CLN/DOC: typos (#46328)

* fix typos

* fix typo

* fix typo

* fix typo

Author: lukemanley

pandas/_libs/hashtable_func_helper.pxi.in

@@ -190,7 +190,7 @@ cdef ismember_{{dtype}}(const {{dtype}}_t[:] arr, const {{dtype}}_t[:] values):
 
     Returns
     -------
-    boolean ndarry len of (arr)
+    boolean ndarray len of (arr)
     """
     cdef:
         Py_ssize_t i, n

pandas/_libs/index.pyx

@@ -1066,7 +1066,7 @@ cdef class ExtensionEngine(SharedEngine):
         try:
             return self.values == val
         except TypeError:
-            # e.g. if __eq__ returns a BooleanArray instead of ndarry[bool]
+            # e.g. if __eq__ returns a BooleanArray instead of ndarray[bool]
             try:
                 return (self.values == val).to_numpy(dtype=bool, na_value=False)
             except (TypeError, AttributeError) as err:

pandas/core/arrays/base.py

@@ -1401,7 +1401,7 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
 
     # ------------------------------------------------------------------------
     # Non-Optimized Default Methods; in the case of the private methods here,
-    #  these are not guaranteeed to be stable across pandas versions.
+    #  these are not guaranteed to be stable across pandas versions.
 
     def tolist(self) -> list:
         """

pandas/core/indexes/multi.py

@@ -2311,7 +2311,7 @@ def swaplevel(self, i=-2, j=-1) -> MultiIndex:
         See Also
         --------
         Series.swaplevel : Swap levels i and j in a MultiIndex.
-        Dataframe.swaplevel : Swap levels i and j in a MultiIndex on a
+        DataFrame.swaplevel : Swap levels i and j in a MultiIndex on a
             particular axis.
 
         Examples

pandas/io/formats/style.py

@@ -3423,7 +3423,7 @@ def highlight_between(
 
         .. figure:: ../../_static/style/hbetw_basic.png
 
-        Using a range input sequnce along an ``axis``, in this case setting a ``left``
+        Using a range input sequence along an ``axis``, in this case setting a ``left``
         and ``right`` for each column individually
 
         >>> df.style.highlight_between(left=[1.4, 2.4, 3.4], right=[1.6, 2.6, 3.6],

pandas/io/formats/style_render.py

@@ -436,7 +436,7 @@ def _generate_col_header_row(self, iter: tuple, max_cols: int, col_lengths: dict
             Looping variables from outer scope
         max_cols : int
             Permissible number of columns
-        col_lenths :
+        col_lengths :
             c
 
         Returns

pandas/io/formats/xml.py

@@ -62,7 +62,7 @@ class BaseXMLFormatter:
     elem_cols : list
         List of columns to write as children in row element.
 
-    namespacess : dict
+    namespaces : dict
         The namespaces to define in XML document as dicts with key
         being namespace and value the URI.
 
@@ -485,9 +485,9 @@ def build_tree(self) -> bytes:
 
     def convert_empty_str_key(self) -> None:
         """
-        Replace zero-lengh string in `namespaces`.
+        Replace zero-length string in `namespaces`.
 
-        This method will replce '' with None to align to `lxml`
+        This method will replace '' with None to align to `lxml`
         requirement that empty string prefixes are not allowed.
         """
 

pandas/io/xml.py

@@ -60,7 +60,7 @@ class _XMLFrameParser:
         The XPath expression to parse required set of nodes for
         migration to `Data Frame`. `etree` supports limited XPath.
 
-    namespacess : dict
+    namespaces : dict
         The namespaces defined in XML document (`xmlns:namespace='URI')
         as dicts with key being namespace and value the URI.
 

pandas/tests/arithmetic/test_datetime64.py

@@ -2018,7 +2018,7 @@ def test_dti_add_tdi(self, tz_naive_fixture):
         expected = date_range("2017-01-01", periods=10, tz=tz)
         expected = expected._with_freq(None)
 
-        # add with TimdeltaIndex
+        # add with TimedeltaIndex
         result = dti + tdi
         tm.assert_index_equal(result, expected)
 
@@ -2040,7 +2040,7 @@ def test_dti_iadd_tdi(self, tz_naive_fixture):
         expected = date_range("2017-01-01", periods=10, tz=tz)
         expected = expected._with_freq(None)
 
-        # iadd with TimdeltaIndex
+        # iadd with TimedeltaIndex
         result = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
         result += tdi
         tm.assert_index_equal(result, expected)

pandas/tests/arrays/masked_shared.py

@@ -127,7 +127,7 @@ def test_ufunc_with_out(self, dtype):
         assert isinstance(result, np.ndarray)
         assert result.all()
 
-        # result |= mask worked because mask could be cast lossslessly to
+        # result |= mask worked because mask could be cast losslessly to
         #  boolean ndarray. mask2 can't, so this raises
         result = np.zeros(3, dtype=bool)
         msg = "Specify an appropriate 'na_value' for this dtype"

pandas/tests/groupby/test_allowlist.py

@@ -419,7 +419,7 @@ def test_all_methods_categorized(mframe):
     # new public method?
     if new_names:
         msg = f"""
-There are uncatgeorized methods defined on the Grouper class:
+There are uncategorized methods defined on the Grouper class:
 {new_names}.
 
