pandas.io.json.json_normalize 非常嵌套 json
pandas.io.json.json_normalize with very nested json
我一直在尝试 normalize
一个非常嵌套的 json 文件,稍后我将对其进行分析。我正在努力解决的问题是如何深入到不止一个层次来规范化。
我浏览了 pandas.io.json.json_normalize 文档,因为它完全符合我的要求。
我已经能够规范化其中的一部分,现在理解了字典是如何工作的,但我仍然不在那里。
使用下面的代码我只能获得第一级。
import json
import pandas as pd
from pandas.io.json import json_normalize
with open('authors_sample.json') as f:
d = json.load(f)
raw = json_normalize(d['hits']['hits'])
authors = json_normalize(data = d['hits']['hits'],
record_path = '_source',
meta = ['_id', ['_source', 'journal'], ['_source', 'title'],
['_source', 'normalized_venue_name']
])
我试图用下面的代码 'dig' 进入 'authors' 字典,但是 record_path = ['_source', 'authors']
抛出了我 TypeError: string indices must be integers
。据我了解 json_normalize
逻辑应该是好的,但我仍然不太明白如何使用 dict
与 list
.[=23 深入研究 json =]
我什至通过了这个简单的 example。
authors = json_normalize(data = d['hits']['hits'],
record_path = ['_source', 'authors'],
meta = ['_id', ['_source', 'journal'], ['_source', 'title'],
['_source', 'normalized_venue_name']
])
下面是 json 文件的一部分(5 条记录)。
{u'_shards': {u'failed': 0, u'successful': 5, u'total': 5},
u'hits': {u'hits': [{u'_id': u'7CB3F2AD',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': None,
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'Physical Review Letters',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'phys rev lett',
u'pages': None,
u'parent_keywords': [u'Chromatography',
u'Quantum mechanics',
u'Particle physics',
u'Quantum field theory',
u'Analytical chemistry',
u'Quantum chromodynamics',
u'Physics',
u'Mass spectrometry',
u'Chemistry'],
u'pub_date': u'1987-03-02 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'mass spectra', u'elementary particles', u'bound states'],
u'title': u'Evidence for a new meson: A quasinuclear NN-bar bound state',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'Physical Review Letters',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7AF8EBC3',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'affiliations': [u'Punjabi University'],
u'author_id': u'780E3459',
u'author_name': u'munish puri'},
{u'affiliations': [u'Punjabi University'],
u'author_id': u'48D92C79',
u'author_name': u'rajesh dhaliwal'},
{u'affiliations': [u'Punjabi University'],
u'author_id': u'7D9BD37C',
u'author_name': u'r s singh'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'Journal of Industrial Microbiology & Biotechnology',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'j ind microbiol biotechnol',
u'pages': None,
u'parent_keywords': [u'Nuclear medicine',
u'Psychology',
u'Hydrology',
u'Chromatography',
u'X-ray crystallography',
u'Nuclear fusion',
u'Medicine',
u'Fluid dynamics',
u'Thermodynamics',
u'Physics',
u'Gas chromatography',
u'Radiobiology',
u'Engineering',
u'Organic chemistry',
u'High-performance liquid chromatography',
u'Chemistry',
u'Organic synthesis',
u'Psychotherapist'],
u'pub_date': u'2008-04-04 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'flow rate',
u'operant conditioning',
u'packed bed reactor',
u'immobilized enzyme',
u'specific activity'],
u'title': u'Development of a stable continuous flow immobilized enzyme reactor for the hydrolysis of inulin',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'Journal of Industrial Microbiology & Biotechnology',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7521A721',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'7FF872BC',
u'author_name': u'barbara eileen ryan'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Social science',
u'Politics',
u'Sociology',
u'Law'],
u'pub_date': u'1992-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'social movements'],
u'title': u"Feminism and the women's movement : dynamics of change in social movement ideology, and activism",
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7DAEB9A4',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'0299B8E9',
u'author_name': u'fraser j harbutt'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Superconductivity',
u'Nuclear fusion',
u'Geology',
u'Chemistry',
u'Metallurgy'],
u'pub_date': u'1988-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'iron'],
u'title': u'The iron curtain : Churchill, America, and the origins of the Cold War',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7B3236C5',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'7DAB7B72',
u'author_name': u'richard m freeland'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Political Science', u'Economics'],
u'pub_date': u'1985-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'foreign policy'],
u'title': u'The Truman Doctrine and the origins of McCarthyism : foreign policy, domestic politics, and internal security, 1946-1948',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'}],
u'max_score': 1.0,
u'total': 36429433},
u'timed_out': False,
u'took': 170}
In the pandas example (below) what do the brackets mean? Is there a logic to be followed to go deeper with the []. [...]
