In [1]:
df = spark.read.option("header", "true").csv("gs://w210/2012_2017/*")

In [3]:
df.count()


Out[3]:
19028469

In [4]:
df


Out[4]:
DataFrame[unique_transaction_id: string, dunsnumber: string, agencyid: string, principalnaicscode: string, productorservicecode: string, fundingrequestingagencyid: string, maj_agency_cat: string, contractingofficeid: string, contractingofficeagencyid: string]

In [5]:
counts = df.groupBy('dunsnumber').count().collect()

In [13]:
sorted(counts, key=lambda row: row[1], reverse= True)


Out[13]:
[Row(dunsnumber='007914906', count=821409),
 Row(dunsnumber='961027315', count=714991),
 Row(dunsnumber='123456787', count=379548),
 Row(dunsnumber='007941230', count=312875),
 Row(dunsnumber='148983229', count=227019),
 Row(dunsnumber='848028494', count=223589),
 Row(dunsnumber='116057019', count=181504),
 Row(dunsnumber='801423062', count=169432),
 Row(dunsnumber='105919864', count=126929),
 Row(dunsnumber='012430880', count=114706),
 Row(dunsnumber='944204924', count=112077),
 Row(dunsnumber='075553560', count=89849),
 Row(dunsnumber='027079776', count=88708),
 Row(dunsnumber='001672120', count=87827),
 Row(dunsnumber='864346320', count=77935),
 Row(dunsnumber='835551474', count=62979),
 Row(dunsnumber='932619265', count=57556),
 Row(dunsnumber='481347552', count=57527),
 Row(dunsnumber='177667227', count=57433),
 Row(dunsnumber='005778613', count=56558),
 Row(dunsnumber='883533879', count=54825),
 Row(dunsnumber='004321519', count=54111),
 Row(dunsnumber='785807611', count=48911),
 Row(dunsnumber='005103494', count=48058),
 Row(dunsnumber='001903137', count=46381),
 Row(dunsnumber='006261481', count=46101),
 Row(dunsnumber='080241867', count=45623),
 Row(dunsnumber='968904698', count=43729),
 Row(dunsnumber='013372573', count=43714),
 Row(dunsnumber='015108087', count=40850),
 Row(dunsnumber='119079903', count=40286),
 Row(dunsnumber='006928857', count=38860),
 Row(dunsnumber='155104938', count=37886),
 Row(dunsnumber='079467211', count=36098),
 Row(dunsnumber='020829396', count=35929),
 Row(dunsnumber='122679228', count=32807),
 Row(dunsnumber='085866580', count=32335),
 Row(dunsnumber='614345809', count=32208),
 Row(dunsnumber='071767334', count=31327),
 Row(dunsnumber='623191194', count=28661),
 Row(dunsnumber='039860122', count=28648),
 Row(dunsnumber='790238638', count=28389),
 Row(dunsnumber='148815173', count=27692),
 Row(dunsnumber='320212822', count=27625),
 Row(dunsnumber='806095217', count=27436),
 Row(dunsnumber='621088843', count=27294),
 Row(dunsnumber='003856143', count=27104),
 Row(dunsnumber='107910259', count=26939),
 Row(dunsnumber='137354572', count=25684),
 Row(dunsnumber='147372960', count=25675),
 Row(dunsnumber='026157235', count=25608),
 Row(dunsnumber='832963495', count=25297),
 Row(dunsnumber='025681164', count=25231),
 Row(dunsnumber='058311945', count=24768),
 Row(dunsnumber='831587949', count=24696),
 Row(dunsnumber='134345169', count=23459),
 Row(dunsnumber='804544724', count=23438),
 Row(dunsnumber='783146454', count=23293),
 Row(dunsnumber='616194916', count=23233),
 Row(dunsnumber='020751082', count=22969),
 Row(dunsnumber='040594561', count=22938),
 Row(dunsnumber='063375141', count=22858),
 Row(dunsnumber='007914989', count=22813),
 Row(dunsnumber='046275301', count=22118),
 Row(dunsnumber='076339782', count=21360),
 Row(dunsnumber='003197803', count=21337),
 Row(dunsnumber='002387603', count=21251),
 Row(dunsnumber='644762783', count=21078),
 Row(dunsnumber='176019107', count=20643),
 Row(dunsnumber='006962500', count=20474),
 Row(dunsnumber='621599893', count=20222),
 Row(dunsnumber='061081477', count=20159),
 Row(dunsnumber='827714507', count=19849),
 Row(dunsnumber='131747628', count=19545),
 Row(dunsnumber='002275782', count=19011),
 Row(dunsnumber='557723564', count=18908),
 Row(dunsnumber='021717889', count=18829),
 Row(dunsnumber='062923321', count=18466),
 Row(dunsnumber='130368145', count=18233),
 Row(dunsnumber='149530219', count=17853),
 Row(dunsnumber='088365767', count=17721),
 Row(dunsnumber='835568965', count=17719),
 Row(dunsnumber='123343027', count=17530),
 Row(dunsnumber='053324711', count=17420),
 Row(dunsnumber='124602793', count=17262),
 Row(dunsnumber='003548489', count=16770),
 Row(dunsnumber='079095242', count=16511),
 Row(dunsnumber='080232168', count=16443),
 Row(dunsnumber='178617031', count=16412),
 Row(dunsnumber='053794533', count=16113),
 Row(dunsnumber='836284091', count=15949),
 Row(dunsnumber='116194192', count=15642),
 Row(dunsnumber='186945325', count=15615),
 Row(dunsnumber='038009866', count=14926),
 Row(dunsnumber='098692374', count=14756),
 Row(dunsnumber='966423352', count=14698),
 Row(dunsnumber='085172005', count=14697),
 Row(dunsnumber='007977770', count=14668),
 Row(dunsnumber='106632750', count=14651),
 Row(dunsnumber='067641597', count=14434),
 Row(dunsnumber='014654966', count=14292),
 Row(dunsnumber='159868624', count=14287),
 Row(dunsnumber='877936518', count=14242),
 Row(dunsnumber='147459916', count=14157),
 Row(dunsnumber='004677399', count=14114),
 Row(dunsnumber='132080123', count=14083),
 Row(dunsnumber='007507671', count=13841),
 Row(dunsnumber='079116895', count=13674),
 Row(dunsnumber='096628409', count=13602),
 Row(dunsnumber='786468199', count=13569),
 Row(dunsnumber='085505951', count=13536),
 Row(dunsnumber='806619115', count=13469),
 Row(dunsnumber='003296175', count=13434),
