Updating DataFrame.mode docstring. (pandas-dev#22404)

Author: datapythonista

pandas/core/frame.py

@@ -7303,38 +7303,82 @@ def _get_agg_axis(self, axis_num):
 
     def mode(self, axis=0, numeric_only=False, dropna=True):
         """
-        Gets the mode(s) of each element along the axis selected. Adds a row
-        for each mode per label, fills in gaps with nan.
+        Get the mode(s) of each element along the selected axis.
 
-        Note that there could be multiple values returned for the selected
-        axis (when more than one item share the maximum frequency), which is
-        the reason why a dataframe is returned. If you want to impute missing
-        values with the mode in a dataframe ``df``, you can just do this:
-        ``df.fillna(df.mode().iloc[0])``
+        The mode of a set of values is the value that appears most often.
+        It can be multiple values.
 
         Parameters
         ----------
         axis : {0 or 'index', 1 or 'columns'}, default 0
+            The axis to iterate over while searching for the mode:
+
             * 0 or 'index' : get mode of each column
             * 1 or 'columns' : get mode of each row
-        numeric_only : boolean, default False
-            if True, only apply to numeric columns
-        dropna : boolean, default True
+        numeric_only : bool, default False
+            If True, only apply to numeric columns.
+        dropna : bool, default True
             Don't consider counts of NaN/NaT.
 
             .. versionadded:: 0.24.0
 
         Returns
         -------
-        modes : DataFrame (sorted)
+        DataFrame
+            The modes of each column or row.
+
+        See Also
+        --------
+        Series.mode : Return the highest frequency value in a Series.
+        Series.value_counts : Return the counts of values in a Series.
 
         Examples
         --------
-        >>> df = pd.DataFrame({'A': [1, 2, 1, 2, 1, 2, 3]})
+        >>> df = pd.DataFrame([('bird', 2, 2),
+        ...                    ('mammal', 4, np.nan),
+        ...                    ('arthropod', 8, 0),
+        ...                    ('bird', 2, np.nan)],
+        ...                   index=('falcon', 'horse', 'spider', 'ostrich'),
+        ...                   columns=('species', 'legs', 'wings'))
+        >>> df
+                   species  legs  wings
+        falcon        bird     2    2.0
+        horse       mammal     4    NaN
+        spider   arthropod     8    0.0
+        ostrich       bird     2    NaN
+
+        By default, missing values are not considered, and the mode of wings
+        are both 0 and 2. The second row of species and legs contains ``NaN``,
+        because they have only one mode, but the DataFrame has two rows.
+
         >>> df.mode()
-           A
-        0  1
-        1  2
+          species  legs  wings
+        0    bird   2.0    0.0
+        1     NaN   NaN    2.0
+
+        Setting ``dropna=False`` ``NaN`` values are considered and they can be
+        the mode (like for wings).
+
+        >>> df.mode(dropna=False)
+          species  legs  wings
+        0    bird     2    NaN
+
+        Setting ``numeric_only=True``, only the mode of numeric columns is
+        computed, and columns of other types are ignored.
+
+        >>> df.mode(numeric_only=True)
+           legs  wings
+        0   2.0    0.0
+        1   NaN    2.0
+
+        To compute the mode over columns and not rows, use the axis parameter:
+
+        >>> df.mode(axis='columns', numeric_only=True)
+                   0    1
+        falcon   2.0  NaN
+        horse    4.0  NaN
+        spider   0.0  8.0
+        ostrich  2.0  NaN
         """
         data = self if not numeric_only else self._get_numeric_data()