BUG: fixed wrong order of ordered labels in pd.cut()

closes #16459 Author: economy <the.economy@gmail.com> This patch had conflicts when merged, resolved by Committer: Jeff Reback <jeff.reback@twosigma.com> Closes #16466 from economy/fix_cut and squashes the following commits: 29128b3 [economy] comments and whatsnew edits 3898b72 [economy] BUG: fixed wrong order of ordered labels in pd.cut()

Author: economy

doc/source/whatsnew/v0.20.2.txt

@@ -46,11 +46,9 @@ Bug Fixes
 - Passing an invalid engine to :func:`read_csv` now raises an informative
  ``ValueError`` rather than ``UnboundLocalError``. (:issue:`16511`)
 - Bug in :func:`unique` on an array of tuples (:issue:`16519`)
-
-
+- Bug in :func:`cut`` when ``labels`` are set, resulting in incorrect label ordering (:issue:`16459`)
 - Fixed a compatibility issue with IPython 6.0's tab completion showing deprecation warnings on Categoricals (:issue:`16409`)
 
-
 Conversion
 ^^^^^^^^^^
 

pandas/core/reshape/tile.py

@@ -254,7 +254,7 @@ def _bins_to_cuts(x, bins, right=True, labels=None,
  raise ValueError('Bin labels must be one fewer than '
  'the number of bin edges')
  if not is_categorical_dtype(labels):
- labels = Categorical(labels, ordered=True)
+ labels = Categorical(labels, categories=labels, ordered=True)
 
  np.putmask(ids, na_mask, 0)
  result = algos.take_nd(labels, ids - 1)

pandas/tests/reshape/test_tile.py

@@ -211,6 +211,7 @@ def test_cut_pass_labels(self):
 
  result = cut(arr, bins, labels=labels)
  exp = Categorical(['Medium'] + 4 * ['Small'] + ['Medium', 'Large'],
+ categories=labels,
  ordered=True)
  tm.assert_categorical_equal(result, exp)
 
@@ -219,6 +220,13 @@ def test_cut_pass_labels(self):
  exp = Categorical.from_codes([1] + 4 * [0] + [1, 2], labels)
  tm.assert_categorical_equal(result, exp)
 
+# issue 16459
+ labels = ['Good', 'Medium', 'Bad']
+ result = cut(arr, 3, labels=labels)
+ exp = cut(arr, 3, labels=Categorical(labels, categories=labels,
+ ordered=True))
+ tm.assert_categorical_equal(result, exp)
+
  def test_qcut_include_lowest(self):
  values = np.arange(10)