 Row(dunsnumber='062722038', count=13277),
 Row(dunsnumber='008231672', count=13002),
 Row(dunsnumber='038062712', count=12885),
 Row(dunsnumber='007919475', count=12881),
 Row(dunsnumber='967511218', count=12874),
 Row(dunsnumber='024589251', count=12871),
 Row(dunsnumber='830966904', count=12864),
 Row(dunsnumber='614948396', count=12862),
 Row(dunsnumber='826929577', count=12792),
 Row(dunsnumber='126431225', count=12763),
 Row(dunsnumber='095633152', count=12442),
 Row(dunsnumber='045483575', count=12308),
 Row(dunsnumber='048485478', count=12243),
 Row(dunsnumber='832426782', count=12235),
 Row(dunsnumber='029107109', count=12192),
 Row(dunsnumber='134303192', count=12118),
 Row(dunsnumber='110345936', count=11978),
 Row(dunsnumber='069172294', count=11903),
 Row(dunsnumber='926581737', count=11875),
 Row(dunsnumber='038049532', count=11753),
 Row(dunsnumber='032672651', count=11599),
 Row(dunsnumber='128729373', count=11498),
 Row(dunsnumber='798069175', count=11421),
 Row(dunsnumber='088162420', count=11298),
 Row(dunsnumber='056410640', count=11297),
 Row(dunsnumber='043964519', count=11260),
 Row(dunsnumber='626578041', count=11142),
 Row(dunsnumber='008016958', count=11130),
 Row(dunsnumber='049281702', count=11121),
 Row(dunsnumber='097779698', count=11038),
 Row(dunsnumber='061888111', count=11011),
 Row(dunsnumber='121701957', count=10978),
 Row(dunsnumber='043175926', count=10783),
 Row(dunsnumber='109070714', count=10774),
 Row(dunsnumber='137488664', count=10624),
 Row(dunsnumber='041477449', count=10623),
 Row(dunsnumber='859395428', count=10592),
 Row(dunsnumber='005094842', count=10582),
 Row(dunsnumber='833063055', count=10517),
 Row(dunsnumber='311018654', count=10342),
 Row(dunsnumber='040901068', count=10284),
 Row(dunsnumber='154666218', count=10234),
 Row(dunsnumber='060605883', count=10189),
 Row(dunsnumber='078883327', count=10172),
 Row(dunsnumber='482449902', count=10154),
 Row(dunsnumber='103933453', count=10118),
 Row(dunsnumber='618563720', count=10111),
 Row(dunsnumber='787857551', count=10066),
 Row(dunsnumber='607775848', count=10053),
 Row(dunsnumber='014607105', count=10015),
 Row(dunsnumber='007901598', count=9978),
 Row(dunsnumber='004031493', count=9856),
 Row(dunsnumber='144293636', count=9812),
 Row(dunsnumber='118860779', count=9782),
 Row(dunsnumber='859385254', count=9749),
 Row(dunsnumber='144405214', count=9727),
 Row(dunsnumber='142440150', count=9587),
 Row(dunsnumber='001307495', count=9565),
 Row(dunsnumber='083235549', count=9500),
 Row(dunsnumber='808576024', count=9473),
 Row(dunsnumber='606896405', count=9428),
 Row(dunsnumber='118509772', count=9418),
 Row(dunsnumber='808787733', count=9414),
 Row(dunsnumber='185743655', count=9399),
 Row(dunsnumber='003176880', count=9368),
 Row(dunsnumber='006012801', count=9365),
 Row(dunsnumber='835130485', count=9351),
 Row(dunsnumber='948188594', count=9289),
 Row(dunsnumber='006173082', count=9251),
 Row(dunsnumber='603493677', count=9236),
 Row(dunsnumber='607373222', count=9193),
 Row(dunsnumber='021631047', count=9184),
 Row(dunsnumber='828953166', count=9153),
 Row(dunsnumber='038361853', count=9137),
 Row(dunsnumber='001826627', count=9088),
 Row(dunsnumber='019121586', count=9021),
 Row(dunsnumber='967474896', count=8977),
 Row(dunsnumber='803347749', count=8951),
 Row(dunsnumber='101905318', count=8904),
 Row(dunsnumber='879944270', count=8902),
 Row(dunsnumber='779912526', count=8853),
 Row(dunsnumber='086710329', count=8831),
 Row(dunsnumber='077817617', count=8775),
 Row(dunsnumber='963737366', count=8758),
 Row(dunsnumber='040549461', count=8661),
 Row(dunsnumber='620485276', count=8652),
 Row(dunsnumber='040200599', count=8649),
 Row(dunsnumber='606870512', count=8636),
 Row(dunsnumber='144140845', count=8582),
 Row(dunsnumber='036121655', count=8519),
 Row(dunsnumber='001818012', count=8497),
 Row(dunsnumber='794598573', count=8470),
 Row(dunsnumber='001447952', count=8438),
 Row(dunsnumber='074809377', count=8349),
 Row(dunsnumber='155890262', count=8342),
 Row(dunsnumber='061962358', count=8219),
 Row(dunsnumber='089896737', count=8127),
 Row(dunsnumber='005065946', count=8126),
 Row(dunsnumber='962972159', count=8080),
 Row(dunsnumber='073838534', count=7996),
 Row(dunsnumber='001161793', count=7985),
 Row(dunsnumber='103385519', count=7960),
 Row(dunsnumber='644774499', count=7954),
 Row(dunsnumber='020149303', count=7951),
 Row(dunsnumber='809678782', count=7902),
 Row(dunsnumber='050471416', count=7885),
 Row(dunsnumber='055189856', count=7867),
 Row(dunsnumber='021640487', count=7834),
 Row(dunsnumber='827771981', count=7820),
 Row(dunsnumber='035612345', count=7788),
 Row(dunsnumber='104012638', count=7731),
 Row(dunsnumber='933678708', count=7686),
 Row(dunsnumber='187929146', count=7675),
 Row(dunsnumber='938836541', count=7661),
 Row(dunsnumber='627785884', count=7635),
 Row(dunsnumber='878053321', count=7630),
 Row(dunsnumber='003408931', count=7581),
 Row(dunsnumber='008184749', count=7519),
 Row(dunsnumber='480520290', count=7500),
 Row(dunsnumber='017573259', count=7449),
 Row(dunsnumber='039267141', count=7444),
 Row(dunsnumber='788222115', count=7443),
 Row(dunsnumber='007923014', count=7404),
 Row(dunsnumber='120909460', count=7396),
 Row(dunsnumber='142371439', count=7367),
 Row(dunsnumber='794034553', count=7336),
 Row(dunsnumber='082193277', count=7333),
 Row(dunsnumber='050246404', count=7312),
