MNT deprecate outputs_2d_ attribute of dummy estimators (#14933)

doc/whats_new/v0.22.rst

@@ -139,12 +139,16 @@ Changelog
   `Adrin Jalali`_.
 
 :mod:`sklearn.dummy`
-............................
+....................
 
 - |Fix| :class:`dummy.DummyClassifier` now handles checking the existence
   of the provided constant in multiouput cases.
   :pr:`14908` by :user:`Martina G. Vilas <martinagvilas>`.
 
+- |API| The ``outputs_2d_`` attribute is deprecated in
+  :class:`dummy.DummyClassifier` and :class:`dummy.DummyRegressor`. It is
+  equivalent to ``n_outputs > 1``. :pr:`14933` by `Nicolas Hug`_
+
 :mod:`sklearn.ensemble`
 .......................
 

sklearn/dummy.py

@@ -17,6 +17,7 @@
 from .utils.random import random_choice_csc
 from .utils.stats import _weighted_percentile
 from .utils.multiclass import class_distribution
+from .utils import deprecated
 
 
 class DummyClassifier(MultiOutputMixin, ClassifierMixin, BaseEstimator):
@@ -120,8 +121,6 @@ def fit(self, X, y, sample_weight=None):
         if not self.sparse_output_:
             y = np.atleast_1d(y)
 
-        self.output_2d_ = y.ndim == 2 and y.shape[1] > 1
-
         if y.ndim == 1:
             y = np.reshape(y, (-1, 1))
 
@@ -154,7 +153,7 @@ def fit(self, X, y, sample_weight=None):
                                .format(self.constant, list(self.classes_[k])))
                     raise ValueError(err_msg)
 
-        if self.n_outputs_ == 1 and not self.output_2d_:
+        if self.n_outputs_ == 1:
             self.n_classes_ = self.n_classes_[0]
             self.classes_ = self.classes_[0]
             self.class_prior_ = self.class_prior_[0]
@@ -185,7 +184,7 @@ def predict(self, X):
         classes_ = self.classes_
         class_prior_ = self.class_prior_
         constant = self.constant
-        if self.n_outputs_ == 1 and not self.output_2d_:
+        if self.n_outputs_ == 1:
             # Get same type even for self.n_outputs_ == 1
             n_classes_ = [n_classes_]
             classes_ = [classes_]
@@ -194,7 +193,7 @@ def predict(self, X):
         # Compute probability only once
         if self.strategy == "stratified":
             proba = self.predict_proba(X)
-            if self.n_outputs_ == 1 and not self.output_2d_:
+            if self.n_outputs_ == 1:
                 proba = [proba]
 
         if self.sparse_output_:
@@ -231,7 +230,7 @@ def predict(self, X):
             elif self.strategy == "constant":
                 y = np.tile(self.constant, (n_samples, 1))
 
-            if self.n_outputs_ == 1 and not self.output_2d_:
+            if self.n_outputs_ == 1:
                 y = np.ravel(y)
 
         return y
@@ -263,7 +262,7 @@ def predict_proba(self, X):
         classes_ = self.classes_
         class_prior_ = self.class_prior_
         constant = self.constant
-        if self.n_outputs_ == 1 and not self.output_2d_:
+        if self.n_outputs_ == 1:
             # Get same type even for self.n_outputs_ == 1
             n_classes_ = [n_classes_]
             classes_ = [classes_]
@@ -294,7 +293,7 @@ def predict_proba(self, X):
 
             P.append(out)
 
-        if self.n_outputs_ == 1 and not self.output_2d_:
+        if self.n_outputs_ == 1:
             P = P[0]
 
         return P
@@ -355,6 +354,15 @@ def score(self, X, y, sample_weight=None):
             X = np.zeros(shape=(len(y), 1))
         return super().score(X, y, sample_weight)
 
+    @deprecated(
+        "The outputs_2d_ attribute is deprecated in version 0.22 "
+        "and will be removed in version 0.24. It is equivalent to "
+        "n_outputs_ > 1."
+    )
+    @property
+    def outputs_2d_(self):
+        return self.n_outputs_ != 1
+
 
 class DummyRegressor(MultiOutputMixin, RegressorMixin, BaseEstimator):
     """
@@ -429,8 +437,6 @@ def fit(self, X, y, sample_weight=None):
         if len(y) == 0:
             raise ValueError("y must not be empty.")
 
-        self.output_2d_ = y.ndim == 2 and y.shape[1] > 1
-
         if y.ndim == 1:
             y = np.reshape(y, (-1, 1))
         self.n_outputs_ = y.shape[1]
@@ -470,7 +476,7 @@ def fit(self, X, y, sample_weight=None):
                                         accept_sparse=['csr', 'csc', 'coo'],
                                         ensure_2d=False, ensure_min_samples=0)
 
-            if self.output_2d_ and self.constant.shape[0] != y.shape[1]:
+            if self.n_outputs_ != 1 and self.constant.shape[0] != y.shape[1]:
                 raise ValueError(
                     "Constant target value should have "
                     "shape (%d, 1)." % y.shape[1])
@@ -508,7 +514,7 @@ def predict(self, X, return_std=False):
                     dtype=np.array(self.constant_).dtype)
         y_std = np.zeros((n_samples, self.n_outputs_))
 
-        if self.n_outputs_ == 1 and not self.output_2d_:
+        if self.n_outputs_ == 1:
             y = np.ravel(y)
             y_std = np.ravel(y_std)
 
@@ -554,3 +560,12 @@ def score(self, X, y, sample_weight=None):
         if X is None:
             X = np.zeros(shape=(len(y), 1))
         return super().score(X, y, sample_weight)
+
+    @deprecated(
+        "The outputs_2d_ attribute is deprecated in version 0.22 "
+        "and will be removed in version 0.24. It is equivalent to "
+        "n_outputs_ > 1."
+    )
+    @property
+    def outputs_2d_(self):
+        return self.n_outputs_ != 1

sklearn/tests/test_dummy.py

@@ -755,3 +755,12 @@ def test_dtype_of_classifier_probas(strategy):
     probas = model.fit(X, y).predict_proba(X)
 
     assert probas.dtype == np.float64
+
+
+@pytest.mark.parametrize("Dummy", (DummyRegressor, DummyClassifier))
+def test_outputs_2d_deprecation(Dummy):
+    X = [[1, 2]]
+    y = [0]
+    with pytest.warns(DeprecationWarning,
+                      match="will be removed in version 0.24"):
+        Dummy().fit(X, y).outputs_2d_