-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathhal_getResults.py
142 lines (121 loc) · 5.9 KB
/
hal_getResults.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
import pymongo
# Connect to MongoDB server
server = pymongo.MongoClient("mongodb://localhost:27017/")
db = server['hal']
col = db['docType']
col.drop()
col = db['primaryDomain']
col.drop()
col = db['publicationDateY']
col.drop()
col = db['documents']
count_fulfill = 403627
# { $and: [{"fr_abstract_s": {"$exists": true}}, {"fr_keyword_s": {"$exists": true}}]}
domains = []
types = []
yearlies = []
cursor = col.find({"$and": [{"fr_match": {"$exists": True}}]}, no_cursor_timeout=True).batch_size(100)
for document in cursor:
count_80 = 0
count_60 = 0
if document['fr_match']['raw_match'] > 0.8:
count_80 = 1
if document['fr_match']['raw_match'] > 0.6:
count_60 = 1
# Update domain's statistics
domain_informed = False
for domain in domains:
if domain['primaryDomain'] == document['primaryDomain_s']:
domain_informed = True
domain['count'] += 1
domain['raw_match_80'] += count_80
domain['raw_match_60'] += count_60
domain['raw_match'] += document['fr_match']['raw_match']
domain['wordnet_similarity'] += document['fr_match']['wordnet_similarity']
domain['avg_keywords_unknown'] += document['fr_match']['avg_keywords_unknown']
domain['avg_words_unknown'] += document['fr_match']['avg_words_unknown']
if not domain_informed:
domains.append({'primaryDomain': document['primaryDomain_s'],
'count': 1,
'raw_match': document['fr_match']['raw_match'],
'raw_match_80': count_80,
'raw_match_60': count_60,
'wordnet_similarity': document['fr_match']['wordnet_similarity'],
'avg_keywords_unknown': document['fr_match']['avg_keywords_unknown'],
'avg_words_unknown': document['fr_match']['avg_words_unknown']
})
# Update type's statistics
type_informed = False
for type in types:
if type['docType'] == document['docType_s']:
type_informed = True
type['count'] += 1
type['raw_match_80'] += count_80
type['raw_match_60'] += count_60
type['raw_match'] += document['fr_match']['raw_match']
type['wordnet_similarity'] += document['fr_match']['wordnet_similarity']
type['avg_keywords_unknown'] += document['fr_match']['avg_keywords_unknown']
type['avg_words_unknown'] += document['fr_match']['avg_words_unknown']
if not type_informed:
types.append({'docType': document['docType_s'],
'count': 1,
'raw_match': document['fr_match']['raw_match'],
'raw_match_80': count_80,
'raw_match_60': count_60,
'wordnet_similarity': document['fr_match']['wordnet_similarity'],
'avg_keywords_unknown': document['fr_match']['avg_keywords_unknown'],
'avg_words_unknown': document['fr_match']['avg_words_unknown']
})
# Update type's statistics
yearly_informed = False
for yearly in yearlies:
if yearly['publicationDateY'] == document['publicationDateY_i']:
yearly_informed = True
yearly['count'] += 1
yearly['raw_match_80'] += count_80
yearly['raw_match_60'] += count_60
yearly['raw_match'] += document['fr_match']['raw_match']
yearly['wordnet_similarity'] += document['fr_match']['wordnet_similarity']
yearly['avg_keywords_unknown'] += document['fr_match']['avg_keywords_unknown']
yearly['avg_words_unknown'] += document['fr_match']['avg_words_unknown']
if not yearly_informed:
yearlies.append({'publicationDateY': document['publicationDateY_i'],
'count': 1,
'raw_match': document['fr_match']['raw_match'],
'raw_match_80': count_80,
'raw_match_60': count_60,
'wordnet_similarity': document['fr_match']['wordnet_similarity'],
'avg_keywords_unknown': document['fr_match']['avg_keywords_unknown'],
'avg_words_unknown': document['fr_match']['avg_words_unknown']
})
cursor.close()
for domain in domains:
domain['lang'] = 'fr'
domain['raw_match'] = domain['raw_match'] / domain['count']
domain['wordnet_similarity'] = domain['wordnet_similarity'] / domain['count']
domain['avg_keywords_unknown'] = domain['avg_keywords_unknown'] / domain['count']
domain['avg_words_unknown'] = domain['avg_words_unknown'] / domain['count']
domain['raw_match_80'] = domain['raw_match_80'] / domain['count']
domain['raw_match_60'] = domain['raw_match_60'] / domain['count']
col = db['primaryDomain']
col.insert_one(domain)
for type in types:
type['lang'] = 'fr'
type['raw_match'] = type['raw_match'] / type['count']
type['wordnet_similarity'] = type['wordnet_similarity'] / type['count']
type['avg_keywords_unknown'] = type['avg_keywords_unknown'] / type['count']
type['avg_words_unknown'] = type['avg_words_unknown'] / type['count']
type['raw_match_80'] = type['raw_match_80'] / type['count']
type['raw_match_60'] = type['raw_match_60'] / type['count']
col = db['docType']
col.insert_one(type)
for yearly in yearlies:
yearly['lang'] = 'fr'
yearly['raw_match'] = yearly['raw_match'] / yearly['count']
yearly['wordnet_similarity'] = yearly['wordnet_similarity'] / yearly['count']
yearly['avg_keywords_unknown'] = yearly['avg_keywords_unknown'] / yearly['count']
yearly['avg_words_unknown'] = yearly['avg_words_unknown'] / yearly['count']
yearly['raw_match_80'] = yearly['raw_match_80'] / yearly['count']
yearly['raw_match_60'] = yearly['raw_match_60'] / yearly['count']
col = db['publicationDateY']
col.insert_one(yearly)