5, n_obs=500, dim_x=20)
     >>> dml_plr_obj = dml.DoubleMLPLR(obj_dml_data, ml_g, ml_m)
-    >>> dml_plr_obj.fit().summary
+    >>> dml_plr_obj.fit().summary # doctest: +SKIP
            coef   std err          t         P>|t|     2.5 %    97.5 %
     d  0.480691  0.040533  11.859129  1.929729e-32  0.401247  0.560135
 
diff --git a/doubleml/utils/_tune_optuna.py b/doubleml/utils/_tune_optuna.py
@@ -478,6 +478,7 @@ def _dml_tune_optuna(
             best_estimator=estimator,
             best_params=best_params,
             best_score=np.nan,
+            scoring_method=scoring_method,
             study=None,
             tuned=False,
         )
@@ -537,38 +538,3 @@ def _dml_tune_optuna(
         study=study,
         tuned=True,
     )
-
-
-def _join_param_spaces(param_space_global, param_space_local):
-    if param_space_global is None:
-        return param_space_local
-    if param_space_local is None:
-        return param_space_global
-
-    def joined_param_space(trial):
-        local_params = param_space_local(trial)
-
-        class _ProxyTrial:
-            def __init__(self, base_trial, overrides):
-                self._base_trial = base_trial
-                self._overrides = overrides
-
-            def __getattr__(self, name):
-                attr = getattr(self._base_trial, name)
-                if not callable(attr) or not name.startswith("suggest_"):
-                    return attr
-
-                def wrapped(*args, **kwargs):
-                    key = args[0] if args else kwargs.get("name")
-                    if key in self._overrides:
-                        return self._overrides[key]
-                    return attr(*args, **kwargs)
-
-                return wrapped
-
-        proxy_trial = _ProxyTrial(trial, local_params)
-        global_params = param_space_global(proxy_trial)
-
-        return {**global_params, **local_params}
-
-    return joined_param_space
