DEPR: remove PanelGroupBy, disable DataFrame.to_panel (pandas-dev#25047)

Author: jbrockmendel

doc/source/whatsnew/v0.25.0.rst

@@ -51,7 +51,7 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
+- Removed (parts of) :class:`Panel` (:issue:`25047`)
 -
 -
 -

pandas/core/frame.py

@@ -1974,45 +1974,7 @@ def to_panel(self):
         -------
         panel : Panel
         """
-        # only support this kind for now
-        if (not isinstance(self.index, MultiIndex) or  # pragma: no cover
-                len(self.index.levels) != 2):
-            raise NotImplementedError('Only 2-level MultiIndex are supported.')
-
-        if not self.index.is_unique:
-            raise ValueError("Can't convert non-uniquely indexed "
-                             "DataFrame to Panel")
-
-        self._consolidate_inplace()
-
-        # minor axis must be sorted
-        if self.index.lexsort_depth < 2:
-            selfsorted = self.sort_index(level=0)
-        else:
-            selfsorted = self
-
-        major_axis, minor_axis = selfsorted.index.levels
-        major_codes, minor_codes = selfsorted.index.codes
-        shape = len(major_axis), len(minor_axis)
-
-        # preserve names, if any
-        major_axis = major_axis.copy()
-        major_axis.name = self.index.names[0]
-
-        minor_axis = minor_axis.copy()
-        minor_axis.name = self.index.names[1]
-
-        # create new axes
-        new_axes = [selfsorted.columns, major_axis, minor_axis]
-
-        # create new manager
-        new_mgr = selfsorted._data.reshape_nd(axes=new_axes,
-                                              labels=[major_codes,
-                                                      minor_codes],
-                                              shape=shape,
-                                              ref_items=selfsorted.columns)
-
-        return self._constructor_expanddim(new_mgr)
+        raise NotImplementedError("Panel is being removed in pandas 0.25.0.")
 
     @deprecate_kwarg(old_arg_name='encoding', new_arg_name=None)
     def to_stata(self, fname, convert_dates=None, write_index=True,

pandas/core/groupby/__init__.py

@@ -1,4 +1,4 @@
 from pandas.core.groupby.groupby import GroupBy  # noqa: F401
 from pandas.core.groupby.generic import (  # noqa: F401
-    SeriesGroupBy, DataFrameGroupBy, PanelGroupBy)
+    SeriesGroupBy, DataFrameGroupBy)
 from pandas.core.groupby.grouper import Grouper  # noqa: F401

pandas/core/groupby/generic.py

@@ -1,5 +1,5 @@
 """
-Define the SeriesGroupBy, DataFrameGroupBy, and PanelGroupBy
+Define the SeriesGroupBy and DataFrameGroupBy
 classes that hold the groupby interfaces (and some implementations).
 
 These are user facing as the result of the ``df.groupby(...)`` operations,
@@ -39,7 +39,6 @@
 from pandas.core.index import CategoricalIndex, Index, MultiIndex
 import pandas.core.indexes.base as ibase
 from pandas.core.internals import BlockManager, make_block
-from pandas.core.panel import Panel
 from pandas.core.series import Series
 
 from pandas.plotting._core import boxplot_frame_groupby
@@ -1586,90 +1585,3 @@ def groupby_series(obj, col=None):
         return results
 
     boxplot = boxplot_frame_groupby
-
-
-class PanelGroupBy(NDFrameGroupBy):
-
-    def aggregate(self, arg, *args, **kwargs):
-        return super(PanelGroupBy, self).aggregate(arg, *args, **kwargs)
-
-    agg = aggregate
-
-    def _iterate_slices(self):
-        if self.axis == 0:
-            # kludge
-            if self._selection is None:
-                slice_axis = self._selected_obj.items
-            else:
-                slice_axis = self._selection_list
-            slicer = lambda x: self._selected_obj[x]
-        else:
-            raise NotImplementedError("axis other than 0 is not supported")
-
-        for val in slice_axis:
-            if val in self.exclusions:
-                continue
-
-            yield val, slicer(val)
-
-    def aggregate(self, arg, *args, **kwargs):
-        """
-        Aggregate using input function or dict of {column -> function}
-
-        Parameters
-        ----------
-        arg : function or dict
-            Function to use for aggregating groups. If a function, must either
-            work when passed a Panel or when passed to Panel.apply. If
-            pass a dict, the keys must be DataFrame column names
-
-        Returns
-        -------
-        aggregated : Panel
-        """
-        if isinstance(arg, compat.string_types):
-            return getattr(self, arg)(*args, **kwargs)
-
-        return self._aggregate_generic(arg, *args, **kwargs)
-
-    def _wrap_generic_output(self, result, obj):
-        if self.axis == 0:
-            new_axes = list(obj.axes)
-            new_axes[0] = self.grouper.result_index
-        elif self.axis == 1:
-            x, y, z = obj.axes
-            new_axes = [self.grouper.result_index, z, x]
-        else:
-            x, y, z = obj.axes
-            new_axes = [self.grouper.result_index, y, x]
-
-        result = Panel._from_axes(result, new_axes)
-
-        if self.axis == 1:
-            result = result.swapaxes(0, 1).swapaxes(0, 2)
-        elif self.axis == 2:
-            result = result.swapaxes(0, 2)
-
-        return result
-
-    def _aggregate_item_by_item(self, func, *args, **kwargs):
-        obj = self._obj_with_exclusions
-        result = {}
-
-        if self.axis > 0:
-            for item in obj:
-                try:
-                    itemg = DataFrameGroupBy(obj[item],
-                                             axis=self.axis - 1,
-                                             grouper=self.grouper)
-                    result[item] = itemg.aggregate(func, *args, **kwargs)
-                except (ValueError, TypeError):
-                    raise
-            new_axes = list(obj.axes)
-            new_axes[self.axis] = self.grouper.result_index
-            return Panel._from_axes(result, new_axes)
-        else:
-            raise ValueError("axis value must be greater than 0")
-
-    def _wrap_aggregated_output(self, output, names=None):
-        raise AbstractMethodError(self)

