{"id":"https://openalex.org/W3042862593","doi":"https://doi.org/10.1145/3382494.3410680","title":"A large-scale comparative analysis of Coding Standard conformance in Open-Source Data Science projects","display_name":"A large-scale comparative analysis of Coding Standard conformance in Open-Source Data Science projects","publication_year":2020,"publication_date":"2020-10-05","ids":{"openalex":"https://openalex.org/W3042862593","doi":"https://doi.org/10.1145/3382494.3410680","mag":"3042862593"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382494.3410680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.08978","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024537636","display_name":"Anj Simmons","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Andrew J. Simmons","raw_affiliation_strings":["Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012088137","display_name":"Scott Barnett","orcid":"https://orcid.org/0000-0002-3187-4937"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Scott Barnett","raw_affiliation_strings":["Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015825556","display_name":"Jessica Rivera\u2010Villicana","orcid":"https://orcid.org/0000-0003-1955-3310"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jessica Rivera-Villicana","raw_affiliation_strings":["Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027911409","display_name":"Akshat Bajaj","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Akshat Bajaj","raw_affiliation_strings":["Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030486012","display_name":"Rajesh Vasa","orcid":"https://orcid.org/0000-0003-4805-1467"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajesh Vasa","raw_affiliation_strings":["Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Applied Artificial Intelligence Inst. Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":5,"citation_normalized_percentile":{"value":0.903586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":79,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998,"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/T10260","display_name":"Software Engineering Research","score":0.9998,"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/T11675","display_name":"Open Source Software Innovations","score":0.9768,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.971,"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/maintainability","display_name":"Maintainability","score":0.4897056},{"id":"https://openalex.org/keywords/open-science","display_name":"Open Science","score":0.42971447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75306785},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.54136646},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5359493},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5241506},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.524041},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.4897056},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.486525},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46733674},{"id":"https://openalex.org/C2778149293","wikidata":"https://www.wikidata.org/wiki/Q309823","display_name":"Open science","level":2,"score":0.42971447},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1193001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10949692},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382494.3410680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2007.08978","pdf_url":"https://arxiv.org/pdf/2007.08978","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2007.08978","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2007.08978","pdf_url":"https://arxiv.org/pdf/2007.08978","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.61,"display_name":"Industry, innovation and infrastructure"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W3042862593","https://openalex.org/W3102694483"],"referenced_works_count":29,"referenced_works":["https://openalex.org/W1517055698","https://openalex.org/W1964962870","https://openalex.org/W1972386298","https://openalex.org/W1992706013","https://openalex.org/W2043662475","https://openalex.org/W2086585198","https://openalex.org/W2125359479","https://openalex.org/W2140609933","https://openalex.org/W2153887189","https://openalex.org/W2189162242","https://openalex.org/W2296669649","https://openalex.org/W2597465230","https://openalex.org/W2757656223","https://openalex.org/W2787379525","https://openalex.org/W2794111250","https://openalex.org/W2809807015","https://openalex.org/W2883626290","https://openalex.org/W2884952956","https://openalex.org/W2898514735","https://openalex.org/W2948033533","https://openalex.org/W2950500938","https://openalex.org/W2954553057","https://openalex.org/W2954683010","https://openalex.org/W2963604246","https://openalex.org/W2980119268","https://openalex.org/W2999751364","https://openalex.org/W38467096","https://openalex.org/W607824204","https://openalex.org/W782525392"],"related_works":["https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W4254960163","https://openalex.org/W4230627789","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W2100255360","https://openalex.org/W1964661231","https://openalex.org/W168761233"],"abstract_inverted_index":{"Background:":[0],"Meeting":[1],"the":[2,59,187],"growing":[3],"industry":[4],"demand":[5],"for":[6],"Data":[7,52,63,95,116,137,155,190],"Science":[8,53,64,96,105,117,138,148,156,191],"requires":[9],"cross-disciplinary":[10],"teams":[11,23],"that":[12,127,154,175],"can":[13],"translate":[14],"machine":[15],"learning":[16],"research":[17],"into":[18],"production-ready":[19],"code.":[20],"Software":[21],"engineering":[22,170,182],"value":[24],"adherence":[25],"to":[26,61,83,98,146],"coding":[27,47],"standards":[28,48,72],"as":[29],"an":[30,129],"indication":[31],"of":[32,46,92,102,111,125,132,189],"code":[33,67],"readability,":[34],"maintainability,":[35],"and":[36,78,113,134,164],"developer":[37],"expertise.":[38],"However,":[39],"there":[40],"are":[41,73,76,158,184],"no":[42],"large-scale":[43],"empirical":[44],"studies":[45],"focused":[49],"specifically":[50],"on":[51],"projects.":[54,149,192],"Aims:":[55],"This":[56],"study":[57],"investigates":[58],"extent":[60],"which":[62,71,75],"projects":[65,97,106,118,139],"follow":[66,141,167],"standards.":[68],"In":[69],"particular,":[70],"followed,":[74],"ignored,":[77],"how":[79],"does":[80],"this":[81,176],"differ":[82],"traditional":[84,161,168,180],"software":[85,162,169,181],"projects?":[86],"Method:":[87],"We":[88],"compare":[89],"a":[90,99,108,121],"corpus":[91],"1048":[93],"Open-Source":[94],"reference":[100],"group":[101],"1099":[103],"non-Data":[104,147],"with":[107],"similar":[109],"level":[110],"quality":[112],"maturity.":[114],"Results:":[115],"suffer":[119],"from":[120,160],"significantly":[122],"higher":[123],"rate":[124],"functions":[126],"use":[128],"excessive":[130],"numbers":[131],"parameters":[133],"local":[135],"variables.":[136],"also":[140],"different":[142],"variable":[143],"naming":[144],"conventions":[145,183],"Conclusions:":[150],"The":[151],"differences":[152],"indicate":[153],"codebases":[157,163],"distinct":[159],"do":[165],"not":[166],"conventions.":[171],"Our":[172],"conjecture":[173],"is":[174],"may":[177],"be":[178],"because":[179],"inappropriate":[185],"in":[186],"context":[188]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3042862593","counts_by_year":[{"year":2021,"cited_by_count":5}],"updated_date":"2025-01-16T07:21:04.809798","created_date":"2020-07-23"}