空DataFrame调用clean_list函数触发ValueError问题求助
2026-8-11
问题：空DataFrame应用自定义函数触发ValueError错误
原代码
def replaceitem(x): if x in ['ORION', 'ACTION', 'ICE', 'IRIS', 'FOCUS']: return 'CRM Application' else: return x def clean_list(row): new_list = sorted(set(row['APLN_NM']), key=lambda x: row['APLN_NM'].index(x)) for idx,i in enumerate(new_list): new_list[idx] = replaceitem(i) new_list = sorted(set(new_list), key=lambda x: new_list.index(x)) return new_list # 应用函数到DataFrame df_agg['APLN_NM_DISTINCT'] = df_agg.apply(clean_list, axis = 1) df_agg_single['APLN_NM_DISTINCT'] = df_agg_single.apply(clean_list, axis = 1)
错误信息
--------------------------------------------------------------------------- KeyError Traceback (most recent call last) /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance) 2890 try: -> 2891 return self._engine.get_loc(casted_key) 2892 except KeyError as err: pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc() pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc() pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item() pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item() KeyError: 'APLN_NM_DISTINCT' The above exception was the direct cause of the following exception: KeyError Traceback (most recent call last) /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/generic.py in _set_item(self, key, value) 3570 try: -> 3571 loc = self._info_axis.get_loc(key) 3572 except KeyError: /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance) 2892 except KeyError as err: -> 2893 raise KeyError(key) from err 2894 KeyError: 'APLN_NM_DISTINCT' During handling of the above exception, another exception occurred: ValueError Traceback (most recent call last) <ipython-input-71-e8b5e8d5b514> in <module> 431 #********************************************************************************************************************************************* 432 df_agg['APLN_NM_DISTINCT'] = df_agg.apply(clean_list, axis = 1) -> 433 df_agg_single['APLN_NM_DISTINCT'] = df_agg_single.apply(clean_list, axis = 1) 434 435 df_agg['TOTAL_HOLD_TIME'] = df_agg_single['TOTAL_HOLD_TIME'].astype(int) /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/frame.py in __setitem__(self, key, value) 3038 else: 3039 # set column -> 3040 self._set_item(key, value) 3041 3042 def _setitem_slice(self, key: slice, value): /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/frame.py in _set_item(self, key, value) 3115 self._ensure_valid_index(value) 3116 value = self._sanitize_column(key, value) -> 3117 NDFrame._set_item(self, key, value) 3118 3119 # check if we are modifying a copy /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/generic.py in _set_item(self, key, value) 3572 except KeyError: 3573 # This item wasn't present, just insert at end -> 3574 self._mgr.insert(len(self._info_axis), key, value) 3575 return 3576 /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/internals/managers.py in insert(self, loc, item, value, allow_duplicates) 1187 value = _safe_reshape(value, (1,) + value.shape) 1188 -> 1189 block = make_block(values=value, ndim=self.ndim, placement=slice(loc, loc + 1)) 1190 1191 for blkno, count in _fast_count_smallints(self.blknos[loc:]): /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/internals/blocks.py in make_block(values, placement, klass, ndim, dtype) 2717 values = DatetimeArray._simple_new(values, dtype=dtype) 2718 -> 2719 return klass(values, ndim=ndim, placement=placement) 2720 2721 /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/internals/blocks.py in __init__(self, values, placement, ndim) 2373 values = np.array(values, dtype=object) 2374 -> 2375 super().__init__(values, ndim=ndim, placement=placement) 2376 2377 @property /opt/rh/rh-python36/root/usr/lib64/python3.6/site-packages/pandas/core/internals/blocks.py in __init__(self, values, placement, ndim) 128 if self._validate_ndim and self.ndim and len(self.mgr_locs) != len(self.values): 129 raise ValueError( -> 130 f"Wrong number of items passed {len(self.values)}, " 131 f"placement implies {len(self.mgr_locs)}" 132 ) ValueError: Wrong number of items passed 3, placement implies 1
问题原因
df_agg_single是空DataFrame，调用apply时自定义函数clean_list不会被执行（无行可处理），此时apply返回的结果无法匹配pandas对新列的结构要求，导致赋值时触发ValueError。
解决方案
方案1：判断DataFrame是否为空再处理
直接跳过空DataFrame的函数应用，手动创建同类型空列：
import pandas as pd # 处理有数据的df_agg df_agg['APLN_NM_DISTINCT'] = df_agg.apply(clean_list, axis=1) # 仅在df_agg_single非空时应用函数，否则创建空列 if not df_agg_single.empty: df_agg_single['APLN_NM_DISTINCT'] = df_agg_single.apply(clean_list, axis=1) else: # 创建存储列表的object类型空列 df_agg_single['APLN_NM_DISTINCT'] = pd.Series(dtype='object')
方案2：增强自定义函数的鲁棒性
修改clean_list，处理空值或缺失列的情况，即使空DataFrame后续有数据也能兼容：
def replaceitem(x): if x in ['ORION', 'ACTION', 'ICE', 'IRIS', 'FOCUS']: return 'CRM Application' else: return x def clean_list(row): # 先获取APLN_NM的值，不存在则返回空列表 apln_nm = row.get('APLN_NM', []) # 处理空列表情况 if not apln_nm: return [] new_list = sorted(set(apln_nm), key=lambda x: apln_nm.index(x)) for idx,i in enumerate(new_list): new_list[idx] = replaceitem(i) new_list = sorted(set(new_list), key=lambda x: new_list.index(x)) return new_list # 直接应用函数，空DataFrame会自动生成空列 df_agg['APLN_NM_DISTINCT'] = df_agg.apply(clean_list, axis=1) df_agg_single['APLN_NM_DISTINCT'] = df_agg_single.apply(clean_list, axis=1)
方案3：强制转换为Series
将apply的结果转为指定类型的Series，确保pandas能正确识别列结构：
import pandas as pd df_agg['APLN_NM_DISTINCT'] = df_agg.apply(clean_list, axis=1) # 强制转为object类型Series，匹配列表存储需求 df_agg_single['APLN_NM_DISTINCT'] = pd.Series(df_agg_single.apply(clean_list, axis=1), dtype='object')
内容的提问来源于stack exchange，提问作者AshishMulupuri
相关产品推荐
相关产品推荐
