DEPR: DataFrame.get_dtype_counts

doc/source/whatsnew/v0.25.0.rst

@@ -616,6 +616,7 @@ Other deprecations
 - :attr:`Series.imag` and :attr:`Series.real` are deprecated. (:issue:`18262`)
 - :meth:`Series.put` is deprecated. (:issue:`18262`)
 - :meth:`Index.item` and :meth:`Series.item` is deprecated. (:issue:`18262`)
+- :meth:`DataFrame.get_dtype_counts` is deprecated. (:issue:`18262`)
 
 .. _whatsnew_0250.prior_deprecations:
 

pandas/core/computation/expressions.py

@@ -79,11 +79,11 @@ def _can_use_numexpr(op, op_str, a, b, dtype_check):
             # check for dtype compatibility
             dtypes = set()
             for o in [a, b]:
-                if hasattr(o, 'get_dtype_counts'):
-                    s = o.get_dtype_counts()
+                if hasattr(o, '_data'):
+                    s = o._data.get_dtype_counts()
                     if len(s) > 1:
                         return False
-                    dtypes |= set(s.index)
+                    dtypes |= set(s.keys())
                 elif isinstance(o, np.ndarray):
                     dtypes |= {o.dtype.name}
 

pandas/core/frame.py

@@ -2325,7 +2325,7 @@ def _sizeof_fmt(num, size_qualifier):
             else:
                 _verbose_repr()
 
-        counts = self.get_dtype_counts()
+        counts = self._data.get_dtype_counts()
         dtypes = ['{k}({kk:d})'.format(k=k[0], kk=k[1]) for k
                   in sorted(counts.items())]
         lines.append('dtypes: {types}'.format(types=', '.join(dtypes)))

pandas/core/generic.py

@@ -5290,6 +5290,9 @@ def get_dtype_counts(self):
         object     1
         dtype: int64
         """
+        warnings.warn("`get_dtype_counts` has been deprecated and will be "
+                      "removed in a future version.", FutureWarning,
+                      stacklevel=2)
         from pandas import Series
         return Series(self._data.get_dtype_counts())
 

pandas/tests/frame/test_api.py

@@ -433,9 +433,10 @@ def test_with_datetimelikes(self):
                          'B': timedelta_range('1 day', periods=10)})
         t = df.T
 
-        result = t.get_dtype_counts()
+        #result = Series(t._data.get_dtype_counts())
+        result = t.dtypes.value_counts()
         if self.klass is DataFrame:
-            expected = Series({'object': 10})
+            expected = Series({np.dtype('object'): 10})
         else:
             expected = Series({'Sparse[object, nan]': 10})
         tm.assert_series_equal(result, expected)

pandas/tests/frame/test_arithmetic.py

@@ -273,8 +273,8 @@ def test_df_flex_cmp_constant_return_types(self, opname):
         df = pd.DataFrame({'x': [1, 2, 3], 'y': [1., 2., 3.]})
         const = 2
 
-        result = getattr(df, opname)(const).get_dtype_counts()
-        tm.assert_series_equal(result, pd.Series([2], ['bool']))
+        result = getattr(df, opname)(const).dtypes.value_counts()
+        tm.assert_series_equal(result, pd.Series([2], index=[np.dtype(bool)]))
 
     @pytest.mark.parametrize('opname', ['eq', 'ne', 'gt', 'lt', 'ge', 'le'])
     def test_df_flex_cmp_constant_return_types_empty(self, opname):
@@ -283,8 +283,8 @@ def test_df_flex_cmp_constant_return_types_empty(self, opname):
         const = 2
 
         empty = df.iloc[:0]
-        result = getattr(empty, opname)(const).get_dtype_counts()
-        tm.assert_series_equal(result, pd.Series([2], ['bool']))
+        result = getattr(empty, opname)(const).dtypes.value_counts()
+        tm.assert_series_equal(result, pd.Series([2], index=[np.dtype(bool)]))
 
 
 # -------------------------------------------------------------------

pandas/tests/frame/test_block_internals.py

@@ -217,19 +217,21 @@ def test_construction_with_mixed(self, float_string_frame):
         df = DataFrame(data)
 
