DOC: boolean->bool, string->str in docstrings (#40698)

Author: jbrockmendel

pandas/_libs/algos.pyx

@@ -933,10 +933,10 @@ def rank_1d(
         * max: highest rank in group
         * first: ranks assigned in order they appear in the array
         * dense: like 'min', but rank always increases by 1 between groups
-    ascending : boolean, default True
+    ascending : bool, default True
         False for ranks by high (1) to low (N)
         na_option : {'keep', 'top', 'bottom'}, default 'keep'
-    pct : boolean, default False
+    pct : bool, default False
         Compute percentage rank of data within each group
     na_option : {'keep', 'top', 'bottom'}, default 'keep'
         * keep: leave NA values where they are

pandas/_libs/groupby.pyx

@@ -402,9 +402,9 @@ def group_any_all(uint8_t[::1] out,
         ordering matching up to the corresponding record in `values`
     values : array containing the truth value of each element
     mask : array indicating whether a value is na or not
-    val_test : str {'any', 'all'}
+    val_test : {'any', 'all'}
         String object dictating whether to use any or all truth testing
-    skipna : boolean
+    skipna : bool
         Flag to ignore nan values during truth testing
 
     Notes
@@ -1083,10 +1083,10 @@ def group_rank(float64_t[:, ::1] out,
         * max: highest rank in group
         * first: ranks assigned in order they appear in the array
         * dense: like 'min', but rank always increases by 1 between groups
-    ascending : boolean, default True
+    ascending : bool, default True
         False for ranks by high (1) to low (N)
         na_option : {'keep', 'top', 'bottom'}, default 'keep'
-    pct : boolean, default False
+    pct : bool, default False
         Compute percentage rank of data within each group
     na_option : {'keep', 'top', 'bottom'}, default 'keep'
         * keep: leave NA values where they are

pandas/_libs/hashtable_class_helper.pxi.in

@@ -523,15 +523,15 @@ cdef class {{name}}HashTable(HashTable):
             any value "val" satisfying val != val is considered missing.
             If na_value is not None, then _additionally_, any value "val"
             satisfying val == na_value is considered missing.
-        ignore_na : boolean, default False
+        ignore_na : bool, default False
             Whether NA-values should be ignored for calculating the uniques. If
             True, the labels corresponding to missing values will be set to
             na_sentinel.
         mask : ndarray[bool], optional
             If not None, the mask is used as indicator for missing values
             (True = missing, False = valid) instead of `na_value` or
             condition "val != val".
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 
@@ -625,7 +625,7 @@ cdef class {{name}}HashTable(HashTable):
         ----------
         values : ndarray[{{dtype}}]
             Array of values of which unique will be calculated
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 
@@ -906,11 +906,11 @@ cdef class StringHashTable(HashTable):
             that is not a string is considered missing. If na_value is
             not None, then _additionally_ any value "val" satisfying
             val == na_value is considered missing.
-        ignore_na : boolean, default False
+        ignore_na : bool, default False
             Whether NA-values should be ignored for calculating the uniques. If
             True, the labels corresponding to missing values will be set to
             na_sentinel.
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 
@@ -998,7 +998,7 @@ cdef class StringHashTable(HashTable):
         ----------
         values : ndarray[object]
             Array of values of which unique will be calculated
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 
@@ -1181,11 +1181,11 @@ cdef class PyObjectHashTable(HashTable):
             any value "val" satisfying val != val is considered missing.
             If na_value is not None, then _additionally_, any value "val"
             satisfying val == na_value is considered missing.
-        ignore_na : boolean, default False
+        ignore_na : bool, default False
             Whether NA-values should be ignored for calculating the uniques. If
             True, the labels corresponding to missing values will be set to
             na_sentinel.
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 
@@ -1251,7 +1251,7 @@ cdef class PyObjectHashTable(HashTable):
         ----------
         values : ndarray[object]
             Array of values of which unique will be calculated
-        return_inverse : boolean, default False
+        return_inverse : bool, default False
             Whether the mapping of the original array values to their location
             in the vector of uniques should be returned.
 

pandas/_libs/reshape.pyx

@@ -48,13 +48,13 @@ def unstack(reshape_t[:, :] values, const uint8_t[:] mask,
     Parameters
     ----------
     values : typed ndarray
-    mask : boolean ndarray
+    mask : np.ndarray[bool]
     stride : int
     length : int
     width : int
     new_values : typed ndarray
         result array
-    new_mask : boolean ndarray
+    new_mask : np.ndarray[bool]
         result mask
     """
     cdef:

pandas/_libs/tslibs/conversion.pyx

@@ -267,7 +267,7 @@ def ensure_timedelta64ns(arr: ndarray, copy: bool=True):
     Parameters
     ----------
     arr : ndarray
-    copy : boolean, default True
+    copy : bool, default True
 
     Returns
     -------

pandas/_libs/tslibs/fields.pyx

@@ -635,9 +635,9 @@ def get_locale_names(name_type: str, locale: object = None):
 
