我有一个严重嵌套的JSON对象。有没有一种方法可以查看分层树图?我经历了一些资源,例如Pydot,Plotly等,但是没有什么可以呈现我格式的JSON。
JSON文件:
{
"found_intents": {
"_DATE": {}
},
"sentence": "What is your name",
"tree": [
[
{
"canonical": null,
"concept": "_START_TAG",
"correct_string": "<start>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<start>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
},
{
"canonical": null,
"concept": "_WHAT_IS",
"correct_string": "what is",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "what",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "what",
"language": "english",
"span": [
1,
2
],
"span_string": "what",
"weight": 1.0
},
{
"canonical": null,
"concept": "",
"correct_string": "is",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "is",
"language": "english",
"span": [
2,
3
],
"span_string": "is",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "what is",
"language": "english",
"span": [
1,
3
],
"span_string": "what is",
"weight": 1.0
},
{
"canonical": null,
"concept": "_DICTIONARY",
"correct_string": "your",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "your",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
},
{
"canonical": null,
"concept": "_DICTIONARY",
"correct_string": "name",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "name",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
},
{
"canonical": null,
"concept": "_END_TAG",
"correct_string": "<end>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<end>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
[
{
"canonical": null,
"concept": "_START_TAG",
"correct_string": "<start>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<start>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
},
{
"canonical": null,
"concept": "_WHAT_IS",
"correct_string": "what is",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "what",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "what",
"language": "english",
"span": [
1,
2
],
"span_string": "what",
"weight": 1.0
},
{
"canonical": null,
"concept": "",
"correct_string": "is",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "is",
"language": "english",
"span": [
2,
3
],
"span_string": "is",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "what is",
"language": "english",
"span": [
1,
3
],
"span_string": "what is",
"weight": 1.0
},
{
"canonical": null,
"concept": "_DICTIONARY",
"correct_string": "your",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "your",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
},
{
"canonical": null,
"concept": "_THEATRE_ID",
"correct_string": "name",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "name",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
},
{
"canonical": null,
"concept": "_END_TAG",
"correct_string": "<end>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<end>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
[
{
"canonical": null,
"concept": "_START_TAG",
"correct_string": "<start>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<start>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
},
{
"canonical": null,
"concept": "_WHAT_IS",
"correct_string": "what is",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "what",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "what",
"language": "english",
"span": [
1,
2
],
"span_string": "what",
"weight": 1.0
},
{
"canonical": null,
"concept": "",
"correct_string": "is",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "is",
"language": "english",
"span": [
2,
3
],
"span_string": "is",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "what is",
"language": "english",
"span": [
1,
3
],
"span_string": "what is",
"weight": 1.0
},
{
"canonical": null,
"concept": "_THEATRE_ID",
"correct_string": "your",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "your",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
},
{
"canonical": null,
"concept": "_DICTIONARY",
"correct_string": "name",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "name",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
},
{
"canonical": null,
"concept": "_END_TAG",
"correct_string": "<end>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<end>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
[
{
"canonical": null,
"concept": "_START_TAG",
"correct_string": "<start>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<start>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<start>",
"language": "english",
"span": [
0,
1
],
"span_string": "<start>",
"weight": 1.0
},
{
"canonical": null,
"concept": "_WHAT_IS",
"correct_string": "what is",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "what",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "what",
"language": "english",
"span": [
1,
2
],
"span_string": "what",
"weight": 1.0
},
{
"canonical": null,
"concept": "",
"correct_string": "is",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "is",
"language": "english",
"span": [
2,
3
],
"span_string": "is",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "what is",
"language": "english",
"span": [
1,
3
],
"span_string": "what is",
"weight": 1.0
},
{
"canonical": null,
"concept": "_THEATRE_ID",
"correct_string": "your",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "your",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "your",
"language": "english",
"span": [
3,
4
],
"span_string": "your",
"weight": 1.0
},
{
"canonical": null,
"concept": "_THEATRE_ID",
"correct_string": "name",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "name",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "name",
"language": "english",
"span": [
4,
5
],
"span_string": "name",
"weight": 1.0
},
{
"canonical": null,
"concept": "_END_TAG",
"correct_string": "<end>",
"definition": "",
"details": [
{
"canonical": null,
"concept": "",
"correct_string": "<end>",
"definition": "",
"details": [],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
],
"e.g.": [],
"grammar": "<end>",
"language": "english",
"span": [
5,
6
],
"span_string": "<end>",
"weight": 1.0
}
]
]
}
更准确地说,我想提取每个级别的平均分支数量。
预期结果将是:
Level 0: 4
Level 1: (1 + 2 + 1 + 1)/4
Level 2: 0
答案 0 :(得分:0)
尚不清楚您要做什么,但是以下代码计算每个嵌套深度的字典和列表数。我们使用collections.deque
作为堆栈来执行广度优先搜索,计算每个级别上嵌套容器的数量,将计数存储在defaultdict
列表中,然后将这些容器推入堆栈以备将来使用处理。完成对所有对象的计数后,我们将计算每个级别的平均分支数量。
我不会将您的数据粘贴到此代码中,因为它的长度约为740行。我将这些数据称为data_string
,在我的机器上,我只是将您的数据用三引号引起来,但是您当然可以将其保存为文件,并使用json.load
进行加载。
import json
from collections import defaultdict, deque
data = json.loads(data_string)
def get_branches(obj):
branches = defaultdict(list)
stack = deque()
stack.append((obj, 0))
while stack:
obj, depth = stack.pop()
newdepth = depth + 1
branch_count = 0
if isinstance(obj, dict):
obj = obj.values()
for child in obj:
if isinstance(child, (list, dict)):
branch_count += 1
stack.append((child, newdepth))
if branch_count:
branches[depth].append(branch_count)
return branches
branches = get_branches(data)
for depth in sorted(branches.keys()):
row = branches[depth]
mean = sum(row) / len(row) if row else None
print('Level', depth, row, mean)
输出
Level 0 [2] 2.0
Level 1 [4, 1] 2.5
Level 2 [5, 5, 5, 5] 5.0
Level 3 [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3] 3.0
Level 4 [1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1] 1.2
Level 5 [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3] 3.0