ENH: plot functions accept multiple axes and layout kw

Author: sinhrks

doc/source/v0.15.0.txt

@@ -303,6 +303,9 @@ Enhancements
 ~~~~~~~~~~~~
 - Added support for bool, uint8, uint16 and uint32 datatypes in ``to_stata`` (:issue:`7097`, :issue:`7365`)
 
+- Added ``layout`` keyword to ``DataFrame.plot`` (:issue:`6667`)
+- Allow to pass multiple axes to ``DataFrame.plot``, ``hist`` and ``boxplot`` (:issue:`5353`, :issue:`6970`, :issue:`7069`)
+
 
 - ``PeriodIndex`` supports ``resolution`` as the same as ``DatetimeIndex`` (:issue:`7708`)
 - ``pandas.tseries.holiday`` has added support for additional holidays and ways to observe holidays (:issue:`7070`)

doc/source/visualization.rst

@@ -946,10 +946,41 @@ with the ``subplots`` keyword:
    @savefig frame_plot_subplots.png
    df.plot(subplots=True, figsize=(6, 6));
 
-Targeting Different Subplots
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Using Layout and Targetting Multiple Axes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-You can pass an ``ax`` argument to :meth:`Series.plot` to plot on a particular axis:
+The layout of subplots can be specified by ``layout`` keyword. It can accept
+``(rows, columns)``. The ``layout`` keyword can be used in
+``hist`` and ``boxplot`` also. If input is invalid, ``ValueError`` will be raised.
+
+The number of axes which can be contained by rows x columns specified by ``layout`` must be
+larger than the number of required subplots. If layout can contain more axes than required,
+blank axes are not drawn.
+
+.. ipython:: python
+
+   @savefig frame_plot_subplots_layout.png
+   df.plot(subplots=True, layout=(2, 3), figsize=(6, 6));
+
+Also, you can pass multiple axes created beforehand as list-like via ``ax`` keyword.
+This allows to use more complicated layout.
+The passed axes must be the same number as the subplots being drawn.
+
+When multiple axes are passed via ``ax`` keyword, ``layout``, ``sharex`` and ``sharey`` keywords are ignored.
+These must be configured when creating axes.
+
+.. ipython:: python
+
+   fig, axes = plt.subplots(4, 4, figsize=(6, 6));
+   plt.adjust_subplots(wspace=0.5, hspace=0.5);
+   target1 = [axes[0][0], axes[1][1], axes[2][2], axes[3][3]]
+   target2 = [axes[3][0], axes[2][1], axes[1][2], axes[0][3]]
+
+   df.plot(subplots=True, ax=target1, legend=False);
+   @savefig frame_plot_subplots_multi_ax.png
+   (-df).plot(subplots=True, ax=target2, legend=False);
+
+Another option is passing an ``ax`` argument to :meth:`Series.plot` to plot on a particular axis:
 
 .. ipython:: python
    :suppress:
@@ -964,12 +995,12 @@ You can pass an ``ax`` argument to :meth:`Series.plot` to plot on a particular a
 .. ipython:: python
 
    fig, axes = plt.subplots(nrows=2, ncols=2)
-   df['A'].plot(ax=axes[0,0]); axes[0,0].set_title('A')
-   df['B'].plot(ax=axes[0,1]); axes[0,1].set_title('B')
-   df['C'].plot(ax=axes[1,0]); axes[1,0].set_title('C')
+   df['A'].plot(ax=axes[0,0]); axes[0,0].set_title('A');
+   df['B'].plot(ax=axes[0,1]); axes[0,1].set_title('B');
+   df['C'].plot(ax=axes[1,0]); axes[1,0].set_title('C');
 
    @savefig series_plot_multi.png
-   df['D'].plot(ax=axes[1,1]); axes[1,1].set_title('D')
+   df['D'].plot(ax=axes[1,1]); axes[1,1].set_title('D');
 
 .. ipython:: python
    :suppress:

pandas/tests/test_graphics.py

@@ -670,7 +670,7 @@ def test_hist_layout_with_by(self):
         axes = _check_plot_works(df.height.hist, by=df.classroom, layout=(2, 2))
         self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
 
-        axes = _check_plot_works(df.height.hist, by=df.category, layout=(4, 2), figsize=(12, 7))
+        axes = df.height.hist(by=df.category, layout=(4, 2), figsize=(12, 7))
         self._check_axes_shape(axes, axes_num=4, layout=(4, 2), figsize=(12, 7))
 
     @slow
@@ -1071,6 +1071,7 @@ def test_subplots(self):
         for kind in ['bar', 'barh', 'line', 'area']:
             axes = df.plot(kind=kind, subplots=True, sharex=True, legend=True)
             self._check_axes_shape(axes, axes_num=3, layout=(3, 1))
+            self.assertEqual(axes.shape, (3, ))
 
             for ax, column in zip(axes, df.columns):
                 self._check_legend_labels(ax, labels=[com.pprint_thing(column)])
@@ -1133,6 +1134,77 @@ def test_subplots_timeseries(self):
                 self._check_visible(ax.get_yticklabels())