result = json_normalize(data, 'counties', ['state', 'shortname', ['info', 'governor']])
['state', 'shortname', ['info', 'governor']]
值中的每个字符串或字符串列表都是要包含的元素的路径,除了selected 行。第二个参数 json_normalize()
参数(record_path
,在文档示例中设置为 'counties'
)告诉函数如何从输入数据结构中 select 组成行的元素输出和 meta
路径添加了进一步的元数据,这些元数据将包含在每一行中。如果愿意,可以将这些视为 table 加入数据库。
the US States documentation example 的输入在一个列表中有两个词典,并且这两个词典都有一个 counties
键引用另一个字典列表:
>>> data = [{'state': 'Florida',
... 'shortname': 'FL',
... 'info': {'governor': 'Rick Scott'},
... 'counties': [{'name': 'Dade', 'population': 12345},
... {'name': 'Broward', 'population': 40000},
... {'name': 'Palm Beach', 'population': 60000}]},
... {'state': 'Ohio',
... 'shortname': 'OH',
... 'info': {'governor': 'John Kasich'},
... 'counties': [{'name': 'Summit', 'population': 1234},
... {'name': 'Cuyahoga', 'population': 1337}]}]
>>> pprint(data[0]['counties'])
[{'name': 'Dade', 'population': 12345},
{'name': 'Broward', 'population': 40000},
{'name': 'Palm Beach', 'population': 60000}]
>>> pprint(data[1]['counties'])
[{'name': 'Summit', 'population': 1234},
{'name': 'Cuyahoga', 'population': 1337}]
它们之间有 5 行数据用于输出:
>>> json_normalize(data, 'counties')
name population
0 Dade 12345
1 Broward 40000
2 Palm Beach 60000
3 Summit 1234
4 Cuyahoga 1337
meta
参数然后命名一些 next 到那些 counties
列表的元素,然后将这些元素单独合并。第一个 data[0]
字典中那些 meta
元素的值分别是 ('Florida', 'FL', 'Rick Scott')
,data[1]
的值是 ('Ohio', 'OH', 'John Kasich')
,所以你会看到附加的这些值到来自同一顶级词典的 counties
行,分别重复 3 次和 2 次:
>>> data[0]['state'], data[0]['shortname'], data[0]['info']['governor']
('Florida', 'FL', 'Rick Scott')
>>> data[1]['state'], data[1]['shortname'], data[1]['info']['governor']
('Ohio', 'OH', 'John Kasich')
>>> json_normalize(data, 'counties', ['state', 'shortname', ['info', 'governor']])
name population state shortname info.governor
0 Dade 12345 Florida FL Rick Scott
1 Broward 40000 Florida FL Rick Scott
2 Palm Beach 60000 Florida FL Rick Scott
3 Summit 1234 Ohio OH John Kasich
4 Cuyahoga 1337 Ohio OH John Kasich
因此,如果您为 meta
参数传入一个列表,则列表中的每个元素都是一个单独的路径,并且每个单独的路径都标识要添加到输出中的行的数据。
在您的示例JSON中,只有少数嵌套列表需要使用第一个参数提升,就像示例中的'counties'
一样。该数据结构中唯一的例子是嵌套的 'authors'
键;您必须提取每个 ['_source', 'authors']
路径,之后您可以从父对象添加其他键以增加这些行。
第二个 meta
参数然后从最外面的对象中拉入 _id
键,然后是嵌套的 ['_source', 'title']
和 ['_source', 'journal']
嵌套路径。
record_path
参数以 authors
列表为起点,它们看起来像:
>>> d['hits']['hits'][0]['_source']['authors'] # this value is None, and is skipped
>>> d['hits']['hits'][1]['_source']['authors']
[{'affiliations': ['Punjabi University'],
'author_id': '780E3459',
'author_name': 'munish puri'},
{'affiliations': ['Punjabi University'],
'author_id': '48D92C79',
'author_name': 'rajesh dhaliwal'},
{'affiliations': ['Punjabi University'],
'author_id': '7D9BD37C',
'author_name': 'r s singh'}]
>>> d['hits']['hits'][2]['_source']['authors']
[{'author_id': '7FF872BC',
'author_name': 'barbara eileen ryan'}]
>>> # etc.
所以给你以下几行:
>>> json_normalize(d['hits']['hits'], ['_source', 'authors'])
affiliations author_id author_name
0 [Punjabi University] 780E3459 munish puri
1 [Punjabi University] 48D92C79 rajesh dhaliwal
2 [Punjabi University] 7D9BD37C r s singh
3 NaN 7FF872BC barbara eileen ryan
4 NaN 0299B8E9 fraser j harbutt
5 NaN 7DAB7B72 richard m freeland
然后我们可以使用第三个 meta
参数添加更多列,例如 _id
、_source.title
和 _source.journal
,使用 ['_id', ['_source', 'journal'], ['_source', 'title']]
:
>>> json_normalize(
... data['hits']['hits'],
... ['_source', 'authors'],
... ['_id', ['_source', 'journal'], ['_source', 'title']]
... )