 Was a new method recently added?

pandas/tests/groupby/test_categorical.py

@@ -1524,7 +1524,7 @@ def test_groupby_agg_non_numeric():
 
 
 @pytest.mark.parametrize("func", ["first", "last"])
-def test_groupy_first_returned_categorical_instead_of_dataframe(func):
+def test_groupby_first_returned_categorical_instead_of_dataframe(func):
     # GH 28641: groupby drops index, when grouping over categorical column with
     # first/last. Renamed Categorical instead of DataFrame previously.
     df = DataFrame({"A": [1997], "B": Series(["b"], dtype="category").cat.as_ordered()})

pandas/tests/groupby/test_indexing.py

@@ -221,7 +221,7 @@ def test_against_head_and_tail(arg, method, simulated):
 @pytest.mark.parametrize("stop", [None, 0, 1, 10, -1, -10])
 @pytest.mark.parametrize("step", [None, 1, 5])
 def test_against_df_iloc(start, stop, step):
-    # Test that a single group gives the same results as DataFame.iloc
+    # Test that a single group gives the same results as DataFrame.iloc
     n_rows = 30
 
     data = {

pandas/tests/groupby/test_nth.py

@@ -665,7 +665,7 @@ def test_first_categorical_and_datetime_data_nat():
     tm.assert_frame_equal(result, expected)
 
 
-def test_first_multi_key_groupbby_categorical():
+def test_first_multi_key_groupby_categorical():
     # GH 22512
     df = DataFrame(
         {

pandas/tests/indexes/categorical/test_reindex.py

@@ -19,7 +19,7 @@ def test_reindex_list_non_unique(self):
         tm.assert_index_equal(res, Index(["a", "a", "c"]), exact=True)
         tm.assert_numpy_array_equal(indexer, np.array([0, 3, 2], dtype=np.intp))
 
-    def test_reindex_categorcal_non_unique(self):
+    def test_reindex_categorical_non_unique(self):
         ci = CategoricalIndex(["a", "b", "c", "a"])
         with tm.assert_produces_warning(FutureWarning, match="non-unique"):
             res, indexer = ci.reindex(Categorical(["a", "c"]))

pandas/tests/indexes/numeric/test_numeric.py

@@ -205,7 +205,7 @@ def test_equals_numeric_other_index_type(self, other):
     def test_lookups_datetimelike_values(self, vals, dtype):
 
         # If we have datetime64 or timedelta64 values, make sure they are
-        #  wrappped correctly  GH#31163
+        #  wrapped correctly  GH#31163
         ser = Series(vals, index=range(3, 6))
         ser.index = ser.index.astype(dtype)
 

pandas/tests/io/formats/test_to_csv.py

@@ -46,7 +46,7 @@ def test_to_csv_with_single_column(self):
             with open(path) as f:
                 assert f.read() == expected2
 
-    def test_to_csv_defualt_encoding(self):
+    def test_to_csv_default_encoding(self):
         # GH17097
         df = DataFrame({"col": ["AAAAA", "ÄÄÄÄÄ", "ßßßßß", "聞聞聞聞聞"]})
 

pandas/tests/scalar/interval/test_arithmetic.py

@@ -52,7 +52,7 @@ def test_numeric_interval_add_timedelta_raises(interval, delta):
 
 
 @pytest.mark.parametrize("klass", [timedelta, np.timedelta64, Timedelta])
-def test_timdelta_add_timestamp_interval(klass):
+def test_timedelta_add_timestamp_interval(klass):
     delta = klass(0)
     expected = Interval(Timestamp("2020-01-01"), Timestamp("2020-02-01"))
 

pandas/tests/scalar/period/test_period.py

@@ -836,7 +836,7 @@ def _period_constructor(bound, offset):
 
     @pytest.mark.parametrize("bound, offset", [(Timestamp.min, -1), (Timestamp.max, 1)])
     @pytest.mark.parametrize("period_property", ["start_time", "end_time"])
-    def test_outter_bounds_start_and_end_time(self, bound, offset, period_property):
+    def test_outer_bounds_start_and_end_time(self, bound, offset, period_property):
         # GH #13346
         period = TestPeriodProperties._period_constructor(bound, offset)
         with pytest.raises(OutOfBoundsDatetime, match="Out of bounds nanosecond"):