Closed
Description
This is an obscure edge case, but I feel it needs to be reported.
For an empty dataframe with 2 or more columns, setting with enlargment of a row that includes a timezoned timestamp, fails.
from pandas import DataFrame, Timestamp
# works:
df = DataFrame(columns=['a', 'b'])
df.loc[len(df)] = [Timestamp.now(), 55]
# does not work:
df = DataFrame(columns=['a', 'b'])
df.loc[len(df)] = [Timestamp.now(tz='Europe/Paris'), 55]
Traceback (most recent call last):
File "/usr/local/lib/python3.4/dist-packages/IPython/core/interactiveshell.py", line 3066, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-53-b144415de186>", line 1, in <module>
df.loc[len(df)] = [Timestamp.now(tz='Europe/Paris'), 55]
File "/usr/local/lib/python3.4/dist-packages/pandas/core/indexing.py", line 141, in __setitem__
self._setitem_with_indexer(indexer, value)
File "/usr/local/lib/python3.4/dist-packages/pandas/core/indexing.py", line 385, in _setitem_with_indexer
self.obj._data = self.obj.append(value)._data
File "/usr/local/lib/python3.4/dist-packages/pandas/core/frame.py", line 4435, in append
verify_integrity=verify_integrity)
File "/usr/local/lib/python3.4/dist-packages/pandas/tools/merge.py", line 1452, in concat
return op.get_result()
File "/usr/local/lib/python3.4/dist-packages/pandas/tools/merge.py", line 1650, in get_result
copy=self.copy)
File "/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py", line 4825, in concatenate_block_managers
placement=placement) for placement, join_units in concat_plan]
File "/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py", line 4825, in <listcomp>
placement=placement) for placement, join_units in concat_plan]
File "/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py", line 4922, in concatenate_join_units
for ju in join_units]
File "/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py", line 4922, in <listcomp>
for ju in join_units]
File "/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py", line 5195, in get_reindexed_values
missing_arr = np.empty(self.shape, dtype=empty_dtype)
TypeError: data type not understood
Output of pd.show_versions()
pd.show_versions()
INSTALLED VERSIONS
------------------
commit: None
python: 3.4.3.final.0
python-bits: 64
OS: Linux
OS-release: 3.19.0-66-generic
machine: x86_64
processor: x86_64
byteorder: little
LC_ALL: None
LANG: en_US.UTF-8
LOCALE: en_US.UTF-8
pandas: 0.19.2
nose: None
pip: 9.0.1
setuptools: 32.3.1
Cython: 0.24.1
numpy: 1.12.1
scipy: 0.17.1
statsmodels: 0.6.1
xarray: None
IPython: 4.0.0
sphinx: None
patsy: 0.4.1
dateutil: 2.6.0
pytz: 2017.2
blosc: None
bottleneck: None
tables: 3.2.2
numexpr: 2.4.6
matplotlib: 1.5.1
openpyxl: None
xlrd: None
xlwt: None
xlsxwriter: None
lxml: None
bs4: None
html5lib: 0.999
httplib2: 0.9.2
apiclient: 1.6.1
sqlalchemy: None
pymysql: None
psycopg2: 2.6.1 (dt dec pq3 ext lo64)
jinja2: 2.8
boto: None
pandas_datareader: None