问题
The following code
import numpy as np
import pandas as pd
df1 = pd.DataFrame({'col1': ['a'], 'col2': ['b'], 'col3': ['15/12/2001']})
df2 = pd.DataFrame()
df2['col1'] = df1.col1
df2['col2'] = df1.col2
df2['col3'] = df1.col3
def convert(r):
return 'a', 'b'
df2.apply(convert, axis=1)
outputs 0 (a, b) dtype: object
In contrast, the following code
import numpy as np
import pandas as pd
df1 = pd.DataFrame({'col1': ['a'], 'col2': ['b'], 'col3': ['15/12/2001']})
df2 = pd.DataFrame()
df2['col1'] = df1.col1
df2['col2'] = df1.col2
df2['col3'] = pd.to_datetime(df1['col3'], dayfirst=True)
def convert(r):
return 'a', 'b'
df2.apply(convert, axis=1)
raises an error :
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in create_block_manager_from_arrays(arrays, names, axes)
3928 blocks = form_blocks(arrays, names, axes)
-> 3929 mgr = BlockManager(blocks, axes)
3930 mgr._consolidate_inplace()
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in __init__(self, blocks, axes, do_integrity_check, fastpath)
2536 if do_integrity_check:
-> 2537 self._verify_integrity()
2538
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in _verify_integrity(self)
2746 if block._verify_integrity and block.shape[1:] != mgr_shape[1:]:
-> 2747 construction_error(tot_items, block.shape[1:], self.axes)
2748 if len(self.items) != tot_items:
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in construction_error(tot_items, block_shape, axes, e)
3898 raise ValueError("Shape of passed values is {0}, indices imply {1}".format(
-> 3899 passed, implied))
3900
ValueError: Shape of passed values is (1, 2), indices imply (1, 3)
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-93-e8fcbf9d6e00> in <module>()
12 return 'a', 'b'
13
---> 14 df2.apply(convert, axis=1)
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/frame.py in apply(self, func, axis, broadcast, raw, reduce, args, **kwds)
4040 if reduce is None:
4041 reduce = True
-> 4042 return self._apply_standard(f, axis, reduce=reduce)
4043 else:
4044 return self._apply_broadcast(f, axis)
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/frame.py in _apply_standard(self, func, axis, ignore_failures, reduce)
4153 index = None
4154
-> 4155 result = self._constructor(data=results, index=index)
4156 result.columns = res_index
4157
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
221 dtype=dtype, copy=copy)
222 elif isinstance(data, dict):
--> 223 mgr = self._init_dict(data, index, columns, dtype=dtype)
224 elif isinstance(data, ma.MaskedArray):
225 import numpy.ma.mrecords as mrecords
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/frame.py in _init_dict(self, data, index, columns, dtype)
357 arrays = [data[k] for k in keys]
358
--> 359 return _arrays_to_mgr(arrays, data_names, index, columns, dtype=dtype)
360
361 def _init_ndarray(self, values, index, columns, dtype=None, copy=False):
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/frame.py in _arrays_to_mgr(arrays, arr_names, index, columns, dtype)
5248 axes = [_ensure_index(columns), _ensure_index(index)]
5249
-> 5250 return create_block_manager_from_arrays(arrays, arr_names, axes)
5251
5252
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in create_block_manager_from_arrays(arrays, names, axes)
3931 return mgr
3932 except ValueError as e:
-> 3933 construction_error(len(arrays), arrays[0].shape, axes, e)
3934
3935
/home/michel/.virtualenvs/stsisi/lib/python3.4/site-packages/pandas/core/internals.py in construction_error(tot_items, block_shape, axes, e)
3897 raise ValueError("Empty data passed with indices specified.")
3898 raise ValueError("Shape of passed values is {0}, indices imply {1}".format(
-> 3899 passed, implied))
3900
3901
ValueError: Shape of passed values is (1, 2), indices imply (1, 3)
It looks to me like a bug involving pandas.to_datetime() and pandas.DataFrame.apply(). Am I missing something ?
I ran it with python 3.4.3 and pandas 0.18.0
来源：https://stackoverflow.com/questions/35992420/pandas-dataframe-apply-failing-after-pandas-to-datetime