     Parameters
     ----------
-    name_type : string, attribute of LocaleTime() in which to return localized
-        names
-    locale : string
+    name_type : str
+        Attribute of LocaleTime() in which to return localized names.
+    locale : str
 
     Returns
     -------

pandas/_libs/tslibs/timedeltas.pyx

@@ -540,7 +540,7 @@ cdef inline int64_t timedelta_as_neg(int64_t value, bint neg):
     Parameters
     ----------
     value : int64_t of the timedelta value
-    neg : boolean if the a negative value
+    neg : bool if the a negative value
     """
     if neg:
         return -value

pandas/_testing/__init__.py

@@ -952,7 +952,7 @@ def get_op_from_name(op_name: str) -> Callable:
 
     Parameters
     ----------
-    op_name : string
+    op_name : str
         The op name, in form of "add" or "__add__".
 
     Returns

pandas/core/algorithms.py

@@ -959,7 +959,7 @@ def mode(values, dropna: bool = True) -> Series:
     ----------
     values : array-like
         Array over which to check for duplicate values.
-    dropna : boolean, default True
+    dropna : bool, default True
         Don't consider counts of NaN/NaT.
 
         .. versionadded:: 0.24.0
@@ -1025,9 +1025,9 @@ def rank(
         - ``keep``: rank each NaN value with a NaN ranking
         - ``top``: replace each NaN with either +/- inf so that they
                    there are ranked at the top
-    ascending : boolean, default True
+    ascending : bool, default True
         Whether or not the elements should be ranked in ascending order.
-    pct : boolean, default False
+    pct : bool, default False
         Whether or not to the display the returned rankings in integer form
         (e.g. 1, 2, 3) or in percentile form (e.g. 0.333..., 0.666..., 1).
     """

pandas/core/array_algos/take.py

@@ -76,7 +76,7 @@ def take_nd(
         Axis to take from
     fill_value : any, default np.nan
         Fill value to replace -1 values with
-    allow_fill : boolean, default True
+    allow_fill : bool, default True
         If False, indexer is assumed to contain no -1 values so no filling
         will be done.  This short-circuits computation of a mask.  Result is
         undefined if allow_fill == False and -1 is present in indexer.

pandas/core/dtypes/cast.py

@@ -508,7 +508,7 @@ def maybe_upcast_putmask(result: np.ndarray, mask: np.ndarray) -> np.ndarray:
     result : ndarray
         The destination array. This will be mutated in-place if no upcasting is
         necessary.
-    mask : boolean ndarray
+    mask : np.ndarray[bool]
 
     Returns
     -------

pandas/core/frame.py

@@ -231,7 +231,7 @@
         If 0 or 'index': apply function to each column.
         If 1 or 'columns': apply function to each row.""",
     "inplace": """
-    inplace : boolean, default False
+    inplace : bool, default False
         If True, performs operation inplace and returns None.""",
     "optional_by": """
         by : str or list of str
@@ -251,7 +251,7 @@
     you to specify a location to update with some value.""",
 }
 
-_numeric_only_doc = """numeric_only : boolean, default None
+_numeric_only_doc = """numeric_only : bool or None, default None
     Include only float, int, boolean data. If None, will attempt to use
     everything, then use only numeric data
 """

pandas/core/generic.py

@@ -181,7 +181,7 @@
     "axes_single_arg": "int or labels for object",
     "args_transpose": "axes to permute (int or label for object)",
     "inplace": """
-    inplace : boolean, default False
+    inplace : bool, default False
         If True, performs operation inplace and returns None.""",
     "optional_by": """
         by : str or list of str

pandas/core/groupby/categorical.py

@@ -34,9 +34,9 @@ def recode_for_groupby(
     Parameters
     ----------
     c : Categorical
-    sort : boolean
+    sort : bool
         The value of the sort parameter groupby was called with.
-    observed : boolean
+    observed : bool
         Account only for the observed values
 
     Returns
@@ -93,7 +93,7 @@ def recode_from_groupby(
     Parameters
     ----------
     c : Categorical
-    sort : boolean
+    sort : bool
         The value of the sort parameter groupby was called with.
     ci : CategoricalIndex
         The codes / categories to recode

pandas/core/groupby/grouper.py

@@ -293,7 +293,7 @@ def _get_grouper(self, obj, validate: bool = True):
         Parameters
         ----------
         obj : the subject object
-        validate : boolean, default True
+        validate : bool, default True
             if True, validate the grouper
 
         Returns

pandas/core/groupby/ops.py

@@ -817,8 +817,8 @@ class BinGrouper(BaseGrouper):
     ----------
     bins : the split index of binlabels to group the item of axis
     binlabels : the label list
-    filter_empty : boolean, default False
-    mutated : boolean, default False
+    filter_empty : bool, default False
+    mutated : bool, default False
     indexer : a intp array
 
