- Timestamp:
- 2019-12-18T21:38:44+13:00 (4 years ago)
- File:
-
- 1 moved
Legend:
- Unmodified
- Added
- Removed
-
other-projects/maori-lang-detection/mongodb-data/counts_allCrawledSites.json
r33811 r33813 1 /* 2 Num websites: 3 db.getCollection('Websites').find({}).count() 4 = 1445 5 6 Num webpages 7 db.getCollection('Webpages').find({}).count() 8 = 117496 9 10 Count of country codes for all sites: 11 db.Websites.aggregate([ 12 13 { $unwind: "$geoLocationCountryCode" }, 14 { 15 $group: { 16 _id: "$geoLocationCountryCode", 17 count: { $sum: 1 } 18 } 19 }, 20 { $sort : { count : -1} } 21 ]); 22 */ 23 1 24 /* 1 */ 2 25 { 3 26 "_id" : "US", 4 "count" : 6 86.027 "count" : 696.0 5 28 } 6 29 … … 8 31 { 9 32 "_id" : "UNKNOWN", 10 "count" : 17 1.033 "count" : 173.0 11 34 } 12 35 13 36 /* 3 */ 14 37 { 38 "_id" : "CN", 39 "count" : 125.0 40 } 41 42 /* 4 */ 43 { 15 44 "_id" : "NZ", 16 "count" : 128.0 17 } 18 19 /* 4 */ 20 { 21 "_id" : "CN", 22 "count" : 124.0 45 "count" : 115.0 23 46 } 24 47 … … 44 67 { 45 68 "_id" : "NL", 46 "count" : 3 1.069 "count" : 32.0 47 70 } 48 71 … … 50 73 { 51 74 "_id" : "CA", 52 "count" : 21.075 "count" : 19.0 53 76 } 54 77 … … 61 84 /* 11 */ 62 85 { 86 "_id" : "DK", 87 "count" : 10.0 88 } 89 90 /* 12 */ 91 { 63 92 "_id" : "JP", 64 93 "count" : 10.0 65 94 } 66 95 67 /* 12 */68 {69 "_id" : "DK",70 "count" : 10.071 }72 73 96 /* 13 */ 74 97 { … … 79 102 /* 14 */ 80 103 { 104 "_id" : "RU", 105 "count" : 7.0 106 } 107 108 /* 15 */ 109 { 110 "_id" : "HK", 111 "count" : 7.0 112 } 113 114 /* 16 */ 115 { 81 116 "_id" : "CZ", 82 117 "count" : 7.0 83 118 } 84 119 85 /* 15 */86 {87 "_id" : "RU",88 "count" : 7.089 }90 91 /* 16 */92 {93 "_id" : "HK",94 "count" : 7.095 }96 97 120 /* 17 */ 98 {99 "_id" : "IT",100 "count" : 5.0101 }102 103 /* 18 */104 {105 "_id" : "SE",106 "count" : 5.0107 }108 109 /* 19 */110 121 { 111 122 "_id" : "UA", … … 113 124 } 114 125 115 /* 20*/126 /* 18 */ 116 127 { 117 128 "_id" : "IE", … … 119 130 } 120 131 132 /* 19 */ 133 { 134 "_id" : "SE", 135 "count" : 4.0 136 } 137 138 /* 20 */ 139 { 140 "_id" : "IT", 141 "count" : 4.0 142 } 143 121 144 /* 21 */ 122 145 { 146 "_id" : "RO", 147 "count" : 3.0 148 } 149 150 /* 22 */ 151 { 152 "_id" : "SG", 153 "count" : 3.0 154 } 155 156 /* 23 */ 157 { 158 "_id" : "AT", 159 "count" : 3.0 160 } 161 162 /* 24 */ 163 { 164 "_id" : "CH", 165 "count" : 3.0 166 } 167 168 /* 25 */ 169 { 170 "_id" : "IL", 171 "count" : 3.0 172 } 173 174 /* 26 */ 175 { 123 176 "_id" : "IN", 124 177 "count" : 3.0 125 178 } 126 179 127 /* 22 */ 128 { 129 "_id" : "CH", 130 "count" : 3.0 131 } 132 133 /* 23 */ 134 { 135 "_id" : "IL", 136 "count" : 3.0 137 } 138 139 /* 24 */ 140 { 141 "_id" : "AT", 142 "count" : 3.0 143 } 144 145 /* 25 */ 146 { 147 "_id" : "RO", 148 "count" : 2.0 149 } 150 151 /* 26 */ 180 /* 27 */ 181 { 182 "_id" : "PL", 183 "count" : 2.0 184 } 185 186 /* 28 */ 187 { 188 "_id" : "ZA", 189 "count" : 2.0 190 } 191 192 /* 29 */ 193 { 194 "_id" : "VG", 195 "count" : 2.0 196 } 197 198 /* 30 */ 152 199 { 153 200 "_id" : "CK", … … 155 202 } 156 203 157 /* 27*/158 { 159 "_id" : " VG",160 "count" : 2.0161 } 162 163 /* 28*/164 { 165 "_id" : " ZA",166 "count" : 2.0167 } 168 169 /* 29*/170 { 171 "_id" : " PL",172 "count" : 2.0173 } 174 175 /* 3 0*/204 /* 31 */ 205 { 206 "_id" : "BG", 207 "count" : 1.0 208 } 209 210 /* 32 */ 211 { 212 "_id" : "PF", 213 "count" : 1.0 214 } 215 216 /* 33 */ 217 { 218 "_id" : "IO", 219 "count" : 1.0 220 } 221 222 /* 34 */ 176 223 { 177 224 "_id" : "GR", … … 179 226 } 180 227 181 /* 31 */ 228 /* 35 */ 229 { 230 "_id" : "MX", 231 "count" : 1.0 232 } 233 234 /* 36 */ 235 { 236 "_id" : "TR", 237 "count" : 1.0 238 } 239 240 /* 37 */ 241 { 242 "_id" : "ME", 243 "count" : 1.0 244 } 245 246 /* 38 */ 182 247 { 183 248 "_id" : "FI", … … 185 250 } 186 251 187 /* 32 */ 188 { 189 "_id" : "ME", 190 "count" : 1.0 191 } 192 193 /* 33 */ 252 /* 39 */ 253 { 254 "_id" : "EU", 255 "count" : 1.0 256 } 257 258 /* 40 */ 259 { 260 "_id" : "IR", 261 "count" : 1.0 262 } 263 264 /* 41 */ 194 265 { 195 266 "_id" : "PT", 196 267 "count" : 1.0 197 268 } 198 199 /* 34 */200 {201 "_id" : "IR",202 "count" : 1.0203 }204 205 /* 35 */206 {207 "_id" : "EU",208 "count" : 1.0209 }210 211 /* 36 */212 {213 "_id" : "TR",214 "count" : 1.0215 }216 217 /* 37 */218 {219 "_id" : "MX",220 "count" : 1.0221 }222 223 /* 38 */224 {225 "_id" : "IO",226 "count" : 1.0227 }228 229 /* 39 */230 {231 "_id" : "PF",232 "count" : 1.0233 }234 235 /* 40 */236 {237 "_id" : "BG",238 "count" : 1.0239 }240 241 /* 41 */242 {243 "_id" : "SG",244 "count" : 1.0245 }
Note:
See TracChangeset
for help on using the changeset viewer.