PYTHON - 對字典列表進行分組

Question

有沒有一種簡單的方法在 Python3 中按鍵對 dict 列表進行分組我有一個復雜的輸入列表，我想格式化

我的輸入 object 是這樣的：

my_input = [
  {
    'name': 'nameA',
    'departments': [
      {
        'name': 'dep1',
        'details': [
          {
            'name': 'name_detA',
            'tech_name': 'techNameA',
            'others': None,
            'sub_details': []
          },
          {
            'name': 'name_detB',
            'tech_name': 'techNameB',
            'others': 22,
            'sub_details': [
             {
                'id': 'idB',
                'column2': 'ZZ',
                'column3': 'CCC',
                'column4': {
                  'id': 'id2',
                  'subColumn1': 'HHH',
                  'subColumn1': 'PPPP',
                  'subColumn1': 'FFFFFF'
                }
              }
            ]
          },
          
          
          {
            'name': 'name_detB',
            'tech_name': 'techNameB',
            'others': 22,
            'sub_details': [
              {
                'id': 'idA',
                'column2': 'AA',
                'column3': 'BBB',
                'column4': {
                  'id': 'id1',
                  'subColumn1': 'XXXX',
                  'subColumn1': 'YYYYY',
                  'subColumn1': 'DDDDDD'
                }
              }
            ]
          }
          
        ]
      }
    ]
  }
]

我的目標是將具有相同details['techName']元素分組為一個元素並合並它們的sub_details

預期 output：

my_output = [
  {
    "name": "nameA",
    "departments": [
      {
        "name": "dep1",
        "details": [
          {
            "name": "name_detA",
            "tech_name": "techNameA",
            "others": None,
            "sub_details": []
          },
          {
            "name": "name_detB",
            "tech_name": "techNameB",
            "others": 22,
            "sub_details": [
             {
                "id": "idB",
                "column2": "ZZ",
                "column3": "CCC",
                "column4": {
                  "id": "id2",
                  "subColumn1": "HHH",
                  "subColumn1": "PPPP",
                  "subColumn1": "FFFFFF"
                }
              },
              {
                "id": "idA",
                "column2": "AA",
                "column3": "BBB",
                "column4": {
                  "id": "id1",
                  "subColumn1": "XXXX",
                  "subColumn1": "YYYYY",
                  "subColumn1": "DDDDDD"
                }
              }
            ]
          }
        ]
      }
    ]
  }
]

我試過了：

result_list = []
sub = []
for elem in my_input:
    for data in elem["departments"]:
        for sub_detail, dicts_for_that_sub in itertools.groupby(data["details"], key=operator.itemgetter("sub_details")):
            sub.append({"sub_details": sub_detail})
        print(sub)

但我正在努力創建新的 output

Answer 1

假設我在這里使用的輸入是您真正想要的，那么您就在正確的軌道上。 我將最里面的 for 循環重新實現為對方法的調用，但這並不是嚴格需要的。

我可能會對使用setdefault()而不是if / else的merge_details()方法采取稍微不同的方法，但如果您以前沒有使用過setdefault() ，這種方法更容易遵循。

import json只是為了打印“不錯”的東西，並且不需要作為解決方案的一部分。

import json

my_input = [
  {
    "name": "nameA",
    "departments": [
      {
        "name": "dep1",
        "details": [
          {
            "name": "name_detB",
            "tech_name": "techNameB",
            "others": 22,
            "sub_details": [
             {
                "id": "idB",
                "column2": "ZZ",
                "column3": "CCC",
                "column4": {
                  "id": "id2",
                  "subColumn1": "HHH",
                  "subColumn2": "PPPP",
                  "subColumn3": "FFFFFF"
                }
              }
            ]
          },
          {
            "name": "name_detA",
            "tech_name": "techNameA",
            "others": None,
            "sub_details": []
          },
          {
            "name": "name_detB",
            "tech_name": "techNameB",
            "others": 22,
            "sub_details": [
              {
                "id": "idA",
                "column2": "AA",
                "column3": "BBB",
                "column4": {
                  "id": "id1",
                  "subColumn1": "XXXX",
                  "subColumn2": "YYYYY",
                  "subColumn3": "DDDDDD"
                }
              }
            ]
          }
        ]
      }
    ]
  }
]

def merge_details(details):
    ## --------------------
    ## dict to hold details by key (tech_name)
    keyed_details = {}
    ## --------------------

    ## --------------------
    ## for each each "detail" if we find it in the key_detail merge the
    ## sub_details lists otherwise add it as the value of the key
    ## --------------------
    for detail in details:
        key = detail["tech_name"]
        if keyed_details.get(key):
            keyed_details[key]["sub_details"].extend(detail["sub_details"])
        else:
            keyed_details[key] = detail
    ## --------------------

    return list(keyed_details.values())

for elem in my_input:
    for department in elem["departments"]:
        department["details"] = merge_details(department["details"])

print(json.dumps(my_input, indent=4, sort_keys=True))