affiliations author_id author_name _id \
0 [Punjabi University] 780E3459 munish puri 7AF8EBC3
1 [Punjabi University] 48D92C79 rajesh dhaliwal 7AF8EBC3
2 [Punjabi University] 7D9BD37C r s singh 7AF8EBC3
3 NaN 7FF872BC barbara eileen ryan 7521A721
4 NaN 0299B8E9 fraser j harbutt 7DAEB9A4
5 NaN 7DAB7B72 richard m freeland 7B3236C5
_source.journal
0 Journal of Industrial Microbiology & Biotechno...
1 Journal of Industrial Microbiology & Biotechno...
2 Journal of Industrial Microbiology & Biotechno...
3 The American Historical Review
4 The American Historical Review
5 The American Historical Review
_source.title \
0 Development of a stable continuous flow immobi...
1 Development of a stable continuous flow immobi...
2 Development of a stable continuous flow immobi...
3 Feminism and the women's movement : dynamics o...
4 The iron curtain : Churchill, America, and the...
5 The Truman Doctrine and the origins of McCarth...
您还可以查看库 flatten_json,它不需要您像 json_normalize:[=12 那样编写列层次结构=]
from flatten_json import flatten
data = d['hits']['hits']
dict_flattened = (flatten(record, '.') for record in data)
df = pd.DataFrame(dict_flattened)
print(df)
我一直在尝试 normalize
一个非常嵌套的 json 文件,稍后我将对其进行分析。我正在努力解决的问题是如何深入到不止一个层次来规范化。
我浏览了 pandas.io.json.json_normalize 文档,因为它完全符合我的要求。
我已经能够规范化其中的一部分,现在理解了字典是如何工作的,但我仍然不在那里。
使用下面的代码我只能获得第一级。
import json
import pandas as pd
from pandas.io.json import json_normalize
with open('authors_sample.json') as f:
d = json.load(f)
raw = json_normalize(d['hits']['hits'])
authors = json_normalize(data = d['hits']['hits'],
record_path = '_source',
meta = ['_id', ['_source', 'journal'], ['_source', 'title'],
['_source', 'normalized_venue_name']
])
我试图用下面的代码 'dig' 进入 'authors' 字典,但是 record_path = ['_source', 'authors']
抛出了我 TypeError: string indices must be integers
。据我了解 json_normalize
逻辑应该是好的,但我仍然不太明白如何使用 dict
与 list
.[=23 深入研究 json =]
我什至通过了这个简单的 example。
authors = json_normalize(data = d['hits']['hits'],
record_path = ['_source', 'authors'],
meta = ['_id', ['_source', 'journal'], ['_source', 'title'],
['_source', 'normalized_venue_name']
])
下面是 json 文件的一部分(5 条记录)。
{u'_shards': {u'failed': 0, u'successful': 5, u'total': 5},
u'hits': {u'hits': [{u'_id': u'7CB3F2AD',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': None,
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'Physical Review Letters',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'phys rev lett',
u'pages': None,
u'parent_keywords': [u'Chromatography',
u'Quantum mechanics',
u'Particle physics',
u'Quantum field theory',
u'Analytical chemistry',
u'Quantum chromodynamics',
u'Physics',
u'Mass spectrometry',
u'Chemistry'],
u'pub_date': u'1987-03-02 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'mass spectra', u'elementary particles', u'bound states'],
