DOC: Fixed PR08 docstring errors in pandas.DataFrame (pandas-dev#28655)

Author: jb8429

pandas/core/frame.py

@@ -2066,7 +2066,7 @@ def to_feather(self, fname):
         Parameters
         ----------
         fname : str
-            string file path
+            String file path.
         """
         from pandas.io.feather_format import to_feather
 
@@ -4772,6 +4772,7 @@ def drop_duplicates(self, subset=None, keep="first", inplace=False):
             Only consider certain columns for identifying duplicates, by
             default use all of the columns
         keep : {'first', 'last', False}, default 'first'
+            Determines which duplicates (if any) to keep.
             - ``first`` : Drop duplicates except for the first occurrence.
             - ``last`` : Drop duplicates except for the last occurrence.
             - False : Drop all duplicates.
@@ -4806,10 +4807,10 @@ def duplicated(self, subset=None, keep="first"):
             Only consider certain columns for identifying duplicates, by
             default use all of the columns
         keep : {'first', 'last', False}, default 'first'
-            - ``first`` : Mark duplicates as ``True`` except for the
-              first occurrence.
-            - ``last`` : Mark duplicates as ``True`` except for the
-              last occurrence.
+            Determines which duplicates (if any) to mark.
+
+            - ``first`` : Mark duplicates as ``True`` except for the first occurrence.
+            - ``last`` : Mark duplicates as ``True`` except for the last occurrence.
             - False : Mark all duplicates as ``True``.
 
         Returns
@@ -6233,8 +6234,8 @@ def unstack(self, level=-1, fill_value=None):
         ----------
         level : int, str, or list of these, default -1 (last level)
             Level(s) of index to unstack, can pass level name
-        fill_value : replace NaN with this value if the unstack produces
-            missing values
+        fill_value : int, string or dict
+            Replace NaN with this value if the unstack produces missing values
 
         Returns
         -------
@@ -6665,6 +6666,8 @@ def apply(
                by result_type='broadcast'.
 
         raw : bool, default False
+            Determines if row or column is passed as a Series or ndarry object:
+
             * ``False`` : passes each row or column as a Series to the
               function.
             * ``True`` : the passed function will receive ndarray objects
@@ -7357,6 +7360,8 @@ def corr(self, method="pearson", min_periods=1):
         Parameters
         ----------
         method : {'pearson', 'kendall', 'spearman'} or callable
+            Method of correlation:
+
             * pearson : standard correlation coefficient
             * kendall : Kendall Tau correlation coefficient
             * spearman : Spearman rank correlation
@@ -7556,10 +7561,13 @@ def corrwith(self, other, axis=0, drop=False, method="pearson"):
         other : DataFrame, Series
             Object with which to compute correlations.
         axis : {0 or 'index', 1 or 'columns'}, default 0
-            0 or 'index' to compute column-wise, 1 or 'columns' for row-wise.
+            The axis to use. 0 or 'index' to compute column-wise, 1 or 'columns' for
+            row-wise.
         drop : bool, default False
             Drop missing indices from result.
         method : {'pearson', 'kendall', 'spearman'} or callable
+            Method of correlation:
+
             * pearson : standard correlation coefficient
             * kendall : Kendall Tau correlation coefficient
             * spearman : Spearman rank correlation
@@ -7939,8 +7947,8 @@ def idxmin(self, axis=0, skipna=True):
         Parameters
         ----------
         axis : {0 or 'index', 1 or 'columns'}, default 0
-            0 or 'index' for row-wise, 1 or 'columns' for column-wise
-        skipna : bool, default True
+            The axis to use. 0 or 'index' for row-wise, 1 or 'columns' for column-wise
+        skipna : boolean, default True
             Exclude NA/null values. If an entire row/column is NA, the result
             will be NA.
 
@@ -7976,8 +7984,8 @@ def idxmax(self, axis=0, skipna=True):
         Parameters
         ----------
         axis : {0 or 'index', 1 or 'columns'}, default 0
-            0 or 'index' for row-wise, 1 or 'columns' for column-wise
-        skipna : bool, default True
+            The axis to use. 0 or 'index' for row-wise, 1 or 'columns' for column-wise
+        skipna : boolean, default True
             Exclude NA/null values. If an entire row/column is NA, the result
             will be NA.
 

pandas/core/generic.py

@@ -2559,10 +2559,10 @@ def to_msgpack(self, path_or_buf=None, encoding="utf-8", **kwargs):
         path : str, buffer-like, or None
             Destination for the serialized object.
             If None, return generated bytes
-        append : bool whether to append to an existing msgpack
-            (default is False)
-        compress : type of compressor (zlib or blosc), default to None (no
-            compression)
+        append : bool, default False
+            Whether to append to an existing msgpack.
+        compress : str, default None
+            Type of compressor (zlib, blosc or None).
 
         Returns
         -------
@@ -2797,10 +2797,10 @@ def to_clipboard(self, excel=True, sep=None, **kwargs):
         Parameters
         ----------
         excel : bool, default True
-            - True, use the provided separator, writing in a csv format for
-              allowing easy pasting into excel.
-            - False, write a string representation of the object to the
-              clipboard.
+            Produce output in a csv format for easy pasting into excel.
+
+            - True, use the provided separator for csv pasting.
+            - False, write a string representation of the object to the clipboard.
 
         sep : str, default ``'\t'``
             Field delimiter.
@@ -5024,15 +5024,15 @@ def sample(
         Parameters
         ----------
         func : function
-            function to apply to the %(klass)s.
+            Function to apply to the %(klass)s.
             ``args``, and ``kwargs`` are passed into ``func``.
             Alternatively a ``(callable, data_keyword)`` tuple where
             ``data_keyword`` is a string indicating the keyword of
             ``callable`` that expects the %(klass)s.
         args : iterable, optional
-            positional arguments passed into ``func``.
+            Positional arguments passed into ``func``.
         kwargs : mapping, optional
-            a dictionary of keyword arguments passed into ``func``.
+            A dictionary of keyword arguments passed into ``func``.
 
         Returns
         -------

pandas/plotting/_core.py

@@ -514,6 +514,8 @@ class PlotAccessor(PandasObject):
         Allows plotting of one column versus another. Only used if data is a
         DataFrame.
     kind : str
+        The kind of plot to produce:
+
         - 'line' : line plot (default)
         - 'bar' : vertical bar plot
         - 'barh' : horizontal bar plot
@@ -537,7 +539,7 @@ class PlotAccessor(PandasObject):
     legend : False/True/'reverse'
         Place legend on axis subplots
     style : list or dict
-        matplotlib line style per column
+        The matplotlib line style per column
     logx : bool or 'sym', default False
         Use log scaling or symlog scaling on x axis
         .. versionchanged:: 0.25.0