                 self._check_ticks_props(ax, xlabelsize=7, xrot=45)
 
+    def test_subplots_layout(self):
+        # GH 6667
+        df = DataFrame(np.random.rand(10, 3),
+                       index=list(string.ascii_letters[:10]))
+
+        axes = df.plot(subplots=True, layout=(2, 2))
+        self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
+        self.assertEqual(axes.shape, (2, 2))
+
+        axes = df.plot(subplots=True, layout=(1, 4))
+        self._check_axes_shape(axes, axes_num=3, layout=(1, 4))
+        self.assertEqual(axes.shape, (1, 4))
+
+        with tm.assertRaises(ValueError):
+            axes = df.plot(subplots=True, layout=(1, 1))
+
+        # single column
+        df = DataFrame(np.random.rand(10, 1),
+                       index=list(string.ascii_letters[:10]))
+        axes = df.plot(subplots=True)
+        self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
+        self.assertEqual(axes.shape, (1, ))
+
+        axes = df.plot(subplots=True, layout=(3, 3))
+        self._check_axes_shape(axes, axes_num=1, layout=(3, 3))
+        self.assertEqual(axes.shape, (3, 3))
+
+    @slow
+    def test_subplots_multiple_axes(self):
+        # GH 5353, 6970, GH 7069
+        fig, axes = self.plt.subplots(2, 3)
+        df = DataFrame(np.random.rand(10, 3),
+                       index=list(string.ascii_letters[:10]))
+
+        returned = df.plot(subplots=True, ax=axes[0])
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assertEqual(returned.shape, (3, ))
+        self.assertIs(returned[0].figure, fig)
+        # draw on second row
+        returned = df.plot(subplots=True, ax=axes[1])
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assertEqual(returned.shape, (3, ))
+        self.assertIs(returned[0].figure, fig)
+        self._check_axes_shape(axes, axes_num=6, layout=(2, 3))
+        tm.close()
+
+        with tm.assertRaises(ValueError):
+            fig, axes = self.plt.subplots(2, 3)
+            # pass different number of axes from required
+            df.plot(subplots=True, ax=axes)
+
+        # pass 2-dim axes and invalid layout
+        # invalid lauout should not affect to input and return value
+        # (show warning is tested in
+        # TestDataFrameGroupByPlots.test_grouped_box_multiple_axes
+        fig, axes = self.plt.subplots(2, 2)
+        df = DataFrame(np.random.rand(10, 4),
+                       index=list(string.ascii_letters[:10]))
+
+        returned = df.plot(subplots=True, ax=axes, layout=(2, 1))
+        self._check_axes_shape(returned, axes_num=4, layout=(2, 2))
+        self.assertEqual(returned.shape, (4, ))
+
+        # single column
+        fig, axes = self.plt.subplots(1, 1)
+        df = DataFrame(np.random.rand(10, 1),
+                       index=list(string.ascii_letters[:10]))
+        axes = df.plot(subplots=True, ax=[axes])
+        self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
+        self.assertEqual(axes.shape, (1, ))
+
     def test_negative_log(self):
         df = - DataFrame(rand(6, 4),
                        index=list(string.ascii_letters[:6]),
@@ -1718,15 +1790,15 @@ def test_hist_df_coord(self):
         normal_df = DataFrame({'A': np.repeat(np.array([1, 2, 3, 4, 5]),
                                               np.array([10, 9, 8, 7, 6])),
                                'B': np.repeat(np.array([1, 2, 3, 4, 5]),
-                                              np.array([8, 8, 8, 8, 8])), 
+                                              np.array([8, 8, 8, 8, 8])),
                                'C': np.repeat(np.array([1, 2, 3, 4, 5]),
                                               np.array([6, 7, 8, 9, 10]))},
                                columns=['A', 'B', 'C'])
 
         nan_df = DataFrame({'A': np.repeat(np.array([np.nan, 1, 2, 3, 4, 5]),
                                            np.array([3, 10, 9, 8, 7, 6])),
                             'B': np.repeat(np.array([1, np.nan, 2, 3, 4, 5]),
-                                           np.array([8, 3, 8, 8, 8, 8])), 
+                                           np.array([8, 3, 8, 8, 8, 8])),
                             'C': np.repeat(np.array([1, 2, 3, np.nan, 4, 5]),
                                            np.array([6, 7, 8, 3, 9, 10]))},