 Row(dunsnumber='207884594', count=7292),
 Row(dunsnumber='174284315', count=7266),
 Row(dunsnumber='033723990', count=7262),
 Row(dunsnumber='139210991', count=7262),
 Row(dunsnumber='149879157', count=7239),
 Row(dunsnumber='830518069', count=7236),
 Row(dunsnumber='005085972', count=7185),
 Row(dunsnumber='958303430', count=7179),
 Row(dunsnumber='620311159', count=7165),
 Row(dunsnumber='131781643', count=7155),
 Row(dunsnumber='864356477', count=7151),
 Row(dunsnumber='057007189', count=7072),
 Row(dunsnumber='833063154', count=7048),
 Row(dunsnumber='006217061', count=7031),
 Row(dunsnumber='615378007', count=7019),
 Row(dunsnumber='013369913', count=6938),
 Row(dunsnumber='186127825', count=6893),
 Row(dunsnumber='148095086', count=6879),
 Row(dunsnumber='110480956', count=6863),
 Row(dunsnumber='078372376', count=6856),
 Row(dunsnumber='097017016', count=6844),
 Row(dunsnumber='061079273', count=6810),
 Row(dunsnumber='069341972', count=6808),
 Row(dunsnumber='609005350', count=6770),
 Row(dunsnumber='858888761', count=6757),
 Row(dunsnumber='626627459', count=6732),
 Row(dunsnumber='806647801', count=6702),
 Row(dunsnumber='088670260', count=6642),
 Row(dunsnumber='123786857', count=6639),
 Row(dunsnumber='779921998', count=6594),
 Row(dunsnumber='016377926', count=6575),
 Row(dunsnumber='086438152', count=6557),
 Row(dunsnumber='013184957', count=6537),
 Row(dunsnumber='603814054', count=6463),
 Row(dunsnumber='606036481', count=6445),
 Row(dunsnumber='144387615', count=6443),
 Row(dunsnumber='927588897', count=6427),
 Row(dunsnumber='003732393', count=6409),
 Row(dunsnumber='134139174', count=6405),
 Row(dunsnumber='017018859', count=6364),
 Row(dunsnumber='827429312', count=6361),
 Row(dunsnumber='002232973', count=6339),
 Row(dunsnumber='002204600', count=6300),
 Row(dunsnumber='841580934', count=6254),
 Row(dunsnumber='833063253', count=6248),
 Row(dunsnumber='201756876', count=6217),
 Row(dunsnumber='147218333', count=6216),
 Row(dunsnumber='534991963', count=6204),
 Row(dunsnumber='153910070', count=6188),
 Row(dunsnumber='790889711', count=6179),
 Row(dunsnumber='001183748', count=6160),
 Row(dunsnumber='072648579', count=6160),
 Row(dunsnumber='168460371', count=6122),
 Row(dunsnumber='102675899', count=6096),
 Row(dunsnumber='057364507', count=6084),
 Row(dunsnumber='141254842', count=6076),
 Row(dunsnumber='078717364', count=6032),
 Row(dunsnumber='153882816', count=6026),
 Row(dunsnumber='160759135', count=5942),
 Row(dunsnumber='017711888', count=5934),
 Row(dunsnumber='103231817', count=5898),
 Row(dunsnumber='006070445', count=5890),
 Row(dunsnumber='609377283', count=5871),
 Row(dunsnumber='071926661', count=5870),
 Row(dunsnumber='119079762', count=5831),
 Row(dunsnumber='082080136', count=5814),
 Row(dunsnumber='928859149', count=5789),
 Row(dunsnumber='945377653', count=5765),
 Row(dunsnumber='007296820', count=5748),
 Row(dunsnumber='107939357', count=5711),
 Row(dunsnumber='150982189', count=5690),
 Row(dunsnumber='182158873', count=5684),
 Row(dunsnumber='121540038', count=5680),
 Row(dunsnumber='186528188', count=5668),
 Row(dunsnumber='612020933', count=5667),
 Row(dunsnumber='829669303', count=5640),
 Row(dunsnumber='962568338', count=5631),
 Row(dunsnumber='964274794', count=5630),
 Row(dunsnumber='695771931', count=5629),
 Row(dunsnumber='078404457', count=5623),
 Row(dunsnumber='043991108', count=5612),
 Row(dunsnumber='338612799', count=5609),
 Row(dunsnumber='041904509', count=5596),
 Row(dunsnumber='154869622', count=5579),
 Row(dunsnumber='069464519', count=5567),
 Row(dunsnumber='012895066', count=5538),
 Row(dunsnumber='001695568', count=5511),
 Row(dunsnumber='001368141', count=5510),
 Row(dunsnumber='001824663', count=5505),
 Row(dunsnumber='140752374', count=5468),
 Row(dunsnumber='275137164', count=5394),
 Row(dunsnumber='868899907', count=5343),
 Row(dunsnumber='129365420', count=5327),
 Row(dunsnumber='086616885', count=5302),
 Row(dunsnumber='617417001', count=5295),
 Row(dunsnumber='197355290', count=5246),
 Row(dunsnumber='004868105', count=5242),
 Row(dunsnumber='805258373', count=5228),
 Row(dunsnumber='828128475', count=5227),
 Row(dunsnumber='332619535', count=5216),
 Row(dunsnumber='035858898', count=5215),
 Row(dunsnumber='044549434', count=5214),
 Row(dunsnumber='177360039', count=5196),
 Row(dunsnumber='791824949', count=5196),
 Row(dunsnumber='027005180', count=5178),
 Row(dunsnumber='055212153', count=5173),
 Row(dunsnumber='054781240', count=5172),
 Row(dunsnumber='148508286', count=5153),
 Row(dunsnumber='139747026', count=5117),
 Row(dunsnumber='607330206', count=5116),
 Row(dunsnumber='197138274', count=5110),
 Row(dunsnumber='008254195', count=5106),
 Row(dunsnumber='064299332', count=5102),
 Row(dunsnumber='556054591', count=5096),
 Row(dunsnumber='070111927', count=5064),
 Row(dunsnumber='022755913', count=5058),
 Row(dunsnumber='076916246', count=5039),
 Row(dunsnumber='173823147', count=5025),
 Row(dunsnumber='091991224', count=5013),
 Row(dunsnumber='034110689', count=5009),
 Row(dunsnumber='962525056', count=5004),
 Row(dunsnumber='134510648', count=4979),
 Row(dunsnumber='786130583', count=4967),
 Row(dunsnumber='003498029', count=4961),
 Row(dunsnumber='011071867', count=4954),
 Row(dunsnumber='807941625', count=4939),
 Row(dunsnumber='041024415', count=4918),
 Row(dunsnumber='781457148', count=4906),
