FIX OneHotEncoder.fit no longer alters the drop parameter (scikit-lea…

…rn#19924)

doc/whats_new/v0.24.rst

@@ -62,6 +62,9 @@ Changelog
 - |Fix| :meth:`preprocessing.OrdinalEncoder.transfrom` correctly handles
   unknown values for string dtypes. :pr:`19888` by `Thomas Fan`_.
 
+- |Fix| :meth:`preprocessing.OneHotEncoder.fit` no longer alters the `drop`
+  parameter. :pr:`19924` by `Thomas Fan`_.
+
 :mod:`sklearn.multioutput`
 ..........................
 

doc/whats_new/v1.0.rst

@@ -105,7 +105,7 @@ Changelog
 - |Fix| Improved convergence detection based on center change in
   :class:`cluster.MiniBatchKMeans` which was almost never achievable.
   :pr:`17622` by :user:`Jérémie du Boisberranger <jeremiedbb>`.
-  
+
 - |FIX| :class:`cluster.AgglomerativeClustering` now supports readonly
   memory-mapped datasets. :pr:`19883` by `Julien Jerphanion <jjerphan>`.
 

sklearn/preprocessing/_encoders.py

@@ -363,22 +363,21 @@ def _compute_drop_idx(self):
 
         else:
             try:
-                self.drop = np.asarray(self.drop, dtype=object)
-                droplen = len(self.drop)
+                drop_array = np.asarray(self.drop, dtype=object)
+                droplen = len(drop_array)
             except (ValueError, TypeError):
                 msg = (
                     "Wrong input for parameter `drop`. Expected "
                     "'first', 'if_binary', None or array of objects, got {}"
                     )
-                raise ValueError(msg.format(type(self.drop)))
+                raise ValueError(msg.format(type(drop_array)))
             if droplen != len(self.categories_):
                 msg = ("`drop` should have length equal to the number "
                        "of features ({}), got {}")
-                raise ValueError(msg.format(len(self.categories_),
-                                            len(self.drop)))
+                raise ValueError(msg.format(len(self.categories_), droplen))
             missing_drops = []
             drop_indices = []
-            for col_idx, (val, cat_list) in enumerate(zip(self.drop,
+            for col_idx, (val, cat_list) in enumerate(zip(drop_array,
                                                           self.categories_)):
                 if not is_scalar_nan(val):
                     drop_idx = np.where(cat_list == val)[0]

sklearn/preprocessing/tests/test_encoders.py

@@ -748,6 +748,8 @@ def test_one_hot_encoder_drop_manual(missing_value):
            [0, 1, 0, 1, 1],
            [0, 0, 0, 0, 0]]
     assert_array_equal(trans, exp)
+    assert enc.drop is cats_to_drop
+
     dropped_cats = [cat[feature]
                     for cat, feature in zip(enc.categories_,
                                             enc.drop_idx_)]