DOC: Run doctests for pandas/plotting (#45019)

pandas-dev · Dec 24, 2021 · 9598f77 · 9598f77
1 parent 149e193
commit 9598f77
Show file tree

Hide file tree

Showing 4 changed files with 42 additions and 10 deletions.
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -75,6 +75,7 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
       pandas/core \
       pandas/errors/ \
       pandas/io/ \
+      pandas/plotting/ \
       pandas/tseries/ \
       pandas/util/ \
       pandas/_typing.py \

diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py
@@ -338,7 +338,7 @@ def hist_frame(
     >>> np.random.seed(1234)
     >>> df = pd.DataFrame(np.random.randn(10, 4),
     ...                   columns=['Col1', 'Col2', 'Col3', 'Col4'])
-    >>> boxplot = df.boxplot(column=['Col1', 'Col2', 'Col3'])
+    >>> boxplot = df.boxplot(column=['Col1', 'Col2', 'Col3'])  # doctest: +SKIP
 
 Boxplots of variables distributions grouped by the values of a third
 variable can be created using the option ``by``. For instance:
@@ -381,7 +381,7 @@ def hist_frame(
 .. plot::
     :context: close-figs
 
-    >>> boxplot = df.boxplot(grid=False, rot=45, fontsize=15)
+    >>> boxplot = df.boxplot(grid=False, rot=45, fontsize=15)  # doctest: +SKIP
 
 The parameter ``return_type`` can be used to select the type of element
 returned by `boxplot`.  When ``return_type='axes'`` is selected,
@@ -591,14 +591,14 @@ def boxplot_frame_groupby(
         >>> data = np.random.randn(len(index),4)
         >>> df = pd.DataFrame(data, columns=list('ABCD'), index=index)
         >>> grouped = df.groupby(level='lvl1')
-        >>> grouped.boxplot(rot=45, fontsize=12, figsize=(8,10))
+        >>> grouped.boxplot(rot=45, fontsize=12, figsize=(8,10))  # doctest: +SKIP
 
     The ``subplots=False`` option shows the boxplots in a single figure.
 
     .. plot::
         :context: close-figs
 
-        >>> grouped.boxplot(subplots=False, rot=45, fontsize=12)
+        >>> grouped.boxplot(subplots=False, rot=45, fontsize=12)  # doctest: +SKIP
     """
     plot_backend = _get_plot_backend(backend)
     return plot_backend.boxplot_frame_groupby(
@@ -987,6 +987,7 @@ def __call__(self, *args, **kwargs):
 
             >>> s = pd.Series([1, 3, 2])
             >>> s.plot.line()
+            <AxesSubplot:ylabel='Density'>
 
         .. plot::
             :context: close-figs

diff --git a/pandas/plotting/_matplotlib/groupby.py b/pandas/plotting/_matplotlib/groupby.py
@@ -49,8 +49,15 @@ def create_iter_data_given_by(
     ...          [3, 4, np.nan, np.nan], [np.nan, np.nan, 5, 6]]
     >>> data = DataFrame(value, columns=mi)
     >>> create_iter_data_given_by(data)
-    {'h1': DataFrame({'a': [1, 3, np.nan], 'b': [3, 4, np.nan]}),
-     'h2': DataFrame({'a': [np.nan, np.nan, 5], 'b': [np.nan, np.nan, 6]})}
+    {'h1':     h1
+         a    b
+    0  1.0  3.0
+    1  3.0  4.0
+    2  NaN  NaN, 'h2':     h2
+         a    b
+    0  NaN  NaN
+    1  NaN  NaN
+    2  5.0  6.0}
     """
 
     # For `hist` plot, before transformation, the values in level 0 are values
@@ -96,10 +103,10 @@ def reconstruct_data_with_by(
     >>> df = DataFrame(d)
     >>> reconstruct_data_with_by(df, by='h', cols=['a', 'b'])
        h1      h2
-       a   b   a   b
-    0  1   3   NaN NaN
-    1  3   4   NaN NaN
-    2  NaN NaN 5   6
+       a     b     a     b
+    0  1.0   3.0   NaN   NaN
+    1  3.0   4.0   NaN   NaN
+    2  NaN   NaN   5.0   6.0
     """
     grouped = data.groupby(by)
 

diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py
@@ -123,6 +123,22 @@ def scatter_matrix(
 
