Merge remote-tracking branch 'upstream/main' into refactor-s3-test

Author: fangchenli

AUTHORS.md

@@ -7,12 +7,12 @@ About the Copyright Holders
     led by Wes McKinney. AQR released the source under this license in 2009.
 *   Copyright (c) 2011-2012, Lambda Foundry, Inc.
 
-    Wes is now an employee of Lambda Foundry, and remains the pandas project
+    Wes became an employee of Lambda Foundry, and remained the pandas project
     lead.
 *   Copyright (c) 2011-2012, PyData Development Team
 
     The PyData Development Team is the collection of developers of the PyData
-    project. This includes all of the PyData sub-projects, including pandas. The
+    project. This includes all of the PyData sub-projects, such as pandas. The
     core team that coordinates development on GitHub can be found here:
     https://github.com/pydata.
 
@@ -23,11 +23,11 @@ Our Copyright Policy
 
 PyData uses a shared copyright model. Each contributor maintains copyright
 over their contributions to PyData. However, it is important to note that
-these contributions are typically only changes to the repositories. Thus,
+these contributions are typically limited to changes to the repositories. Thus,
 the PyData source code, in its entirety, is not the copyright of any single
 person or institution. Instead, it is the collective copyright of the
 entire PyData Development Team. If individual contributors want to maintain
-a record of what changes/contributions they have specific copyright on,
+a record of the specific changes or contributions they hold copyright to,
 they should indicate their copyright in the commit message of the change
 when they commit the change to one of the PyData repositories.
 
@@ -50,7 +50,7 @@ Other licenses can be found in the LICENSES directory.
 License
 =======
 
-pandas is distributed under a 3-clause ("Simplified" or "New") BSD
+pandas is distributed under the 3-clause ("Simplified" or "New") BSD
 license. Parts of NumPy, SciPy, numpydoc, bottleneck, which all have
-BSD-compatible licenses, are included. Their licenses follow the pandas
+BSD-compatible licenses, are included. Their licenses are compatible with the pandas
 license.

doc/source/reference/indexing.rst

@@ -98,6 +98,7 @@ Conversion
    :toctree: api/
 
    Index.astype
+   Index.infer_objects
    Index.item
    Index.map
    Index.ravel

scripts/validate_docstrings.py

@@ -69,8 +69,10 @@
 }
 ALL_ERRORS = set(NUMPYDOC_ERROR_MSGS).union(set(ERROR_MSGS))
 duplicated_errors = set(NUMPYDOC_ERROR_MSGS).intersection(set(ERROR_MSGS))
-assert not duplicated_errors, (f"Errors {duplicated_errors} exist in both pandas "
-                               "and numpydoc, should they be removed from pandas?")
+assert not duplicated_errors, (
+    f"Errors {duplicated_errors} exist in both pandas "
+    "and numpydoc, should they be removed from pandas?"
+)
 
 
 def pandas_error(code, **kwargs):
@@ -245,7 +247,15 @@ def pandas_validate(func_name: str):
     # Some objects are instances, e.g. IndexSlice, which numpydoc can't validate
     doc_obj = get_doc_object(func_obj, doc=func_obj.__doc__)
     doc = PandasDocstring(func_name, doc_obj)
-    result = validate(doc_obj)
+    if func_obj.__doc__ is not None:
+        result = validate(doc_obj)
+    else:
+        result = {
+            "docstring": "",
+            "file": None,
+            "file_line": None,
+            "errors": [("GL08", "The object does not have a docstring")],
+        }
     mentioned_errs = doc.mentioned_private_classes
     if mentioned_errs:
         result["errors"].append(
@@ -257,7 +267,7 @@ def pandas_validate(func_name: str):
             pandas_error(
                 "SA05",
                 reference_name=rel_name,
-                right_reference=rel_name[len("pandas."):],
+                right_reference=rel_name[len("pandas.") :],
             )
             for rel_name in doc.see_also
             if rel_name.startswith("pandas.")
@@ -365,12 +375,13 @@ def print_validate_all_results(
     for func_name, res in result.items():
         error_messages = dict(res["errors"])
         actual_failures = set(error_messages)
-        expected_failures = (ignore_errors.get(func_name, set())
-                             | ignore_errors.get(None, set()))
+        expected_failures = ignore_errors.get(func_name, set()) | ignore_errors.get(
+            None, set()
+        )
         for err_code in actual_failures - expected_failures:
             sys.stdout.write(
                 f'{prefix}{res["file"]}:{res["file_line"]}:'
-                f'{err_code}:{func_name}:{error_messages[err_code]}\n'
+                f"{err_code}:{func_name}:{error_messages[err_code]}\n"
             )
             exit_status += 1
         for err_code in ignore_errors.get(func_name, set()) - actual_failures:
@@ -384,8 +395,9 @@ def print_validate_all_results(
     return exit_status
 
