Fix typos (#47275)

* fix codespell violations

* drop rule files: ^(pandas|doc)/ from codespell pre-commit config

also fix typos fempto -> femto

* improve codespell ignore-regex in setup.cfg

Co-authored-by: Marco Edward Gorelli <[email protected]>

Co-authored-by: Marco Edward Gorelli <[email protected]>

Author: janosh

.pre-commit-config.yaml

@@ -26,7 +26,6 @@ repos:
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
-        files: ^(pandas|doc)/
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.2.0
     hooks:

asv_bench/benchmarks/frame_ctor.py

@@ -37,7 +37,7 @@ def setup(self):
         self.dict_list = frame.to_dict(orient="records")
         self.data2 = {i: {j: float(j) for j in range(100)} for i in range(2000)}
 
-        # arrays which we wont consolidate
+        # arrays which we won't consolidate
         self.dict_of_categoricals = {i: Categorical(np.arange(N)) for i in range(K)}
 
     def time_list_of_dict(self):
@@ -60,7 +60,7 @@ def time_nested_dict_int64(self):
         DataFrame(self.data2)
 
     def time_dict_of_categoricals(self):
-        # dict of arrays that we wont consolidate
+        # dict of arrays that we won't consolidate
         DataFrame(self.dict_of_categoricals)
 
 

asv_bench/benchmarks/groupby.py

@@ -527,7 +527,7 @@ def time_dtype_as_field(self, dtype, method, application, ncols):
 
 class GroupByCythonAgg:
     """
-    Benchmarks specifically targetting our cython aggregation algorithms
+    Benchmarks specifically targeting our cython aggregation algorithms
     (using a big enough dataframe with simple key, so a large part of the
     time is actually spent in the grouped aggregation).
     """

asv_bench/benchmarks/libs.py

@@ -2,7 +2,7 @@
 Benchmarks for code in pandas/_libs, excluding pandas/_libs/tslibs,
 which has its own directory.
 
-If a PR does not edit anything in _libs/, then it is unlikely that thes
+If a PR does not edit anything in _libs/, then it is unlikely that the
 benchmarks will be affected.
 """
 import numpy as np

asv_bench/benchmarks/replace.py

@@ -50,7 +50,7 @@ def time_replace_list(self, inplace):
         self.df.replace([np.inf, -np.inf], np.nan, inplace=inplace)
 
     def time_replace_list_one_match(self, inplace):
-        # the 1 can be held in self._df.blocks[0], while the inf and -inf cant
+        # the 1 can be held in self._df.blocks[0], while the inf and -inf can't
         self.df.replace([np.inf, -np.inf, 1], np.nan, inplace=inplace)
 
 

asv_bench/benchmarks/reshape.py

@@ -78,7 +78,7 @@ def time_stack(self, dtype):
         self.df.stack()
 
     def time_unstack_fast(self, dtype):
-        # last level -> doesnt have to make copies
+        # last level -> doesn't have to make copies
         self.ser.unstack("bar")
 
     def time_unstack_slow(self, dtype):

asv_bench/benchmarks/tslibs/period.py

@@ -1,6 +1,6 @@
 """
-Period benchmarks that rely only on tslibs.  See benchmarks.period for
-Period benchmarks that rely on other parts fo pandas.
+Period benchmarks that rely only on tslibs. See benchmarks.period for
+Period benchmarks that rely on other parts of pandas.
 """
 
 import numpy as np

asv_bench/benchmarks/tslibs/timedelta.py

@@ -1,6 +1,6 @@
 """
-Timedelta benchmarks that rely only on tslibs.  See benchmarks.timedeltas for
-Timedelta benchmarks that rely on other parts fo pandas.
+Timedelta benchmarks that rely only on tslibs. See benchmarks.timedeltas for
+Timedelta benchmarks that rely on other parts of pandas.
 """
 import datetime
 

doc/source/user_guide/style.ipynb

@@ -1762,7 +1762,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In the above case the text is blue because the selector `#T_b_ .cls-1` is worth 110 (ID plus class), which takes precendence."
+    "In the above case the text is blue because the selector `#T_b_ .cls-1` is worth 110 (ID plus class), which takes precedence."
    ]
   },
   {

pandas/_libs/groupby.pyx

@@ -1011,7 +1011,7 @@ cdef numeric_t _get_na_val(numeric_t val, bint is_datetimelike):
     elif numeric_t is int64_t and is_datetimelike:
         na_val = NPY_NAT
     else:
-        # Will not be used, but define to avoid unitialized warning.
+        # Will not be used, but define to avoid uninitialized warning.
         na_val = 0
     return na_val