         # check dtypes
-        result = df.get_dtype_counts().sort_values()
+        result = df.dtypes
         expected = Series({'datetime64[ns]': 3})
 
         # mixed-type frames
         float_string_frame['datetime'] = datetime.now()
         float_string_frame['timedelta'] = timedelta(days=1, seconds=1)
         assert float_string_frame['datetime'].dtype == 'M8[ns]'
         assert float_string_frame['timedelta'].dtype == 'm8[ns]'
-        result = float_string_frame.get_dtype_counts().sort_values()
-        expected = Series({'float64': 4,
-                           'object': 1,
-                           'datetime64[ns]': 1,
-                           'timedelta64[ns]': 1}).sort_values()
+        result = float_string_frame.dtypes
+        expected = Series([np.dtype('float64')] * 4 +
+                          [np.dtype('object'),
+                           np.dtype('datetime64[ns]'),
+                           np.dtype('timedelta64[ns]')],
+                          index=list('ABCD') + ['foo', 'datetime',
+                                                'timedelta'])
         assert_series_equal(result, expected)
 
     def test_construction_with_conversions(self):
@@ -409,11 +411,12 @@ def test_get_numeric_data(self):
         df = DataFrame({'a': 1., 'b': 2, 'c': 'foo',
                         'f': Timestamp('20010102')},
                        index=np.arange(10))
-        result = df.get_dtype_counts()
-        expected = Series({'int64': 1, 'float64': 1,
-                           datetime64name: 1, objectname: 1})
-        result = result.sort_index()
-        expected = expected.sort_index()
+        result = df.dtypes
+        expected = Series([np.dtype('float64'),
+                           np.dtype('int64'),
+                           np.dtype(objectname),
+                           np.dtype(datetime64name)],
+                          index=['a', 'b', 'c', 'f'])
         assert_series_equal(result, expected)
 
         df = DataFrame({'a': 1., 'b': 2, 'c': 'foo',

pandas/tests/frame/test_combine_concat.py

@@ -17,7 +17,7 @@ def test_concat_multiple_frames_dtypes(self):
         A = DataFrame(data=np.ones((10, 2)), columns=[
                       'foo', 'bar'], dtype=np.float64)
         B = DataFrame(data=np.ones((10, 2)), dtype=np.float32)
-        results = pd.concat((A, B), axis=1).get_dtype_counts()
+        results = Series(pd.concat((A, B), axis=1)._data.get_dtype_counts())
         expected = Series(dict(float64=2, float32=2))
         assert_series_equal(results, expected)
 

pandas/tests/frame/test_constructors.py

@@ -1579,7 +1579,7 @@ def test_constructor_with_datetimes(self):
                         'D': Timestamp("20010101"),
                         'E': datetime(2001, 1, 2, 0, 0)},
                        index=np.arange(10))
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 1, datetime64name: 2, objectname: 2})
         result.sort_index()
         expected.sort_index()
@@ -1591,7 +1591,7 @@ def test_constructor_with_datetimes(self):
                         floatname: np.array(1., dtype=floatname),
                         intname: np.array(1, dtype=intname)},
                        index=np.arange(10))
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = {objectname: 1}
         if intname == 'int64':
             expected['int64'] = 2
@@ -1613,7 +1613,7 @@ def test_constructor_with_datetimes(self):
                         floatname: np.array([1.] * 10, dtype=floatname),
                         intname: np.array([1] * 10, dtype=intname)},
                        index=np.arange(10))
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         result = result.sort_index()
         tm.assert_series_equal(result, expected)
 
@@ -1623,7 +1623,7 @@ def test_constructor_with_datetimes(self):
         datetime_s = Series(datetimes)
         assert datetime_s.dtype == 'M8[ns]'
         df = DataFrame({'datetime_s': datetime_s})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({datetime64name: 1})
         result = result.sort_index()
         expected = expected.sort_index()
@@ -1634,7 +1634,7 @@ def test_constructor_with_datetimes(self):
         datetimes = [ts.to_pydatetime() for ts in ind]
         dates = [ts.date() for ts in ind]
         df = DataFrame({'datetimes': datetimes, 'dates': dates})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({datetime64name: 1, objectname: 1})
         result = result.sort_index()
         expected = expected.sort_index()
@@ -1693,7 +1693,7 @@ def test_constructor_datetimes_with_nulls(self):
         for arr in [np.array([None, None, None, None,
                               datetime.now(), None]),
                     np.array([None, None, datetime.now(), None])]:
-            result = DataFrame(arr).get_dtype_counts()
+            result = Series(DataFrame(arr)._data.get_dtype_counts())
             expected = Series({'datetime64[ns]': 1})
             tm.assert_series_equal(result, expected)
 
