Fix validation error type SS05 and check in CI (pandas-dev#25133)

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, RT04)' ; echo $MSG
- $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04,RT04
+ MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, EX04, RT04, SS05)' ; echo $MSG
+ $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04,RT04,SS05
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

pandas/_libs/tslibs/nattype.pyx

@@ -183,7 +183,9 @@ cdef class _NaT(datetime):
  return np.datetime64(NPY_NAT, 'ns')
 
  def to_datetime64(self):
- """ Returns a numpy.datetime64 object with 'ns' precision """
+ """
+ Return a numpy.datetime64 object with 'ns' precision.
+ """
  return np.datetime64('NaT', 'ns')
 
  def __repr__(self):
@@ -448,7 +450,7 @@ class NaTType(_NaT):
  """
  Timestamp.now(tz=None)
 
- Returns new Timestamp object representing current time local to
+ Return new Timestamp object representing current time local to
  tz.
 
  Parameters

pandas/_libs/tslibs/timestamps.pyx

@@ -340,7 +340,9 @@ cdef class _Timestamp(datetime):
  self.microsecond, self.tzinfo)
 
  cpdef to_datetime64(self):
- """ Returns a numpy.datetime64 object with 'ns' precision """
+ """
+ Return a numpy.datetime64 object with 'ns' precision.
+ """
  return np.datetime64(self.value, 'ns')
 
  def __add__(self, other):
@@ -614,7 +616,7 @@ class Timestamp(_Timestamp):
  """
  Timestamp.now(tz=None)
 
- Returns new Timestamp object representing current time local to
+ Return new Timestamp object representing current time local to
  tz.
 
  Parameters

pandas/core/arrays/categorical.py

@@ -214,7 +214,7 @@ def contains(cat, key, container):
 
 class Categorical(ExtensionArray, PandasObject):
  """
- Represents a categorical variable in classic R / S-plus fashion
+ Represent a categorical variable in classic R / S-plus fashion
 
  `Categoricals` can only take on only a limited, and usually fixed, number
  of possible values (`categories`). In contrast to statistical categorical
@@ -747,7 +747,7 @@ def _set_dtype(self, dtype):
 
  def set_ordered(self, value, inplace=False):
  """
- Sets the ordered attribute to the boolean value
+ Set the ordered attribute to the boolean value
 
  Parameters
  ----------
@@ -793,7 +793,7 @@ def as_unordered(self, inplace=False):
  def set_categories(self, new_categories, ordered=None, rename=False,
  inplace=False):
  """
- Sets the categories to the specified new_categories.
+ Set the categories to the specified new_categories.
 
  `new_categories` can include new categories (which will result in
  unused categories) or remove old categories (which results in values
@@ -864,7 +864,7 @@ def set_categories(self, new_categories, ordered=None, rename=False,
 
  def rename_categories(self, new_categories, inplace=False):
  """
- Renames categories.
+ Rename categories.
 
  Parameters
  ----------
@@ -958,7 +958,7 @@ def rename_categories(self, new_categories, inplace=False):
 
  def reorder_categories(self, new_categories, ordered=None, inplace=False):
  """
- Reorders categories as specified in new_categories.
+ Reorder categories as specified in new_categories.
 
  `new_categories` need to include all old categories and no new category
  items.
@@ -1051,7 +1051,7 @@ def add_categories(self, new_categories, inplace=False):
 
  def remove_categories(self, removals, inplace=False):
  """
- Removes the specified categories.
+ Remove the specified categories.
 
  `removals` must be included in the old categories. Values which were in
  the removed categories will be set to NaN
@@ -1104,7 +1104,7 @@ def remove_categories(self, removals, inplace=False):
 
  def remove_unused_categories(self, inplace=False):
  """
- Removes categories which are not used.
+ Remove categories which are not used.
 
  Parameters
  ----------
@@ -1454,7 +1454,7 @@ def dropna(self):
 
  def value_counts(self, dropna=True):
  """
- Returns a Series containing counts of each category.
+ Return a Series containing counts of each category.
 
  Every category will have an entry, even those with a count of 0.
 
@@ -1570,7 +1570,7 @@ def argsort(self, *args, **kwargs):
 
  def sort_values(self, inplace=False, ascending=True, na_position='last'):
  """
- Sorts the Categorical by category value returning a new
+ Sort the Categorical by category value returning a new
  Categorical by default.
 
  While an ordering is applied to the category values, sorting in this

pandas/core/dtypes/common.py

@@ -2006,7 +2006,7 @@ 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/dtypes/dtypes.py

@@ -17,7 +17,8 @@
 
 
 def register_extension_dtype(cls):
- """Class decorator to register an ExtensionType with pandas.
+ """
+ Register an ExtensionType with pandas as class decorator.
 
  .. versionadded:: 0.24.0
 

pandas/core/frame.py

@@ -6009,7 +6009,7 @@ def unstack(self, level=-1, fill_value=None):
  return unstack(self, level, fill_value)
 
  _shared_docs['melt'] = ("""
- Unpivots a DataFrame from wide format to long format, optionally
+ Unpivot a DataFrame from wide format to long format, optionally
  leaving identifier variables set.
 
  This function is useful to massage a DataFrame into a format where one

pandas/core/generic.py

@@ -10125,7 +10125,7 @@ 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/groupby/generic.py

@@ -1021,7 +1021,9 @@ def true_and_notna(x, *args, **kwargs):
  return filtered
 
  def nunique(self, dropna=True):
- """ Returns number of unique elements in the group """
+ """
+ Return number of unique elements in the group.
+ """
  ids, _, _ = self.grouper.group_info
 
  val = self.obj.get_values()

pandas/core/groupby/groupby.py

@@ -625,7 +625,7 @@ def curried(x):
 
  def get_group(self, name, obj=None):
  """
- Constructs NDFrame from group with provided name.
+ Construct NDFrame from group with provided name.
 
  Parameters
  ----------
@@ -1047,7 +1047,7 @@ def result_to_bool(result):
  @Appender(_common_see_also)
  def any(self, skipna=True):
  """
- Returns True if any value in the group is truthful, else False.
+ Return True if any value in the group is truthful, else False.
 
  Parameters
  ----------
@@ -1060,7 +1060,7 @@ def any(self, skipna=True):
  @Appender(_common_see_also)
  def all(self, skipna=True):
  """
- Returns True if all values in the group are truthful, else False.
+ Return True if all values in the group are truthful, else False.
 
  Parameters
  ----------
@@ -1813,7 +1813,7 @@ def cumcount(self, ascending=True):
  def rank(self, method='average', ascending=True, na_option='keep',
  pct=False, axis=0):
  """
- Provides the rank of values within each group.
+ Provide the rank of values within each group.
 
  Parameters
  ----------
@@ -2039,7 +2039,7 @@ def pct_change(self, periods=1, fill_method='pad', limit=None, freq=None,
  @Substitution(name='groupby', see_also=_common_see_also)
  def head(self, n=5):
  """
- Returns first n rows of each group.
+ Return first n rows of each group.
 
  Essentially equivalent to ``.apply(lambda x: x.head(n))``,
  except ignores as_index flag.
@@ -2067,7 +2067,7 @@ def head(self, n=5):
  @Substitution(name='groupby', see_also=_common_see_also)
  def tail(self, n=5):
  """
- Returns last n rows of each group.
+ Return last n rows of each group.
 
  Essentially equivalent to ``.apply(lambda x: x.tail(n))``,
  except ignores as_index flag.