python - python 将具有相同键值对的多个字典合并为一个字典

Question

我有一个存储在列表中的字典列表。我想将相同的字典合并为一个。我有三个字段。 Task_id 提供要检查的字段。 value 是该字段的值。首先，它检查字典中的值，并为要合并的字典创建一个新字典。如果所有值都相同并且只有一个值不同，则将字典合并为一。如何使其成为可能

这是我尝试过的示例代码:

field_to_be_check ="state"
merger = ["city", "ads"]
merge_name = ["cities", "my_ads"]

data = [
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'tirunelveli'}, 
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad4', 'city': 'nagerkoil'}, 
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'tuticorin'}, 
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'madurai'}, 
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'chennai'}, 
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'palakad'}, 
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'guruvayor'}, 
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'kolikodu'}, 
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'kottayam'}, 
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'idukki'}, 
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Akola'}, 
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Washim'}, 
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Jalna'}, 
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Nanded'}, 
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Latur'}
]

d = []
list1 = []
for item in data:
    value = item[field_to_be_check]
    inserted = False
    for l in list1: 
        if l[field_to_be_check] == value:
            inserted = True
            for m_name in merge_name:

    if inserted == False:
        list1.append(item)

print(list1)

所需输出:

   [
    {'state': 'tamil nadu','my_ads':[{'ads': 'ad1'},{'ads': 'ad4'}], 'cities':[{'city': 'tirunelveli'},{'city': 'nagerkoil'},{'city': 'tuticorin'},{'city': 'madurai'},{'city': 'chennai'}]}, 
    {'state': 'kerala',,'my_ads':[{'ads': 'ad2'}], 'cities': [{'city': 'palakad'},{'city': 'guruvayor'},{'city': 'kolikodu'},{'city': 'kottayam'},{'city': 'idukki'}]}, 
    {'state': 'mumbai', 'my_ads':[{'ads': 'ad3'}],'cities':[{'city': 'Akola'},{'city': 'Washim'},{'city': 'Jalna'},{'city': 'Nanded'},{'city': 'Latur'}]}
    ]

Answer 1

这是一个展示 itertools.groupby 力量的完美场景。 请注意，我假设 haps、state 和 ads 将出现在所有词典中，并且重复次数相似

from itertools import groupby

field_to_be_check =  "state"
merger = ["city", "ads"]
merge_name = ["cities", "my_ads"]

data = [
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'tirunelveli'},
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad4', 'city': 'nagerkoil'},
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'tuticorin'},
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'madurai'},
{'haps': 'hap0', 'state': 'tamil nadu', 'ads': 'ad1', 'city': 'chennai'},
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'palakad'},
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'guruvayor'},
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'kolikodu'},
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'kottayam'},
{'haps': 'hap1', 'state': 'kerala', 'ads': 'ad2', 'city': 'idukki'},
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Akola'},
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Washim'},
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Jalna'},
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Nanded'},
{'haps': 'hap2', 'state': 'mumbai', 'ads': 'ad3', 'city': 'Latur'}
]

#Function to make the merger lists
def process_group(group, merger_item):

    item_set = set()
    item_list = []
    for item in group:
        item_set.add(item[merger_item])

    for item in item_set:
        item_list.append({merger_item: item})

    return item_list

#Group on haps, state and ads
grp = groupby(data,key=lambda x:(x[field_to_be_check]))
result = []

#Iterate through the group and build your result list
for model, group in grp:
    cities_dict = {}

    cities_dict[field_to_be_check] = model

    group_list = list(group)

    #Make the list for merger fields
    for idx, name in enumerate(merger):
        cities_dict[merge_name[idx]] = process_group(group_list, name)

    result.append(cities_dict)

print(result)

输出将如下所示

[{'state': 'tamil nadu', 
'cities': [{'city': 'nagerkoil'}, {'city': 'tuticorin'}, {'city': 'chennai'}, {'city': 'madurai'}, {'city': 'tirunelveli'}], 
'my_ads': [{'ads': 'ad4'}, {'ads': 'ad1'}]}, 
{'state': 'kerala', 
'cities': [{'city': 'guruvayor'}, {'city': 'idukki'}, {'city': 'kottayam'}, {'city': 'palakad'}, {'city': 'kolikodu'}], 
'my_ads': [{'ads': 'ad2'}]}, 
{'state': 'mumbai', 
'cities': [{'city': 'Jalna'}, {'city': 'Nanded'}, {'city': 'Washim'}, {'city': 'Latur'}, {'city': 'Akola'}], 
'my_ads': [{'ads': 'ad3'}]}]