python - 如何应用 if 条件并应用于数据框

Question

需要查看'detected' bool3_res的 key 带 key is_doc1的 bool_res和 bool_2资源

如果 bool3_res['detected'] == bool1_res['is_doc1'] == True然后我的resp必须返回

如果 bool3_res['detected'] == bool2_res['is_doc1'] == True然后我的resp必须返回\

3:否则返回“无效”

数据框

user_uid,bool1,bool2,bool3,bool1_res,bool2_res,bool3_res
1001,27452.webp,981.webp,d92e.webp,"{'is_doc1': False, 'is_doc2': True}","{'is_doc1': True, 'is_doc2': True}","{'detected': True, 'count': 1}"
1002,27452.webp,981.webp,d92e.webp,"{'is_doc1': True, 'is_doc2': True}","{'is_doc1': False, 'is_doc2': True}","{'detected': True, 'count': 1}"

我的代码

def new_func(x):
    d1 = df['bool1_res'].to_dict()
    d1 = eval(d1[0])
    d2 = df['bool2_res'].to_dict()
    d2 = eval(d2[0])
    d3 = df['bool3_res'].to_dict()
    d3 = eval(d3[0])

    if d1['is_doc1'] == d3['detected'] == True:
        resp = {
            "task_id": "uid",
            "group_id": "uid",
            "data": {
            "document1": df['bool1'],
            "document2": df['bool3']
            }
            }

    elif d2['is_doc1'] == d3['detected'] == True:
        resp = {
            "task_id": "user_uid",
            "group_id": "uid",
            "data": {
            "document1": df['bool2'],
            "document2": df['bool3']
            }
            }
    elif d3['detected'] == False:
        resp = 'Not valid'
    else:
        resp = 'Not valid'
    return resp
df['new'] = df.apply(new_func, axis = 1)
#df['new'] = df[['bool1', 'bool2', 'bool3', 'bool1_res', 'bool2_res', 'bool3_res']].applymap(new_func)

我的预期

df['新']

{'u_id': 'uid', 'group': 'uid', 'data': {'document1': ['981.webp'], 'document2': {'d92e.webp'}}}"
{'u_id': 'uid', 'group': 'uid', 'data': {'document1': ['27452.webp'], 'document2': {'d92e.webp'}}}"

我的出局
df['新']

0    {'task_id': 'user_uid', 'group_id': 'uid', 'data': {'document1': ['981.webp', '981.webp'], 'document2': ['d92e.webp', 'd92e.webp']}}
1    {'task_id': 'user_uid', 'group_id': 'uid', 'data': {'document1': ['981.webp', '981.webp'], 'document2': ['d92e.webp', 'd92e.webp']}}
Name: new, dtype: object

Answer 1

你应该避免 eval 而是使用 ast.literal_eval 与 x而是 df对于每行处理和一个元素列表添加 []至x['bool1'] , x['bool2']和 x['bool3'] :

import ast

def new_func(x):
    d1 = ast.literal_eval(x['bool1_res'])
    d2 = ast.literal_eval(x['bool2_res'])
    d3 = ast.literal_eval(x['bool3_res'])

    if d1['is_doc1'] == d3['detected'] == True:
        resp = {
            "task_id": "uid",
            "group_id": "uid",
            "data": {
            "document1": [x['bool1']],
            "document2": [x['bool3']]
            }
            }
    elif d2['is_doc1'] == d3['detected'] == True:
        resp = {
            "task_id": "user_uid",
            "group_id": "uid",
            "data": {
            "document1": [x['bool2']],
            "document2": [x['bool3']]
            }
            }
    elif d3['detected'] == False:
        resp = 'Not valid'
    else:
        resp = 'Not valid'
    return resp
df['new'] = df.apply(new_func, axis = 1)

print (df['new'].iat[0])
{'task_id': 'user_uid', 'group_id': 'uid', 'data': {'document1': ['981.webp'], 'document2': ['d92e.webp']}}

print (df['new'].iat[1])
{'task_id': 'uid', 'group_id': 'uid', 'data': {'document1': ['27452.webp'], 'document2': ['d92e.webp']}}