 
-def print_validate_one_results(func_name: str,
-                               ignore_errors: dict[str, set[str]]) -> int:
+def print_validate_one_results(
+    func_name: str, ignore_errors: dict[str, set[str]]
+) -> int:
     def header(title, width=80, char="#") -> str:
         full_line = char * width
         side_len = (width - len(title) - 2) // 2
@@ -396,8 +408,11 @@ def header(title, width=80, char="#") -> str:
 
     result = pandas_validate(func_name)
 
-    result["errors"] = [(code, message) for code, message in result["errors"]
-                        if code not in ignore_errors.get(None, set())]
+    result["errors"] = [
+        (code, message)
+        for code, message in result["errors"]
+        if code not in ignore_errors.get(None, set())
+    ]
 
     sys.stderr.write(header(f"Docstring ({func_name})"))
     sys.stderr.write(f"{result['docstring']}\n")
@@ -431,14 +446,16 @@ def _format_ignore_errors(raw_ignore_errors):
                     raise ValueError(
                         f"Object `{obj_name}` is present in more than one "
                         "--ignore_errors argument. Please use it once and specify "
-                        "the errors separated by commas.")
+                        "the errors separated by commas."
+                    )
                 ignore_errors[obj_name] = set(error_codes.split(","))
 
                 unknown_errors = ignore_errors[obj_name] - ALL_ERRORS
                 if unknown_errors:
                     raise ValueError(
                         f"Object `{obj_name}` is ignoring errors {unknown_errors} "
-                        f"which are not known. Known errors are: {ALL_ERRORS}")
+                        f"which are not known. Known errors are: {ALL_ERRORS}"
+                    )
 
             # global errors "PR02,ES01"
             else:
@@ -448,27 +465,19 @@ def _format_ignore_errors(raw_ignore_errors):
         if unknown_errors:
             raise ValueError(
                 f"Unknown errors {unknown_errors} specified using --ignore_errors "
-                "Known errors are: {ALL_ERRORS}")
+                "Known errors are: {ALL_ERRORS}"
+            )
 
     return ignore_errors
 
 
-def main(
-    func_name,
-    output_format,
-    prefix,
-    ignore_deprecated,
-    ignore_errors
-):
+def main(func_name, output_format, prefix, ignore_deprecated, ignore_errors):
     """
     Main entry point. Call the validation for one or for all docstrings.
     """
     if func_name is None:
         return print_validate_all_results(
-            output_format,
-            prefix,
-            ignore_deprecated,
-            ignore_errors
+            output_format, prefix, ignore_deprecated, ignore_errors
         )
     else:
         return print_validate_one_results(func_name, ignore_errors)
@@ -524,10 +533,11 @@ def main(
     args = argparser.parse_args(sys.argv[1:])
 
     sys.exit(
-        main(args.function,
-             args.format,
-             args.prefix,
-             args.ignore_deprecated,
-             _format_ignore_errors(args.ignore_errors),
-             )
+        main(
+            args.function,
+            args.format,
+            args.prefix,
+            args.ignore_deprecated,
+            _format_ignore_errors(args.ignore_errors),
+        )
     )