{"id":"https://openalex.org/W2948897128","doi":"https://doi.org/10.1145/3299869.3320210","title":"Unit Testing Data with Deequ","display_name":"Unit Testing Data with Deequ","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948897128","doi":"https://doi.org/10.1145/3299869.3320210","mag":"2948897128"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3320210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3320210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["Amazon Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Research, New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024953386","display_name":"Felix Bie\u00dfmann","orcid":"https://orcid.org/0000-0002-3422-1026"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Biessmann","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070190076","display_name":"Dustin Lange","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dustin Lange","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027386823","display_name":"Tammo Rukat","orcid":"https://orcid.org/0000-0002-6186-0077"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tammo Rukat","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086741151","display_name":"Phillipp Schmidt","orcid":"https://orcid.org/0000-0002-3058-0582"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Phillipp Schmidt","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054547456","display_name":"Stephan Seufert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stephan Seufert","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028967481","display_name":"Pierre Brunelle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pierre Brunelle","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010036219","display_name":"Andrey Taptunov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrey Taptunov","raw_affiliation_strings":["Amazon Research, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon Research, Berlin, Germany","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5090934117"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2687,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88523631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1993","last_page":"1996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8035656213760376},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.583381175994873},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5778969526290894},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5474057197570801},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5417582988739014},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5329001545906067},{"id":"https://openalex.org/keywords/unit-testing","display_name":"Unit testing","score":0.512458860874176},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5042539834976196},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.45019224286079407},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41345125436782837},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3776666522026062},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3524585962295532},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3244026303291321},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16557732224464417},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10660046339035034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035656213760376},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.583381175994873},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5778969526290894},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5474057197570801},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5417582988739014},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5329001545906067},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.512458860874176},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5042539834976196},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.45019224286079407},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41345125436782837},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3776666522026062},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3524585962295532},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3244026303291321},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16557732224464417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10660046339035034},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299869.3320210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3320210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2038412523","https://openalex.org/W2119803607","https://openalex.org/W2167036165","https://openalex.org/W2189162242","https://openalex.org/W2613597870","https://openalex.org/W2753069234","https://openalex.org/W2926314329"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W2270762093","https://openalex.org/W4200551113","https://openalex.org/W4255072332","https://openalex.org/W2028861106","https://openalex.org/W3126834064","https://openalex.org/W1754154538","https://openalex.org/W3169246587","https://openalex.org/W4253714063","https://openalex.org/W2984010599"],"abstract_inverted_index":{"Modern":[0],"companies":[1],"and":[2,52,74,109,131,149],"institutions":[3],"rely":[4],"on":[5,159],"data":[6,33,124,163,170],"to":[7,76,85,122,133,141,144,154,166],"guide":[8],"every":[9],"single":[10],"decision.":[11],"Missing":[12],"or":[13],"incorrect":[14],"information":[15],"seriously":[16],"compromises":[17],"any":[18],"decision":[19],"process.":[20],"We":[21,118],"demonstrate":[22,139],"\"Deequ\",":[23],"an":[24],"Apache":[25],"Spark-based":[26],"library":[27,38],"for":[28,57],"automating":[29],"the":[30,66,83,169],"verification":[31],"of":[32,68,80,100,152,162],"quality":[34,46,164],"at":[35,72],"scale.":[36],"This":[37],"provides":[39],"a":[40,95,106,113],"declarative":[41],"API,":[42],"which":[43],"combines":[44],"common":[45],"constraints":[47,84,130],"with":[48,78],"user-defined":[49],"validation":[50],"code,":[51],"thereby":[53],"enables":[54],"\"unit":[55],"tests":[56,126],"data\".":[58],"Deequ":[59,143],"is":[60,110],"available":[61],"as":[62],"open":[63],"source,":[64],"meets":[65],"requirements":[67],"production":[69],"use":[70,98],"cases":[71],"Amazon,":[73],"scales":[75],"datasets":[77],"billions":[79],"records":[81],"if":[82],"evaluate":[86],"are":[87],"chosen":[88],"carefully.":[89],"Our":[90],"demonstration":[91],"walks":[92],"attendees":[93,120],"through":[94],"fictitious":[96],"business":[97],"case":[99],"validating":[101],"daily":[102],"product":[103],"reviews":[104],"from":[105,127],"public":[107],"dataset,":[108],"executed":[111],"in":[112],"proprietary":[114],"interactive":[115],"notebook":[116],"environment.":[117],"show":[119],"how":[121,132,140,153],"define":[123],"unit":[125],"automatically":[128],"suggested":[129],"create":[134],"customized":[135],"tests.":[136],"Additionally,":[137],"we":[138],"apply":[142],"validate":[145],"incrementally":[146],"growing":[147],"datasets,":[148],"give":[150],"examples":[151],"configure":[155],"anomaly":[156],"detection":[157],"algorithms":[158],"time":[160],"series":[161],"metrics":[165],"further":[167],"automate":[168],"validation.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}