BUG: Update added tests to use Categorical.from_codes. Update whats new lines. Updated docstrings (#33141)

Author: mabelvj

doc/source/whatsnew/v1.1.0.rst

@@ -91,6 +91,7 @@ Other enhancements
 - The :meth:`DataFrame.to_feather` method now supports additional keyword
   arguments (e.g. to set the compression) that are added in pyarrow 0.17
   (:issue:`33422`).
+- The :func:`cut` will now accept parameter ``ordered`` with default ``ordered=True``. If ``ordered=False`` and no labels are provided, an error will be raised.
 
 .. ---------------------------------------------------------------------------
 
@@ -540,8 +541,7 @@ Reshaping
 - Bug in :meth:`concat` where when passing a non-dict mapping as ``objs`` would raise a ``TypeError`` (:issue:`32863`)
 - :meth:`DataFrame.agg` now provides more descriptive ``SpecificationError`` message when attempting to aggregating non-existant column (:issue:`32755`)
 - Bug in :meth:`DataFrame.unstack` when MultiIndexed columns and MultiIndexed rows were used (:issue:`32624`, :issue:`24729` and :issue:`28306`)
-- Bug in :func:`cut` when non-unique labels used an error raised. Added input parameter ``ordered`` to :func:`cut` with default (``ordered=True``).
-  If ``ordered=False`` and no labels are provided, an error will be raised (:issue:33141`)
+- Bug in :func:`cut` raised an error when non-unique labels (:issue:`33141`)
 
 
 Sparse

pandas/core/reshape/tile.py

@@ -153,12 +153,13 @@ def cut(
     [bad, good, medium, medium, good, bad]
     Categories (3, object): [bad < medium < good]
 
-    ``ordered=False`` will result in unordered categories when labels are passed:
+    ``ordered=False`` will result in unordered categories when labels are passed.
+    This parameter can be used to allow non-unique labels:
 
-    >>> pd.cut(np.array([1, 7, 5, 4, 6, 3]),
-    ...        3, labels=["B", "C", "A"])
-    [B, A, C, C, A, B]
-    Categories (3, object): [B < C < A]
+    >>> pd.cut(np.array([1, 7, 5, 4, 6, 3]), 3,
+    ...        labels=["B", "A", "B"], ordered=False)
+    [B, B, A, A, B, B]
+    Categories (2, object): [A, B]
 
     ``labels=False`` implies you just want the bins back.
 

pandas/tests/reshape/test_cut.py

@@ -628,40 +628,38 @@ def test_cut_nullable_integer(bins, right, include_lowest):
 
 
 @pytest.mark.parametrize(
-    "data, bins, labels",
+    "data, bins, labels, expected_codes, expected_labels",
     [
-        ([15, 17, 19], [14, 16, 18, 20], ["A", "B", "A"]),
-        ([1, 3, 5], [0, 2, 4, 6, 8], [2, 0, 1, 2]),
+        ([15, 17, 19], [14, 16, 18, 20], ["A", "B", "A"], [0, 1, 0], ["A", "B"]),
+        ([1, 3, 5], [0, 2, 4, 6, 8], [2, 0, 1, 2], [2, 0, 1], [0, 1, 2]),
     ],
 )
-def test_cut_non_unique_labels(data, bins, labels):
+def test_cut_non_unique_labels(data, bins, labels, expected_codes, expected_labels):
+    # GH 33141
     result = cut(data, bins=bins, labels=labels, ordered=False)
-    expected = cut(
-        data, bins=bins, labels=Categorical(labels, ordered=False), ordered=False
+    expected = Categorical.from_codes(
+        expected_codes, categories=expected_labels, ordered=False
     )
     tm.assert_categorical_equal(result, expected)
 
 
 @pytest.mark.parametrize(
-    "data, bins, labels",
+    "data, bins, labels, expected_codes, expected_labels",
     [
-        ([15, 17, 19], [14, 16, 18, 20], ["C", "B", "A"]),
-        ([1, 3, 5], [0, 2, 4, 6, 8], [3, 0, 1, 2]),
+        ([15, 17, 19], [14, 16, 18, 20], ["C", "B", "A"], [0, 1, 2], ["C", "B", "A"]),
+        ([1, 3, 5], [0, 2, 4, 6, 8], [3, 0, 1, 2], [0, 1, 2], [3, 0, 1, 2]),
     ],
 )
-def test_cut_unordered_labels(data, bins, labels):
+def test_cut_unordered_labels(data, bins, labels, expected_codes, expected_labels):
+    # GH 33141
     result = cut(data, bins=bins, labels=labels, ordered=False)
-    expected = cut(
-        data,
-        bins=bins,
-        labels=Categorical(labels, categories=labels, ordered=False),
-        ordered=False,
+    expected = Categorical.from_codes(
+        expected_codes, categories=expected_labels, ordered=False
     )
     tm.assert_categorical_equal(result, expected)
 
 
-@pytest.mark.parametrize("data, bins,", [([0.5, 3], [0, 1, 2])])
-def test_cut_unordered_with_missing_labels_raises_error(data, bins):
+def test_cut_unordered_with_missing_labels_raises_error():
     msg = "'labels' must be provided if 'ordered = False'"
     with pytest.raises(ValueError, match=msg):
-        cut(data, bins=bins, ordered=False)
+        cut([0.5, 3], bins=[0, 1, 2], ordered=False)