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.
In [1]: to_datetime(['2020-01-01', ''], format='%Y-%m-%d') # works
Out[1]: DatetimeIndex(['2020-01-01', 'NaT'], dtype='datetime64[ns]', freq=None)
In [2]: to_datetime(['2020-01-01', ''], format='%Y-%d-%m') # fails
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[2], line 1
----> 1 to_datetime(['2020-01-01', ''], format='%Y-%d-%m')
File ~/pandas-dev/pandas/core/tools/datetimes.py:1098, in to_datetime(arg, errors, dayfirst, yearfirst, utc, format, exact, unit, infer_datetime_format, origin, cache)
1096 result = _convert_and_box_cache(argc, cache_array)
1097 else:
-> 1098 result = convert_listlike(argc, format)
1099 else:
1100 result = convert_listlike(np.array([arg]), format)[0]
File ~/pandas-dev/pandas/core/tools/datetimes.py:442, in _convert_listlike_datetimes(arg, format, name, utc, unit, errors, dayfirst, yearfirst, exact)
439 require_iso8601 = format is not None and format_is_iso(format)
441 if format is not None and not require_iso8601:
--> 442 return _to_datetime_with_format(
443 arg,
444 orig_arg,
445 name,
446 utc,
447 format,
448 exact,
449 errors,
450 )
452 result, tz_parsed = objects_to_datetime64ns(
453 arg,
454 dayfirst=dayfirst,
(...)
461 exact=exact,
462 )
464 if tz_parsed is not None:
465 # We can take a shortcut since the datetime64 numpy array
466 # is in UTC
File ~/pandas-dev/pandas/core/tools/datetimes.py:543, in _to_datetime_with_format(arg, orig_arg, name, utc, fmt, exact, errors)
540 return _box_as_indexlike(result, utc=utc, name=name)
542 # fallback
--> 543 res = _array_strptime_with_fallback(arg, name, utc, fmt, exact, errors)
544 return res
File ~/pandas-dev/pandas/core/tools/datetimes.py:485, in _array_strptime_with_fallback(arg, name, utc, fmt, exact, errors)
481 """
482 Call array_strptime, with fallback behavior depending on 'errors'.
483 """
484 try:
--> 485 result, timezones = array_strptime(
486 arg, fmt, exact=exact, errors=errors, utc=utc
487 )
488 except OutOfBoundsDatetime:
489 if errors == "raise":
File ~/pandas-dev/pandas/_libs/tslibs/strptime.pyx:198, in pandas._libs.tslibs.strptime.array_strptime()
196 iresult[i] = NPY_NAT
197 continue
--> 198 raise ValueError(f"time data '{val}' does not match "
199 f"format '{fmt}' (match)")
200 if len(val) != found.end():
ValueError: time data '' does not match format '%Y-%d-%m' (match) Issue Description
In both cases, the empty string should become NaT
In both cases, the empty string should become NaT
commit : 20411cb
python : 3.8.15.final.0
python-bits : 64
OS : Linux
OS-release : 5.10.102.1-microsoft-standard-WSL2
Version : #1 SMP Wed Mar 2 00:30:59 UTC 2022
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : None
LANG : en_GB.UTF-8
LOCALE : en_GB.UTF-8
pandas : 2.0.0.dev0+919.g20411cb047
numpy : 1.23.5
pytz : 2022.6
dateutil : 2.8.2
setuptools : 65.5.1
pip : 22.3.1
Cython : 0.29.32
pytest : 7.2.0
hypothesis : 6.61.0
sphinx : 4.5.0
blosc : None
feather : None
xlsxwriter : 3.0.3
lxml.etree : 4.9.1
html5lib : 1.1
pymysql : 1.0.2
psycopg2 : 2.9.3
jinja2 : 3.1.2
IPython : 8.7.0
pandas_datareader: None
bs4 : 4.11.1
bottleneck : 1.3.5
brotli :
fastparquet : 2022.12.0
fsspec : 2021.11.0
gcsfs : 2021.11.0
matplotlib : 3.6.2
numba : 0.56.4
numexpr : 2.8.3
odfpy : None
openpyxl : 3.0.10
pandas_gbq : None
pyarrow : 9.0.0
pyreadstat : 1.2.0
pyxlsb : 1.0.10
s3fs : 2021.11.0
scipy : 1.9.3
snappy :
sqlalchemy : 1.4.45
tables : 3.7.0
tabulate : 0.9.0
xarray : 2022.12.0
xlrd : 2.0.1
zstandard : 0.19.0
tzdata : None
qtpy : None
pyqt5 : None
None
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4