CI/STYLE Fix misspellings exposed by codespell (pandas-dev#39264)

Author: zitorelova

.pre-commit-config.yaml

@@ -189,7 +189,8 @@ repos:
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
-        files: ^pandas/core/
+        files: ^pandas/
+        exclude: ^pandas/tests/
 -   repo: https://github.com/MarcoGorelli/no-string-hints
     rev: v0.1.5
     hooks:

pandas/_testing/__init__.py

@@ -679,7 +679,7 @@ def makeCustomDataframe(
     # 4-level multindex on rows with names provided, 2-level multindex
     # on columns with default labels and default names.
     >> a=makeCustomDataframe(5,3,r_idx_nlevels=4,
-                             r_idx_names=["FEE","FI","FO","FAM"],
+                             r_idx_names=["FEE","FIH","FOH","FUM"],
                              c_idx_nlevels=2)
 
     >> a=mkdf(5,3,r_idx_nlevels=2,c_idx_nlevels=4)

pandas/_version.py

@@ -293,7 +293,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
         # TAG-NUM-gHEX
         mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
         if not mo:
-            # unparseable. Maybe git-describe is misbehaving?
+            # unparsable. Maybe git-describe is misbehaving?
             pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
             return pieces
 

pandas/io/clipboard/__init__.py

@@ -271,12 +271,12 @@ def copy_dev_clipboard(text):
         if "\r" in text:
             warnings.warn("Pyperclip cannot handle \\r characters on Cygwin.")
 
-        with open("/dev/clipboard", "wt") as fo:
-            fo.write(text)
+        with open("/dev/clipboard", "wt") as fd:
+            fd.write(text)
 
     def paste_dev_clipboard() -> str:
-        with open("/dev/clipboard") as fo:
-            content = fo.read()
+        with open("/dev/clipboard") as fd:
+            content = fd.read()
         return content
 
     return copy_dev_clipboard, paste_dev_clipboard

pandas/io/common.py

@@ -292,7 +292,7 @@ def _get_filepath_or_buffer(
         # urlopen function defined elsewhere in this module
         import urllib.request
 
-        # assuming storage_options is to be interpretted as headers
+        # assuming storage_options is to be interpreted as headers
         req_info = urllib.request.Request(filepath_or_buffer, headers=storage_options)
         with urlopen(req_info) as req:
             content_encoding = req.headers.get("Content-Encoding", None)

pandas/io/excel/_base.py

@@ -190,7 +190,7 @@
     * dict, e.g. {'foo' : [1, 3]} -> parse columns 1, 3 as date and call
       result 'foo'
 
-    If a column or index contains an unparseable date, the entire column or
+    If a column or index contains an unparsable date, the entire column or
     index will be returned unaltered as an object data type. If you don`t want to
     parse some cells as date just change their type in Excel to "Text".
     For non-standard datetime parsing, use ``pd.to_datetime`` after ``pd.read_excel``.

pandas/io/formats/format.py

@@ -919,7 +919,7 @@ class DataFrameRenderer:
     Parameters
     ----------
     fmt : DataFrameFormatter
-        Formatter with the formating options.
+        Formatter with the formatting options.
     """
 
     def __init__(self, fmt: DataFrameFormatter):

pandas/io/formats/info.py

@@ -683,7 +683,7 @@ def _gen_columns(self) -> Iterator[str]:
 
 def _get_dataframe_dtype_counts(df: DataFrame) -> Mapping[str, int]:
     """
-    Create mapping between datatypes and their number of occurences.
+    Create mapping between datatypes and their number of occurrences.
     """
     # groupby dtype.name to collect e.g. Categorical columns
     return df.dtypes.value_counts().groupby(lambda x: x.name).sum()

pandas/io/formats/style.py

@@ -1697,7 +1697,7 @@ def from_custom_template(cls, searchpath, name):
         """
         loader = jinja2.ChoiceLoader([jinja2.FileSystemLoader(searchpath), cls.loader])
 
-        # mypy doesnt like dynamically-defined class
+        # mypy doesn't like dynamically-defined classes
         # error: Variable "cls" is not valid as a type  [valid-type]
         # error: Invalid base class "cls"  [misc]
         class MyStyler(cls):  # type:ignore[valid-type,misc]

pandas/io/json/_normalize.py

@@ -162,40 +162,40 @@ def _json_normalize(
     Examples
     --------
     >>> data = [{'id': 1, 'name': {'first': 'Coleen', 'last': 'Volk'}},
-    ...         {'name': {'given': 'Mose', 'family': 'Regner'}},
+    ...         {'name': {'given': 'Mark', 'family': 'Regner'}},
     ...         {'id': 2, 'name': 'Faye Raker'}]
     >>> pd.json_normalize(data)
         id name.first name.last name.given name.family        name
     0  1.0     Coleen      Volk        NaN         NaN         NaN
-    1  NaN        NaN       NaN       Mose      Regner         NaN
+    1  NaN        NaN       NaN       Mark      Regner         NaN
     2  2.0        NaN       NaN        NaN         NaN  Faye Raker
 
     >>> data = [{'id': 1,
     ...          'name': "Cole Volk",
     ...          'fitness': {'height': 130, 'weight': 60}},
-    ...         {'name': "Mose Reg",
+    ...         {'name': "Mark Reg",
     ...          'fitness': {'height': 130, 'weight': 60}},
     ...         {'id': 2, 'name': 'Faye Raker',
     ...          'fitness': {'height': 130, 'weight': 60}}]
     >>> pd.json_normalize(data, max_level=0)
         id        name                        fitness
     0  1.0   Cole Volk  {'height': 130, 'weight': 60}
-    1  NaN    Mose Reg  {'height': 130, 'weight': 60}
+    1  NaN    Mark Reg  {'height': 130, 'weight': 60}
     2  2.0  Faye Raker  {'height': 130, 'weight': 60}
 
     Normalizes nested data up to level 1.
 
     >>> data = [{'id': 1,
     ...          'name': "Cole Volk",
     ...          'fitness': {'height': 130, 'weight': 60}},
-    ...         {'name': "Mose Reg",
+    ...         {'name': "Mark Reg",
     ...          'fitness': {'height': 130, 'weight': 60}},
     ...         {'id': 2, 'name': 'Faye Raker',
     ...          'fitness': {'height': 130, 'weight': 60}}]
     >>> pd.json_normalize(data, max_level=1)
         id        name  fitness.height  fitness.weight
     0  1.0   Cole Volk             130              60
-    1  NaN    Mose Reg             130              60
+    1  NaN    Mark Reg             130              60
     2  2.0  Faye Raker             130              60
 
     >>> data = [{'state': 'Florida',

setup.cfg

@@ -68,6 +68,7 @@ junit_family=xunit2
 
 [codespell]
 ignore-words-list=ba,blocs,coo,hist,nd,ser
+ignore-regex=https://(\w+\.)+
 
 [coverage:run]
 branch = False