Pandas version checks
-
[X] I have checked that this issue has not already been reported.
-
[X] I have confirmed this bug exists on the latest version of pandas.
-
[X] I have confirmed this bug exists on the main branch of pandas.
Reproducible Example
git clone https://github.com/pandas-dev/pandas.git
cd pandas
conda env create --file environment.yml
conda activate pandas-dev
python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
cd doc
python make.py html
python make.py clean
python make.py --single user_guide/enhancingperf.rst
Issue Description
I was following the steps to build the documentation as given here, but while running python make.py html it failed when building user_guide/enhancingperf.rst :
WARNING: ources... [ 95%] user_guide/enhancingperf
>>>-------------------------------------------------------------------------
Exception in C:\Users\91942\Documents\GitHub\pandas\doc\source\user_guide\enhancingperf.rst at block ending on line 101
Specify :okexcept: as an option in the ipython:: block to suppress this message
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
Cell In[6], line 1
----> 1 get_ipython().run_line_magic('prun', '-l 4 df.apply(lambda x: integrate_f(x["a"], x["b"], x["N"]), axis=1) # noqa E999')
File ~\anaconda3\envs\pandas-dev\lib\site-packages\IPython\core\interactiveshell.py:2480, in InteractiveShell.run_line_magic(self, magic_name, line, _stack_depth)
2478 kwargs['local_ns'] = self.get_local_scope(stack_depth)
2479 with self.builtin_trap:
-> 2480 result = fn(*args, **kwargs)
2482 # The code below prevents the output from being displayed
2483 # when using magics with decorator @output_can_be_silenced
2484 # when the last Python token in the expression is a ';'.
2485 if getattr(fn, magic.MAGIC_OUTPUT_CAN_BE_SILENCED, False):
File ~\anaconda3\envs\pandas-dev\lib\site-packages\IPython\core\magics\execution.py:317, in ExecutionMagics.prun(self, parameter_s, cell)
315 arg_str += '\n' + cell
316 arg_str = self.shell.transform_cell(arg_str)
--> 317 return self._run_with_profiler(arg_str, opts, self.shell.user_ns)
File ~\anaconda3\envs\pandas-dev\lib\site-packages\IPython\core\magics\execution.py:339, in ExecutionMagics._run_with_profiler(self, code, opts, namespace)
337 prof = profile.Profile()
338 try:
--> 339 prof = prof.runctx(code, namespace, namespace)
340 sys_exit = ''
341 except SystemExit:
File ~\anaconda3\envs\pandas-dev\lib\cProfile.py:101, in Profile.runctx(self, cmd, globals, locals)
99 self.enable()
100 try:
--> 101 exec(cmd, globals, locals)
102 finally:
103 self.disable()
File <string>:1
File ~\Documents\GitHub\pandas\pandas\core\frame.py:10398, in DataFrame.apply(self, func, axis, raw, result_type, args, by_row, engine, engine_kwargs, **kwargs)
10384 from pandas.core.apply import frame_apply
10386 op = frame_apply(
10387 self,
10388 func=func,
(...)