 Row(dunsnumber='006958318', count=4904),
 Row(dunsnumber='083070925', count=4902),
 Row(dunsnumber='968058177', count=4894),
 Row(dunsnumber='066523528', count=4858),
 Row(dunsnumber='938535028', count=4852),
 Row(dunsnumber='608461898', count=4849),
 Row(dunsnumber='867258972', count=4829),
 Row(dunsnumber='141089040', count=4824),
 Row(dunsnumber='799855812', count=4820),
 Row(dunsnumber='790238851', count=4809),
 Row(dunsnumber='136721250', count=4776),
 Row(dunsnumber='114896066', count=4772),
 Row(dunsnumber='061665857', count=4771),
 Row(dunsnumber='072581718', count=4767),
 Row(dunsnumber='117071386', count=4765),
 Row(dunsnumber='013358002', count=4746),
 Row(dunsnumber='784141384', count=4731),
 Row(dunsnumber='087192134', count=4728),
 Row(dunsnumber='021411467', count=4727),
 Row(dunsnumber='797016701', count=4723),
 Row(dunsnumber='159776806', count=4718),
 Row(dunsnumber='080911274', count=4708),
 Row(dunsnumber='781316096', count=4699),
 Row(dunsnumber='155505485', count=4693),
 Row(dunsnumber='803836345', count=4692),
 Row(dunsnumber='841355811', count=4664),
 Row(dunsnumber='158988878', count=4640),
 Row(dunsnumber='796560394', count=4638),
 Row(dunsnumber='966424491', count=4637),
 Row(dunsnumber='013550462', count=4628),
 Row(dunsnumber='078367304', count=4626),
 Row(dunsnumber='361517212', count=4621),
 Row(dunsnumber='024042079', count=4620),
 Row(dunsnumber='194903670', count=4604),
 Row(dunsnumber='947803078', count=4570),
 Row(dunsnumber='067943220', count=4559),
 Row(dunsnumber='077532422', count=4526),
 Row(dunsnumber='785809349', count=4512),
 Row(dunsnumber='966833766', count=4504),
 Row(dunsnumber='831597484', count=4493),
 Row(dunsnumber='077652761', count=4481),
 Row(dunsnumber='040540304', count=4481),
 Row(dunsnumber='196778419', count=4470),
 Row(dunsnumber='169601999', count=4451),
 Row(dunsnumber='069373090', count=4450),
 Row(dunsnumber='961530545', count=4445),
 Row(dunsnumber='197425523', count=4435),
 Row(dunsnumber='788283989', count=4428),
 Row(dunsnumber='068595685', count=4427),
 Row(dunsnumber='134160873', count=4423),
 Row(dunsnumber='022459429', count=4418),
 Row(dunsnumber='958987877', count=4387),
 Row(dunsnumber='131266926', count=4385),
 Row(dunsnumber='129278169', count=4366),
 Row(dunsnumber='088736686', count=4337),
 Row(dunsnumber='040370249', count=4321),
 Row(dunsnumber='735854031', count=4305),
 Row(dunsnumber='055363428', count=4290),
 Row(dunsnumber='116012659', count=4268),
 Row(dunsnumber='084142785', count=4263),
 Row(dunsnumber='109234716', count=4260),
 Row(dunsnumber='027408483', count=4244),
 Row(dunsnumber='004206397', count=4238),
 Row(dunsnumber='961003720', count=4235),
 Row(dunsnumber='127136252', count=4228),
 Row(dunsnumber='095931486', count=4223),
 Row(dunsnumber='056280621', count=4219),
 Row(dunsnumber='145969783', count=4214),
 Row(dunsnumber='831749754', count=4208),
 Row(dunsnumber='625684469', count=4205),
 Row(dunsnumber='178041406', count=4205),
 Row(dunsnumber='121306984', count=4186),
 Row(dunsnumber='048341838', count=4171),
 Row(dunsnumber='003268869', count=4157),
 Row(dunsnumber='877672683', count=4150),
 Row(dunsnumber='032093028', count=4140),
 Row(dunsnumber='024482296', count=4133),
 Row(dunsnumber='195185348', count=4120),
 Row(dunsnumber='829067219', count=4101),
 Row(dunsnumber='179092028', count=4078),
 Row(dunsnumber='083655498', count=4073),
 Row(dunsnumber='017979027', count=4064),
 Row(dunsnumber='005149120', count=4063),
 Row(dunsnumber='020016718', count=4060),
 Row(dunsnumber='804754141', count=4041),
 Row(dunsnumber='128601312', count=4039),
 Row(dunsnumber='007365984', count=4030),
 Row(dunsnumber='006096200', count=4012),
 Row(dunsnumber='078498831', count=4006),
 Row(dunsnumber='092658152', count=3976),
 Row(dunsnumber='801397204', count=3972),
 Row(dunsnumber='161021597', count=3948),
 Row(dunsnumber='010944650', count=3945),
 Row(dunsnumber='024052821', count=3940),
 Row(dunsnumber='139727148', count=3928),
 Row(dunsnumber='121597462', count=3923),
 Row(dunsnumber='809887164', count=3910),
 Row(dunsnumber='064632888', count=3906),
 Row(dunsnumber='075293423', count=3903),
 Row(dunsnumber='017259326', count=3900),
 Row(dunsnumber='783140346', count=3888),
 Row(dunsnumber='782053516', count=3886),
 Row(dunsnumber='094373495', count=3880),
 Row(dunsnumber='878901396', count=3871),
 Row(dunsnumber='153718502', count=3864),
 Row(dunsnumber='038086125', count=3856),
 Row(dunsnumber='807445499', count=3856),
 Row(dunsnumber='002103166', count=3847),
 Row(dunsnumber='064465503', count=3844),
 Row(dunsnumber='963450866', count=3839),
 Row(dunsnumber='006016547', count=3838),
 Row(dunsnumber='602938771', count=3826),
 Row(dunsnumber='616385667', count=3823),
 Row(dunsnumber='626516223', count=3816),
 Row(dunsnumber='606837698', count=3812),
 Row(dunsnumber='075916762', count=3812),
 Row(dunsnumber='008198421', count=3807),
 Row(dunsnumber='804788545', count=3793),
 Row(dunsnumber='831765891', count=3792),
 Row(dunsnumber='059069211', count=3790),
 Row(dunsnumber='831017848', count=3779),
 Row(dunsnumber='006154611', count=3773),
 Row(dunsnumber='065152217', count=3767),
 Row(dunsnumber='033305264', count=3757),
 Row(dunsnumber='534594507', count=3757),
 Row(dunsnumber='626771021', count=3743),
 Row(dunsnumber='003567125', count=3729),
 Row(dunsnumber='004245668', count=3709),
 Row(dunsnumber='098813470', count=3708),