@@ -1706,49 +1706,49 @@ def test_constructor_for_list_with_dtypes(self):
 
         # test list of lists/ndarrays
         df = DataFrame([np.arange(5) for x in range(5)])
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 5})
 
         df = DataFrame([np.array(np.arange(5), dtype='int32')
                         for x in range(5)])
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int32': 5})
 
         # overflow issue? (we always expecte int64 upcasting here)
         df = DataFrame({'a': [2 ** 31, 2 ** 31 + 1]})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 1})
         tm.assert_series_equal(result, expected)
 
         # GH #2751 (construction with no index specified), make sure we cast to
         # platform values
         df = DataFrame([1, 2])
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 1})
         tm.assert_series_equal(result, expected)
 
         df = DataFrame([1., 2.])
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'float64': 1})
         tm.assert_series_equal(result, expected)
 
         df = DataFrame({'a': [1, 2]})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 1})
         tm.assert_series_equal(result, expected)
 
         df = DataFrame({'a': [1., 2.]})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'float64': 1})
         tm.assert_series_equal(result, expected)
 
         df = DataFrame({'a': 1}, index=range(3))
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'int64': 1})
         tm.assert_series_equal(result, expected)
 
         df = DataFrame({'a': 1.}, index=range(3))
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'float64': 1})
         tm.assert_series_equal(result, expected)
 
@@ -1757,7 +1757,7 @@ def test_constructor_for_list_with_dtypes(self):
                         'c': list('abcd'),
                         'd': [datetime(2000, 1, 1) for i in range(4)],
                         'e': [1., 2, 4., 7]})
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series(
             {'int64': 1, 'float64': 2, datetime64name: 1, objectname: 1})
         result = result.sort_index()
@@ -2077,14 +2077,14 @@ def test_from_records_misc_brokenness(self):
         rows.append([datetime(2010, 1, 1), 1])
         rows.append([datetime(2010, 1, 2), 'hi'])  # test col upconverts to obj
         df2_obj = DataFrame.from_records(rows, columns=['date', 'test'])
-        results = df2_obj.get_dtype_counts()
+        results = Series(df2_obj._data.get_dtype_counts())
         expected = Series({'datetime64[ns]': 1, 'object': 1})
 
         rows = []
         rows.append([datetime(2010, 1, 1), 1])
         rows.append([datetime(2010, 1, 2), 1])
         df2_obj = DataFrame.from_records(rows, columns=['date', 'test'])
-        results = df2_obj.get_dtype_counts().sort_index()
+        results = Series(df2_obj._data.get_dtype_counts()).sort_index()
         expected = Series({'datetime64[ns]': 1, 'int64': 1})
         tm.assert_series_equal(results, expected)
 

pandas/tests/frame/test_dtypes.py

@@ -836,23 +836,23 @@ def test_timedeltas(self):
         df = DataFrame(dict(A=Series(date_range('2012-1-1', periods=3,
                                                 freq='D')),
                             B=Series([timedelta(days=i) for i in range(3)])))
-        result = df.get_dtype_counts().sort_index()
+        result = Series(df._data.get_dtype_counts()).sort_index()
         expected = Series(
             {'datetime64[ns]': 1, 'timedelta64[ns]': 1}).sort_index()
         assert_series_equal(result, expected)
 
         df['C'] = df['A'] + df['B']
         expected = Series(
             {'datetime64[ns]': 2, 'timedelta64[ns]': 1}).sort_values()
-        result = df.get_dtype_counts().sort_values()
+        result = Series(df._data.get_dtype_counts()).sort_values()
         assert_series_equal(result, expected)
 
