Last change
on this file since 33823 was 33823, checked in by ak19, 4 years ago |
Recommitting mongo-data folder with renamed files with numbering.
|
File size:
2.3 KB
|
Line | |
---|
1 | /*
|
---|
2 | Number of sites containing at least one sentence for which OpenNLP detected the best language = MRI
|
---|
3 |
|
---|
4 | db.getCollection('Websites').find({numPagesContainingMRI: {$gt: 0}}).count()
|
---|
5 | 868
|
---|
6 |
|
---|
7 |
|
---|
8 | Obviously, the following should be equal to that:
|
---|
9 |
|
---|
10 | db.getCollection('Websites').find({ $or: [ { numPagesInMRI: { $gt: 0 } }, { numPagesContainingMRI: {$gt: 0} } ] } ).count()
|
---|
11 | 868
|
---|
12 |
|
---|
13 |
|
---|
14 | Count of country codes for sites that have at least one page containing at least one sentence detected as MRI by OpenNLP:
|
---|
15 |
|
---|
16 | db.Websites.aggregate([
|
---|
17 | {
|
---|
18 | $match: {
|
---|
19 | numPagesContainingMRI: {$gt: 0}
|
---|
20 | }
|
---|
21 | },
|
---|
22 | { $unwind: "$geoLocationCountryCode" },
|
---|
23 | {
|
---|
24 | $group: {
|
---|
25 | _id: {$toLower: '$geoLocationCountryCode'},
|
---|
26 | count: { $sum: 1 }
|
---|
27 | }
|
---|
28 | },
|
---|
29 | { $sort : { count : -1} }
|
---|
30 | ]);
|
---|
31 |
|
---|
32 | */
|
---|
33 |
|
---|
34 | /* 1 */
|
---|
35 | {
|
---|
36 | "_id" : "us",
|
---|
37 | "count" : 486.0
|
---|
38 | }
|
---|
39 |
|
---|
40 | /* 2 */
|
---|
41 | {
|
---|
42 | "_id" : "cn",
|
---|
43 | "count" : 114.0
|
---|
44 | }
|
---|
45 |
|
---|
46 | /* 3 */
|
---|
47 | {
|
---|
48 | "_id" : "nz",
|
---|
49 | "count" : 89.0
|
---|
50 | }
|
---|
51 |
|
---|
52 | /* 4 */
|
---|
53 | {
|
---|
54 | "_id" : "fr",
|
---|
55 | "count" : 36.0
|
---|
56 | }
|
---|
57 |
|
---|
58 | /* 5 */
|
---|
59 | {
|
---|
60 | "_id" : "de",
|
---|
61 | "count" : 27.0
|
---|
62 | }
|
---|
63 |
|
---|
64 | /* 6 */
|
---|
65 | {
|
---|
66 | "_id" : "nl",
|
---|
67 | "count" : 22.0
|
---|
68 | }
|
---|
69 |
|
---|
70 | /* 7 */
|
---|
71 | {
|
---|
72 | "_id" : "au",
|
---|
73 | "count" : 21.0
|
---|
74 | }
|
---|
75 |
|
---|
76 | /* 8 */
|
---|
77 | {
|
---|
78 | "_id" : "ca",
|
---|
79 | "count" : 12.0
|
---|
80 | }
|
---|
81 |
|
---|
82 | /* 9 */
|
---|
83 | {
|
---|
84 | "_id" : "dk",
|
---|
85 | "count" : 8.0
|
---|
86 | }
|
---|
87 |
|
---|
88 | /* 10 */
|
---|
89 | {
|
---|
90 | "_id" : "es",
|
---|
91 | "count" : 7.0
|
---|
92 | }
|
---|
93 |
|
---|
94 | /* 11 */
|
---|
95 | {
|
---|
96 | "_id" : "gb",
|
---|
