Sharey keyword for boxplot (#20968)

Author: Sören

doc/source/whatsnew/v0.23.1.txt

@@ -48,40 +48,53 @@ Bug Fixes
 ~~~~~~~~~
 
 Groupby/Resample/Rolling
+~~~~~~~~~~~~~~~~~~~~~~~~
 
 - Bug in :func:`DataFrame.agg` where applying multiple aggregation functions to a :class:`DataFrame` with duplicated column names would cause a stack overflow (:issue:`21063`)
 - Bug in :func:`pandas.core.groupby.GroupBy.ffill` and :func:`pandas.core.groupby.GroupBy.bfill` where the fill within a grouping would not always be applied as intended due to the implementations' use of a non-stable sort (:issue:`21207`)
 - Bug in :func:`pandas.core.groupby.GroupBy.rank` where results did not scale to 100% when specifying ``method='dense'`` and ``pct=True``
 
 Data-type specific
+~~~~~~~~~~~~~~~~~~
 
 - Bug in :meth:`Series.str.replace()` where the method throws `TypeError` on Python 3.5.2 (:issue: `21078`)
 - Bug in :class:`Timedelta`: where passing a float with a unit would prematurely round the float precision (:issue: `14156`)
 - Bug in :func:`pandas.testing.assert_index_equal` which raised ``AssertionError`` incorrectly, when comparing two :class:`CategoricalIndex` objects with param ``check_categorical=False`` (:issue:`19776`)
 
 Sparse
+~~~~~~
 
 - Bug in :attr:`SparseArray.shape` which previously only returned the shape :attr:`SparseArray.sp_values` (:issue:`21126`)
 
 Indexing
+~~~~~~~~
 
 - Bug in :meth:`Series.reset_index` where appropriate error was not raised with an invalid level name (:issue:`20925`)
 - Bug in :func:`interval_range` when ``start``/``periods`` or ``end``/``periods`` are specified with float ``start`` or ``end`` (:issue:`21161`)
 - Bug in :meth:`MultiIndex.set_names` where error raised for a ``MultiIndex`` with ``nlevels == 1`` (:issue:`21149`)
 - Bug in :class:`IntervalIndex` constructors where creating an ``IntervalIndex`` from categorical data was not fully supported (:issue:`21243`, issue:`21253`)
 - Bug in :meth:`MultiIndex.sort_index` which was not guaranteed to sort correctly with ``level=1``; this was also causing data misalignment in particular :meth:`DataFrame.stack` operations (:issue:`20994`, :issue:`20945`, :issue:`21052`)
 
+Plotting
+~~~~~~~~
+
+- New keywords (sharex, sharey) to turn on/off sharing of x/y-axis by subplots generated with pandas.DataFrame().groupby().boxplot() (:issue: `20968`)
+
 I/O
+~~~
 
 - Bug in IO methods specifying ``compression='zip'`` which produced uncompressed zip archives (:issue:`17778`, :issue:`21144`)
 - Bug in :meth:`DataFrame.to_stata` which prevented exporting DataFrames to buffers and most file-like objects (:issue:`21041`)
 - Bug in :meth:`read_stata` and :class:`StataReader` which did not correctly decode utf-8 strings on Python 3 from Stata 14 files (dta version 118) (:issue:`21244`)
 
+
 Reshaping
+~~~~~~~~~
 
 - Bug in :func:`concat` where error was raised in concatenating :class:`Series` with numpy scalar and tuple names (:issue:`21015`)
 - Bug in :func:`concat` warning message providing the wrong guidance for future behavior (:issue:`21101`)
 
 Other
+~~~~~
 
 - Tab completion on :class:`Index` in IPython no longer outputs deprecation warnings (:issue:`21125`)

pandas/plotting/_core.py

@@ -2548,7 +2548,7 @@ def plot_group(group, ax):
 
 def boxplot_frame_groupby(grouped, subplots=True, column=None, fontsize=None,
                           rot=0, grid=True, ax=None, figsize=None,
-                          layout=None, **kwds):
+                          layout=None, sharex=False, sharey=True, **kwds):
     """
     Make box plots from DataFrameGroupBy data.
 
@@ -2567,6 +2567,14 @@ def boxplot_frame_groupby(grouped, subplots=True, column=None, fontsize=None,
     figsize : A tuple (width, height) in inches
     layout : tuple (optional)
         (rows, columns) for the layout of the plot
+    sharex : bool, default False
