{"id":"https://openalex.org/W2038412523","doi":"https://doi.org/10.1145/2723372.2742797","title":"Spark SQL","display_name":"Spark SQL","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2038412523","doi":"https://doi.org/10.1145/2723372.2742797","mag":"2038412523"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2742797","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD 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/A5073379366","display_name":"Michael Armbrust","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Armbrust","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reynold S. Xin","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023414498","display_name":"Cheng Lian","orcid":"https://orcid.org/0000-0002-9016-832X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Lian","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024496751","display_name":"Yin Huai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Huai","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049060330","display_name":"Davies Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davies Liu","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005512393","display_name":"Joseph K. Bradley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph K. Bradley","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062292480","display_name":"Xiangrui Meng","orcid":"https://orcid.org/0000-0002-2628-9960"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangrui Meng","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063315065","display_name":"Tomer Kaftan","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomer Kaftan","raw_affiliation_strings":["UC Berkeley, Berkeley, USA","UC-Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC-Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["UC Berkeley, Berkeley, USA","UC-Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC-Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035859","display_name":"Ali Ghodsi","orcid":"https://orcid.org/0000-0003-1866-246X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Ghodsi","raw_affiliation_strings":["Databricks, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, Berkeley, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Databricks, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5073379366"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":175.6169,"has_fulltext":false,"cited_by_count":1217,"citation_normalized_percentile":{"value":0.99995087,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1383","last_page":"1394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8310126662254333},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.8043004274368286},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7051259279251099},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6096904873847961},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43450629711151123},{"id":"https://openalex.org/keywords/scala","display_name":"Scala","score":0.4338029623031616},{"id":"https://openalex.org/keywords/language-integrated-query","display_name":"Language Integrated Query","score":0.43291518092155457},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.42970210313796997},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4247227907180786},{"id":"https://openalex.org/keywords/sql/psm","display_name":"SQL/PSM","score":0.424103319644928},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.36688876152038574},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3244222402572632},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16889938712120056},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.09661939740180969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310126662254333},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.8043004274368286},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7051259279251099},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6096904873847961},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43450629711151123},{"id":"https://openalex.org/C109701466","wikidata":"https://www.wikidata.org/wiki/Q460584","display_name":"Scala","level":3,"score":0.4338029623031616},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.43291518092155457},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.42970210313796997},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4247227907180786},{"id":"https://openalex.org/C167544706","wikidata":"https://www.wikidata.org/wiki/Q360842","display_name":"SQL/PSM","level":5,"score":0.424103319644928},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.36688876152038574},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3244222402572632},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16889938712120056},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.09661939740180969},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2723372.2742797","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W135863099","https://openalex.org/W1448681276","https://openalex.org/W1606121052","https://openalex.org/W1978924650","https://openalex.org/W1989017925","https://openalex.org/W1993892970","https://openalex.org/W2010150096","https://openalex.org/W2011716962","https://openalex.org/W2018030107","https://openalex.org/W2074935284","https://openalex.org/W2081182443","https://openalex.org/W2096544401","https://openalex.org/W2098935637","https://openalex.org/W2101234009","https://openalex.org/W2108350934","https://openalex.org/W2114303224","https://openalex.org/W2121810937","https://openalex.org/W2123229843","https://openalex.org/W2129603526","https://openalex.org/W2131975293","https://openalex.org/W2136202785","https://openalex.org/W2139072600","https://openalex.org/W2146635036","https://openalex.org/W2154475850","https://openalex.org/W2156000708","https://openalex.org/W2158141386","https://openalex.org/W2169724035","https://openalex.org/W2318935314","https://openalex.org/W2394680079","https://openalex.org/W6605485969","https://openalex.org/W6678385900"],"related_works":["https://openalex.org/W2047116498","https://openalex.org/W1980548249","https://openalex.org/W2348171219","https://openalex.org/W4386768611","https://openalex.org/W2614112517","https://openalex.org/W2912795851","https://openalex.org/W650213220","https://openalex.org/W2340883001","https://openalex.org/W4316658535","https://openalex.org/W2486394024"],"abstract_inverted_index":{"Spark":[0,8,24,27,50,58,84,151,161,174],"SQL":[1,25,43,59,152],"is":[2],"a":[3,76,89,122],"new":[4],"module":[5],"in":[6,49],"Apache":[7],"that":[9,80,102],"integrates":[10,81],"relational":[11,33,71],"processing":[12,34],"with":[13,22,82],"Spark's":[14],"functional":[15],"programming":[16,100,175],"API.":[17],"Built":[18],"on":[19],"our":[20],"experience":[21],"Shark,":[23],"lets":[26,42],"programmers":[28],"leverage":[29],"the":[30,98,142,170,173],"benefits":[31,171],"of":[32,97,124,145,156,160,172],"(e.g.":[35,51,126],"declarative":[36,77],"queries":[37],"and":[38,41,72,113,134,159,166],"optimized":[39],"storage),":[40],"users":[44],"call":[45],"complex":[46,143],"analytics":[47],"libraries":[48],"machine":[52,131],"learning).":[53],"Compared":[54],"to":[55,106,137],"previous":[56],"systems,":[57],"makes":[60,103],"two":[61],"main":[62],"additions.":[63],"First,":[64],"it":[65,87,104],"offers":[66],"much":[67],"tighter":[68],"integration":[69],"between":[70],"procedural":[73,83],"processing,":[74],"through":[75],"DataFrame":[78],"API":[79],"code.":[85],"Second,":[86],"includes":[88],"highly":[90],"extensible":[91],"optimizer,":[92],"Catalyst,":[93,118],"built":[94,121],"using":[95],"features":[96,125],"Scala":[99],"language,":[101],"easy":[105],"add":[107],"composable":[108],"rules,":[109],"control":[110],"code":[111],"generation,":[112],"define":[114],"extension":[115],"points.":[116],"Using":[117],"we":[119],"have":[120],"variety":[123],"schema":[127],"inference":[128],"for":[129,141],"JSON,":[130],"learning":[132],"types,":[133],"query":[135],"federation":[136],"external":[138],"databases)":[139],"tailored":[140],"needs":[144],"modern":[146],"data":[147],"analysis.":[148],"We":[149],"see":[150],"as":[153],"an":[154],"evolution":[155],"both":[157],"SQL-on-Spark":[158],"itself,":[162],"offering":[163],"richer":[164],"APIs":[165],"optimizations":[167],"while":[168],"keeping":[169],"model.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":73},{"year":2023,"cited_by_count":77},{"year":2022,"cited_by_count":75},{"year":2021,"cited_by_count":128},{"year":2020,"cited_by_count":132},{"year":2019,"cited_by_count":166},{"year":2018,"cited_by_count":195},{"year":2017,"cited_by_count":154},{"year":2016,"cited_by_count":123},{"year":2015,"cited_by_count":29}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2016-06-24T00:00:00"}