dupehell 0.6.0

Synthetic multi-domain dataset generator for record linkage benchmarking
Documentation
1
2
3
4
5
6
7
8
{
  "en": ["10001","90001","60601","77001","85001","19101","78201","92101","75201","73301","33101","98101","80201","37201","46201","43201","28201","73001","94102","20001","02201","89101","97201","38101","40201","21201","53201","87101","85701","93701","10002","10003","10004","10005","10006","10007","10008","10009","10010","10011","10012","10013","10014","10015","10016","10017","10018","10019","10020","10021","10022","10023","10024","10025","10026","10027","10028","10029","10030","10031","10032","10033","10034","10035","10036","10037","10038","10039","10040","10044","10128","10280","11201","11203","11204","11205","11206","11207","11208","11209","11210","11211","11212","11213","11214","11215","11216","11217","11218","11219","11220","11221","11222","11223","11224","11225","11226","11228","11229","11230","11231","11232","11233","11234","11235","11236","11237","11238","11239","94101"],
  "fr": ["75001","75002","75003","75004","75005","75006","75007","75008","75009","75010","75011","75012","75013","75014","75015","75016","75017","75018","75019","75020","13001","13002","13003","13004","13005","13006","13007","13008","13009","13010","13011","13012","13013","13014","13015","13016","69001","69002","69003","69004","69005","69006","69007","69008","69009","31000","31100","31200","31300","31400","31500","44000","44100","44200","44300","33000","33100","33200","33300","33400","33500","59000","59100","59200","59300","59400","59500","59600","59700","59800","59900","06000","06100","06200","06300","06400","20000","20100","20200","20300","20400","67000","67100","67200","67300","67400","67500","80000","80100","80200","80300","80400","80500","38100","38200","38300","38400","38500","14000","14100","14200","14300","14400","34000","34100","34200","34300","34400","34900","34920"],
  "de": ["10115","10117","10119","10178","10179","10243","10245","10247","10249","10315","10317","10318","10319","10365","10367","10369","10405","10407","10409","10435","10437","10439","10551","10553","10555","10557","10559","10623","10625","10627","10629","10707","10709","10711","10713","10715","10717","10719","10777","10779","10781","10783","10785","10787","10789","10823","10825","10827","10829","10961","10963","10965","10967","10969","10997","10999","20095","20097","20099","20144","20146","20148","20149","20249","20251","20253","20255","20257","20259","20354","20355","20357","20359","20457","20459","20535","20537","20539","21029","21031","21033","21035","21037","21039","21107","21109","21129","21147","21149","22081","22083","22085","22087","22089","22111","22113","22115","22117","22119","22143","22145","22147","22149","22159","22175","22177","22179","22301","22303","22305","22307","22309","22335","22337","22339","22359","22391","22393","22395","22397","22399","22415","22417","22419","22453","22455","22457","22459","22523","22525","22527","22529","22547","22549","22559","22587","22589","22605","22607","22609","22761","22763","22765","22767","22769"],
  "es": ["28001","28002","28003","28004","28005","28006","28007","28008","28009","28010","28011","28012","28013","28014","28015","28016","28017","28018","28019","28020","28021","28022","28023","28024","28025","28026","28027","28028","28029","28030","28031","28032","28033","28034","28035","28036","28037","28038","28039","28040","28041","28042","28043","28044","28045","28046","28047","28048","28049","28050","08001","08002","08003","08004","08005","08006","08007","08008","08009","08010","08011","08012","08013","08014","08015","08016","08017","08018","08019","08020","08021","08022","08023","08024","08025","08026","08027","08028","08029","08030","08031","08032","08033","08034","08035","08036","08037","08038","08039","08040","08041","08042","08043","41001","41002","41003","41004","41005","41006","41007","41008","41009","41010","41011","41012","41013","41014","41015","41016","41017","41018","41019","41020","46001","46002","46003","46004","46005","46006","46007","46008","46009","46010","46011","46012","46013","46014","46015","46016","46017","46018","46019","46020","46021","46022","46023","46024","46025","46026","50001","50002","50003","50004","50005","50006","50007","50008","50009","50010","50011","50012","50013","50014","50015","50016","50017","50018","50019","50020"],
  "it": ["00100","00118","00119","00120","00121","00122","00123","00124","00125","00126","00127","00128","00131","00132","00133","00134","00135","00136","00137","00138","00139","00141","00142","00143","00144","00145","00146","00147","00148","00149","00151","00152","00153","00154","00155","00156","00157","00158","00159","00161","00162","00163","00164","00165","00166","00167","00168","00169","00171","00172","00173","00174","00175","00176","00177","00178","00179","00181","00182","00183","00184","00185","00186","00187","00188","00189","00191","00192","00193","00195","00196","00197","00198","00199","20121","20122","20123","20124","20125","20126","20127","20128","20129","20131","20132","20133","20134","20135","20136","20137","20138","20139","20141","20142","20143","20144","20145","20146","20147","20148","20149","20151","20152","20153","20154","20155","20156","20157","20158","20159","20161","20162","20163","20164","20166","20167","20168","20169","20171","20172","20173","20174","20175","20176","20177","20178","20179","20181","20182","20183","20184","20185","20186","20187","20188","20189","20191","20192","20193","20194","20195","20196","20197","20198","20199"],
  "pt": ["01000-000","01001-000","01002-000","01003-000","01004-000","01005-000","01006-000","01007-000","01008-000","01009-000","01010-000","01011-000","01012-000","01013-000","01014-000","01015-000","01016-000","01017-000","01018-000","01019-000","01020-000","01300-000","01301-000","01302-000","01303-000","01304-000","01305-000","01306-000","01307-000","01308-000","01309-000","01310-000","01311-000","01312-000","01313-000","01314-000","01315-000","01316-000","01317-000","01318-000","01319-000","01320-000","01321-000","01322-000","01323-000","01324-000","01325-000","01326-000","01327-000","01328-000","01329-000","01330-000","01331-000","01332-000","01500-000","01501-000","01502-000","01503-000","01504-000","01505-000","01506-000","01507-000","01508-000","01509-000","01510-000","02000-000","02001-000","02002-000","02003-000","02004-000","02005-000","02006-000","02007-000","02008-000","02009-000","02010-000","02011-000","02012-000","02013-000","02014-000","02015-000","02016-000","02017-000","02018-000","02019-000","02020-000","02500-000","02501-000","02502-000","02503-000","02504-000","02505-000","02506-000","02507-000","02508-000","02509-000","02510-000","02511-000","02512-000","02513-000","02514-000","02515-000","02516-000","02517-000","02518-000","02519-000","02520-000","03000-000","03001-000","03002-000","03003-000","03004-000","03005-000","03006-000","03007-000","03008-000","03009-000","03010-000","03011-000","03012-000","03013-000","03014-000","03015-000","03016-000","03017-000","03018-000","03019-000","03020-000","03500-000","04000-000","04001-000","04002-000","04003-000","04004-000","04005-000","04006-000","04007-000","04008-000","04009-000","04010-000","04011-000","04012-000","04013-000","04014-000","04015-000","04016-000","04017-000","04018-000","04019-000","04020-000"]
}