     Examples

pandas/core/indexing.py

@@ -2009,7 +2009,7 @@ def _align_series(self, indexer, ser: Series, multiindex_indexer: bool = False):
             Indexer used to get the locations that will be set to `ser`.
         ser : pd.Series
             Values to assign to the locations specified by `indexer`.
-        multiindex_indexer : boolean, optional
+        multiindex_indexer : bool, optional
             Defaults to False. Should be set to True if `indexer` was from
             a `pd.MultiIndex`, to avoid unnecessary broadcasting.
 

pandas/core/missing.py

@@ -789,7 +789,7 @@ def _interp_limit(invalid, fw_limit, bw_limit):
 
     Parameters
     ----------
-    invalid : boolean ndarray
+    invalid : np.ndarray[bool]
     fw_limit : int or None
         forward limit to index
     bw_limit : int or None

pandas/core/resample.py

@@ -1272,7 +1272,7 @@ def _upsample(self, method, limit=None, fill_value=None):
         """
         Parameters
         ----------
-        method : string {'backfill', 'bfill', 'pad', 'ffill'}
+        method : {'backfill', 'bfill', 'pad', 'ffill'}
             Method for upsampling.
         limit : int, default None
             Maximum size gap to fill when reindexing.

pandas/core/series.py

@@ -162,7 +162,7 @@
     "axes_single_arg": "{0 or 'index'}",
     "axis": """axis : {0 or 'index'}
         Parameter needed for compatibility with DataFrame.""",
-    "inplace": """inplace : boolean, default False
+    "inplace": """inplace : bool, default False
         If True, performs operation inplace and returns None.""",
     "unique": "np.ndarray",
     "duplicated": "Series",

pandas/core/sorting.py

@@ -278,7 +278,7 @@ def lexsort_indexer(
     ----------
     keys : sequence of arrays
         Sequence of ndarrays to be sorted by the indexer
-    orders : boolean or list of booleans, optional
+    orders : bool or list of booleans, optional
         Determines the sorting order for each element in keys. If a list,
         it must be the same length as keys. This determines whether the
         corresponding element in keys should be sorted in ascending

pandas/core/tools/datetimes.py

@@ -171,7 +171,7 @@ def _maybe_cache(
     arg : listlike, tuple, 1-d array, Series
     format : string
         Strftime format to parse time
-    cache : boolean
+    cache : bool
         True attempts to create a cache of converted values
     convert_listlike : function
         Conversion function to apply on dates
@@ -313,9 +313,9 @@ def _convert_listlike_datetimes(
         error handing behaviors from to_datetime, 'raise', 'coerce', 'ignore'
     infer_datetime_format : bool, default False
         inferring format behavior from to_datetime
-    dayfirst : boolean
+    dayfirst : bool
         dayfirst parsing behavior from to_datetime
-    yearfirst : boolean
+    yearfirst : bool
         yearfirst parsing behavior from to_datetime
     exact : bool, default True
         exact format matching behavior from to_datetime

pandas/io/clipboards.py

@@ -86,7 +86,7 @@ def to_clipboard(obj, excel=True, sep=None, **kwargs):  # pragma: no cover
     Parameters
     ----------
     obj : the object to write to the clipboard
-    excel : boolean, defaults to True
+    excel : bool, defaults to True
             if True, use the provided separator, writing in a csv
             format for allowing easy pasting into excel.
             if False, write a string representation of the object

pandas/io/common.py

@@ -565,9 +565,9 @@ def get_handle(
            Passing compression options as keys in dict is now
            supported for compression modes 'gzip' and 'bz2' as well as 'zip'.
 
-    memory_map : boolean, default False
+    memory_map : bool, default False
         See parsers._parser_params for more information.
-    is_text : boolean, default True
+    is_text : bool, default True
         Whether the type of the content passed to the file/buffer is string or
         bytes. This is not the same as `"b" not in mode`. If a string content is
         passed to a binary file/buffer, a wrapper is inserted.

pandas/io/excel/_odfreader.py

@@ -23,7 +23,7 @@ class ODFReader(BaseExcelReader):
 
     Parameters
     ----------
-    filepath_or_buffer : string, path to be parsed or
+    filepath_or_buffer : str, path to be parsed or
         an open readable stream.
     storage_options : dict, optional
         passed to fsspec for appropriate URLs (see ``_get_filepath_or_buffer``)

pandas/io/excel/_openpyxl.py

@@ -488,7 +488,7 @@ def __init__(
 
         Parameters
         ----------
-        filepath_or_buffer : string, path object or Workbook
+        filepath_or_buffer : str, path object or Workbook
             Object to be parsed.
         storage_options : dict, optional
             passed to fsspec for appropriate URLs (see ``_get_filepath_or_buffer``)

pandas/io/excel/_xlrd.py

@@ -15,7 +15,7 @@ def __init__(self, filepath_or_buffer, storage_options: StorageOptions = None):
 
         Parameters
         ----------
-        filepath_or_buffer : string, path object or Workbook
+        filepath_or_buffer : str, path object or Workbook
             Object to be parsed.
         storage_options : dict, optional
             passed to fsspec for appropriate URLs (see ``_get_filepath_or_buffer``)