ENH - Modify Dataframe.select_dtypes to accept scalar values

doc/source/basics.rst

@@ -2229,7 +2229,3 @@ All numpy dtypes are subclasses of ``numpy.generic``:
 
     Pandas also defines the types ``category``, and ``datetime64[ns, tz]``, which are not integrated into the normal
     numpy hierarchy and wont show up with the above function.
-
-.. note::
-
-   The ``include`` and ``exclude`` parameters must be non-string sequences.

doc/source/style.ipynb

@@ -935,7 +935,7 @@
     "\n",
     "<span style=\"color: red\">*Experimental: This is a new feature and still under development. We'll be adding features and possibly making breaking changes in future releases. We'd love to hear your feedback.*</span>\n",
     "\n",
-    "Some support is available for exporting styled `DataFrames` to Excel worksheets using the `OpenPyXL` engine. CSS2.2 properties handled include:\n",
+    "Some support is available for exporting styled `DataFrames` to Excel worksheets using the `OpenPyXL` engine. CSS2.2 properties handled include:\n",
     "\n",
     "- `background-color`\n",
     "- `border-style`, `border-width`, `border-color` and their {`top`, `right`, `bottom`, `left` variants}\n",

doc/source/whatsnew/v0.21.0.txt

@@ -39,6 +39,7 @@ Other Enhancements
 - :func:`read_feather` has gained the ``nthreads`` parameter for multi-threaded operations (:issue:`16359`)
 - :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
+- :func:`Dataframe.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
 
 .. _whatsnew_0210.api_breaking:
 

pandas/core/frame.py

@@ -2285,18 +2285,16 @@ def select_dtypes(self, include=None, exclude=None):
 
         Parameters
         ----------
-        include, exclude : list-like
-            A list of dtypes or strings to be included/excluded. You must pass
-            in a non-empty sequence for at least one of these.
+        include, exclude : scalar or list-like
+            A selection of dtypes or strings to be included/excluded. At least
+            one of these parameters must be supplied.
 
         Raises
         ------
         ValueError
             * If both of ``include`` and ``exclude`` are empty
             * If ``include`` and ``exclude`` have overlapping elements
             * If any kind of string dtype is passed in.
-        TypeError
-            * If either of ``include`` or ``exclude`` is not a sequence
 
         Returns
         -------
@@ -2348,10 +2346,15 @@ def select_dtypes(self, include=None, exclude=None):
         4   True
         5  False
         """
-        include, exclude = include or (), exclude or ()
-        if not (is_list_like(include) and is_list_like(exclude)):
-            raise TypeError('include and exclude must both be non-string'
-                            ' sequences')
+
+        # GH16855 - If either include or exclude is a non-None scalar then
+        # convert to a tuple of length 1 and continue.
+        # This allows, for example, df.select_dtypes(include='object').
+        if not is_list_like(include):
+            include = (include,) if include is not None else ()
+        if not is_list_like(exclude):
+            exclude = (exclude,) if exclude is not None else ()
+
         selection = tuple(map(frozenset, (include, exclude)))
 
         if not any(selection):

pandas/tests/frame/test_dtypes.py

@@ -149,6 +149,10 @@ def test_select_dtypes_include(self):
         ei = df[['k']]
         assert_frame_equal(ri, ei)
 
+        ri = df.select_dtypes(include='category')
+        ei = df[['f']]
+        assert_frame_equal(ri, ei)
+
         pytest.raises(NotImplementedError,
                       lambda: df.select_dtypes(include=['period']))
 
@@ -162,6 +166,10 @@ def test_select_dtypes_exclude(self):
         ee = df[['a', 'e']]
         assert_frame_equal(re, ee)
 
+        re = df.select_dtypes(exclude=np.number)
+        ee = df[['a', 'e']]
+        assert_frame_equal(re, ee)
+
     def test_select_dtypes_exclude_include(self):
         df = DataFrame({'a': list('abc'),
                         'b': list(range(1, 4)),
@@ -181,6 +189,12 @@ def test_select_dtypes_exclude_include(self):
         e = df[['b', 'e']]
         assert_frame_equal(r, e)
 
+        exclude = 'datetime'
+        include = 'bool'
+        r = df.select_dtypes(include=include, exclude=exclude)
+        e = df[['e']]
+        assert_frame_equal(r, e)
+
     def test_select_dtypes_not_an_attr_but_still_valid_dtype(self):
         df = DataFrame({'a': list('abc'),
                         'b': list(range(1, 4)),
@@ -205,18 +219,6 @@ def test_select_dtypes_empty(self):
                                     'must be nonempty'):
             df.select_dtypes()
 
-    def test_select_dtypes_raises_on_string(self):
-        df = DataFrame({'a': list('abc'), 'b': list(range(1, 4))})
-        with tm.assert_raises_regex(TypeError, 'include and exclude '
-                                    '.+ non-'):
-            df.select_dtypes(include='object')
-        with tm.assert_raises_regex(TypeError, 'include and exclude '
-                                    '.+ non-'):
-            df.select_dtypes(exclude='object')
-        with tm.assert_raises_regex(TypeError, 'include and exclude '
-                                    '.+ non-'):
-            df.select_dtypes(include=int, exclude='object')
-
     def test_select_dtypes_bad_datetime64(self):
         df = DataFrame({'a': list('abc'),
                         'b': list(range(1, 4)),