从 api 响应中解析嵌套 json 的最佳方法
Best way to parse nested json from an api response
所以我有一些代码可以从 api:
生成 json 响应
r4 = requests.get(url, params=mlp)
mlpr = r4.json()
1 行响应如下所示。
'command': 'SELECT', 'rowCount': 134, 'oid': None, 'rows': [{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans': [{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2}, {'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5}, {'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8}, {'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11}, {'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14}, {'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17}, {'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20}, {'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]}
如您所见，picks_bans“列有一个包含 3 个附加列的嵌套字典，我需要提取并分布在每个匹配 ID 中。
这是我用来将我的回复放入初始 Dataframe 的代码，但它只是让我达到初始水平。
mlpr_df = pd.DataFrame(mlpr.get('rows'))
mlpr_df
[示例数据框][1]
如何适当地取消嵌套 picks_bans 列？
编辑：我试图将代码更改为：
r4 = requests.get(url, params=mlp)
mlpr = r4.json()
data = mlpr.get('rows')
df = pd.concat([pd.DataFrame(data),
json_normalize(data['picks_bans'])],
axis=1).drop('picks_bans', 1)
我收到错误提示 "list indices must be integers or slices, not str"
json_normalize 就是您要找的。
作为一个技巧，我使用第一行数据的键列表减去要扩展的字段以获得要用作元数据的字段列表——它更容易编写并且更有弹性。为了更明确，我将参数名称放在调用中。
import pandas as pd
from pandas import json_normalize
df = json_normalize(data, record_path="picks_bans",
meta=[col for col in data[0].keys() if col != "picks_bans"])
df.head()
# is_pick hero_id team order match_id start_time leagueid patch name radiant_team dire_team
# -- --------- --------- ------ ------- ---------- ------------ ---------- ------- ------------------------------------------------ -------------- -----------
# 0 False 98 0 0 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
# 1 False 95 1 1 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
# 2 False 66 0 2 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
数据样本
data = [{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans':
[{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2},
{'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5},
{'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8},
{'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11},
{'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14},
{'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17},
{'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20},
{'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]},
{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans':
[{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2},
{'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5},
{'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8},
{'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11},
{'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14},
{'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17},
{'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20},
{'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]}
]
所以我有一些代码可以从 api:
生成 json 响应r4 = requests.get(url, params=mlp)
mlpr = r4.json()
1 行响应如下所示。
'command': 'SELECT', 'rowCount': 134, 'oid': None, 'rows': [{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans': [{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2}, {'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5}, {'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8}, {'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11}, {'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14}, {'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17}, {'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20}, {'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]}
如您所见，picks_bans“列有一个包含 3 个附加列的嵌套字典，我需要提取并分布在每个匹配 ID 中。
这是我用来将我的回复放入初始 Dataframe 的代码，但它只是让我达到初始水平。
mlpr_df = pd.DataFrame(mlpr.get('rows'))
mlpr_df
[示例数据框][1]
如何适当地取消嵌套 picks_bans 列？
编辑：我试图将代码更改为：
r4 = requests.get(url, params=mlp)
mlpr = r4.json()
data = mlpr.get('rows')
df = pd.concat([pd.DataFrame(data),
json_normalize(data['picks_bans'])],
axis=1).drop('picks_bans', 1)
我收到错误提示 "list indices must be integers or slices, not str"
json_normalize 就是您要找的。
作为一个技巧，我使用第一行数据的键列表减去要扩展的字段以获得要用作元数据的字段列表——它更容易编写并且更有弹性。为了更明确，我将参数名称放在调用中。
import pandas as pd
from pandas import json_normalize
df = json_normalize(data, record_path="picks_bans",
meta=[col for col in data[0].keys() if col != "picks_bans"])
df.head()
# is_pick hero_id team order match_id start_time leagueid patch name radiant_team dire_team
# -- --------- --------- ------ ------- ---------- ------------ ---------- ------- ------------------------------------------------ -------------- -----------
# 0 False 98 0 0 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
# 1 False 95 1 1 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
# 2 False 66 0 2 5334428840 1586029157 11823 7.25 ESL One Los Angeles 2020 Online powered by Intel Cyber Legacy B8
数据样本
data = [{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans':
[{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2},
{'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5},
{'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8},
{'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11},
{'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14},
{'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17},
{'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20},
{'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]},
{'match_id': 5334428840, 'start_time': 1586029157, 'leagueid': 11823, 'patch': '7.25', 'name': 'ESL One Los Angeles 2020 Online powered by Intel', 'radiant_team': 'Cyber Legacy', 'dire_team': 'B8', 'picks_bans':
[{'is_pick': False, 'hero_id': 98, 'team': 0, 'order': 0}, {'is_pick': False, 'hero_id': 95, 'team': 1, 'order': 1}, {'is_pick': False, 'hero_id': 66, 'team': 0, 'order': 2},
{'is_pick': False, 'hero_id': 43, 'team': 1, 'order': 3}, {'is_pick': False, 'hero_id': 49, 'team': 0, 'order': 4}, {'is_pick': False, 'hero_id': 110, 'team': 1, 'order': 5},
{'is_pick': False, 'hero_id': 79, 'team': 0, 'order': 6}, {'is_pick': False, 'hero_id': 106, 'team': 1, 'order': 7}, {'is_pick': True, 'hero_id': 96, 'team': 0, 'order': 8},
{'is_pick': True, 'hero_id': 86, 'team': 1, 'order': 9}, {'is_pick': True, 'hero_id': 129, 'team': 1, 'order': 10}, {'is_pick': True, 'hero_id': 50, 'team': 0, 'order': 11},
{'is_pick': False, 'hero_id': 12, 'team': 0, 'order': 12}, {'is_pick': False, 'hero_id': 77, 'team': 1, 'order': 13}, {'is_pick': True, 'hero_id': 128, 'team': 1, 'order': 14},
{'is_pick': True, 'hero_id': 121, 'team': 0, 'order': 15}, {'is_pick': True, 'hero_id': 41, 'team': 1, 'order': 16}, {'is_pick': True, 'hero_id': 42, 'team': 0, 'order': 17},
{'is_pick': False, 'hero_id': 126, 'team': 1, 'order': 18}, {'is_pick': False, 'hero_id': 65, 'team': 0, 'order': 19}, {'is_pick': True, 'hero_id': 31, 'team': 0, 'order': 20},
{'is_pick': True, 'hero_id': 45, 'team': 1, 'order': 21}]}
]