在python中，通过使用lambda增加值将空列表添加到dataframe列中

Question

我能够重现合成数据：

import pandas as pd
from datetime import datetime

df1 = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
                    'B': ['B0', 'B1', 'B2', 'B3'],
                    'C': [datetime.now(), datetime.now(), datetime.now(), datetime.now()],
                    'D': ['D0', 'D1', 'D2', 'D3']},
                   index=[0, 1, 2, 3]);
df2 = pd.DataFrame({'A': ['A1', 'A2', 'A3', 'A4'],
                    'E': ['E1', 'E2', 'E3', 'E4']},
                   index=[0,1,2,3]);

df = pd.merge(df1, df2, how='left', on=['A', 'A']);

def getList(row):
    r = [];
    if row["A"] == "A1": r.append("test-01");
    if row["B"] == "B1": r.append("test-02");
    if row["B"] == "B2": r.append("test-03");
    return r;

df["NEW_COLUMN"] = df.apply(lambda row: getList(row), axis = 1);

我想在pandas dataframe中基于多个条件创建一个新列。新列的值应为list。但是我得到了“ValueError:Empty data passed with index specified.”（值错误：通过指定索引传递的空数据）。如果是空列表。在

^{pr2}$

完全错误：

ValueError Traceback (most recent call last) C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in create_block_manager_from_arrays(arrays, names, axes) 4636 try: -> 4637 blocks = form_blocks(arrays, names, axes) 4638 mgr = BlockManager(blocks, axes)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in form_blocks(arrays, names, axes) 4728 if len(object_items) > 0: -> 4729 object_blocks = _simple_blockify(object_items, np.object_) 4730 blocks.extend(object_blocks)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in _simple_blockify(tuples, dtype) 4758 """ -> 4759 values, placement = _stack_arrays(tuples, dtype) 4760

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in _stack_arrays(tuples, dtype) 4822 for i, arr in enumerate(arrays): -> 4823 stacked[i] = _asarray_compat(arr) 4824

ValueError: could not broadcast input array from shape (2) into shape (195)

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last) in () ----> 1 df["new_list_field"] = df.apply(lambda row: getList(row), axis = 1);

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, args, **kwds) 4875 f, axis, 4876 reduce=reduce, -> 4877 ignore_failures=ignore_failures) 4878 else: 4879 return self._apply_broadcast(f, axis)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in _apply_standard(self, func, axis, ignore_failures, reduce) 4988 index = None 4989 -> 4990 result = self._constructor(data=results, index=index) 4991 result.columns = res_index 4992

C:\ProgramData\Anaconda3\lib\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

C:\ProgramData\Anaconda3\lib\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):

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in _arrays_to_mgr(arrays, arr_names, index, columns, dtype) 6171 axes = [_ensure_index(columns), _ensure_index(index)] 6172 -> 6173 return create_block_manager_from_arrays(arrays, arr_names, axes) 6174 6175

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in create_block_manager_from_arrays(arrays, names, axes) 4640
return mgr 4641 except ValueError as e: -> 4642 construction_error(len(arrays), arrays[0].shape, axes, e) 4643 4644

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in construction_error(tot_items, block_shape, axes, e) 4604
raise e 4605 if block_shape[0] == 0: -> 4606 raise ValueError("Empty data passed with indices specified.")

4607 raise ValueError("Shape of passed values is {0}, indices imply {1}".format( 4608 passed, implied))

ValueError: Empty data passed with indices specified.

Answer 1

此函数的输出长度因行而异，但不能将长度不等的列表分配给新的pandas列。您可以通过以下方式进行验证：

for idx,row in df.iterrows():
    print(getList(row))

另一种方法是将输出转换为字符串：

^{pr2}$

Answer 2

最后生成了一个列表列表，将其转换为pd.Series()，并将其分配给一个新列。字典key2list返回可变长度列表作为值：

new_col_list = []

for _, row in my_df.iterrows():
    new_col_list.append(key2list[row[u'key']])

my_df[u'new_col'] = pd.Series(new_col_list)