Python JSON到树图
我有一个严重嵌套的JSON对象。有没有一种方法可以让我查看分层树形图？我浏览了一些资源，如Pydot、Plotly等，但没有任何东西能够以我的格式呈现JSON JSON文件：Python JSON到树图,python,json,dictionary,Python,Json,Dictionary,我有一个严重嵌套的JSON对象。有没有一种方法可以让我查看分层树形图？我浏览了一些资源，如Pydot、Plotly等，但没有任何东西能够以我的格式呈现JSON JSON文件： { "found_intents": { "_DATE": {} }, "sentence": "What is your name", "tree": [ [ { "canonical": null, "concept": "_START_TAG
{
"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
}
]
]
}
现在还不完全清楚您想要做什么，但是下面的代码统计了每个嵌套深度的dict和列表的数量。我们使用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，将计数存储在一系列列表中，并将这些容器推到堆栈上以供将来处理。当我们计算完所有对象后，我们计算出每个级别的平均分支数 我不会将您的数据粘贴到此代码中，因为它大约有740行长。我将该数据称为data_string，在我的机器上，我只是将数据用三个引号括起来，但您当然可以将其保存为文件，并使用json.load加载它
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)
谢谢你的回答。有没有办法让我知道整个json的哪一部分属于相应的级别？一个这样的例子是不言自明的。@nikinlpds这听起来是一个新问题的好话题；如果你愿意，你可以在新问题中添加一个链接回到这个问题。你需要准确地解释你想如何测量它。我假设您希望以节点项目的数量来衡量它，但也许您希望以字符来衡量它。感谢您的快速响应。基本上，在遍历时，JSON的任何部分都必须被提取出来。我在这里提出了一个单独的问题-。最后，我想做的是看看每个级别上有多少元素对应于say概念。@nikinlpds正如bruno所说，你需要更清楚地解释你的问题，否则问题会被搁置。好的。我会简化的。目前，我们有每个嵌套深度的DICT和列表的计数。我只想把这些dict/列表作为一个整体按级别提取。现在清楚了吗？
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)
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