Move GroupBy to Submodule and Add FutureWarning (#20506)

Author: WillAyd

pandas/core/api.py

@@ -7,7 +7,7 @@
 from pandas.core.algorithms import factorize, unique, value_counts
 from pandas.core.dtypes.missing import isna, isnull, notna, notnull
 from pandas.core.arrays import Categorical
-from pandas.core.groupby import Grouper
+from pandas.core.groupby.groupby import Grouper
 from pandas.io.formats.format import set_eng_float_format
 from pandas.core.index import (Index, CategoricalIndex, Int64Index,
                                UInt64Index, RangeIndex, Float64Index,

pandas/core/generic.py

@@ -6589,7 +6589,7 @@ def groupby(self, by=None, axis=0, level=None, as_index=True, sort=True,
         resample : Convenience method for frequency conversion and resampling
             of time series.
         """
-        from pandas.core.groupby import groupby
+        from pandas.core.groupby.groupby import groupby
 
         if level is None and by is None:
             raise TypeError("You have to supply one of 'by' and 'level'")

pandas/core/groupby/__init__.py

@@ -0,0 +1,4 @@
+# flake8: noqa
+from pandas.core.groupby.groupby import (
+    Grouper, GroupBy, SeriesGroupBy, DataFrameGroupBy
+)

pandas/core/groupby.py renamed to pandas/core/groupby/groupby.py

@@ -912,7 +912,7 @@ def groupby(self, function, axis='major'):
         -------
         grouped : PanelGroupBy
         """
-        from pandas.core.groupby import PanelGroupBy
+        from pandas.core.groupby.groupby import PanelGroupBy
         axis = self._get_axis_number(axis)
         return PanelGroupBy(self, function, axis=axis)
 

pandas/core/panel.py

@@ -7,9 +7,10 @@
 import pandas as pd
 from pandas.core.base import GroupByMixin
 
-from pandas.core.groupby import (BinGrouper, Grouper, _GroupBy, GroupBy,
-                                 SeriesGroupBy, groupby, PanelGroupBy,
-                                 _pipe_template)
+from pandas.core.groupby.groupby import (
+    BinGrouper, Grouper, _GroupBy, GroupBy, SeriesGroupBy, groupby,
+    PanelGroupBy, _pipe_template
+)
 
 from pandas.tseries.frequencies import to_offset, is_subperiod, is_superperiod
 from pandas.core.indexes.datetimes import DatetimeIndex, date_range

pandas/core/resample.py

@@ -6,7 +6,7 @@
 
 from pandas.core.reshape.concat import concat
 from pandas.core.series import Series
-from pandas.core.groupby import Grouper
+from pandas.core.groupby.groupby import Grouper
 from pandas.core.reshape.util import cartesian_product
 from pandas.core.index import Index, _get_objs_combined_axis
 from pandas.compat import range, lrange, zip

pandas/core/reshape/pivot.py

@@ -10,7 +10,7 @@
 import pandas as pd
 
 from pandas import concat, DataFrame, Index, MultiIndex, Series
-from pandas.core.groupby import Grouping, SpecificationError
+from pandas.core.groupby.groupby import Grouping, SpecificationError
 from pandas.compat import OrderedDict
 import pandas.util.testing as tm
 

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -14,7 +14,7 @@
 
 from pandas import (bdate_range, DataFrame, Index, Series, Timestamp,
                     Timedelta, NaT)
-from pandas.core.groupby import DataError
+from pandas.core.groupby.groupby import DataError
 import pandas.util.testing as tm
 
 

pandas/tests/groupby/aggregate/test_cython.py

@@ -18,7 +18,7 @@
 from pandas import (
     date_range, DataFrame, Index, MultiIndex, PeriodIndex, period_range, Series
 )
-from pandas.core.groupby import SpecificationError
+from pandas.core.groupby.groupby import SpecificationError
 from pandas.io.formats.printing import pprint_thing
 import pandas.util.testing as tm
 

pandas/tests/groupby/aggregate/test_other.py

@@ -54,7 +54,7 @@ def setup_method(self, method):
         self.bins = np.array([3, 6], dtype=np.int64)
 
     def test_generate_bins(self):
-        from pandas.core.groupby import generate_bins_generic
+        from pandas.core.groupby.groupby import generate_bins_generic
         values = np.array([1, 2, 3, 4, 5, 6], dtype=np.int64)
         binner = np.array([0, 3, 6, 9], dtype=np.int64)
 

pandas/tests/groupby/test_bin_groupby.py

@@ -340,7 +340,7 @@ def test_groupby_grouper_f_sanity_checked(self):
         pytest.raises(AssertionError, ts.groupby, lambda key: key[0:6])
 
     def test_grouping_error_on_multidim_input(self):
-        from pandas.core.groupby import Grouping
+        from pandas.core.groupby.groupby import Grouping
         pytest.raises(ValueError,
                       Grouping, self.df.index, self.df[['A', 'A']])
 

pandas/tests/groupby/test_grouping.py

@@ -57,11 +57,12 @@ def test_groupby_with_timegrouper(self):
             result3 = df.groupby(pd.Grouper(freq='5D')).sum()
             assert_frame_equal(result3, expected)
 
-    def test_groupby_with_timegrouper_methods(self):
+    @pytest.mark.parametrize("should_sort", [True, False])
+    def test_groupby_with_timegrouper_methods(self, should_sort):
         # GH 3881
         # make sure API of timegrouper conforms
 
-        df_original = pd.DataFrame({
+        df = pd.DataFrame({
             'Branch': 'A A A A A B'.split(),
             'Buyer': 'Carl Mark Carl Joe Joe Carl'.split(),
             'Quantity': [1, 3, 5, 8, 9, 3],
@@ -75,16 +76,18 @@ def test_groupby_with_timegrouper_methods(self):
             ]
         })
 
-        df_sorted = df_original.sort_values(by='Quantity', ascending=False)
+        if should_sort:
+            df = df.sort_values(by='Quantity', ascending=False)
 
-        for df in [df_original, df_sorted]:
-            df = df.set_index('Date', drop=False)
-            g = df.groupby(pd.Grouper(freq='6M'))
-            assert g.group_keys
-            assert isinstance(g.grouper, pd.core.groupby.BinGrouper)
-            groups = g.groups
-            assert isinstance(groups, dict)
-            assert len(groups) == 3
+        df = df.set_index('Date', drop=False)
+        g = df.groupby(pd.Grouper(freq='6M'))
+        assert g.group_keys
+
+        import pandas.core.groupby.groupby
+        assert isinstance(g.grouper, pandas.core.groupby.groupby.BinGrouper)
+        groups = g.groups
+        assert isinstance(groups, dict)
+        assert len(groups) == 3
 
     def test_timegrouper_with_reg_groups(self):
 

pandas/tests/groupby/test_timegrouper.py

@@ -13,7 +13,7 @@
 from .common import MixIn, assert_fp_equal
 
 from pandas.util.testing import assert_frame_equal, assert_series_equal
-from pandas.core.groupby import DataError
+from pandas.core.groupby.groupby import DataError
 from pandas.core.config import option_context
 
 

pandas/tests/groupby/test_transform.py

@@ -21,7 +21,7 @@
 from pandas.core.dtypes.generic import ABCSeries, ABCDataFrame
 from pandas.compat import range, lrange, zip, product, OrderedDict
 from pandas.errors import UnsupportedFunctionCall
-from pandas.core.groupby import DataError
+from pandas.core.groupby.groupby import DataError
 import pandas.core.common as com
 
 from pandas.tseries.frequencies import to_offset