{"id":"https://openalex.org/W2443893970","doi":"https://doi.org/10.1145/2882903.2903740","title":"SparkR","display_name":"SparkR","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2443893970","doi":"https://doi.org/10.1145/2882903.2903740","mag":"2443893970"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2903740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2903740","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2903740&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2903740&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082710354","display_name":"Shivaram Venkataraman","orcid":"https://orcid.org/0000-0001-9575-7935"},"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":"Shivaram Venkataraman","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"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/A5103011963","display_name":"Zongheng Yang","orcid":"https://orcid.org/0000-0001-8716-8743"},"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":"Zongheng Yang","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"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/A5049060330","display_name":"Davies Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davies Liu","raw_affiliation_strings":["Databricks Inc., San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064891668","display_name":"Eric Liang","orcid":"https://orcid.org/0000-0002-3760-6845"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Liang","raw_affiliation_strings":["Databricks Inc, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc, San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057382362","display_name":"Hossein Falaki","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hossein Falaki","raw_affiliation_strings":["Databricks Inc., San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062292480","display_name":"Xiangrui Meng","orcid":"https://orcid.org/0000-0002-2628-9960"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangrui Meng","raw_affiliation_strings":["Databricks Inc., San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reynold Xin","raw_affiliation_strings":["Databricks Inc., San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035859","display_name":"Ali Ghodsi","orcid":"https://orcid.org/0000-0003-1866-246X"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Ghodsi","raw_affiliation_strings":["Databricks Inc., San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090643027","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0001-9600-4150"},"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 Franklin","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"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/A5041920173","display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]},{"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":"Ion Stoica","raw_affiliation_strings":["UC Berkeley &amp; Databricks Inc., Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley &amp; Databricks Inc., Berkeley, USA","institution_ids":["https://openalex.org/I4401726825","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Massachusetts Institute of Technology &amp; Databricks Inc., Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology &amp; Databricks Inc., Boston, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1099","last_page":"1104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9969000220298767,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9940999746322632,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8689887523651123},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7353255152702332},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7072238326072693},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6154894232749939},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5649450421333313},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5094459652900696},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4445019066333771},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38067102432250977},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26663002371788025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689887523651123},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7353255152702332},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7072238326072693},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6154894232749939},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5649450421333313},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5094459652900696},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4445019066333771},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38067102432250977},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26663002371788025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2903740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2903740","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2903740&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2882903.2903740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2882903.2903740","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2903740&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4654920669","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320332169","funder_display_name":"Directorate for Computer and Information Science and Engineering"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G579401873","display_name":null,"funder_award_id":"NSF CISE Expeditions Award CCF-1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G589244659","display_name":null,"funder_award_id":"XData Award FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6398089940","display_name":"Making Sense at Scale with Algorithms, Machines, and People","funder_award_id":"1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7103680314","display_name":null,"funder_award_id":"FA8750-12-2-0331","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7891692621","display_name":null,"funder_award_id":"SN10040 DE-SC0012463","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G900736768","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320312638","display_name":"Thomas and Stacey Siebel Foundation","ror":null},{"id":"https://openalex.org/F4320316505","display_name":"NetApp","ror":"https://ror.org/05c4cm338"},{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null},{"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"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2443893970.pdf","grobid_xml":"https://content.openalex.org/works/W2443893970.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1448681276","https://openalex.org/W1973262089","https://openalex.org/W2003281274","https://openalex.org/W2013373704","https://openalex.org/W2020199039","https://openalex.org/W2030623053","https://openalex.org/W2038412523","https://openalex.org/W2051685933","https://openalex.org/W2095430247","https://openalex.org/W2097360283","https://openalex.org/W2102458936","https://openalex.org/W2118447204","https://openalex.org/W2121810937","https://openalex.org/W2131975293","https://openalex.org/W2138542364","https://openalex.org/W2139072600","https://openalex.org/W2256629785","https://openalex.org/W2342249984","https://openalex.org/W2394680079","https://openalex.org/W2582743722","https://openalex.org/W4294541781","https://openalex.org/W4399570526","https://openalex.org/W4399590352","https://openalex.org/W4399648541"],"related_works":["https://openalex.org/W3015859229","https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049","https://openalex.org/W2792181990"],"abstract_inverted_index":{"R":[0,25,31,53,76],"is":[1,26,33],"a":[2,8,45,57],"popular":[3],"statistical":[4],"programming":[5],"language":[6],"with":[7],"number":[9],"of":[10,84,98,102],"extensions":[11],"that":[12,42,55],"support":[13],"data":[14,22,40,72],"processing":[15],"and":[16,36,62,95],"machine":[17],"learning":[18],"tasks.":[19],"However,":[20],"interactive":[21],"analysis":[23,73],"in":[24,44],"usually":[27],"limited":[28],"as":[29],"the":[30,75,80,88,99],"runtime":[32],"single":[34,46],"threaded":[35],"can":[37],"only":[38],"process":[39],"sets":[41],"fit":[43],"machine's":[47],"memory.":[48],"We":[49,78],"present":[50,96],"SparkR,":[51,85],"an":[52],"package":[54],"provides":[56],"frontend":[58],"to":[59,68],"Apache":[60],"Spark":[61],"uses":[63],"Spark's":[64],"distributed":[65],"computation":[66,94],"engine":[67],"enable":[69],"large":[70],"scale":[71],"from":[74],"shell.":[77],"describe":[79],"main":[81],"design":[82],"goals":[83],"discuss":[86],"how":[87],"high-level":[89],"DataFrame":[90],"API":[91],"enables":[92],"scalable":[93],"some":[97],"key":[100],"details":[101],"our":[103],"implementation.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-06-24T00:00:00"}