+        Whether x-axes will be shared among subplots
+
+        .. versionadded:: 0.23.1
+    sharey : bool, default True
+        Whether y-axes will be shared among subplots
+
+        .. versionadded:: 0.23.1
     `**kwds` : Keyword Arguments
         All other plotting keyword arguments to be passed to
         matplotlib's boxplot function
@@ -2598,7 +2606,7 @@ def boxplot_frame_groupby(grouped, subplots=True, column=None, fontsize=None,
     if subplots is True:
         naxes = len(grouped)
         fig, axes = _subplots(naxes=naxes, squeeze=False,
-                              ax=ax, sharex=False, sharey=True,
+                              ax=ax, sharex=sharex, sharey=sharey,
                               figsize=figsize, layout=layout)
         axes = _flatten(axes)
 

pandas/tests/plotting/test_frame.py

@@ -40,6 +40,14 @@ def setup_method(self, method):
                                     "C": np.arange(20) + np.random.uniform(
                                         size=20)})
 
+    def _assert_ytickslabels_visibility(self, axes, expected):
+        for ax, exp in zip(axes, expected):
+            self._check_visible(ax.get_yticklabels(), visible=exp)
+
+    def _assert_xtickslabels_visibility(self, axes, expected):
+        for ax, exp in zip(axes, expected):
+            self._check_visible(ax.get_xticklabels(), visible=exp)
+
     @pytest.mark.slow
     def test_plot(self):
         df = self.tdf
@@ -367,6 +375,57 @@ def test_subplots(self):
             for ax in axes:
                 assert ax.get_legend() is None
 
+    def test_groupby_boxplot_sharey(self):
+        # https://github.com/pandas-dev/pandas/issues/20968
+        # sharey can now be switched check whether the right
+        # pair of axes is turned on or off
+
+        df = DataFrame({'a': [-1.43, -0.15, -3.70, -1.43, -0.14],
+                        'b': [0.56, 0.84, 0.29, 0.56, 0.85],
+                        'c': [0, 1, 2, 3, 1]},
+                       index=[0, 1, 2, 3, 4])
+
+        # behavior without keyword
+        axes = df.groupby('c').boxplot()
+        expected = [True, False, True, False]
+        self._assert_ytickslabels_visibility(axes, expected)
+
+        # set sharey=True should be identical
+        axes = df.groupby('c').boxplot(sharey=True)
+        expected = [True, False, True, False]
+        self._assert_ytickslabels_visibility(axes, expected)
+
+        # sharey=False, all yticklabels should be visible
+        axes = df.groupby('c').boxplot(sharey=False)
+        expected = [True, True, True, True]
+        self._assert_ytickslabels_visibility(axes, expected)
+
+    def test_groupby_boxplot_sharex(self):
+        # https://github.com/pandas-dev/pandas/issues/20968
+        # sharex can now be switched check whether the right
+        # pair of axes is turned on or off
+
+        df = DataFrame({'a': [-1.43, -0.15, -3.70, -1.43, -0.14],
+                        'b': [0.56, 0.84, 0.29, 0.56, 0.85],
+                        'c': [0, 1, 2, 3, 1]},
+                       index=[0, 1, 2, 3, 4])
+
+        # behavior without keyword
+        axes = df.groupby('c').boxplot()
+        expected = [True, True, True, True]
+        self._assert_xtickslabels_visibility(axes, expected)
+
+        # set sharex=False should be identical
+        axes = df.groupby('c').boxplot(sharex=False)
+        expected = [True, True, True, True]
+        self._assert_xtickslabels_visibility(axes, expected)
+
+        # sharex=True, yticklabels should be visible
+        # only for bottom plots
+        axes = df.groupby('c').boxplot(sharex=True)
+        expected = [False, False, True, True]
+        self._assert_xtickslabels_visibility(axes, expected)
+
     @pytest.mark.slow
     def test_subplots_timeseries(self):
         idx = date_range(start='2014-07-01', freq='M', periods=10)