         # mixed int types
         df['D'] = 1
         expected = Series({'datetime64[ns]': 2,
                            'timedelta64[ns]': 1,
                            'int64': 1}).sort_values()
-        result = df.get_dtype_counts().sort_values()
+        result = Series(df._data.get_dtype_counts()).sort_values()
         assert_series_equal(result, expected)
 
     def test_arg_for_errors_in_astype(self):

pandas/tests/frame/test_indexing.py

@@ -300,14 +300,14 @@ def test_getitem_boolean_casting(self, datetime_frame):
         df['F1'] = df['F'].copy()
 
         casted = df[df > 0]
-        result = casted.get_dtype_counts()
+        result = Series(casted._data.get_dtype_counts())
         expected = Series({'float64': 4, 'int32': 2, 'int64': 2})
         assert_series_equal(result, expected)
 
         # int block splitting
         df.loc[df.index[1:3], ['E1', 'F1']] = 0
         casted = df[df > 0]
-        result = casted.get_dtype_counts()
+        result = Series(casted._data.get_dtype_counts())
         expected = Series({'float64': 6, 'int32': 1, 'int64': 1})
         assert_series_equal(result, expected)
 
@@ -615,7 +615,7 @@ def test_setitem_cast(self, float_frame):
         df = DataFrame(np.random.rand(30, 3), columns=tuple('ABC'))
         df['event'] = np.nan
         df.loc[10, 'event'] = 'foo'
-        result = df.get_dtype_counts().sort_values()
+        result = Series(df._data.get_dtype_counts()).sort_values()
         expected = Series({'float64': 3, 'object': 1}).sort_values()
         assert_series_equal(result, expected)
 
@@ -1614,7 +1614,7 @@ def test_setitem_single_column_mixed_datetime(self):
         df['timestamp'] = Timestamp('20010102')
 
         # check our dtypes
-        result = df.get_dtype_counts()
+        result = Series(df._data.get_dtype_counts())
         expected = Series({'float64': 3, 'datetime64[ns]': 1})
         assert_series_equal(result, expected)
 
@@ -2637,7 +2637,7 @@ def _check_get(df, cond, check_dtypes=True):
                         for c in ['float32', 'float64',
                                   'int32', 'int64']})
         df.iloc[1, :] = 0
-        result = df.where(df >= 0).get_dtype_counts()
+        result = Series(df.where(df >= 0)._data.get_dtype_counts())
 
         # when we don't preserve boolean casts
         #

pandas/tests/frame/test_missing.py

@@ -407,13 +407,13 @@ def test_fillna_downcast(self):
     def test_fillna_dtype_conversion(self):
         # make sure that fillna on an empty frame works
         df = DataFrame(index=["A", "B", "C"], columns=[1, 2, 3, 4, 5])
-        result = df.get_dtype_counts().sort_values()
+        result = Series(df._data.get_dtype_counts()).sort_values()
         expected = Series({'object': 5})
         assert_series_equal(result, expected)
 
         result = df.fillna(1)
         expected = DataFrame(1, index=["A", "B", "C"], columns=[1, 2, 3, 4, 5])
-        result = result.get_dtype_counts().sort_values()
+        result = Series(result._data.get_dtype_counts()).sort_values()
         expected = Series({'int64': 5})
         assert_series_equal(result, expected)
 

pandas/tests/frame/test_mutate_columns.py

@@ -159,16 +159,22 @@ def test_insert(self):
         # new item
         df['x'] = df['a'].astype('float32')
         result = Series(dict(float32=1, float64=5))
-        assert (df.get_dtype_counts().sort_index() == result).all()
+        assert (Series(
+            df._data.get_dtype_counts()
+        ).sort_index() == result).all()
 
         # replacing current (in different block)
         df['a'] = df['a'].astype('float32')
         result = Series(dict(float32=2, float64=4))
-        assert (df.get_dtype_counts().sort_index() == result).all()
+        assert (Series(
+            df._data.get_dtype_counts()
+        ).sort_index() == result).all()
 
         df['y'] = df['a'].astype('int32')
         result = Series(dict(float32=2, float64=4, int32=1))
-        assert (df.get_dtype_counts().sort_index() == result).all()
+        assert (Series(
+            df._data.get_dtype_counts()
+        ).sort_index() == result).all()
 
         with pytest.raises(ValueError, match='already exists'):
             df.insert(1, 'a', df['b'])