97 | "count" : 7.0
|
---|
98 | }
|
---|
99 |
|
---|
100 | /* 12 */
|
---|
101 | {
|
---|
102 | "_id" : "cz",
|
---|
103 | "count" : 4.0
|
---|
104 | }
|
---|
105 |
|
---|
106 | /* 13 */
|
---|
107 | {
|
---|
108 | "_id" : "unknown",
|
---|
109 | "count" : 3.0
|
---|
110 | }
|
---|
111 |
|
---|
112 | /* 14 */
|
---|
113 | {
|
---|
114 | "_id" : "at",
|
---|
115 | "count" : 3.0
|
---|
116 | }
|
---|
117 |
|
---|
118 | /* 15 */
|
---|
119 | {
|
---|
120 | "_id" : "ro",
|
---|
121 | "count" : 3.0
|
---|
122 | }
|
---|
123 |
|
---|
124 | /* 16 */
|
---|
125 | {
|
---|
126 | "_id" : "it",
|
---|
127 | "count" : 3.0
|
---|
128 | }
|
---|
129 |
|
---|
130 | /* 17 */
|
---|
131 | {
|
---|
132 | "_id" : "sg",
|
---|
133 | "count" : 2.0
|
---|
134 | }
|
---|
135 |
|
---|
136 | /* 18 */
|
---|
137 | {
|
---|
138 | "_id" : "jp",
|
---|
139 | "count" : 2.0
|
---|
140 | }
|
---|
141 |
|
---|
142 | /* 19 */
|
---|
143 | {
|
---|
144 | "_id" : "ie",
|
---|
145 | "count" : 2.0
|
---|
146 | }
|
---|
147 |
|
---|
148 | /* 20 */
|
---|
149 | {
|
---|
150 | "_id" : "hk",
|
---|
151 | "count" : 2.0
|
---|
152 | }
|
---|
153 |
|
---|
154 | /* 21 */
|
---|
155 | {
|
---|
156 | "_id" : "ua",
|
---|
157 | "count" : 2.0
|
---|
158 | }
|
---|
159 |
|
---|
160 | /* 22 */
|
---|
161 | {
|
---|
162 | "_id" : "ru",
|
---|
163 | "count" : 2.0
|
---|
164 | }
|
---|
165 |
|
---|
166 | /* 23 */
|
---|
167 | {
|
---|
168 | "_id" : "ch",
|
---|
169 | "count" : 2.0
|
---|
170 | }
|
---|
171 |
|
---|
172 | /* 24 */
|
---|
173 | {
|
---|
174 | "_id" : "il",
|
---|
175 | "count" : 2.0
|
---|
176 | }
|
---|
177 |
|
---|
178 | /* 25 */
|
---|
179 | {
|
---|
180 | "_id" : "tr",
|
---|
181 | "count" : 1.0
|
---|
182 | }
|
---|
183 |
|
---|
184 | /* 26 */
|
---|
185 | {
|
---|
186 | "_id" : "mx",
|
---|
187 | "count" : 1.0
|
---|
188 | }
|
---|
189 |
|
---|
190 | /* 27 */
|
---|
191 | {
|
---|
192 | "_id" : "ir",
|
---|
193 | "count" : 1.0
|
---|
194 | }
|
---|
195 |
|
---|
196 | /* 28 */
|
---|
197 | {
|
---|
198 | "_id" : "gr",
|
---|
199 | "count" : 1.0
|
---|
200 | }
|
---|
201 |
|
---|
202 | /* 29 */
|
---|
203 | {
|
---|
204 | "_id" : "bg",
|
---|
205 | "count" : 1.0
|
---|
206 | }
|
---|
207 |
|
---|
208 | /* 30 */
|
---|
209 | {
|
---|
210 | "_id" : "eu",
|
---|
211 | "count" : 1.0
|
---|
212 | }
|
---|
213 |
|
---|
214 | /* 31 */
|
---|
215 | {
|
---|
216 | "_id" : "fi",
|
---|
217 | "count" : 1.0
|
---|
218 | }
|
---|
Note:
See
TracBrowser
for help on using the repository browser.