10396 kwargs=kwargs,
10397 )
> 10398 return op.apply().__finalize__(self, method="apply")
File ~\Documents\GitHub\pandas\pandas\core\apply.py:903, in FrameApply.apply(self)
900 elif self.raw:
901 return self.apply_raw(engine=self.engine, engine_kwargs=self.engine_kwargs)
--> 903 return self.apply_standard()
File ~\Documents\GitHub\pandas\pandas\core\apply.py:1054, in FrameApply.apply_standard(self)
1052 def apply_standard(self):
1053 if self.engine == "python":
-> 1054 results, res_index = self.apply_series_generator()
1055 else:
1056 results, res_index = self.apply_series_numba()
File ~\Documents\GitHub\pandas\pandas\core\apply.py:1070, in FrameApply.apply_series_generator(self)
1067 results = {}
1069 for i, v in enumerate(series_gen):
-> 1070 results[i] = self.func(v, *self.args, **self.kwargs)
1071 if isinstance(results[i], ABCSeries):
1072 # If we have a view on v, we need to make a copy because
1073 # series_generator will swap out the underlying data
1074 results[i] = results[i].copy(deep=False)
File <string>:1, in <lambda>(x)
File ~\Documents\GitHub\pandas\pandas\core\series.py:969, in Series.__getitem__(self, key)
966 key = np.asarray(key, dtype=bool)
967 return self._get_rows_with_mask(key)
--> 969 return self._get_with(key)
File ~\Documents\GitHub\pandas\pandas\core\series.py:981, in Series._get_with(self, key)
978 elif isinstance(key, tuple):
979 return self._get_values_tuple(key)
--> 981 return self.loc[key]
File ~\Documents\GitHub\pandas\pandas\core\indexing.py:1195, in _LocationIndexer.__getitem__(self, key)
1193 maybe_callable = com.apply_if_callable(key, self.obj)
1194 maybe_callable = self._raise_callable_usage(key, maybe_callable)
-> 1195 return self._getitem_axis(maybe_callable, axis=axis)
File ~\Documents\GitHub\pandas\pandas\core\indexing.py:1424, in _LocIndexer._getitem_axis(self, key, axis)
1421 if hasattr(key, "ndim") and key.ndim > 1:
1422 raise ValueError("Cannot index with multidimensional key")
-> 1424 return self._getitem_iterable(key, axis=axis)
1426 # nested tuple slicing
1427 if is_nested_tuple(key, labels):
File ~\Documents\GitHub\pandas\pandas\core\indexing.py:1364, in _LocIndexer._getitem_iterable(self, key, axis)
1361 self._validate_key(key, axis)
1363 # A collection of keys
-> 1364 keyarr, indexer = self._get_listlike_indexer(key, axis)
1365 return self.obj._reindex_with_indexers(
1366 {axis: [keyarr, indexer]}, allow_dups=True
1367 )
File ~\Documents\GitHub\pandas\pandas\core\indexing.py:1562, in _LocIndexer._get_listlike_indexer(self, key, axis)
1559 ax = self.obj._get_axis(axis)
1560 axis_name = self.obj._get_axis_name(axis)
-> 1562 keyarr, indexer = ax._get_indexer_strict(key, axis_name)
1564 return keyarr, indexer
File ~\Documents\GitHub\pandas\pandas\core\indexes\base.py:6056, in Index._get_indexer_strict(self, key, axis_name)
6053 else:
6054 keyarr, indexer, new_indexer = self._reindex_non_unique(keyarr)
-> 6056 self._raise_if_missing(keyarr, indexer, axis_name)
6058 keyarr = self.take(indexer)
6059 if isinstance(key, Index):
6060 # GH 42790 - Preserve name from an Index
File ~\Documents\GitHub\pandas\pandas\core\indexes\base.py:6108, in Index._raise_if_missing(self, key, indexer, axis_name)
6105 raise KeyError(f"None of [{key}] are in the [{axis_name}]")
6107 not_found = list(ensure_index(key)[missing_mask.nonzero()[0]].unique())
-> 6108 raise KeyError(f"{not_found} not in index")
KeyError: "['c'] not in index"
<<<-------------------------------------------------------------------------
Exception occurred:
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\IPython\sphinxext\ipython_directive.py", line 584, in process_input
raise RuntimeError(
RuntimeError: Unexpected exception in `C:\Users\91942\Documents\GitHub\pandas\doc\source\user_guide\enhancingperf.rst` line 101
The full traceback has been saved in C:\Users\91942\AppData\Local\Temp\sphinx-err-5kwabx28.log, if you want to report the issue to the developers.
Please also report this if it was a user error, so that a better error message can be provided next time.
A bug report can be filed in the tracker at <https://github.com/sphinx-doc/sphinx/issues>. Thanks!
The same error occurs while running python make.py --single user_guide/enhancingperf.rst.