pandas/core/panel.py

@@ -917,9 +917,7 @@ def groupby(self, function, axis='major'):
         -------
         grouped : PanelGroupBy
         """
-        from pandas.core.groupby import PanelGroupBy
-        axis = self._get_axis_number(axis)
-        return PanelGroupBy(self, function, axis=axis)
+        raise NotImplementedError("Panel is removed in pandas 0.25.0")
 
     def to_frame(self, filter_observations=True):
         """

pandas/core/resample.py

@@ -20,7 +20,7 @@
 import pandas.core.algorithms as algos
 from pandas.core.generic import _shared_docs
 from pandas.core.groupby.base import GroupByMixin
-from pandas.core.groupby.generic import PanelGroupBy, SeriesGroupBy
+from pandas.core.groupby.generic import SeriesGroupBy
 from pandas.core.groupby.groupby import (
     GroupBy, _GroupBy, _pipe_template, groupby)
 from pandas.core.groupby.grouper import Grouper
@@ -340,12 +340,7 @@ def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
 
         obj = self._selected_obj
 
-        try:
-            grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
-        except TypeError:
-
-            # panel grouper
-            grouped = PanelGroupBy(obj, grouper=grouper, axis=self.axis)
+        grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
 
         try:
             if isinstance(obj, ABCDataFrame) and compat.callable(how):

pandas/io/pytables.py

@@ -31,7 +31,7 @@
     PeriodIndex, Series, SparseDataFrame, SparseSeries, TimedeltaIndex, compat,
     concat, isna, to_datetime)
 from pandas.core import config
-from pandas.core.algorithms import match, unique
+from pandas.core.algorithms import unique
 from pandas.core.arrays.categorical import (
     Categorical, _factorize_from_iterables)
 from pandas.core.arrays.sparse import BlockIndex, IntIndex
@@ -3944,29 +3944,7 @@ def read(self, where=None, columns=None, **kwargs):
                 objs.append(obj)
 
         else:
-            warnings.warn(duplicate_doc, DuplicateWarning, stacklevel=5)
-
-            # reconstruct
-            long_index = MultiIndex.from_arrays(
-                [i.values for i in self.index_axes])
-
-            for c in self.values_axes:
-                lp = DataFrame(c.data, index=long_index, columns=c.values)
-
-                # need a better algorithm
-                tuple_index = long_index.values
-
-                unique_tuples = unique(tuple_index)
-                unique_tuples = com.asarray_tuplesafe(unique_tuples)
-
-                indexer = match(unique_tuples, tuple_index)
-                indexer = ensure_platform_int(indexer)
-
-                new_index = long_index.take(indexer)
-                new_values = lp.values.take(indexer, axis=0)
-
-                lp = DataFrame(new_values, index=new_index, columns=lp.columns)
-                objs.append(lp.to_panel())
+            raise NotImplementedError("Panel is removed in pandas 0.25.0")
 
         # create the composite object
         if len(objs) == 1:
@@ -4875,16 +4853,3 @@ def select_coords(self):
             return self.coordinates
 
         return np.arange(start, stop)
-
-# utilities ###
-
-
-def timeit(key, df, fn=None, remove=True, **kwargs):
-    if fn is None:
-        fn = 'timeit.h5'
-    store = HDFStore(fn, mode='w')
-    store.append(key, df, **kwargs)
-    store.close()
-
-    if remove:
-        os.remove(fn)

pandas/tests/dtypes/test_generic.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-from warnings import catch_warnings, simplefilter
+from warnings import catch_warnings
 
 import numpy as np
 
@@ -39,9 +39,6 @@ def test_abc_types(self):
         assert isinstance(pd.Int64Index([1, 2, 3]), gt.ABCIndexClass)
         assert isinstance(pd.Series([1, 2, 3]), gt.ABCSeries)
         assert isinstance(self.df, gt.ABCDataFrame)
-        with catch_warnings(record=True):
-            simplefilter('ignore', FutureWarning)
-            assert isinstance(self.df.to_panel(), gt.ABCPanel)
         assert isinstance(self.sparse_series, gt.ABCSparseSeries)
         assert isinstance(self.sparse_array, gt.ABCSparseArray)
         assert isinstance(self.sparse_frame, gt.ABCSparseDataFrame)

pandas/tests/frame/test_subclass.py

@@ -6,7 +6,7 @@
 import pytest
 
 import pandas as pd
-from pandas import DataFrame, Index, MultiIndex, Panel, Series
+from pandas import DataFrame, Index, MultiIndex, Series
 from pandas.tests.frame.common import TestData
 import pandas.util.testing as tm
 