u'title': u'Evidence for a new meson: A quasinuclear NN-bar bound state',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'Physical Review Letters',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7AF8EBC3',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'affiliations': [u'Punjabi University'],
u'author_id': u'780E3459',
u'author_name': u'munish puri'},
{u'affiliations': [u'Punjabi University'],
u'author_id': u'48D92C79',
u'author_name': u'rajesh dhaliwal'},
{u'affiliations': [u'Punjabi University'],
u'author_id': u'7D9BD37C',
u'author_name': u'r s singh'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'Journal of Industrial Microbiology & Biotechnology',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'j ind microbiol biotechnol',
u'pages': None,
u'parent_keywords': [u'Nuclear medicine',
u'Psychology',
u'Hydrology',
u'Chromatography',
u'X-ray crystallography',
u'Nuclear fusion',
u'Medicine',
u'Fluid dynamics',
u'Thermodynamics',
u'Physics',
u'Gas chromatography',
u'Radiobiology',
u'Engineering',
u'Organic chemistry',
u'High-performance liquid chromatography',
u'Chemistry',
u'Organic synthesis',
u'Psychotherapist'],
u'pub_date': u'2008-04-04 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'flow rate',
u'operant conditioning',
u'packed bed reactor',
u'immobilized enzyme',
u'specific activity'],
u'title': u'Development of a stable continuous flow immobilized enzyme reactor for the hydrolysis of inulin',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'Journal of Industrial Microbiology & Biotechnology',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7521A721',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'7FF872BC',
u'author_name': u'barbara eileen ryan'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Social science',
u'Politics',
u'Sociology',
u'Law'],
u'pub_date': u'1992-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'social movements'],
u'title': u"Feminism and the women's movement : dynamics of change in social movement ideology, and activism",
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7DAEB9A4',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'0299B8E9',
u'author_name': u'fraser j harbutt'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Superconductivity',
u'Nuclear fusion',
u'Geology',
u'Chemistry',
u'Metallurgy'],
u'pub_date': u'1988-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'iron'],
u'title': u'The iron curtain : Churchill, America, and the origins of the Cold War',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'},
{u'_id': u'7B3236C5',
u'_index': u'scibase_listings',
u'_score': 1.0,
u'_source': {u'authors': [{u'author_id': u'7DAB7B72',
u'author_name': u'richard m freeland'}],
u'deleted': 0,
u'description': None,
u'doi': u'',
u'is_valid': 1,
u'issue': None,
u'journal': u'The American Historical Review',
u'link': None,
u'meta_description': None,