Full traceback given in sphinx-err-5kwabx28.log is:
# Platform: win32; (Windows-10-10.0.22631-SP0)
# Sphinx version: 8.1.3
# Python version: 3.10.15 (CPython)
# Docutils version: 0.21.2
# Jinja2 version: 3.1.4
# Pygments version: 2.18.0
# Last messages:
# user_guide/dsintro
#
#
# reading sources... [ 95%]
# user_guide/duplicates
#
#
# reading sources... [ 95%]
# user_guide/enhancingperf
#
# Loaded extensions:
# sphinx.ext.mathjax (8.1.3)
# alabaster (1.0.0)
# sphinxcontrib.applehelp (2.0.0)
# sphinxcontrib.devhelp (2.0.0)
# sphinxcontrib.htmlhelp (2.1.0)
# sphinxcontrib.serializinghtml (1.1.10)
# sphinxcontrib.qthelp (2.0.0)
# contributors (0.1)
# IPython.sphinxext.ipython_directive (unknown version)
# IPython.sphinxext.ipython_console_highlighting (unknown version)
# matplotlib.sphinxext.plot_directive (3.9.2)
# sphinx.ext.autodoc.preserve_defaults (8.1.3)
# sphinx.ext.autodoc.type_comment (8.1.3)
# sphinx.ext.autodoc.typehints (8.1.3)
# sphinx.ext.autodoc (8.1.3)
# sphinx.ext.autosummary (8.1.3)
# numpydoc (1.8.0)
# sphinx_copybutton (0.5.2)
# sphinx_design (0.6.1)
# sphinx.ext.coverage (8.1.3)
# sphinx.ext.doctest (8.1.3)
# sphinx.ext.extlinks (8.1.3)
# sphinx.ext.ifconfig (8.1.3)
# sphinx.ext.intersphinx (8.1.3)
# sphinx.ext.linkcode (8.1.3)
# sphinx.ext.todo (8.1.3)
# nbsphinx (0.9.5)
# pydata_sphinx_theme (unknown version)
# Traceback:
Traceback (most recent call last):
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\cmd\build.py", line 514, in build_main
app.build(args.force_all, args.filenames)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\application.py", line 381, in build
self.builder.build_update()
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\builders\__init__.py", line 358, in build_update
self.build(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\builders\__init__.py", line 385, in build
updated_docnames = set(self.read())
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\builders\__init__.py", line 502, in read
self._read_serial(docnames)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\builders\__init__.py", line 567, in _read_serial
self.read_doc(docname)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\builders\__init__.py", line 630, in read_doc
publisher.publish()
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\core.py", line 234, in publish
self.document = self.reader.read(self.source, self.parser,
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\io.py", line 106, in read
self.parse()
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\readers\__init__.py", line 76, in parse
self.parser.parse(self.input, document)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\sphinx\parsers.py", line 85, in parse
self.statemachine.run(inputlines, document, inliner=self.inliner)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 169, in run
results = StateMachineWS.run(self, input_lines, input_offset,
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 233, in run
context, next_state, result = self.check_line(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 445, in check_line
return method(match, context, next_state)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 3034, in text
self.section(title.lstrip(), source, style, lineno + 1, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 325, in section
self.new_subsection(title, lineno, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 391, in new_subsection
newabsoffset = self.nested_parse(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 279, in nested_parse
state_machine.run(block, input_offset, memo=self.memo,
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 195, in run
results = StateMachineWS.run(self, input_lines, input_offset)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 233, in run
context, next_state, result = self.check_line(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 445, in check_line
return method(match, context, next_state)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2790, in underline
self.section(title, source, style, lineno - 1, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 325, in section
self.new_subsection(title, lineno, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 391, in new_subsection
newabsoffset = self.nested_parse(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 279, in nested_parse
state_machine.run(block, input_offset, memo=self.memo,
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 195, in run