                            columns=['A', 'B', 'C'])
@@ -2712,6 +2784,41 @@ def test_grouped_box_layout(self):
             return_type='dict')
         self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 4))
 
+    @slow
+    def test_grouped_box_multiple_axes(self):
+        # GH 6970, GH 7069
+        df = self.hist_df
+
+        # check warning to ignore sharex / sharey
+        # this check should be done in the first function which
+        # passes multiple axes to plot, hist or boxplot
+        # location should be changed if other test is added
+        # which has earlier alphabetical order
+        with tm.assert_produces_warning(UserWarning):
+            fig, axes = self.plt.subplots(2, 2)
+            df.groupby('category').boxplot(column='height', return_type='axes', ax=axes)
+            self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(2, 2))
+
+        fig, axes = self.plt.subplots(2, 3)
+        returned = df.boxplot(column=['height', 'weight', 'category'], by='gender',
+                              return_type='axes', ax=axes[0])
+        returned = np.array(returned.values())
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assert_numpy_array_equal(returned, axes[0])
+        self.assertIs(returned[0].figure, fig)
+        # draw on second row
+        returned = df.groupby('classroom').boxplot(column=['height', 'weight', 'category'],
+                                                   return_type='axes', ax=axes[1])
+        returned = np.array(returned.values())
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assert_numpy_array_equal(returned, axes[1])
+        self.assertIs(returned[0].figure, fig)
+
+        with tm.assertRaises(ValueError):
+            fig, axes = self.plt.subplots(2, 3)
+            # pass different number of axes from required
+            axes = df.groupby('classroom').boxplot(ax=axes)
+
     @slow
     def test_grouped_hist_layout(self):
 
@@ -2724,12 +2831,12 @@ def test_grouped_hist_layout(self):
         axes = _check_plot_works(df.hist, column='height', by=df.gender, layout=(2, 1))
         self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
 
-        axes = _check_plot_works(df.hist, column='height', by=df.category, layout=(4, 1))
+        axes = df.hist(column='height', by=df.category, layout=(4, 1))
         self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
 
-        axes = _check_plot_works(df.hist, column='height', by=df.category,
-                                 layout=(4, 2), figsize=(12, 8))
+        axes = df.hist(column='height', by=df.category, layout=(4, 2), figsize=(12, 8))
         self._check_axes_shape(axes, axes_num=4, layout=(4, 2), figsize=(12, 8))
+        tm.close()
 
         # GH 6769
         axes = _check_plot_works(df.hist, column='height', by='classroom', layout=(2, 2))
@@ -2739,13 +2846,32 @@ def test_grouped_hist_layout(self):
         axes = _check_plot_works(df.hist, by='classroom')
         self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
 
-        axes = _check_plot_works(df.hist, by='gender', layout=(3, 5))
+        axes = df.hist(by='gender', layout=(3, 5))
         self._check_axes_shape(axes, axes_num=2, layout=(3, 5))
 
-        axes = _check_plot_works(df.hist, column=['height', 'weight', 'category'])
+        axes = df.hist(column=['height', 'weight', 'category'])
         self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
 
     @slow
+    def test_grouped_hist_multiple_axes(self):
+        # GH 6970, GH 7069
+        df = self.hist_df
+
+        fig, axes = self.plt.subplots(2, 3)
+        returned = df.hist(column=['height', 'weight', 'category'], ax=axes[0])
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assert_numpy_array_equal(returned, axes[0])
+        self.assertIs(returned[0].figure, fig)
+        returned = df.hist(by='classroom', ax=axes[1])
+        self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
+        self.assert_numpy_array_equal(returned, axes[1])
+        self.assertIs(returned[0].figure, fig)
+
+        with tm.assertRaises(ValueError):
+            fig, axes = self.plt.subplots(2, 3)
+            # pass different number of axes from required
+            axes = df.hist(column='height', ax=axes)
+    @slow
     def test_axis_share_x(self):
         df = self.hist_df
         # GH4089