{"id":"https://openalex.org/W3008534594","doi":"https://doi.org/10.1109/bigdata47090.2019.9006303","title":"AFrame: Extending DataFrames for Large-Scale Modern Data Analysis","display_name":"AFrame: Extending DataFrames for Large-Scale Modern Data Analysis","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008534594","doi":"https://doi.org/10.1109/bigdata47090.2019.9006303","mag":"3008534594"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big 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/A5074096341","display_name":"Phanwadee Sinthong","orcid":"https://orcid.org/0009-0006-4423-3860"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Phanwadee Sinthong","raw_affiliation_strings":["Dept. of Computer Science, University of California, Irvine"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011512061","display_name":"Michael J. Carey","orcid":"https://orcid.org/0000-0003-1561-4059"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Carey","raw_affiliation_strings":["Dept. of Computer Science, University of California, Irvine"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074096341"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":3.0523,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93138706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8556270003318787},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6470641493797302},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6185158491134644},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5205315351486206},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.5035318732261658},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4959486424922943},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4872237741947174},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4569739103317261},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.44198063015937805},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3683475852012634},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33265140652656555},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32518500089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556270003318787},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6470641493797302},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6185158491134644},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5205315351486206},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.5035318732261658},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4959486424922943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4872237741947174},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4569739103317261},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44198063015937805},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3683475852012634},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33265140652656555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32518500089645386},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4099999964237213,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1520331889","https://openalex.org/W1569570229","https://openalex.org/W1964691382","https://openalex.org/W1985229168","https://openalex.org/W2038412523","https://openalex.org/W2052312648","https://openalex.org/W2088675571","https://openalex.org/W2101234009","https://openalex.org/W2119738171","https://openalex.org/W2251939518","https://openalex.org/W2256629785","https://openalex.org/W2265297126","https://openalex.org/W2342249984","https://openalex.org/W2402144811","https://openalex.org/W2443893970","https://openalex.org/W2472803348","https://openalex.org/W2542459869","https://openalex.org/W2553567329","https://openalex.org/W2804619229","https://openalex.org/W2953384591","https://openalex.org/W2963288913","https://openalex.org/W2963390429","https://openalex.org/W2966892244","https://openalex.org/W4288260411","https://openalex.org/W4295830359","https://openalex.org/W6614148910","https://openalex.org/W6633958470","https://openalex.org/W6641330010","https://openalex.org/W6675354045","https://openalex.org/W6691459498","https://openalex.org/W6703928569","https://openalex.org/W6713134421","https://openalex.org/W6747481501","https://openalex.org/W6752079579","https://openalex.org/W6766822908","https://openalex.org/W6982728064"],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W3089119258","https://openalex.org/W2514636569","https://openalex.org/W2553396476","https://openalex.org/W2519462635","https://openalex.org/W2115553997","https://openalex.org/W3154441264","https://openalex.org/W298027295","https://openalex.org/W4225748383"],"abstract_inverted_index":{"Analyzing":[0],"the":[1,13,21,56,84,126,158,163,177,184],"increasingly":[2],"large":[3],"volumes":[4],"of":[5,15,23,78,86,151,160,166],"data":[6,35,44,57,67,99,111,119,172,190],"that":[7,54,168],"are":[8],"available":[9],"today,":[10],"possibly":[11],"including":[12],"application":[14],"custom":[16],"machine":[17,90],"learning":[18,91],"models,":[19],"requires":[20],"utilization":[22],"distributed":[24,146],"frameworks.":[25],"This":[26,37,155],"can":[27],"result":[28],"in":[29,138,142],"serious":[30],"productivity":[31],"issues":[32],"for":[33,136,188],"\u201cnormal\u201d":[34],"scientists.":[36],"paper":[38,130,156],"introduces":[39,132],"AFrame,":[40,161],"a":[41,49,74,95,149],"new":[42],"scalable":[43],"analysis":[45],"package":[46],"powered":[47],"by":[48,193],"Big":[50],"Data":[51],"management":[52,100,112],"system":[53],"extends":[55],"scientists'":[58],"familiar":[59],"DataFrame":[60,87,140,195],"operations":[61,88],"to":[62,124,180],"efficiently":[63,169],"operate":[64],"on":[65,76],"managed":[66],"at":[68],"scale.":[69],"AFrame":[70,102],"is":[71],"implemented":[72],"as":[73],"layer":[75],"top":[77],"Apache":[79],"AsterixDB,":[80],"transparently":[81],"scaling":[82],"out":[83],"execution":[85],"and":[89,107,117,145,175,182,186],"model":[92],"invocation":[93],"through":[94],"parallel,":[96],"shared-nothing":[97],"big":[98],"system.":[101],"incrementally":[103],"constructs":[104],"SQL++":[105],"queries":[106],"leverages":[108],"AsterixDB's":[109],"semistructured":[110],"facilities,":[113],"user-defined":[114],"function":[115],"support,":[116],"live":[118],"ingestion":[120],"support.":[121],"In":[122],"order":[123],"evaluate":[125,181],"proposed":[127,178],"approach,":[128],"this":[129],"also":[131],"an":[133],"extensible":[134],"micro-benchmark":[135],"use":[137],"evaluating":[139],"performance":[141,185],"both":[143],"single-node":[144],"settings":[147],"via":[148],"collection":[150],"representative":[152],"analytic":[153,173],"operations.":[154],"presents":[157],"architecture":[159],"describes":[162],"underlying":[164],"capabilities":[165],"AsterixDB":[167],"support":[170,187],"modern":[171],"operations,":[174],"utilizes":[176],"benchmark":[179],"compare":[183],"largescale":[189],"analyses":[191],"provided":[192],"alternative":[194],"libraries.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}