{"id":"https://openalex.org/W4410431566","doi":"https://doi.org/10.21105/joss.07932","title":"ParquetDB: A Lightweight Python Parquet-Based Database","display_name":"ParquetDB: A Lightweight Python Parquet-Based Database","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4410431566","doi":"https://doi.org/10.21105/joss.07932"},"language":"en","primary_location":{"id":"doi:10.21105/joss.07932","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.07932","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.07932.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://joss.theoj.org/papers/10.21105/joss.07932.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061855965","display_name":"Logan Lang","orcid":"https://orcid.org/0000-0003-2867-1706"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Logan L. Lang","raw_affiliation_strings":["Department of Physics, West Virginia University, Morgantown, United States"],"raw_orcid":"https://orcid.org/0000-0003-2867-1706","affiliations":[{"raw_affiliation_string":"Department of Physics, West Virginia University, Morgantown, United States","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066323617","display_name":"Eduardo Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-1164-2856"},"institutions":[{"id":"https://openalex.org/I4210118429","display_name":"Instituto de Ciencia de Materiales de Madrid","ror":"https://ror.org/02qqy8j09","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210118429"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo R. Hernandez","raw_affiliation_strings":["Instituto de Ciencia de Materiales de Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1164-2856","affiliations":[{"raw_affiliation_string":"Instituto de Ciencia de Materiales de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I4210118429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019215236","display_name":"Kamal Choudhary","orcid":"https://orcid.org/0000-0001-9737-8074"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamal Choudhary","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, United States"],"raw_orcid":"https://orcid.org/0000-0001-9737-8074","affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, United States","institution_ids":["https://openalex.org/I1321296531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064664549","display_name":"A. Romero","orcid":"https://orcid.org/0000-0001-5968-0571"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aldo H. Romero","raw_affiliation_strings":["Department of Physics, West Virginia University, Morgantown, United States"],"raw_orcid":"https://orcid.org/0000-0001-5968-0571","affiliations":[{"raw_affiliation_string":"Department of Physics, West Virginia University, Morgantown, United States","institution_ids":["https://openalex.org/I12097938"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061855965"],"corresponding_institution_ids":["https://openalex.org/I12097938"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10298325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"109","first_page":"7932","last_page":"7932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9926000237464905,"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":0.9926000237464905,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13681","display_name":"Engineering and Information Technology","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/python","display_name":"Python (programming language)","score":0.9434847235679626},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6481177806854248},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6437729597091675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5125696659088135}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.9434847235679626},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6481177806854248},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6437729597091675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5125696659088135}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21105/joss.07932","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.07932","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.07932.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21105/joss.07932","is_oa":true,"landing_page_url":"https://doi.org/10.21105/joss.07932","pdf_url":"https://joss.theoj.org/papers/10.21105/joss.07932.pdf","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1693976111","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2284220777","display_name":null,"funder_award_id":"OAC-2117575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G2815302120","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G3339971651","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G3406661761","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4248962021","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G4559496704","display_name":"MRI: Acquisition of Dolly Sods GPU Cluster for Accelerated High-Performance Computing and Applications in Machine Learning and Artificial Intelligence in West Virginia","funder_award_id":"2117575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5212984984","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G586857820","display_name":null,"funder_award_id":"501100011033/FEDER","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6071709581","display_name":null,"funder_award_id":"13039/501100011033/","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6115906668","display_name":null,"funder_award_id":"80NSSC22M0173","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G6121277264","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G6128126499","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6965887028","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G7187228201","display_name":null,"funder_award_id":"23-007","funder_id":"https://openalex.org/F4320317258","funder_display_name":"West Virginia Higher Education Policy Commission"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7713225158","display_name":null,"funder_award_id":"80NSSC22M0173","funder_id":"https://openalex.org/F4320317258","funder_display_name":"West Virginia Higher Education Policy Commission"},{"id":"https://openalex.org/G8174472116","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320314505","display_name":"State Council of Higher Education for Virginia","ror":"https://ror.org/058gp5587"},{"id":"https://openalex.org/F4320317258","display_name":"West Virginia Higher Education Policy Commission","ror":"https://ror.org/01yaers16"},{"id":"https://openalex.org/F4320322037","display_name":"Nuclear Safety and Security Commission","ror":"https://ror.org/05qk3ge34"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320338283","display_name":"Office of Experimental Program to Stimulate Competitive Research","ror":"https://ror.org/04k9mqs78"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410431566.pdf","grobid_xml":"https://content.openalex.org/works/W4410431566.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W186032443","https://openalex.org/W2605380649","https://openalex.org/W4407373391"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"ParquetDB":[0],"is":[1,154,160],"a":[2,7,62],"Python":[3,119],"library":[4],"serving":[5],"as":[6,71],"\"middleware\"":[8],"solution,":[9],"bridging":[10],"the":[11,26,36,50],"gap":[12],"between":[13],"file-based":[14],"storage":[15,88],"and":[16,41,49,54,97,137],"full":[17],"database":[18,152],"systems.A":[19],"key":[20],"driver":[21],"for":[22,66,147],"its":[23,57,145],"development":[24],"was":[25,61],"need":[27],"to":[28,38,52,125],"support":[29],"iterative":[30],"research":[31],"workflows,":[32],"requiring":[33],"schema":[34],"evolvability,":[35],"ability":[37,51],"manage":[39],"complex":[40,113],"evolving":[42],"nested":[43,117],"data":[44,114,122],"structures":[45],"without":[46,100],"predefined":[47],"rigidity,":[48],"handle-table":[53],"field-level":[55],"metadata.Additionally,":[56],"\"classically":[58],"serverless\"":[59],"nature":[60],"crucial":[63],"design":[64],"point":[65],"deployment":[67],"in":[68,106],"environments":[69],"such":[70],"HPC":[72],"clusters":[73],"with":[74,90],"limited":[75],"connectivity.Leveraging":[76],"Apache":[77,81],"Parquet":[78],"(\"Parquet,\"":[79],"n.d.;":[80],"Software":[82],"Foundation,":[83],"n.d.),":[84],"it":[85],"combines":[86],"file":[87,127,158],"portability":[89],"advanced":[91],"querying":[92],"capabilities,":[93],"enabling":[94],"efficient":[95],"compression":[96],"read":[98],"performance":[99,140],"dedicated":[101],"server":[102],"overhead.ParquetDB":[103],"addresses":[104],"limitations":[105],"both":[107],"traditional":[108],"approaches":[109],"by":[110],"seamlessly":[111],"handling":[112],"types":[115],"(arrays,":[116],"structures,":[118],"objects),":[120],"simplifying":[121],"interaction":[123],"compared":[124],"direct":[126],"manipulation":[128],"or":[129],"manual":[130],"serialization.Performance":[131],"benchmarks":[132],"show":[133],"competitive":[134],"read/write":[135],"speeds":[136],"effective":[138],"query":[139],"via":[141],"predicate":[142],"pushdown,":[143],"demonstrating":[144],"utility":[146],"managing":[148],"medium-to-large":[149],"datasets":[150],"where":[151],"complexity":[153],"unwarranted":[155],"but":[156],"basic":[157],"I/O":[159],"insufficient.":[161]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