 Row(dunsnumber='361542434', count=3708),
 Row(dunsnumber='806276700', count=3691),
 Row(dunsnumber='150780674', count=3686),
 Row(dunsnumber='830562026', count=3679),
 Row(dunsnumber='074800160', count=3673),
 Row(dunsnumber='175357672', count=3667),
 Row(dunsnumber='147795132', count=3660),
 Row(dunsnumber='043700660', count=3658),
 Row(dunsnumber='622051969', count=3646),
 Row(dunsnumber='093738722', count=3638),
 Row(dunsnumber='145454182', count=3637),
 Row(dunsnumber='827470456', count=3632),
 Row(dunsnumber='718910532', count=3628),
 Row(dunsnumber='057799637', count=3623),
 Row(dunsnumber='074334264', count=3622),
 Row(dunsnumber='079116889', count=3616),
 Row(dunsnumber='056354640', count=3613),
 Row(dunsnumber='329182323', count=3610),
 Row(dunsnumber='938289527', count=3590),
 Row(dunsnumber='007936842', count=3581),
 Row(dunsnumber='078561768', count=3570),
 Row(dunsnumber='135962137', count=3569),
 Row(dunsnumber='780231150', count=3569),
 Row(dunsnumber='144763067', count=3564),
 Row(dunsnumber='799126172', count=3558),
 Row(dunsnumber='802318951', count=3553),
 Row(dunsnumber='557179124', count=3551),
 Row(dunsnumber='154577456', count=3531),
 Row(dunsnumber='938647021', count=3530),
 Row(dunsnumber='049997380', count=3525),
 Row(dunsnumber='055124077', count=3508),
 Row(dunsnumber='196189385', count=3496),
 Row(dunsnumber='068715424', count=3495),
 Row(dunsnumber='965961860', count=3495),
 Row(dunsnumber='188991954', count=3494),
 Row(dunsnumber='021715206', count=3493),
 Row(dunsnumber='101624476', count=3488),
 Row(dunsnumber='170944768', count=3487),
 Row(dunsnumber='063134175', count=3484),
 Row(dunsnumber='147814735', count=3478),
 Row(dunsnumber='084915540', count=3476),
 Row(dunsnumber='825063311', count=3473),
 Row(dunsnumber='023669401', count=3461),
 Row(dunsnumber='033145939', count=3460),
 Row(dunsnumber='148298396', count=3457),
 Row(dunsnumber='010018737', count=3447),
 Row(dunsnumber='054989991', count=3447),
 Row(dunsnumber='038006110', count=3440),
 Row(dunsnumber='029330792', count=3434),
 Row(dunsnumber='609717462', count=3426),
 Row(dunsnumber='933337875', count=3419),
 Row(dunsnumber='968538079', count=3409),
 Row(dunsnumber='001690924', count=3406),
 Row(dunsnumber='003403953', count=3397),
 Row(dunsnumber='964825280', count=3378),
 Row(dunsnumber='063931836', count=3365),
 Row(dunsnumber='318327509', count=3361),
 Row(dunsnumber='086657111', count=3357),
 Row(dunsnumber='063079268', count=3350),
 Row(dunsnumber='364124651', count=3346),
 Row(dunsnumber='136127482', count=3343),
 Row(dunsnumber='037187080', count=3332),
 Row(dunsnumber='045256000', count=3326),
 Row(dunsnumber='158140041', count=3314),
 Row(dunsnumber='171068344', count=3306),
 Row(dunsnumber='004117594', count=3299),
 Row(dunsnumber='041964057', count=3293),
 Row(dunsnumber='089107726', count=3285),
 Row(dunsnumber='078769590', count=3285),
 Row(dunsnumber='056543879', count=3278),
 Row(dunsnumber='045953718', count=3278),
 Row(dunsnumber='798318598', count=3274),
 Row(dunsnumber='112762443', count=3262),
 Row(dunsnumber='086785110', count=3252),
 Row(dunsnumber='106293954', count=3243),
 Row(dunsnumber='005167242', count=3238),
 Row(dunsnumber='157637570', count=3233),
 Row(dunsnumber='964899483', count=3222),
 Row(dunsnumber='046007688', count=3216),
 Row(dunsnumber='058215778', count=3212),
 Row(dunsnumber='061191391', count=3209),
 Row(dunsnumber='004105904', count=3193),
 Row(dunsnumber='078552676', count=3182),
 Row(dunsnumber='124120655', count=3173),
 Row(dunsnumber='166569850', count=3169),
 Row(dunsnumber='195580881', count=3162),
 Row(dunsnumber='824684229', count=3158),
 Row(dunsnumber='077799799', count=3157),
 Row(dunsnumber='004469300', count=3155),
 Row(dunsnumber='619822075', count=3146),
 Row(dunsnumber='008983355', count=3141),
 Row(dunsnumber='054863428', count=3139),
 Row(dunsnumber='809670008', count=3138),
 Row(dunsnumber='131142747', count=3133),
 Row(dunsnumber='170015171', count=3132),
 Row(dunsnumber='931483556', count=3128),
 Row(dunsnumber='149975554', count=3121),
 Row(dunsnumber='014586911', count=3106),
 Row(dunsnumber='306111290', count=3106),
 Row(dunsnumber='157616335', count=3105),
 Row(dunsnumber='048918643', count=3105),
 Row(dunsnumber='006254833', count=3088),
 Row(dunsnumber='130598238', count=3086),
 Row(dunsnumber='929022028', count=3084),
 Row(dunsnumber='186579173', count=3078),
 Row(dunsnumber='879585248', count=3075),
 Row(dunsnumber='363596297', count=3072),
 Row(dunsnumber='610703282', count=3068),
 Row(dunsnumber='064683464', count=3048),
 Row(dunsnumber='794571448', count=3045),
 Row(dunsnumber='182004838', count=3044),
 Row(dunsnumber='019710586', count=3043),
 Row(dunsnumber='015192505', count=3042),
 Row(dunsnumber='083193409', count=3040),
 Row(dunsnumber='138388090', count=3039),
 Row(dunsnumber='038157756', count=3032),
 Row(dunsnumber='103079174', count=3026),
 Row(dunsnumber='080708241', count=3024),
 Row(dunsnumber='006919484', count=3023),
 Row(dunsnumber='139422950', count=3012),
 Row(dunsnumber='174713623', count=3009),
 Row(dunsnumber='021964036', count=3007),
 Row(dunsnumber='064491319', count=3007),
 Row(dunsnumber='830135799', count=3007),
 Row(dunsnumber='804936177', count=2999),
 Row(dunsnumber='009232752', count=2998),
 Row(dunsnumber='010816486', count=2998),
 Row(dunsnumber='072595457', count=2993),
 Row(dunsnumber='609570742', count=2987),
