我有一个python函数：
from collections import defaultdict
from csv import DictReader
def solution(csv_filename):
by_subject_id = defaultdict(lambda: {
'name': None,
'dob': None,
'gender': None,
'visits': {},
'samples': {}
})
with open(csv_filename) as f:
dict_reader = DictReader(f)
for row in dict_reader:
non_empty = {k: v for k, v in row.items() if v}
subject_id = non_empty['subid'] # must have to group by
first_visit = non_empty.get('firstvisit') # optional
sample = non_empty.get('samplenumber') # optional
visit = non_empty.get('visitdate1') # optional
if first_visit:
by_subject_id[subject_id].update({
'name': non_empty.get('name'),
'dob': non_empty.get('dob'),
'gender': non_empty.get('gender')
})
elif visit:
by_subject_id[subject_id]['visits'][visit] = {
'age': non_empty.get('age'),
'visit_category': non_empty.get('visitcategory')
}
elif sample:
by_subject_id[subject_id]['samples'][sample] = {
'completed_by': non_empty.get('completed_by'),
'label_on_sample': non_empty.get('label_on_sample')
}
return [{'subject_id': k, **v} for k, v in by_subject_id.items()]
将CSV转换为：
'subid,firstvisit,name,contact,dob,gender,visitdate1,age,visitcategory,samplenumber,label_on_sample,completed_by
1,12/31/11,Bob,,12/31/00,Male,,,,,,
1,,,,,,12/31/15,17,Baseline Visit,,,
1,,,,,,12/31/16,18,Follow Up Visit,,,
1,,,,,,12/31/17,18,Follow Up Visit,,,
1,,,,12/31/00,Male,,17,,XXX123,1,Sally
2,1/1/12,,,1/1/01,Female,,,,,,
2,,,,,,1/1/11,10,Baseline Visit,,,
2,,,,,,1/1/12,11,Follow Up Visit,,,
2,,,,,,1/1/13,12,Follow Up Visit,,,
2,,,,,,1/1/14,13,Follow Up Visit,,,
2,,,,,,1/1/15,14,Follow Up Visit,,,
2,,,,1/1/01,Female,,15,,YYY456,2,
2,,,,1/1/01,Female,,15,,ZZZ789,2,Sally'
对于像这样的Json：
[
{
"subject_id": "1",
"name": "Bob",
"dob": "12/31/00",
"gender": "Male",
"visits": {
"12/31/15": {
"age": "17",
"visit_category": "Baseline Visit"
},
"12/31/16": {
"age": "18",
"visit_category": "Follow Up Visit"
},
"12/31/17": {
"age": "18",
"visit_category": "Follow Up Visit"
}
},
"samples": {
"XXX123": {
"completed_by": "Sally",
"label_on_sample": "1"
}
}
},
{
"subject_id": "2",
"name": null,
"dob": "1/1/01",
"gender": "Female",
"visits": {
"1/1/11": {
"age": "10",
"visit_category": "Baseline Visit"
},
"1/1/12": {
"age": "11",
"visit_category": "Follow Up Visit"
},
"1/1/13": {
"age": "12",
"visit_category": "Follow Up Visit"
},
"1/1/14": {
"age": "13",
"visit_category": "Follow Up Visit"
},
"1/1/15": {
"age": "14",
"visit_category": "Follow Up Visit"
}
},
"samples": {
"YYY456": {
"completed_by": null,
"label_on_sample": "2"
},
"ZZZ789": {
"completed_by": "Sally",
"label_on_sample": "2"
}
}
}
]
用于导出到Mongodb。但是，一旦进入Mongodb，我就会发现访问和样本的变量字段名称使查询变得非常困难。我可以对我的函数进行哪些修改，以返回像这样的json：
[
{
"subject_id": "1",
"name": "Maria",
"dob": "1/1/00",
"gender": "F",
"visits": [
{ "date": "1/1/18",
"date_entered": "1/2/18",
"entered_by": "Sally"
},
{ "date" : "1/2/18",
"date_entered": "1/2/18",
"entered_by": "Tim"
}
],
"samples": [
{ "sample_id" : "XXX123",
"collected_by": "Sally",
"collection_date": "1/3/18"
}
]
},
{
"subject_id": "2",
"name": "Bob",
"dob": "1/2/00",
"gender": "M",
"visits": [
{ "date" : "1/3/18",
"date_entered": "1/4/18",
"entered_by": "Tim"
}
],
"samples": [
{ "sample_id": "YYY456",
"collected_by": "Sally",
"collection_date": "1/5/18"
},
{ "sample_id" : "ZZZ789",
"collected_by": "Tim",
"collection_date": "1/6/18"
},
{ "sample_id": "AAA123",
"collected_by": "Sally",
"collection_date": "1/7/18"
}
]
}
]
任何建议将不胜感激。