我有这个数据框：
df = pd.DataFrame([[1,2,3], [2,3,4]], columns=['a', 'b', 'c'])
我可以这样改变它：
pd.DataFrame(df.apply(lambda x: [x.a, x.b], 1).tolist())
或者像这样：
pd.DataFrame(df.apply(lambda x: [1, 2, 3, 4], 1).tolist())
现在让我们来看看df_train：
df_train.dtypes
给我们
actionDate datetime64[ns]
actionType object
clientSubmitDate datetime64[ns]
content object
conversationId object
creationDate datetime64[ns]
folder object
hasForwarded bool
hasReplied bool
lastModified datetime64[ns]
messageDelivery datetime64[ns]
originalConversation object
recipients object
sender object
subject object
dtype: object
就像我这样做：
df_train.apply(lambda x: [1, 2], 1)
我得到的是：
ValueError: Shape of passed values is (10, 2), indices imply (10, 15)
我不知道为什么因为我向你发誓昨天有效。
我的实际目标是像这样转换数据框：
df_train.apply(lambda x: [x.actionType == 'DELETED', x.hasForwarded, x.hasReplied], 1).tolist()
但由于某种原因，我得到了这个ValueError，我只是不知道问题所在。
df_train[['actionType', 'hasReplied', 'hasForwarded']].head()
显示
actionType hasReplied hasForwarded
id
129931 DELETED False False
123345 DELETED False False
136596 FORWARD False False
123344 DELETED False False
123343 DELETED False False
完整堆栈跟踪：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in create_block_manager_from_arrays(arrays, names, axes)
4632 blocks = form_blocks(arrays, names, axes)
-> 4633 mgr = BlockManager(blocks, axes)
4634 mgr._consolidate_inplace()
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in __init__(self, blocks, axes, do_integrity_check, fastpath)
3027 if do_integrity_check:
-> 3028 self._verify_integrity()
3029
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in _verify_integrity(self)
3238 if block._verify_integrity and block.shape[1:] != mgr_shape[1:]:
-> 3239 construction_error(tot_items, block.shape[1:], self.axes)
3240 if len(self.items) != tot_items:
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in construction_error(tot_items, block_shape, axes, e)
4602 raise ValueError("Shape of passed values is {0}, indices imply {1}".format(
-> 4603 passed, implied))
4604
ValueError: Shape of passed values is (130182, 3), indices imply (130182, 15)
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-114-59888fe52c27> in <module>()
----> 1 df_train.apply(lambda x: [x.actionType == 'DELETED', x.hasForwarded, x.hasReplied], 1)
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/frame.py in apply(self, func, axis, broadcast, raw, reduce, args, **kwds)
4852 f, axis,
4853 reduce=reduce,
-> 4854 ignore_failures=ignore_failures)
4855 else:
4856 return self._apply_broadcast(f, axis)
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/frame.py in _apply_standard(self, func, axis, ignore_failures, reduce)
4965 index = None
4966
-> 4967 result = self._constructor(data=results, index=index)
4968 result.columns = res_index
4969
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
328 dtype=dtype, copy=copy)
329 elif isinstance(data, dict):
--> 330 mgr = self._init_dict(data, index, columns, dtype=dtype)
331 elif isinstance(data, ma.MaskedArray):
332 import numpy.ma.mrecords as mrecords
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/frame.py in _init_dict(self, data, index, columns, dtype)
459 arrays = [data[k] for k in keys]
460
--> 461 return _arrays_to_mgr(arrays, data_names, index, columns, dtype=dtype)
462
463 def _init_ndarray(self, values, index, columns, dtype=None, copy=False):
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/frame.py in _arrays_to_mgr(arrays, arr_names, index, columns, dtype)
6138 axes = [_ensure_index(columns), _ensure_index(index)]
6139
-> 6140 return create_block_manager_from_arrays(arrays, arr_names, axes)
6141
6142
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in create_block_manager_from_arrays(arrays, names, axes)
4635 return mgr
4636 except ValueError as e:
-> 4637 construction_error(len(arrays), arrays[0].shape, axes, e)
4638
4639
~/miniconda3/envs/daimler/lib/python3.5/site-packages/pandas/core/internals.py in construction_error(tot_items, block_shape, axes, e)
4601 raise ValueError("Empty data passed with indices specified.")
4602 raise ValueError("Shape of passed values is {0}, indices imply {1}".format(
-> 4603 passed, implied))
4604
4605
ValueError: Shape of passed values is (130182, 3), indices imply (130182, 15)