 Row(dunsnumber='102067378', count=2985),
 Row(dunsnumber='047442731', count=2984),
 Row(dunsnumber='217304393', count=2981),
 Row(dunsnumber='690535224', count=2978),
 Row(dunsnumber='046560702', count=2974),
 Row(dunsnumber='034165373', count=2965),
 Row(dunsnumber='962048646', count=2963),
 Row(dunsnumber='041014242', count=2948),
 Row(dunsnumber='112947395', count=2947),
 Row(dunsnumber='011556719', count=2942),
 Row(dunsnumber='929445492', count=2934),
 Row(dunsnumber='069510246', count=2932),
 Row(dunsnumber='003184462', count=2929),
 Row(dunsnumber='050987460', count=2924),
 Row(dunsnumber='083171244', count=2922),
 Row(dunsnumber='097967608', count=2922),
 Row(dunsnumber='002212710', count=2916),
 Row(dunsnumber='125465190', count=2902),
 Row(dunsnumber='003268989', count=2897),
 Row(dunsnumber='053945259', count=2887),
 Row(dunsnumber='009577768', count=2883),
 Row(dunsnumber='059012893', count=2883),
 Row(dunsnumber='091808832', count=2882),
 Row(dunsnumber='064677243', count=2870),
 Row(dunsnumber='002136877', count=2866),
 Row(dunsnumber='796646453', count=2863),
 Row(dunsnumber='006365803', count=2863),
 Row(dunsnumber='825054810', count=2860),
 Row(dunsnumber='196882310', count=2852),
 Row(dunsnumber='132010856', count=2846),
 Row(dunsnumber='079400351', count=2846),
 Row(dunsnumber='942603358', count=2844),
 Row(dunsnumber='056168214', count=2842),
 Row(dunsnumber='107171589', count=2839),
 Row(dunsnumber='121763932', count=2834),
 Row(dunsnumber='808350172', count=2833),
 Row(dunsnumber='009224163', count=2832),
 Row(dunsnumber='803638477', count=2824),
 Row(dunsnumber='859716677', count=2819),
 Row(dunsnumber='076256809', count=2816),
 Row(dunsnumber='050516509', count=2815),
 Row(dunsnumber='060728268', count=2799),
 Row(dunsnumber='607690989', count=2799),
 Row(dunsnumber='009158932', count=2798),
 Row(dunsnumber='006908511', count=2798),
 Row(dunsnumber='049231319', count=2795),
 Row(dunsnumber='799813931', count=2794),
 Row(dunsnumber='127112147', count=2776),
 Row(dunsnumber='193049236', count=2768),
 Row(dunsnumber='959391509', count=2760),
 Row(dunsnumber='061747671', count=2756),
 Row(dunsnumber='067459326', count=2754),
 Row(dunsnumber='113512359', count=2753),
 Row(dunsnumber='107965472', count=2746),
 Row(dunsnumber='032212990', count=2745),
 Row(dunsnumber='079850673', count=2744),
 Row(dunsnumber='056971781', count=2739),
 Row(dunsnumber='166669742', count=2736),
 Row(dunsnumber='001408509', count=2735),
 Row(dunsnumber='019732036', count=2735),
 Row(dunsnumber='094738007', count=2734),
 Row(dunsnumber='129983776', count=2731),
 Row(dunsnumber='148744493', count=2722),
 Row(dunsnumber='151049756', count=2721),
 Row(dunsnumber='011443269', count=2714),
 Row(dunsnumber='079537375', count=2711),
 Row(dunsnumber='076192475', count=2710),
 Row(dunsnumber='024249146', count=2710),
 Row(dunsnumber='609815618', count=2708),
 Row(dunsnumber='005687343', count=2707),
 Row(dunsnumber='957050883', count=2706),
 Row(dunsnumber='027519248', count=2705),
 Row(dunsnumber='003061124', count=2703),
 Row(dunsnumber='060897063', count=2699),
 Row(dunsnumber='948410048', count=2693),
 Row(dunsnumber='054905427', count=2692),
 Row(dunsnumber='113068027', count=2692),
 Row(dunsnumber='049508120', count=2692),
 Row(dunsnumber='248477523', count=2692),
 Row(dunsnumber='788518806', count=2687),
 Row(dunsnumber='791780778', count=2686),
 Row(dunsnumber='801218087', count=2678),
 Row(dunsnumber='067379743', count=2672),
 Row(dunsnumber='073737822', count=2670),
 Row(dunsnumber='008391682', count=2659),
 Row(dunsnumber='154050959', count=2658),
 Row(dunsnumber='127208879', count=2653),
 Row(dunsnumber='017234571', count=2651),
 Row(dunsnumber='787411917', count=2647),
 Row(dunsnumber='051237027', count=2641),
 Row(dunsnumber='122515708', count=2636),
 Row(dunsnumber='082355652', count=2634),
 Row(dunsnumber='109515259', count=2632),
 Row(dunsnumber='053385738', count=2628),
 Row(dunsnumber='967025602', count=2626),
 Row(dunsnumber='081466849', count=2619),
 Row(dunsnumber='025460908', count=2617),
 Row(dunsnumber='096277595', count=2615),
 Row(dunsnumber='020201427', count=2607),
 Row(dunsnumber='010527179', count=2604),
 Row(dunsnumber='130027592', count=2603),
 Row(dunsnumber='192201689', count=2601),
 Row(dunsnumber='001903202', count=2600),
 Row(dunsnumber='883012874', count=2598),
 Row(dunsnumber='073891921', count=2593),
 Row(dunsnumber='122598159', count=2591),
 Row(dunsnumber='087403499', count=2588),
 Row(dunsnumber='020278375', count=2587),
 Row(dunsnumber='859716750', count=2587),
 Row(dunsnumber='828447594', count=2587),
 Row(dunsnumber='809919038', count=2585),
 Row(dunsnumber='169819476', count=2580),
 Row(dunsnumber='039322250', count=2575),
 Row(dunsnumber='040841306', count=2574),
 Row(dunsnumber='021860424', count=2573),
 Row(dunsnumber='967162251', count=2570),
 Row(dunsnumber='606290401', count=2569),
 Row(dunsnumber='056286347', count=2568),
 Row(dunsnumber='694271222', count=2568),
 Row(dunsnumber='001738046', count=2567),
 Row(dunsnumber='155389224', count=2565),
 Row(dunsnumber='556565836', count=2562),
 Row(dunsnumber='003001070', count=2562),
 Row(dunsnumber='624004441', count=2561),
 Row(dunsnumber='795140433', count=2558),
 Row(dunsnumber='116193400', count=2557),
 Row(dunsnumber='051794915', count=2555),
 Row(dunsnumber='785182705', count=2554),
