Fix: Inaccurate Attribute Listing with dir(obj) (scikit-learn#28558)

Inaccurate Attribute Listing with dir(obj) in classes with conditional methods, I overwrote the python method _dir_ in all the classes that contain conditional methods

sklearn/ensemble/_bagging.py

@@ -833,6 +833,9 @@ def __init__(
             verbose=verbose,
         )
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _get_estimator(self):
         """Resolve which estimator to return (default is DecisionTreeClassifier)"""
         return self.estimator or DecisionTreeClassifier()

sklearn/ensemble/_stacking.py

@@ -597,6 +597,9 @@ def __init__(
             verbose=verbose,
         )
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _validate_final_estimator(self):
         self._clone_final_estimator(default=LogisticRegression())
         if not is_classifier(self.final_estimator_):

sklearn/ensemble/_voting.py

@@ -352,6 +352,9 @@ def __init__(
         self.flatten_transform = flatten_transform
         self.verbose = verbose
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @_fit_context(
         # estimators in VotingClassifier.estimators are not validated yet
         prefer_skip_nested_validation=False

sklearn/feature_selection/_from_model.py

@@ -270,6 +270,9 @@ def __init__(
         self.norm_order = norm_order
         self.max_features = max_features
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _get_support_mask(self):
         estimator = getattr(self, "estimator_", self.estimator)
         max_features = getattr(self, "max_features_", self.max_features)

sklearn/feature_selection/_rfe.py

@@ -225,6 +225,9 @@ def __init__(
         self.importance_getter = importance_getter
         self.verbose = verbose
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @property
     def _estimator_type(self):
         return self.estimator._estimator_type

sklearn/linear_model/_stochastic_gradient.py

@@ -1273,6 +1273,9 @@ def __init__(
             average=average,
         )
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _check_proba(self):
         if self.loss not in ("log_loss", "modified_huber"):
             raise AttributeError(

sklearn/model_selection/_search.py

@@ -431,6 +431,9 @@ def __init__(
     def _estimator_type(self):
         return self.estimator._estimator_type
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _more_tags(self):
         # allows cross-validation to see 'precomputed' metrics
         return {

sklearn/multiclass.py

@@ -321,6 +321,9 @@ def __init__(self, estimator, *, n_jobs=None, verbose=0):
         self.n_jobs = n_jobs
         self.verbose = verbose
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @_fit_context(
         # OneVsRestClassifier.estimator is not validated yet
         prefer_skip_nested_validation=False
@@ -752,6 +755,9 @@ def __init__(self, estimator, *, n_jobs=None):
         self.estimator = estimator
         self.n_jobs = n_jobs
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @_fit_context(
         # OneVsOneClassifier.estimator is not validated yet
         prefer_skip_nested_validation=False
@@ -1141,6 +1147,9 @@ def __init__(self, estimator, *, code_size=1.5, random_state=None, n_jobs=None):
         self.random_state = random_state
         self.n_jobs = n_jobs
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @_fit_context(
         # OutputCodeClassifier.estimator is not validated yet
         prefer_skip_nested_validation=False

sklearn/multioutput.py

@@ -409,6 +409,10 @@ class MultiOutputRegressor(RegressorMixin, _MultiOutputEstimator):
     def __init__(self, estimator, *, n_jobs=None):
         super().__init__(estimator, n_jobs=n_jobs)
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
+
     @_available_if_estimator_has("partial_fit")
     def partial_fit(self, X, y, sample_weight=None, **partial_fit_params):
         """Incrementally fit the model to data, for each output variable.

sklearn/neighbors/_lof.py

@@ -218,6 +218,9 @@ def __init__(
         self.contamination = contamination
         self.novelty = novelty
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _check_novelty_fit_predict(self):
         if self.novelty:
             msg = (

sklearn/neural_network/_multilayer_perceptron.py

@@ -150,6 +150,9 @@ def __init__(
         self.n_iter_no_change = n_iter_no_change
         self.max_fun = max_fun
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _unpack(self, packed_parameters):
         """Extract the coefficients and intercepts from packed_parameters."""
         for i in range(self.n_layers_ - 1):

sklearn/pipeline.py

@@ -2,6 +2,7 @@
 The :mod:`sklearn.pipeline` module implements utilities to build a composite
 estimator, as a chain of transforms and estimators.
 """
+
 # Author: Edouard Duchesnay
 #         Gael Varoquaux
 #         Virgile Fritsch
@@ -170,6 +171,9 @@ def __init__(self, steps, *, memory=None, verbose=False):
         self.memory = memory
         self.verbose = verbose
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def set_output(self, *, transform=None):
         """Set the output container when `"transform"` and `"fit_transform"` are called.
 

sklearn/preprocessing/_function_transformer.py

@@ -185,6 +185,9 @@ def __init__(
         self.kw_args = kw_args
         self.inv_kw_args = inv_kw_args
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _check_input(self, X, *, reset):
         if self.validate:
             return self._validate_data(X, accept_sparse=self.accept_sparse, reset=reset)

sklearn/semi_supervised/_self_training.py

@@ -184,6 +184,9 @@ def __init__(
         self.max_iter = max_iter
         self.verbose = verbose
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     @_fit_context(
         # SelfTrainingClassifier.base_estimator is not validated yet
         prefer_skip_nested_validation=False

sklearn/svm/_base.py

@@ -734,6 +734,9 @@ def __init__(
             random_state=random_state,
         )
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def _validate_targets(self, y):
         y_ = column_or_1d(y, warn=True)
         check_classification_targets(y)

sklearn/utils/_mocking.py

@@ -383,6 +383,9 @@ class _MockEstimatorOnOffPrediction(BaseEstimator):
     def __init__(self, response_methods=None):
         self.response_methods = response_methods
 
+    def __dir__(self):
+        return [attr for attr in super().__dir__() if hasattr(self, attr)]
+
     def fit(self, X, y):
         self.classes_ = np.unique(y)
         return self