Update

Author: thoo

ci/code_checks.sh

@@ -240,8 +240,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, EX04)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04
+    MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, EX04, SS05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04, SS05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

pandas/core/dtypes/common.py

@@ -1980,7 +1980,7 @@ def _validate_date_like_dtype(dtype):
 
 def pandas_dtype(dtype):
     """
-    Converts input into a pandas only dtype object or a numpy dtype object.
+    Convert input into a pandas only dtype object or a numpy dtype object.
 
     Parameters
     ----------

pandas/core/generic.py

@@ -10127,7 +10127,8 @@ def nanptp(values, axis=0, skipna=True):
 
         cls.ptp = _make_stat_function(
             cls, 'ptp', name, name2, axis_descr,
-            """Returns the difference between the maximum value and the
+            """
+            Return the difference between the maximum value and the
             minimum value in the object. This is the equivalent of the
             ``numpy.ndarray`` method ``ptp``.\n\n.. deprecated:: 0.24.0
                 Use numpy.ptp instead""",

pandas/core/indexes/category.py

@@ -232,7 +232,7 @@ def _is_dtype_compat(self, other):
 
     def equals(self, other):
         """
-        Determines if two CategorialIndex objects contain the same elements.
+        Determine if two CategorialIndex objects contain the same elements.
         """
         if self.is_(other):
             return True

pandas/core/indexes/datetimes.py

@@ -1284,7 +1284,7 @@ def delete(self, loc):
 
     def indexer_at_time(self, time, asof=False):
         """
-        Returns index locations of index values at particular time of day
+        Return index locations of index values at particular time of day
         (e.g. 9:30AM).
 
         Parameters

pandas/core/ops.py

@@ -447,7 +447,7 @@ def _get_op_name(op, special):
         _op_descriptions[reverse_op]['reverse'] = key
 
 _flex_doc_SERIES = """
-{desc} of series and other, element-wise (binary operator `{op_name}`).
+Generate {desc} of series and other, element-wise (binary operator `{op_name}`).
 
 Equivalent to ``{equiv}``, but with support to substitute a fill_value for
 missing data in one of the inputs.
@@ -525,7 +525,7 @@ def _get_op_name(op, special):
 """
 
 _flex_doc_FRAME = """
-{desc} of dataframe and other, element-wise (binary operator `{op_name}`).
+Generate {desc} of dataframe and other, element-wise (binary operator `{op_name}`).
 
 Equivalent to ``{equiv}``, but with support to substitute a fill_value
 for missing data in one of the inputs. With reverse version, `{reverse}`.
@@ -679,7 +679,7 @@ def _get_op_name(op, special):
 """
 
 _flex_comp_doc_FRAME = """
-{desc} of dataframe and other, element-wise (binary operator `{op_name}`).
+Generate {desc} of dataframe and other, element-wise (binary operator `{op_name}`).
 
 Among flexible wrappers (`eq`, `ne`, `le`, `lt`, `ge`, `gt`) to comparison
 operators.
@@ -825,7 +825,7 @@ def _get_op_name(op, special):
 """
 
 _flex_doc_PANEL = """
-{desc} of series and other, element-wise (binary operator `{op_name}`).
+Generate {desc} of series and other, element-wise (binary operator `{op_name}`).
 Equivalent to ``{equiv}``.
 
 Parameters

pandas/core/strings.py

@@ -2869,7 +2869,7 @@ def rindex(self, sub, start=0, end=None):
         return self._wrap_result(result)
 
     _shared_docs['len'] = ("""
-    Computes the length of each element in the Series/Index. The element may be
+    Compute the length of each element in the Series/Index. The element may be
     a sequence (such as a string, tuple or list) or a collection
     (such as a dictionary).
 

pandas/core/window.py

@@ -438,7 +438,7 @@ def aggregate(self, arg, *args, **kwargs):
 
 class Window(_Window):
     """
-    Provides rolling window calculations.
+    Provide rolling window calculations.
 
     .. versionadded:: 0.18.0
 
@@ -1803,7 +1803,7 @@ def corr(self, other=None, pairwise=None, **kwargs):
 
 class RollingGroupby(_GroupByMixin, Rolling):
     """
-    Provides a rolling groupby implementation.
+    Provide a rolling groupby implementation.
 
     .. versionadded:: 0.18.1
 
@@ -1834,7 +1834,7 @@ def _validate_monotonic(self):
 
 class Expanding(_Rolling_and_Expanding):
     """
-    Provides expanding transformations.
+    Provide expanding transformations.
 