 Row(dunsnumber='836196972', count=2541),
 Row(dunsnumber='079392044', count=2540),
 Row(dunsnumber='602479149', count=2539),
 Row(dunsnumber='872978978', count=2539),
 Row(dunsnumber='006966030', count=2537),
 Row(dunsnumber='001910777', count=2537),
 Row(dunsnumber='068015924', count=2535),
 Row(dunsnumber='779913441', count=2532),
 Row(dunsnumber='008254708', count=2531),
 Row(dunsnumber='078542823', count=2530),
 Row(dunsnumber='007246630', count=2527),
 Row(dunsnumber='068528376', count=2522),
 Row(dunsnumber='077493513', count=2522),
 Row(dunsnumber='800205952', count=2522),
 Row(dunsnumber='190309067', count=2521),
 Row(dunsnumber='143521784', count=2519),
 Row(dunsnumber='151066763', count=2518),
 Row(dunsnumber='044519429', count=2518),
 Row(dunsnumber='008018525', count=2517),
 Row(dunsnumber='133819347', count=2516),
 Row(dunsnumber='690619705', count=2513),
 Row(dunsnumber='004961678', count=2511),
 Row(dunsnumber='127393978', count=2508),
 Row(dunsnumber='037482122', count=2504),
 Row(dunsnumber='113377659', count=2501),
 Row(dunsnumber='793374034', count=2501),
 Row(dunsnumber='556895332', count=2494),
 Row(dunsnumber='039192216', count=2493),
 Row(dunsnumber='963425322', count=2487),
 Row(dunsnumber='005128988', count=2484),
 Row(dunsnumber='005088112', count=2483),
 Row(dunsnumber='121360627', count=2476),
 Row(dunsnumber='096500483', count=2476),
 Row(dunsnumber='126511963', count=2475),
 Row(dunsnumber='166665245', count=2463),
 Row(dunsnumber='048827364', count=2460),
 Row(dunsnumber='626882609', count=2457),
 Row(dunsnumber='018517698', count=2456),
 Row(dunsnumber='116211863', count=2456),
 Row(dunsnumber='969540751', count=2453),
 Row(dunsnumber='001210996', count=2453),
 Row(dunsnumber='006095616', count=2452),
 Row(dunsnumber='805412665', count=2449),
 Row(dunsnumber='048900901', count=2444),
 Row(dunsnumber='034045922', count=2443),
 Row(dunsnumber='180015336', count=2443),
 Row(dunsnumber='015101848', count=2441),
 Row(dunsnumber='195823570', count=2441),
 Row(dunsnumber='056114218', count=2437),
 Row(dunsnumber='136950180', count=2437),
 Row(dunsnumber='043397520', count=2437),
 Row(dunsnumber='041220799', count=2436),
 Row(dunsnumber='697669679', count=2429),
 Row(dunsnumber='932902364', count=2423),
 Row(dunsnumber='055727580', count=2422),
 Row(dunsnumber='619719693', count=2421),
 Row(dunsnumber='803406797', count=2420),
 Row(dunsnumber='622824886', count=2414),
 Row(dunsnumber='024230633', count=2414),
 Row(dunsnumber='003090198', count=2413),
 Row(dunsnumber='145014242', count=2412),
 Row(dunsnumber='174911131', count=2409),
 Row(dunsnumber='874569015', count=2409),
 Row(dunsnumber='050506836', count=2408),
 Row(dunsnumber='620864504', count=2407),
 Row(dunsnumber='035207807', count=2406),
 Row(dunsnumber='046245411', count=2405),
 Row(dunsnumber='004076030', count=2402),
 Row(dunsnumber='961228780', count=2399),
 Row(dunsnumber='079186185', count=2398),
 Row(dunsnumber='041491895', count=2395),
 Row(dunsnumber='835406539', count=2395),
 Row(dunsnumber='073090917', count=2391),
 Row(dunsnumber='175096619', count=2384),
 Row(dunsnumber='174245993', count=2384),
 Row(dunsnumber='091441089', count=2383),
 Row(dunsnumber='129300799', count=2377),
 Row(dunsnumber='009752957', count=2376),
 Row(dunsnumber='092158245', count=2372),
 Row(dunsnumber='781797712', count=2369),
 Row(dunsnumber='956711444', count=2368),
 Row(dunsnumber='028139517', count=2367),
 Row(dunsnumber='613251024', count=2366),
 Row(dunsnumber='963588939', count=2362),
 Row(dunsnumber='618753768', count=2359),
 Row(dunsnumber='139602320', count=2358),
 Row(dunsnumber='807040258', count=2357),
 Row(dunsnumber='196602866', count=2357),
 Row(dunsnumber='152173928', count=2355),
 Row(dunsnumber='006580799', count=2352),
 Row(dunsnumber='687737494', count=2347),
 Row(dunsnumber='659711576', count=2339),
 Row(dunsnumber='847436391', count=2334),
 Row(dunsnumber='053950783', count=2333),
 Row(dunsnumber='926684788', count=2331),
 Row(dunsnumber='829108211', count=2328),
 Row(dunsnumber='002266575', count=2328),
 Row(dunsnumber='216891663', count=2327),
 Row(dunsnumber='003253788', count=2325),
 Row(dunsnumber='833157261', count=2323),
 Row(dunsnumber='604357087', count=2322),
 Row(dunsnumber='025100970', count=2321),
 Row(dunsnumber='606173334', count=2314),
 Row(dunsnumber='078317148', count=2313),
 Row(dunsnumber='806026852', count=2306),
 Row(dunsnumber='556915205', count=2304),
 Row(dunsnumber='069381812', count=2298),
 Row(dunsnumber='172316432', count=2297),
 Row(dunsnumber='786996272', count=2296),
 Row(dunsnumber='049111594', count=2289),
 Row(dunsnumber='078669280', count=2282),
 Row(dunsnumber='174894576', count=2281),
 Row(dunsnumber='033359266', count=2278),
 Row(dunsnumber='008263857', count=2277),
 Row(dunsnumber='962289393', count=2276),
 Row(dunsnumber='160975009', count=2275),
 Row(dunsnumber='076164771', count=2273),
 Row(dunsnumber='055778088', count=2273),
 Row(dunsnumber='153500434', count=2271),
 Row(dunsnumber='197294564', count=2270),
 Row(dunsnumber='079105006', count=2266),
 Row(dunsnumber='156992745', count=2266),
 Row(dunsnumber='165012100', count=2258),
 Row(dunsnumber='194953634', count=2257),
 Row(dunsnumber='809841898', count=2257),
 Row(dunsnumber='800933397', count=2255),
 Row(dunsnumber='103202859', count=2249),
 Row(dunsnumber='809699650', count=2243),
 Row(dunsnumber='118649891', count=2240),
