[MRG+2] FIX DummyEstimator and a single output 2d input list/array

doc/whats_new/v0.21.rst

@@ -146,6 +146,10 @@ Support for Python 3.4 and below has been officially dropped.
   float64 for the ``stratified`` strategy. :issue:`13266` by
   :user:`Christos Aridas<chkoar>`.
 
+- |Fix| Fixed a bug in :class:`dummy.DummyClassifier` where 1d dimensional y
+  with ndim=2 was throwing a dimension mismatch error in prediction time.
+  :issue:`10786` by :user:`Nick Sorros <nsorros>` and `Adrin Jalali`_.
+
 :mod:`sklearn.ensemble`
 .......................
 

sklearn/dummy.py

@@ -120,7 +120,8 @@ def fit(self, X, y, sample_weight=None):
         if not self.sparse_output_:
             y = np.atleast_1d(y)
 
-        self.output_2d_ = y.ndim == 2
+        self.output_2d_ = y.ndim == 2 and y.shape[1] > 1
+
         if y.ndim == 1:
             y = np.reshape(y, (-1, 1))
 
@@ -425,7 +426,8 @@ 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
+        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]

sklearn/tests/test_dummy.py

@@ -102,6 +102,22 @@ def test_most_frequent_and_prior_strategy():
                                       clf.class_prior_.reshape((1, -1)) > 0.5)
 
 
+def test_most_frequent_and_prior_strategy_with_2d_column_y():
+    # non-regression test added in
+    # https://github.com/scikit-learn/scikit-learn/pull/13545
+    X = [[0], [0], [0], [0]]
+    y_1d = [1, 2, 1, 1]
+    y_2d = [[1], [2], [1], [1]]
+
+    for strategy in ("most_frequent", "prior"):
+        clf_1d = DummyClassifier(strategy=strategy, random_state=0)
+        clf_2d = DummyClassifier(strategy=strategy, random_state=0)
+
+        clf_1d.fit(X, y_1d)
+        clf_2d.fit(X, y_2d)
+        assert_array_equal(clf_1d.predict(X), clf_2d.predict(X))
+
+
 def test_most_frequent_and_prior_strategy_multioutput():
     X = [[0], [0], [0], [0]]  # ignored
     y = np.array([[1, 0],