u'meta_keywords': None,
u'normalized_venue_name': u'american historical review',
u'pages': None,
u'parent_keywords': [u'Political Science', u'Economics'],
u'pub_date': u'1985-01-01 00:00:00',
u'pubtype': None,
u'rating_avg_weighted': 0,
u'rating_clarity': 0.0,
u'rating_clarity_weighted': 0.0,
u'rating_innovation': 0.0,
u'rating_innovation_weighted': 0.0,
u'rating_num_weighted': 0,
u'rating_reproducability': 0,
u'rating_reproducibility_weighted': 0.0,
u'rating_versatility': 0.0,
u'rating_versatility_weighted': 0.0,
u'review_count': 0,
u'tag': [u'foreign policy'],
u'title': u'The Truman Doctrine and the origins of McCarthyism : foreign policy, domestic politics, and internal security, 1946-1948',
u'userAvg': 0.0,
u'user_id': None,
u'venue_name': u'The American Historical Review',
u'views_count': 0,
u'volume': None},
u'_type': u'listing'}],
u'max_score': 1.0,
u'total': 36429433},
u'timed_out': False,
u'took': 170}
In the pandas example (below) what do the brackets mean? Is there a logic to be followed to go deeper with the []. [...]
result = json_normalize(data, 'counties', ['state', 'shortname', ['info', 'governor']])
['state', 'shortname', ['info', 'governor']]
值中的每个字符串或字符串列表都是要包含的元素的路径,除了selected 行。第二个参数 json_normalize()
参数(record_path
,在文档示例中设置为 'counties'
)告诉函数如何从输入数据结构中 select 组成行的元素输出和 meta
路径添加了进一步的元数据,这些元数据将包含在每一行中。如果愿意,可以将这些视为 table 加入数据库。
the US States documentation example 的输入在一个列表中有两个词典,并且这两个词典都有一个 counties
键引用另一个字典列表:
>>> data = [{'state': 'Florida',
... 'shortname': 'FL',
... 'info': {'governor': 'Rick Scott'},
... 'counties': [{'name': 'Dade', 'population': 12345},
... {'name': 'Broward', 'population': 40000},
... {'name': 'Palm Beach', 'population': 60000}]},
... {'state': 'Ohio',
... 'shortname': 'OH',
... 'info': {'governor': 'John Kasich'},
... 'counties': [{'name': 'Summit', 'population': 1234},
... {'name': 'Cuyahoga', 'population': 1337}]}]
>>> pprint(data[0]['counties'])
[{'name': 'Dade', 'population': 12345},
{'name': 'Broward', 'population': 40000},
{'name': 'Palm Beach', 'population': 60000}]
>>> pprint(data[1]['counties'])
[{'name': 'Summit', 'population': 1234},
{'name': 'Cuyahoga', 'population': 1337}]
它们之间有 5 行数据用于输出:
>>> json_normalize(data, 'counties')
name population
0 Dade 12345
1 Broward 40000
2 Palm Beach 60000
3 Summit 1234
4 Cuyahoga 1337
meta
参数然后命名一些 next 到那些 counties
列表的元素,然后将这些元素单独合并。第一个 data[0]
字典中那些 meta
元素的值分别是 ('Florida', 'FL', 'Rick Scott')
,data[1]
的值是 ('Ohio', 'OH', 'John Kasich')
,所以你会看到附加的这些值到来自同一顶级词典的 counties
行,分别重复 3 次和 2 次:
>>> data[0]['state'], data[0]['shortname'], data[0]['info']['governor']
('Florida', 'FL', 'Rick Scott')
>>> data[1]['state'], data[1]['shortname'], data[1]['info']['governor']
('Ohio', 'OH', 'John Kasich')
>>> json_normalize(data, 'counties', ['state', 'shortname', ['info', 'governor']])
name population state shortname info.governor