 Row(dunsnumber='012641031', count=2236),
 Row(dunsnumber='043203249', count=2235),
 Row(dunsnumber='157224205', count=2230),
 Row(dunsnumber='042256222', count=2226),
 Row(dunsnumber='556328334', count=2226),
 Row(dunsnumber='624770475', count=2226),
 Row(dunsnumber='115978041', count=2224),
 Row(dunsnumber='049975238', count=2224),
 Row(dunsnumber='194239018', count=2214),
 Row(dunsnumber='174716113', count=2214),
 Row(dunsnumber='123399383', count=2211),
 Row(dunsnumber='035375757', count=2209),
 Row(dunsnumber='067930706', count=2209),
 Row(dunsnumber='132075388', count=2207),
 Row(dunsnumber='622377369', count=2206),
 Row(dunsnumber='139627525', count=2204),
 Row(dunsnumber='076880744', count=2203),
 Row(dunsnumber='083139394', count=2186),
 Row(dunsnumber='060928587', count=2186),
 Row(dunsnumber='074108176', count=2179),
 Row(dunsnumber='807545538', count=2178),
 Row(dunsnumber='193803103', count=2174),
 Row(dunsnumber='807201207', count=2171),
 Row(dunsnumber='005083209', count=2170),
 Row(dunsnumber='616858908', count=2166),
 Row(dunsnumber='009188884', count=2166),
 Row(dunsnumber='832930585', count=2166),
 Row(dunsnumber='793477758', count=2164),
 Row(dunsnumber='016434201', count=2161),
 Row(dunsnumber='023363542', count=2160),
 Row(dunsnumber='791516933', count=2159),
 Row(dunsnumber='010848489', count=2158),
 Row(dunsnumber='004649125', count=2157),
 Row(dunsnumber='126505833', count=2157),
 Row(dunsnumber='603168931', count=2157),
 Row(dunsnumber='013326038', count=2155),
 Row(dunsnumber='086057924', count=2154),
 Row(dunsnumber='066516480', count=2153),
 Row(dunsnumber='073220071', count=2148),
 Row(dunsnumber='144202843', count=2146),
 Row(dunsnumber='806203014', count=2144),
 Row(dunsnumber='799009782', count=2142),
 Row(dunsnumber='942408766', count=2142),
 Row(dunsnumber='011494957', count=2141),
 Row(dunsnumber='009553637', count=2139),
 Row(dunsnumber='005262308', count=2138),
 Row(dunsnumber='805834827', count=2136),
 Row(dunsnumber='968581348', count=2135),
 Row(dunsnumber='042370734', count=2132),
 Row(dunsnumber='790470749', count=2132),
 Row(dunsnumber='152791091', count=2131),
 Row(dunsnumber='697442416', count=2124),
 Row(dunsnumber='084993604', count=2121),
 Row(dunsnumber='076089622', count=2119),
 Row(dunsnumber='046909524', count=2118),
 Row(dunsnumber='078411646', count=2118),
 Row(dunsnumber='002271674', count=2114),
 Row(dunsnumber='086003852', count=2113),
 Row(dunsnumber='627168110', count=2112),
 Row(dunsnumber='023394158', count=2112),
 Row(dunsnumber='176091689', count=2111),
 Row(dunsnumber='025189338', count=2110),
 Row(dunsnumber='140055034', count=2108),
 Row(dunsnumber='042598482', count=2101),
 Row(dunsnumber='037297421', count=2100),
 Row(dunsnumber='828671482', count=2100),
 Row(dunsnumber='005957329', count=2097),
 Row(dunsnumber='606624653', count=2097),
 Row(dunsnumber='191996354', count=2095),
 Row(dunsnumber='042445700', count=2095),
 Row(dunsnumber='130866817', count=2090),
 Row(dunsnumber='809614733', count=2090),
 Row(dunsnumber='017035762', count=2087),
 Row(dunsnumber='001992338', count=2087),
 Row(dunsnumber='039413299', count=2085),
 Row(dunsnumber='175344753', count=2083),
 Row(dunsnumber='623331717', count=2082),
 Row(dunsnumber='131463705', count=2082),
 Row(dunsnumber='078364948', count=2081),
 Row(dunsnumber='809968902', count=2079),
 Row(dunsnumber='051645935', count=2078),
 Row(dunsnumber='186618869', count=2077),
 Row(dunsnumber='038997573', count=2077),
 Row(dunsnumber='011182784', count=2076),
 Row(dunsnumber='039603477', count=2076),
 Row(dunsnumber='039467761', count=2075),
 Row(dunsnumber='127208127', count=2071),
 Row(dunsnumber='561519815', count=2069),
 Row(dunsnumber='119193803', count=2067),
 Row(dunsnumber='024292732', count=2066),
 Row(dunsnumber='191341627', count=2063),
 Row(dunsnumber='620117791', count=2058),
 Row(dunsnumber='008385312', count=2057),
 Row(dunsnumber='083662916', count=2056),
 Row(dunsnumber='963908004', count=2052),
 Row(dunsnumber='088887757', count=2049),
 Row(dunsnumber='002049880', count=2037),
 Row(dunsnumber='797203932', count=2036),
 Row(dunsnumber='028758290', count=2031),
 Row(dunsnumber='147768563', count=2029),
 Row(dunsnumber='791133023', count=2027),
 Row(dunsnumber='933397929', count=2019),
 Row(dunsnumber='849626338', count=2018),
 Row(dunsnumber='954521568', count=2018),
 Row(dunsnumber='126085120', count=2017),
 Row(dunsnumber='008862315', count=2016),
 Row(dunsnumber='082971578', count=2014),
 Row(dunsnumber='615503877', count=2013),
 Row(dunsnumber='829030365', count=2013),
 Row(dunsnumber='051398089', count=2013),
 Row(dunsnumber='028525582', count=2011),
 Row(dunsnumber='781175112', count=2010),
 Row(dunsnumber='165266854', count=2008),
 Row(dunsnumber='878069798', count=2006),
 Row(dunsnumber='779908334', count=2004),
 Row(dunsnumber='795463553', count=2003),
 ...]

In [14]:
agencyCounts = df.groupBy(['dunsnumber','fundingrequestingagencyid']).count()

In [15]:
agencyCounts.first()


Out[15]:
Row(dunsnumber='121547657', fundingrequestingagencyid='7022: FEDERAL EMERGENCY MANAGEMENT AGENCY', count=74)

In [20]:
from pyspark.ml.feature import StringIndexer

vindexer = StringIndexer(inputCol="dunsnumber", outputCol="dunsIndex")

In [24]:
indexer = vindexer.fit(agencyCounts)

In [25]:
agencyCountsWithIndex = indexer.transform(agencyCounts)

In [28]:
agencyCountsWithIndex.first()

In [ ]: