将JSON嵌套字典列表转换为DataFrame

[
    {"name": "Alice", "age": 25, "hobbies": ["reading", "swimming"]},
    {"name": "Bob", "age": 30, "hobbies": ["gaming", "hiking"]},
    {"name": "Charlie", "age": 35, "hobbies": ["cooking", "painting"]}
]

import pandas as pd

# JSON 嵌套字典列表
data = [
    {"name": "Alice", "age": 25, "hobbies": ["reading", "swimming"]},
    {"name": "Bob", "age": 30, "hobbies": ["gaming", "hiking"]},
    {"name": "Charlie", "age": 35, "hobbies": ["cooking", "painting"]}
]

# 转换为 DataFrame
df = pd.DataFrame(data)

print(df)

      name  age          hobbies
0    Alice   25  [reading, swimming]
1      Bob   30     [gaming, hiking]
2  Charlie   35  [cooking, painting]

import json

def flatten_json(y):
    out = {}

    def flatten(x, name=''):
        if type(x) is dict:
            for a in x:
                flatten(x[a], name + a + '_')
        elif type(x) is list:
            i = 0
            for a in x:
                flatten(a, name + str(i) + '_')
                i += 1
        else:
            out[name[:-1]] = x

    flatten(y)
    return out

# 嵌套字典列表
nested_data = [
    {"name": "Alice", "info": {"age": 25, "hobbies": ["reading", "swimming"]}},
    {"name": "Bob", "info": {"age": 30, "hobbies": ["gaming", "hiking"]}},
    {"name": "Charlie", "info": {"age": 35, "hobbies": ["cooking", "painting"]}}
]

# 扁平化嵌套数据
flattened_data = [flatten_json(item) for item in nested_data]

# 转换为 DataFrame
df = pd.DataFrame(flattened_data)

print(df)

      name  info_age          info_hobbies_0  info_hobbies_1
0    Alice       25             reading       swimming
1      Bob       30              gaming        hiking
2  Charlie       35             cooking       painting