@@ -125,29 +125,6 @@ def test_indexing_sliced(self):
         tm.assert_series_equal(res, exp)
         assert isinstance(res, tm.SubclassedSeries)
 
-    @pytest.mark.filterwarnings("ignore:\\nPanel:FutureWarning")
-    def test_to_panel_expanddim(self):
-        # GH 9762
-
-        class SubclassedFrame(DataFrame):
-
-            @property
-            def _constructor_expanddim(self):
-                return SubclassedPanel
-
-        class SubclassedPanel(Panel):
-            pass
-
-        index = MultiIndex.from_tuples([(0, 0), (0, 1), (0, 2)])
-        df = SubclassedFrame({'X': [1, 2, 3], 'Y': [4, 5, 6]}, index=index)
-        result = df.to_panel()
-        assert isinstance(result, SubclassedPanel)
-        expected = SubclassedPanel([[[1, 2, 3]], [[4, 5, 6]]],
-                                   items=['X', 'Y'], major_axis=[0],
-                                   minor_axis=[0, 1, 2],
-                                   dtype='int64')
-        tm.assert_panel_equal(result, expected)
-
     def test_subclass_attr_err_propagation(self):
         # GH 11808
         class A(DataFrame):

pandas/tests/groupby/test_groupby.py

@@ -1239,31 +1239,6 @@ def _check_work(gp):
     # _check_work(panel.groupby(lambda x: x.month, axis=1))
 
 
-@pytest.mark.filterwarnings("ignore:\\nPanel:FutureWarning")
-def test_panel_groupby():
-    panel = tm.makePanel()
-    tm.add_nans(panel)
-    grouped = panel.groupby({'ItemA': 0, 'ItemB': 0, 'ItemC': 1},
-                            axis='items')
-    agged = grouped.mean()
-    agged2 = grouped.agg(lambda x: x.mean('items'))
-
-    tm.assert_panel_equal(agged, agged2)
-
-    tm.assert_index_equal(agged.items, Index([0, 1]))
-
-    grouped = panel.groupby(lambda x: x.month, axis='major')
-    agged = grouped.mean()
-
-    exp = Index(sorted(list(set(panel.major_axis.month))))
-    tm.assert_index_equal(agged.major_axis, exp)
-
-    grouped = panel.groupby({'A': 0, 'B': 0, 'C': 1, 'D': 1},
-                            axis='minor')
-    agged = grouped.mean()
-    tm.assert_index_equal(agged.minor_axis, Index([0, 1]))
-
-
 def test_groupby_2d_malformed():
     d = DataFrame(index=lrange(2))
     d['group'] = ['g1', 'g2']

pandas/tests/groupby/test_grouping.py

@@ -14,8 +14,7 @@
 from pandas.core.groupby.grouper import Grouping
 import pandas.util.testing as tm
 from pandas.util.testing import (
-    assert_almost_equal, assert_frame_equal, assert_panel_equal,
-    assert_series_equal)
+    assert_almost_equal, assert_frame_equal, assert_series_equal)
 
 # selection
 # --------------------------------
@@ -563,17 +562,7 @@ def test_list_grouper_with_nat(self):
 # --------------------------------
 
 class TestGetGroup():
-
-    @pytest.mark.filterwarnings("ignore:\\nPanel:FutureWarning")
     def test_get_group(self):
-        wp = tm.makePanel()
-        grouped = wp.groupby(lambda x: x.month, axis='major')
-
-        gp = grouped.get_group(1)
-        expected = wp.reindex(
-            major=[x for x in wp.major_axis if x.month == 1])
-        assert_panel_equal(gp, expected)
-
         # GH 5267
         # be datelike friendly
         df = DataFrame({'DATE': pd.to_datetime(
@@ -755,19 +744,6 @@ def test_multi_iter_frame(self, three_group):
         for key, group in grouped:
             pass
 
-    @pytest.mark.filterwarnings("ignore:\\nPanel:FutureWarning")
-    def test_multi_iter_panel(self):
-        wp = tm.makePanel()
-        grouped = wp.groupby([lambda x: x.month, lambda x: x.weekday()],
-                             axis=1)
-
-        for (month, wd), group in grouped:
-            exp_axis = [x
-                        for x in wp.major_axis
-                        if x.month == month and x.weekday() == wd]
-            expected = wp.reindex(major=exp_axis)
-            assert_panel_equal(group, expected)
-
     def test_dictify(self, df):
         dict(iter(df.groupby('A')))
         dict(iter(df.groupby(['A', 'B'])))