Input
The InputTable has 341 distinct users and the identifiers of the items they purchased in an office supplies store.
| userid | itemid |
|---|---|
| 1 | 1 |
| 2 | 2 3 |
| 3 | 4 |
| 4 | 2 |
| 5 | 3 1 |
| 6 | 1 |
| 7 | 5 |
| 8 | 5 6 |
| 9 | 2 1 |
| 10 | 3 |
| 11 | 8 |
| 12 | 10 |
| 13 | 11 4 |
| ... | ... |
| itemid | Items |
|---|---|
| 1 | Storage |
| 2 | Appliances |
| 3 | Binders |
| 4 | Telephones |
| 5 | Paper |
| 6 | Rubber Bands |
| 7 | Computer Peripherals |
| 8 | Office Furnishings |
| 9 | Office Machines |
| 10 | Envelopes |
| 11 | Bookcases |
| 12 | Tables |
| 13 | Pens & Art Supplies |
| 14 | Chairs & Chairmats |
| 15 | Scissors |
| 16 | Rulers & Trimmers |
| 17 | Copiers & Fax Storage |
| 18 | Labels |
SQL Call
SELECT * FROM MinHash (
ON salesdata AS InputTable
OUT TABLE OutputTable (minhashoutput)
USING
UserIdColumn ('userid')
ItemIdColumn ('itemid')
HashNum (1002)
KeyGroups (3)
InputFormat ('integer')
MinClusterSize (3)
MaxClusterSize (5)
) AS dt ;
Output
message ------------------------------------------------------------------------- Result has been stored in the table specified in the argument OutputTable
SELECT clusterid, CAST(userid AS varchar(50)) FROM minhashoutput ORDER BY clusterid;
clusterid userid ----------------------------- -------------------- 10001632024477502928557112 115 143 33 1000181818172837758261472850 188 19 82 1000672928162506536467975178 172 201 8 1000672928162506536745194009 154 200 219 227 1000888321111525381245325420 231 278 279 292 43 10011398202195032931017789807 336 64 73 100200255478713962251455059 116 16 255 100200255691628539183060642 155 193 331 61 1002732123681872942919652130 142 153 22 229 273 100330557752858893780017760 106 65 94 10049170655836044391306314718 234 306 341 101328785814130588977849993 162 41 76 1015945565890613405523781488 155 193 331 10162828715827479001108091687 298 300 75 10175358509427418841426707515 154 219 227 1018466901986895211628049263 281 299 335 83 10220852810629588885324013 116 126 162 264 10220852817106841885324013 106 41 76 10226181701140395735173738032 115 159 199 10226181701254897345173738032 101 168 85 1022618170911392515173738032 165 210 229 102470444162678584793019606 142 153 22 273 102573341535757391533154664 116 126 264 102582206635867650161809733 162 234 306 341 56 102623915513963258275858860 15 154 200 219 227 1026873304546698627309800948 105 336 64 73 10293886931561094382367763 106 162 41 76 102938869926494095286052740 234 236 306 341 10313304113308841641346899945 15 154 219 227 1032014682918918621081479027 289 336 64 73 1034189323961653552588687202 116 16 162 255 103496462682875859105446942 131 319 329 103496462935523058105446942 101 115 168 85 103515721179174677712162623 154 200 219 227 277 1038787405450816405695980004 101 165 168 85 1047626411340449545590476206 220 336 64 73 105052222736915977534827861 334 49 99 1051524537188532351351736 162 234 306 341 1057328301636481327290076924 145 336 64 73 1062215657510129744623106336 159 199 329 1063074461401270656411541334 233 336 64 73 10681161985692751835793351 202 303 94 107352482206748926533638949 324 56 89 1077178555125838598220450673 142 153 213 22 273 108438676963330722908898142 323 336 64 73 1087091491051791057376376151 188 19 218 82 109565221148920194151646465 115 159 199 229 329 1104425083111007915632360455 137 324 33 11055405515522574861231316557 220 323 336 64 73 111384661784027554142923817 234 306 341 56 111878725277983383626020309 115 159 199 229 112000660881277414161330932 159 199 229 329 1135787282425554248855512 122 184 265 1135787282425554263955699 200 277 56 11364216137098692168568745 101 115 165 168 85 1163182571989967097544757011 105 233 336 64 73 118532648453415513812155324 162 334 99 1189747526909957268830076 329 56 98 12825749399292881511221643896 105 220 336 64 73 1303860321293646116676660877 154 219 227 303 130386032436060809270744284 172 201 56 8 13374366813446055233013996 162 334 49 99 141470682104264009341272583 159 199 229 143046875878802443317379604 215 23 33 155750144284072563472764756 115 159 199 329 16820489119808089544814447 162 234 236 306 341 213210460572199928292570925 105 323 336 64 73 2307301181223266695850700 234 236 306 341 56 23086115553832635553266216 145 323 336 64 73 246998243209606930167297798 116 162 165 3763388498647598191062219618 233 289 336 64 73 416520801194525772520154227 15 154 219 227 303 5010953953499458161174109310 145 233 336 64 73 503532392896216635761870770 289 323 336 64 73 607403481884103145578369013 220 233 336 64 73 68523913398609725423998883 220 289 336 64 73 7474160351045857577413872845 145 220 336 64 73
Download a zip file of all examples and a SQL script file that creates their input tables.