0 Dade 12345 Florida FL Rick Scott
1 Broward 40000 Florida FL Rick Scott
2 Palm Beach 60000 Florida FL Rick Scott
3 Summit 1234 Ohio OH John Kasich
4 Cuyahoga 1337 Ohio OH John Kasich
因此,如果您为 meta
参数传入一个列表,则列表中的每个元素都是一个单独的路径,并且每个单独的路径都标识要添加到输出中的行的数据。
在您的示例JSON中,只有少数嵌套列表需要使用第一个参数提升,就像示例中的'counties'
一样。该数据结构中唯一的例子是嵌套的 'authors'
键;您必须提取每个 ['_source', 'authors']
路径,之后您可以从父对象添加其他键以增加这些行。
第二个 meta
参数然后从最外面的对象中拉入 _id
键,然后是嵌套的 ['_source', 'title']
和 ['_source', 'journal']
嵌套路径。
record_path
参数以 authors
列表为起点,它们看起来像:
>>> d['hits']['hits'][0]['_source']['authors'] # this value is None, and is skipped
>>> d['hits']['hits'][1]['_source']['authors']
[{'affiliations': ['Punjabi University'],
'author_id': '780E3459',
'author_name': 'munish puri'},
{'affiliations': ['Punjabi University'],
'author_id': '48D92C79',
'author_name': 'rajesh dhaliwal'},
{'affiliations': ['Punjabi University'],
'author_id': '7D9BD37C',
'author_name': 'r s singh'}]
>>> d['hits']['hits'][2]['_source']['authors']
[{'author_id': '7FF872BC',
'author_name': 'barbara eileen ryan'}]
>>> # etc.
所以给你以下几行:
>>> json_normalize(d['hits']['hits'], ['_source', 'authors'])
affiliations author_id author_name
0 [Punjabi University] 780E3459 munish puri
1 [Punjabi University] 48D92C79 rajesh dhaliwal
2 [Punjabi University] 7D9BD37C r s singh
3 NaN 7FF872BC barbara eileen ryan
4 NaN 0299B8E9 fraser j harbutt
5 NaN 7DAB7B72 richard m freeland
然后我们可以使用第三个 meta
参数添加更多列,例如 _id
、_source.title
和 _source.journal
,使用 ['_id', ['_source', 'journal'], ['_source', 'title']]
:
>>> json_normalize(
... data['hits']['hits'],
... ['_source', 'authors'],
... ['_id', ['_source', 'journal'], ['_source', 'title']]
... )
affiliations author_id author_name _id \
0 [Punjabi University] 780E3459 munish puri 7AF8EBC3
1 [Punjabi University] 48D92C79 rajesh dhaliwal 7AF8EBC3
2 [Punjabi University] 7D9BD37C r s singh 7AF8EBC3
3 NaN 7FF872BC barbara eileen ryan 7521A721
4 NaN 0299B8E9 fraser j harbutt 7DAEB9A4
5 NaN 7DAB7B72 richard m freeland 7B3236C5
_source.journal
0 Journal of Industrial Microbiology & Biotechno...
1 Journal of Industrial Microbiology & Biotechno...
2 Journal of Industrial Microbiology & Biotechno...
3 The American Historical Review
4 The American Historical Review
5 The American Historical Review
_source.title \
0 Development of a stable continuous flow immobi...
1 Development of a stable continuous flow immobi...
2 Development of a stable continuous flow immobi...
3 Feminism and the women's movement : dynamics o...
4 The iron curtain : Churchill, America, and the...
5 The Truman Doctrine and the origins of McCarth...
您还可以查看库 flatten_json,它不需要您像 json_normalize:[=12 那样编写列层次结构=]
from flatten_json import flatten
data = d['hits']['hits']
dict_flattened = (flatten(record, '.') for record in data)
df = pd.DataFrame(dict_flattened)
print(df)