Easy Peasy: It's Lemon Squeezy

Predict Workers Compensation claims using highly realistic synthetic data

@kaggle.lucamassaron_easy_peasy_its_lemon_squeezy

Table List

1 table(5.59 MB)

Data

@kaggle.lucamassaron_easy_peasy_its_lemon_squeezy.data

5.59 MB
54000 rows
26 columns

claimnumber ClaimNumber	datetimeofaccident DateTimeOfAccident	datereported DateReported	age Age	gender Gender	maritalstatus MaritalStatus	weeklywages WeeklyWages	parttimefulltime PartTimeFullTime	hoursworkedperweek HoursWorkedPerWeek	daysworkedperweek DaysWorkedPerWeek	claimdescriptionkeyword_0 ClaimDescriptionKeyword 0	claimdescriptionkeyword_1 ClaimDescriptionKeyword 1	claimdescriptionkeyword_2 ClaimDescriptionKeyword 2	claimdescriptionkeyword_3 ClaimDescriptionKeyword 3	claimdescriptionkeyword_4 ClaimDescriptionKeyword 4	claimdescriptionkeyword_5 ClaimDescriptionKeyword 5	claimdescriptionkeyword_6 ClaimDescriptionKeyword 6	claimdescriptionkeyword_7 ClaimDescriptionKeyword 7	claimdescriptionkeyword_8 ClaimDescriptionKeyword 8	claimdescriptionkeyword_9 ClaimDescriptionKeyword 9	claimdescriptionkeyword_10 ClaimDescriptionKeyword 10	claimdescriptionkeyword_11 ClaimDescriptionKeyword 11	initialincurredclaimscost InitialIncurredClaimsCost	ultimateincurredclaimcost UltimateIncurredClaimCost
WC8285054	2002-04-09T07:00:00Z	2002-07-05T00:00:00Z	48	M	M	500	F	38	5	2.254325483605694	-1.4660845711805583	-1.2781553782887105	-0.4221645616329368	-0.1370392145909606	1.6342394894955776	-1.43609647078137	-0.7578707207132609	-1.0919204117683274	0.8807670549328954	0.168496724552454	1.1612938171115206	1500	4748.203388
WC6982224	1999-01-07T11:00:00Z	1999-01-20T00:00:00Z	43	F	M	509.34	F	37.5	5	2.3560017146958625	-1.259902902630351	1.4904096266919715	-0.8184667314945583	1.7889939237624428	0.4594817313203485	0.662757245047338	-0.2404995468185485	-0.1624510502957691	0.6652419144322136	0.8440194530806153	-1.3053320669881077	5500	6326.285819
WC5481426	1996-03-25T00:00:00Z	1996-04-14T00:00:00Z	30	M	U	709.1	F	38	5	0.817684960568234	-1.0881152272330403	1.5203397364079512	-0.2330312432851614	-0.0457123736977016	-0.1927422806467619	-0.0478810054746615	0.1390513039017301	-0.3395511200819218	-0.3864204284259112	-0.3979188662419994	-0.2597503569896752	1700	2293.949087
WC9775968	2005-06-22T13:00:00Z	2005-07-22T00:00:00Z	41	M	S	555.46	F	38	5	4.022863658720778	3.184172176127525	-0.0146035047271487	1.2193557017608576	0.0670528421838686	1.1054707978245508	0.6094616495230749	1.495271897840282	-0.5272573123408812	-0.1872086152217335	-0.8570312269208111	-0.3435942917994566	15000	17786.48717
WC2634037	1990-08-29T08:00:00Z	1990-09-27T00:00:00Z	36	M	M	377.1	F	38	5	3.3830556215647323	0.0099408306863548	1.691871294508091	-1.3903782443396135	-0.6474806108865128	-1.413972952069804	-0.8073691621055312	0.2431388340734831	1.0312369446038567	0.3661831018728455	0.4279453169447682	-0.0382338158167201	2800	4014.002925
WC6828422	1999-06-21T11:00:00Z	1999-09-09T00:00:00Z	50	M	M	200	F	38	5	1.1339062932147386	-0.4764693173574716	0.341174822793166	1.5515291027288023	0.6387350245334242	-0.9975115639605152	1.5724722277239809	-0.7345398646654924	0.0263545510892183	0.8653365357097212	0.4998197061988965	0.2615444043718233	500	598.7623150000001
WC8058150	2001-07-13T11:00:00Z	2001-07-23T00:00:00Z	39	M	M	200	F	38	5	1.7752472149841008	-1.5506511257146274	1.4530797273786	-0.0970942604690901	0.5763163564072417	0.7746611819501898	-1.0210661810298105	0.5771679970200185	0.2329066728930005	-0.4810769191861159	0.4337960078619867	-0.7353754189187516	500	279.0681777
WC7539849	2000-03-09T09:00:00Z	2000-04-16T00:00:00Z	56	M	M	200	F	40	5	2.7442553477366287	-1.929975800951532	2.9001414955548657	-0.99202575070756	-0.0623838720000032	0.3332269570549725	-1.5332174119673831	1.1289239131059716	1.151812832910933	1.0511624920259757	-0.8393227642922749	-0.4608034260572816	500	1877.172243
WC4427179	1994-03-24T16:00:00Z	1994-04-26T00:00:00Z	49	M	M	623.6	F	38	5	3.0691263291451563	-1.3007930285609948	1.6760715397751904	1.8424263514804025	-1.603341290365433	0.6151955465609366	-1.9516483813859116	0.9135729386348794	0.4706934025993957	-1.4013076254476688	1.3651765743272553	-0.3571158384133325	925	1254.129811
WC9907636	2005-12-07T11:00:00Z	2005-12-22T00:00:00Z	30	M	S	857.28	F	37	5	1.666143069695633	-1.0279491702954977	1.6011954764467553	-0.2781502426873143	-0.1559595773331502	-0.2362668244343946	1.7418565705223037	-0.2827326964013714	-0.1511937651082369	0.516168984143606	0.2295390480555217	0.2754019188668563	1500	1031.603044


CREATE TABLE data (
  "claimnumber" VARCHAR,
  "datetimeofaccident" VARCHAR,
  "datereported" VARCHAR,
  "age" BIGINT,
  "gender" VARCHAR,
  "maritalstatus" VARCHAR,
  "dependentchildren" BIGINT,
  "dependentsother" BIGINT,
  "weeklywages" DOUBLE,
  "parttimefulltime" VARCHAR,
  "hoursworkedperweek" DOUBLE,
  "daysworkedperweek" BIGINT,
  "claimdescriptionkeyword_0" DOUBLE,
  "claimdescriptionkeyword_1" DOUBLE,
  "claimdescriptionkeyword_2" DOUBLE,
  "claimdescriptionkeyword_3" DOUBLE,
  "claimdescriptionkeyword_4" DOUBLE,
  "claimdescriptionkeyword_5" DOUBLE,
  "claimdescriptionkeyword_6" DOUBLE,
  "claimdescriptionkeyword_7" DOUBLE,
  "claimdescriptionkeyword_8" DOUBLE,
  "claimdescriptionkeyword_9" DOUBLE,
  "claimdescriptionkeyword_10" DOUBLE,
  "claimdescriptionkeyword_11" DOUBLE,
  "initialincurredclaimscost" BIGINT,
  "ultimateincurredclaimcost" DOUBLE
);