You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\c_parser_wrapper.py:333, in CParserWrapper.read(self, nrows)
330 data = {k: v for k, (i, v) in zip(names, data_tups)}
332 names, date_data = self._do_date_conversions(names, data)
--> 333 index, column_names = self._make_index(date_data, alldata, names)
335 return index, column_names, date_data
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:371, in ParserBase._make_index(self, data, alldata, columns, indexnamerow)
369 elif not self._has_complex_date_col:
370 simple_index = self._get_simple_index(alldata, columns)
--> 371 index = self._agg_index(simple_index)
372 elif self._has_complex_date_col:
373 if not self._name_processed:
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:468, in ParserBase._agg_index(self, index, try_parse_dates)
466 for i, arr in enumerate(index):
467 if try_parse_dates and self._should_parse_dates(i):
--> 468 arr = self._date_conv(
469 arr,
470 col=self.index_names[i] if self.index_names is not None else None,
471 )
473 if self.na_filter:
474 col_na_values = self.na_values
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:1142, in _make_date_converter..converter(col, *date_cols)
1139 return date_cols[0]
1141 if date_parser is lib.no_default:
-> 1142 strs = parsing.concat_date_cols(date_cols)
1143 date_fmt = (
1144 date_format.get(col) if isinstance(date_format, dict) else date_format
1145 )
1147 with warnings.catch_warnings():
File parsing.pyx:1155, in pandas._libs.tslibs.parsing.concat_date_cols()
ValueError: not all elements from date_cols are numpy arrays
Expected Behavior
As with dtype_backend="numpy_nullable" the index column should be parsed correctly.
It works with the following set-up, so likely an issue with the C parser (?)
Installed Versions
INSTALLED VERSIONS
commit : a671b5a
python : 3.11.8.final.0
python-bits : 64
OS : Windows
OS-release : 10
Version : 10.0.19042
machine : AMD64
processor : AMD64 Family 23 Model 24 Stepping 1, AuthenticAMD
byteorder : little
LC_ALL : None
LANG : None
LOCALE : Dutch_Belgium.1252
Pandas version checks
I have checked that this issue has not already been reported.
I have confirmed this bug exists on the latest version of pandas.
I have confirmed this bug exists on the main branch of pandas.
Reproducible Example
the following fails :
Issue Description
returns
ValueError: not all elements from date_cols are numpy arrays
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\readers.py:948, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
935 kwds_defaults = _refine_defaults_read(
936 dialect,
937 delimiter,
(...)
944 dtype_backend=dtype_backend,
945 )
946 kwds.update(kwds_defaults)
--> 948 return _read(filepath_or_buffer, kwds)
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\readers.py:617, in _read(filepath_or_buffer, kwds)
614 return parser
616 with parser:
--> 617 return parser.read(nrows)
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\readers.py:1748, in TextFileReader.read(self, nrows)
1741 nrows = validate_integer("nrows", nrows)
1742 try:
1743 # error: "ParserBase" has no attribute "read"
1744 (
1745 index,
1746 columns,
1747 col_dict,
-> 1748 ) = self._engine.read( # type: ignore[attr-defined]
1749 nrows
1750 )
1751 except Exception:
1752 self.close()
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\c_parser_wrapper.py:333, in CParserWrapper.read(self, nrows)
330 data = {k: v for k, (i, v) in zip(names, data_tups)}
332 names, date_data = self._do_date_conversions(names, data)
--> 333 index, column_names = self._make_index(date_data, alldata, names)
335 return index, column_names, date_data
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:371, in ParserBase._make_index(self, data, alldata, columns, indexnamerow)
369 elif not self._has_complex_date_col:
370 simple_index = self._get_simple_index(alldata, columns)
--> 371 index = self._agg_index(simple_index)
372 elif self._has_complex_date_col:
373 if not self._name_processed:
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:468, in ParserBase._agg_index(self, index, try_parse_dates)
466 for i, arr in enumerate(index):
467 if try_parse_dates and self._should_parse_dates(i):
--> 468 arr = self._date_conv(
469 arr,
470 col=self.index_names[i] if self.index_names is not None else None,
471 )
473 if self.na_filter:
474 col_na_values = self.na_values
File c:\ProgramData\miniconda3\envs\DLL_Forecast\Lib\site-packages\pandas\io\parsers\base_parser.py:1142, in _make_date_converter..converter(col, *date_cols)
1139 return date_cols[0]
1141 if date_parser is lib.no_default:
-> 1142 strs = parsing.concat_date_cols(date_cols)
1143 date_fmt = (
1144 date_format.get(col) if isinstance(date_format, dict) else date_format
1145 )
1147 with warnings.catch_warnings():
File parsing.pyx:1155, in pandas._libs.tslibs.parsing.concat_date_cols()
ValueError: not all elements from date_cols are numpy arrays
Expected Behavior
As with dtype_backend="numpy_nullable" the index column should be parsed correctly.
It works with the following set-up, so likely an issue with the C parser (?)
Installed Versions
INSTALLED VERSIONS
commit : a671b5a
python : 3.11.8.final.0
python-bits : 64
OS : Windows
OS-release : 10
Version : 10.0.19042
machine : AMD64
processor : AMD64 Family 23 Model 24 Stepping 1, AuthenticAMD
byteorder : little
LC_ALL : None
LANG : None
LOCALE : Dutch_Belgium.1252
pandas : 2.1.4
numpy : 1.26.4
pytz : 2024.1
dateutil : 2.9.0
setuptools : 69.2.0
pip : 24.0
Cython : None
pytest : 8.1.1
hypothesis : None
sphinx : 7.2.6
blosc : None
feather : None
xlsxwriter : 3.1.9
lxml.etree : 5.1.0
html5lib : 1.1
pymysql : None
psycopg2 : None
jinja2 : 3.1.3
IPython : 8.22.2
pandas_datareader : None
bs4 : 4.12.3
bottleneck : 1.3.8
dataframe-api-compat: None
fastparquet : None
fsspec : 2024.3.0
gcsfs : None
matplotlib : 3.8.3
numba : 0.59.0
numexpr : 2.9.0
odfpy : None
openpyxl : 3.1.2
pandas_gbq : None
pyarrow : 15.0.0
pyreadstat : None
pyxlsb : 1.0.10
s3fs : None
scipy : 1.12.0
sqlalchemy : 2.0.28
tables : None
tabulate : 0.9.0
xarray : None
xlrd : 2.0.1
zstandard : 0.22.0
tzdata : 2024.1
qtpy : 2.4.1
pyqt5 : None
The text was updated successfully, but these errors were encountered: