DEPR: Add deprecation warning for factorize() order keyword (pandas-dev#19751)

Author: EricChea

doc/source/whatsnew/v0.23.0.txt

@@ -610,6 +610,7 @@ Deprecations
 
 - The ``broadcast`` parameter of ``.apply()`` is deprecated in favor of ``result_type='broadcast'`` (:issue:`18577`)
 - The ``reduce`` parameter of ``.apply()`` is deprecated in favor of ``result_type='reduce'`` (:issue:`18577`)
+- The ``order`` parameter of :func:`factorize` is deprecated and will be removed in a future release (:issue:`19727`)
 
 .. _whatsnew_0230.prior_deprecations:
 

pandas/core/algorithms.py

@@ -32,6 +32,7 @@
 from pandas.core import common as com
 from pandas._libs import algos, lib, hashtable as htable
 from pandas._libs.tslib import iNaT
+from pandas.util._decorators import deprecate_kwarg
 
 
 # --------------- #
@@ -436,6 +437,7 @@ def isin(comps, values):
     return f(comps, values)
 
 
+@deprecate_kwarg(old_arg_name='order', new_arg_name=None)
 def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
     """
     Encode input values as an enumerated type or categorical variable

pandas/tests/test_algos.py

@@ -248,6 +248,15 @@ def test_uint64_factorize(self):
         tm.assert_numpy_array_equal(labels, exp_labels)
         tm.assert_numpy_array_equal(uniques, exp_uniques)
 
+    def test_deprecate_order(self):
+        # gh 19727 - check warning is raised for deprecated keyword, order.
+        # Test not valid once order keyword is removed.
+        data = np.array([2**63, 1, 2**63], dtype=np.uint64)
+        with tm.assert_produces_warning(expected_warning=FutureWarning):
+            algos.factorize(data, order=True)
+        with tm.assert_produces_warning(False):
+            algos.factorize(data)
+
 
 class TestUnique(object):
 

pandas/tests/util/test_util.py

@@ -34,9 +34,14 @@ def _f2(new=False):
         def _f3(new=0):
             return new
 
+        @deprecate_kwarg('old', None)
+        def _f4(old=True, unchanged=True):
+            return old
+
         self.f1 = _f1
         self.f2 = _f2
         self.f3 = _f3
+        self.f4 = _f4
 
     def test_deprecate_kwarg(self):
         x = 78
@@ -72,6 +77,15 @@ def test_bad_deprecate_kwarg(self):
             def f4(new=None):
                 pass
 
+    def test_deprecate_keyword(self):
+        x = 9
+        with tm.assert_produces_warning(FutureWarning):
+            result = self.f4(old=x)
+        assert result is x
+        with tm.assert_produces_warning(None):
+            result = self.f4(unchanged=x)
+        assert result is True
+
 
 def test_rands():
     r = tm.rands(10)

pandas/util/_decorators.py

@@ -65,8 +65,9 @@ def deprecate_kwarg(old_arg_name, new_arg_name, mapping=None, stacklevel=2):
     ----------
     old_arg_name : str
         Name of argument in function to deprecate
-    new_arg_name : str
-        Name of preferred argument in function
+    new_arg_name : str or None
+        Name of preferred argument in function. Use None to raise warning that
+        ``old_arg_name`` keyword is deprecated.
     mapping : dict or callable
         If mapping is present, use it to translate old arguments to
         new arguments. A callable must do its own value checking;
@@ -82,12 +83,15 @@ def deprecate_kwarg(old_arg_name, new_arg_name, mapping=None, stacklevel=2):
     ...
     >>> f(columns='should work ok')
     should work ok
+
     >>> f(cols='should raise warning')
     FutureWarning: cols is deprecated, use columns instead
       warnings.warn(msg, FutureWarning)
     should raise warning
+
     >>> f(cols='should error', columns="can\'t pass do both")
     TypeError: Can only specify 'cols' or 'columns', not both
+
     >>> @deprecate_kwarg('old', 'new', {'yes': True, 'no': False})
     ... def f(new=False):
     ...     print('yes!' if new else 'no!')
@@ -96,6 +100,25 @@ def deprecate_kwarg(old_arg_name, new_arg_name, mapping=None, stacklevel=2):
     FutureWarning: old='yes' is deprecated, use new=True instead
       warnings.warn(msg, FutureWarning)
     yes!
+
+
+    To raise a warning that a keyword will be removed entirely in the future
+
+    >>> @deprecate_kwarg(old_arg_name='cols', new_arg_name=None)
+    ... def f(cols='', another_param=''):
+    ...     print(cols)
+    ...
+    >>> f(cols='should raise warning')
+    FutureWarning: the 'cols' keyword is deprecated and will be removed in a
+    future version please takes steps to stop use of 'cols'
+    should raise warning
+    >>> f(another_param='should not raise warning')
+    should not raise warning
+
+    >>> f(cols='should raise warning', another_param='')
+    FutureWarning: the 'cols' keyword is deprecated and will be removed in a
+    future version please takes steps to stop use of 'cols'
+    should raise warning
     """
 
     if mapping is not None and not hasattr(mapping, 'get') and \
@@ -107,6 +130,17 @@ def _deprecate_kwarg(func):
         @wraps(func)
         def wrapper(*args, **kwargs):
             old_arg_value = kwargs.pop(old_arg_name, None)
+
+            if new_arg_name is None and old_arg_value is not None:
+                msg = (
+                    "the '{old_name}' keyword is deprecated and will be "
+                    "removed in a future version "
+                    "please takes steps to stop use of '{old_name}'"
+                ).format(old_name=old_arg_name)
+                warnings.warn(msg, FutureWarning, stacklevel=stacklevel)
+                kwargs[old_arg_name] = old_arg_value
+                return func(*args, **kwargs)
+
             if old_arg_value is not None:
                 if mapping is not None:
                     if hasattr(mapping, 'get'):