results = StateMachineWS.run(self, input_lines, input_offset)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 233, in run
context, next_state, result = self.check_line(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 445, in check_line
return method(match, context, next_state)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2790, in underline
self.section(title, source, style, lineno - 1, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 325, in section
self.new_subsection(title, lineno, messages)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 391, in new_subsection
newabsoffset = self.nested_parse(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 279, in nested_parse
state_machine.run(block, input_offset, memo=self.memo,
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 195, in run
results = StateMachineWS.run(self, input_lines, input_offset)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 233, in run
context, next_state, result = self.check_line(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\statemachine.py", line 445, in check_line
return method(match, context, next_state)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2357, in explicit_markup
nodelist, blank_finish = self.explicit_construct(match)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2369, in explicit_construct
return method(self, expmatch)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2106, in directive
return self.run_directive(
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\docutils\parsers\rst\states.py", line 2156, in run_directive
result = directive_instance.run()
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\IPython\sphinxext\ipython_directive.py", line 1033, in run
rows, figure = self.shell.process_block(block)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\IPython\sphinxext\ipython_directive.py", line 732, in process_block
self.process_input(data, input_prompt, lineno)
File "C:\Users\91942\anaconda3\envs\pandas-dev\lib\site-packages\IPython\sphinxext\ipython_directive.py", line 584, in process_input
raise RuntimeError(
RuntimeError: Unexpected exception in `C:\Users\91942\Documents\GitHub\pandas\doc\source\user_guide\enhancingperf.rst` line 101
The issue appears to be with this line:
https://github.com/pandas-dev/pandas/blob/9cd4a281c42838cd32261b92a55aed830ebeae03/doc/source/user_guide/enhancingperf.rst?plain=1#L101
Should I add :okexcept: to the block to suppress this message?
Expected Behavior
HTML doc should be successfully built.
Installed Versions
INSTALLED VERSIONS
------------------
commit : 7bd594c81acb5f6428e9ef54ba5a9da1f2860a89
python : 3.10.15
python-bits : 64
OS : Windows
OS-release : 10
Version : 10.0.22631
machine : AMD64
processor : Intel64 Family 6 Model 154 Stepping 4, GenuineIntel
byteorder : little
LC_ALL : None
LANG : None
LOCALE : English_India.1252
pandas : 3.0.0.dev0+1600.g7bd594c81a
numpy : 1.26.4
dateutil : 2.9.0
pip : 24.3.1
Cython : 3.0.11
sphinx : 8.1.3
IPython : 8.29.0
adbc-driver-postgresql: None
adbc-driver-sqlite : None
bs4 : 4.12.3
blosc : None
bottleneck : 1.4.2
fastparquet : 2024.5.0
fsspec : 2024.10.0
html5lib : 1.1
hypothesis : 6.115.6
gcsfs : 2024.10.0
jinja2 : 3.1.4
lxml.etree : 5.3.0
matplotlib : 3.9.2
numba : 0.60.0
numexpr : 2.10.1
odfpy : None
openpyxl : 3.1.5
psycopg2 : 2.9.9
pymysql : 1.4.6
pyarrow : 18.0.0
pyreadstat : 1.2.8
pytest : 8.3.3
python-calamine : None
pytz : 2024.2
pyxlsb : 1.0.10
s3fs : 2024.10.0
scipy : 1.14.1
sqlalchemy : 2.0.36
tables : 3.10.1
tabulate : 0.9.0
xarray : 2024.9.0
xlrd : 2.0.1
xlsxwriter : 3.2.0
zstandard : 0.23.0
tzdata : 2024.2
qtpy : None
pyqt5 : None
Comment From: jorisvandenbossche
On the dev docs (https://pandas.pydata.org/docs/dev/user_guide/enhancingperf.html#pure-python) it is not failing, so ideally we shouldn't add a okexcept because that could then hide actual errors if it would later start to error (i.e. for the online docs, we never want this to error, so we want to get notified if that would happen).
Now, that said, I don't directly understand what would cause the error you see. Especially the KeyError: "['c'] not in index" error message, because the code example being run there doesn't mention any "c" column.
Comment From: cobaltt7
I ran in to the same bug, which I eventually found to be an Windows iPython bug - https://github.com/ipython/ipython/issues/11200
Comment From: ethandavidlee
@cobaltt7 Was the iPython issue ever properly fixed, I'm also having the same build issue.