     .. versionadded:: 0.18.0
 
@@ -2076,7 +2076,7 @@ def corr(self, other=None, pairwise=None, **kwargs):
 
 class ExpandingGroupby(_GroupByMixin, Expanding):
     """
-    Provides a expanding groupby implementation.
+    Provide a expanding groupby implementation.
 
     .. versionadded:: 0.18.1
 

pandas/io/stata.py

@@ -119,7 +119,7 @@
        _iterator_params)
 
 _data_method_doc = """\
-Reads observations from Stata file, converting them into a dataframe
+Read observations from Stata file, converting them into a dataframe
 
 .. deprecated::
     This is a legacy method.  Use `read` in new code.
@@ -1726,18 +1726,22 @@ def _do_convert_categoricals(self, data, value_label_dict, lbllist,
         return data
 
     def data_label(self):
-        """Returns data label of Stata file"""
+        """
+        Return data label of Stata file.
+        """
         return self.data_label
 
     def variable_labels(self):
-        """Returns variable labels as a dict, associating each variable name
-        with corresponding label
+        """
+        Return variable labels as a dict, associating each variable name
+        with corresponding label.
         """
         return dict(zip(self.varlist, self._variable_labels))
 
     def value_labels(self):
-        """Returns a dict, associating each variable name a dict, associating
-        each value its corresponding label
+        """
+        Return a dict, associating each variable name a dict, associating
+        each value its corresponding label.
         """
         if not self._value_labels_read:
             self._read_value_labels()
@@ -1747,7 +1751,7 @@ def value_labels(self):
 
 def _open_file_binary_write(fname):
     """
-    Open a binary file or no-op if file-like
+    Open a binary file or no-op if file-like.
 
     Parameters
     ----------
@@ -1778,14 +1782,14 @@ def _set_endianness(endianness):
 
 def _pad_bytes(name, length):
     """
-    Takes a char string and pads it with null bytes until it's length chars
+    Take a char string and pads it with null bytes until it's length chars.
     """
     return name + "\x00" * (length - len(name))
 
 
 def _convert_datetime_to_stata_type(fmt):
     """
-    Converts from one of the stata date formats to a type in TYPE_MAP
+    Convert from one of the stata date formats to a type in TYPE_MAP.
     """
     if fmt in ["tc", "%tc", "td", "%td", "tw", "%tw", "tm", "%tm", "tq",
                "%tq", "th", "%th", "ty", "%ty"]:
@@ -1812,7 +1816,7 @@ def _maybe_convert_to_int_keys(convert_dates, varlist):
 
 def _dtype_to_stata_type(dtype, column):
     """
-    Converts dtype types to stata types. Returns the byte of the given ordinal.
+    Convert dtype types to stata types. Returns the byte of the given ordinal.
     See TYPE_MAP and comments for an explanation. This is also explained in
     the dta spec.
     1 - 244 are strings of this length
@@ -1850,7 +1854,7 @@ def _dtype_to_stata_type(dtype, column):
 def _dtype_to_default_stata_fmt(dtype, column, dta_version=114,
                                 force_strl=False):
     """
-    Maps numpy dtype to stata's default format for this type. Not terribly
+    Map numpy dtype to stata's default format for this type. Not terribly
     important since users can change this in Stata. Semantics are
 
     object  -> "%DDs" where DD is the length of the string.  If not a string,

pandas/plotting/_misc.py

@@ -273,7 +273,7 @@ def normalize(series):
 def andrews_curves(frame, class_column, ax=None, samples=200, color=None,
                    colormap=None, **kwds):
     """
-    Generates a matplotlib plot of Andrews curves, for visualising clusters of
+    Generate a matplotlib plot of Andrews curves, for visualising clusters of
     multivariate data.
 
     Andrews curves have the functional form:
@@ -598,7 +598,8 @@ def lag_plot(series, lag=1, ax=None, **kwds):
 
 
 def autocorrelation_plot(series, ax=None, **kwds):
-    """Autocorrelation plot for time series.
+    """
+    Autocorrelation plot for time series.
 
     Parameters:
     -----------

pandas/util/_decorators.py

@@ -9,7 +9,8 @@
 
 def deprecate(name, alternative, version, alt_name=None,
               klass=None, stacklevel=2, msg=None):
-    """Return a new function that emits a deprecation warning on use.
+    """
+    Return a new function that emits a deprecation warning on use.
 
     To use this method for a deprecated function, another function
     `alternative` with the same signature must exist. The deprecated