         >>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
         >>> pd.plotting.scatter_matrix(df, alpha=0.2)
+        array([[<AxesSubplot:xlabel='A', ylabel='A'>,
+            <AxesSubplot:xlabel='B', ylabel='A'>,
+            <AxesSubplot:xlabel='C', ylabel='A'>,
+            <AxesSubplot:xlabel='D', ylabel='A'>],
+           [<AxesSubplot:xlabel='A', ylabel='B'>,
+            <AxesSubplot:xlabel='B', ylabel='B'>,
+            <AxesSubplot:xlabel='C', ylabel='B'>,
+            <AxesSubplot:xlabel='D', ylabel='B'>],
+           [<AxesSubplot:xlabel='A', ylabel='C'>,
+            <AxesSubplot:xlabel='B', ylabel='C'>,
+            <AxesSubplot:xlabel='C', ylabel='C'>,
+            <AxesSubplot:xlabel='D', ylabel='C'>],
+           [<AxesSubplot:xlabel='A', ylabel='D'>,
+            <AxesSubplot:xlabel='B', ylabel='D'>,
+            <AxesSubplot:xlabel='C', ylabel='D'>,
+            <AxesSubplot:xlabel='D', ylabel='D'>]], dtype=object)
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.scatter_matrix(
@@ -208,6 +224,7 @@ def radviz(frame, class_column, ax=None, color=None, colormap=None, **kwds):
         ...     }
         ... )
         >>> pd.plotting.radviz(df, 'Category')
+        <AxesSubplot:xlabel='y(t)', ylabel='y(t + 1)'>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.radviz(
@@ -266,6 +283,7 @@ def andrews_curves(
         ...     'pandas/master/pandas/tests/io/data/csv/iris.csv'
         ... )
         >>> pd.plotting.andrews_curves(df, 'Name')
+        <AxesSubplot:title={'center':'width'}>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.andrews_curves(
@@ -325,6 +343,7 @@ def bootstrap_plot(series, fig=None, size=50, samples=500, **kwds):
 
         >>> s = pd.Series(np.random.uniform(size=100))
         >>> pd.plotting.bootstrap_plot(s)
+        <Figure size 640x480 with 6 Axes>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.bootstrap_plot(
@@ -392,6 +411,7 @@ def parallel_coordinates(
         >>> pd.plotting.parallel_coordinates(
         ...     df, 'Name', color=('#556270', '#4ECDC4', '#C7F464')
         ... )
+        <AxesSubplot:xlabel='y(t)', ylabel='y(t + 1)'>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.parallel_coordinates(
@@ -440,13 +460,15 @@ def lag_plot(series, lag=1, ax=None, **kwds):
         >>> x = np.cumsum(np.random.normal(loc=1, scale=5, size=50))
         >>> s = pd.Series(x)
         >>> s.plot()
+        <AxesSubplot:xlabel='Midrange'>
 
     A lag plot with ``lag=1`` returns
 
     .. plot::
         :context: close-figs
 
         >>> pd.plotting.lag_plot(s, lag=1)
+        <AxesSubplot:xlabel='y(t)', ylabel='y(t + 1)'>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.lag_plot(series=series, lag=lag, ax=ax, **kwds)
@@ -480,6 +502,7 @@ def autocorrelation_plot(series, ax=None, **kwargs):
         >>> spacing = np.linspace(-9 * np.pi, 9 * np.pi, num=1000)
         >>> s = pd.Series(0.7 * np.random.rand(1000) + 0.3 * np.sin(spacing))
         >>> pd.plotting.autocorrelation_plot(s)
+        <AxesSubplot:title={'center':'width'}, xlabel='Lag', ylabel='Autocorrelation'>
     """
     plot_backend = _get_plot_backend("matplotlib")
     return plot_backend.autocorrelation_plot(series=series, ax=ax, **kwargs)