-
Notifications
You must be signed in to change notification settings - Fork 0
/
query_elastic_all_details.py
156 lines (127 loc) · 4.84 KB
/
query_elastic_all_details.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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
#!/usr/bin/env python3
#-*- coding: utf-8 -*-
import json
# import Python's JSON library for its loads() method
import json, requests
# import time for its sleep method
from time import sleep
# import the datetime libraries datetime.now() method
from datetime import datetime
import sys
# use the Elasticsearch client's helpers class for _bulk API
from elasticsearch import Elasticsearch, helpers
# declare a client instance of the Python Elasticsearch library
client = Elasticsearch("localhost:9200")
out = dict()
out_verbose = dict()
total_ids = 100
score_over_90 = 0
html = "<head><style>span {color: red;} em {font-style: normal; color: black;}</style></head><body>"
with open('local-app/spud_bjorn.json') as f:
data = json.load(f)
# iterate over all ES ids
for idx in range (0,len(data)):
id = int(data[idx]['Reference ID (ID)'])
found = False
# construct query
search_param = {
# "_source": ["title","abstract","doi","year"],
"query": {
"more_like_this": {
"fields": [ "title", "abstract", "year"],
"like": [
{
"_index": "some_index",
"_id": str(id)
}
]
}
}
}
# run query
response = client.search(index="some_index", body=search_param)
# desconstruct response
took = response["took"]
max_score = response["hits"]["max_score"]
hits_no = response["hits"]["total"]["value"]
hits = response["hits"]["hits"]
temp = []
orig_record = client.search(index="some_index", body={"query": { "ids" : { "values" : [str(id)] } } })
temp.append(orig_record)
orig_title = orig_record["hits"]["hits"][0]["_source"]["title"]
orig_year = orig_record["hits"]["hits"][0]["_source"]["year"]
orig_abstract = orig_record["hits"]["hits"][0]["_source"]["abstract"]
for hit in hits:
# save score
score = hit["_score"]
# temp.append(score)
year = hit["_source"]["year"]
sim_id = hit["_id"]
sim_score = hit["_score"]
# save title
# title = hit["_source"]["title"]
if score > 90 and found == False:
found = True
score_over_90 += 1
# out_verbose[id] = hit
# title highlighting
temp_search_param = {
"_source": ["title"],
"query": {
"match": {
"title": orig_title
}
},
"highlight": {
"fields": {
"title": {"number_of_fragments" : 0}
}
}
}
highlight_response = client.search(index="some_index", body=temp_search_param)
highlighted = highlight_response["hits"]["hits"][1]["highlight"]["title"][0]
html += "<div>ORIGINAL ID: " + str(id) + ", SIMILAR TO ID: " + str(sim_id) + ", SCORE: " + str(sim_score) + "</div></br>"
html += "<div>" + orig_title + "</div><br/><span>" + highlighted + "</span><br/>"
# year highlighting
# year = highlight_response["hits"]["hits"][1]["_source"]["year"]
html += "<br/><div>" + orig_year + "</div><br/>"
if int(orig_year) != int(year):
html += "<span>" + orig_year + "</span><br/>"
else:
html += "<span><em>" + year + "</em></span><br/>"
# abstract highlighting
temp_search_param = {
"_source": ["title"],
"query": {
"match": {
"abstract": orig_abstract
}
},
"highlight": {
"fields": {
"abstract": {"number_of_fragments" : 0}
}
}
}
try:
highlight_response = client.search(index="some_index", body=temp_search_param)
highlighted = highlight_response["hits"]["hits"][1]["highlight"]["abstract"][0]
# print(highlighted)
html += "<br/><br/><div>" + orig_abstract + "</div><br/><span>" + highlighted + "</span><br/><br/>"
except:
print("Hmm smth wrong with ids: " + str(id) + " vs " + str(sim_id) )
html += "<hr>"
# print(orig_title)
# print(html)
# print()
# temp.append(test)
# if score > 50:
# score_over_50 += 1
# out_verbose[id] = temp
# print(temp)
# print("\nSaving ES responses to file: over_90s_"+str(total_ids)+".json")
# with open('over_90s_'+str(total_ids)+'.json', 'w') as outfile:
# json.dump(out_verbose, outfile)
html += "</body>"
with open('test_'+str(total_ids)+'.html','w') as outfile:
outfile.write(html)