{"id":"https://openalex.org/W3143356065","doi":"https://doi.org/10.1145/3448016.3457330","title":"DataPrep.EDA: Task-Centric Exploratory Data Analysis for Statistical Modeling in Python","display_name":"DataPrep.EDA: Task-Centric Exploratory Data Analysis for Statistical Modeling in Python","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3143356065","doi":"https://doi.org/10.1145/3448016.3457330","mag":"3143356065"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457330","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457330","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457330","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jinglin Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jinglin Peng","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiyuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiyuan Wu","raw_affiliation_strings":["Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Brandon Lockhart","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brandon Lockhart","raw_affiliation_strings":["Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Song Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Bian","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Nathan Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Nathan Yan","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linghao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Linghao Xu","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhixuan Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhixuan Chi","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jeffrey M. Rzeszotarski","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey M. Rzeszotarski","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jiannan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":1.8453,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.87264768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2271","last_page":"2280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13398","display_name":"Data Analysis with R","score":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7479000091552734},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.560699999332428},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.5514000058174133},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4763000011444092},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3978999853134155},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.39590001106262207},{"id":"https://openalex.org/keywords/data-exploration","display_name":"Data exploration","score":0.3637999892234802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285999894142151},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7479000091552734},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32019999623298645},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C64260653","wikidata":"https://www.wikidata.org/wiki/Q1194864","display_name":"Electronic design automation","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3448016.3457330","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457330","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457330","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.00841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00841","pdf_url":"https://arxiv.org/pdf/2104.00841","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3448016.3457330","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457330","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457330","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4318706298","display_name":null,"funder_award_id":"IIS-1850195","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4945104495","display_name":null,"funder_award_id":"Accelerate Grant","funder_id":"https://openalex.org/F4320322675","funder_display_name":"Mitacs"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3143356065.pdf","grobid_xml":"https://content.openalex.org/works/W3143356065.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1617242785","https://openalex.org/W2011301426","https://openalex.org/W2113411758","https://openalex.org/W2232417456","https://openalex.org/W2337337754","https://openalex.org/W2592469568","https://openalex.org/W2793630790","https://openalex.org/W2795226127","https://openalex.org/W2809353149","https://openalex.org/W2886887279","https://openalex.org/W2946535156","https://openalex.org/W2962841871","https://openalex.org/W3084638819","https://openalex.org/W6676014748"],"related_works":[],"abstract_inverted_index":{"Exploratory":[0],"Data":[1],"Analysis":[2],"(EDA)":[3],"is":[4,34,40,52,174],"a":[5,65,79,89,95],"crucial":[6],"step":[7],"in":[8,19,70,85,155,165],"any":[9],"data":[10,21,74,128],"science":[11],"project.":[12],"However,":[13],"existing":[14],"Python":[15],"libraries":[16],"fall":[17],"short":[18],"supporting":[20],"scientists":[22,75],"to":[23,54,76,99,106,125,138,146],"complete":[24],"common":[25],"EDA":[26,58,68,83,132,153,178],"tasks":[27,84,133],"for":[28,42,131],"statistical":[29],"modeling.":[30],"Their":[31],"API":[32],"design":[33],"either":[35],"too":[36,48],"low":[37],"level,":[38,50],"which":[39,51],"optimized":[41],"plotting":[43],"rather":[44],"than":[45],"EDA,":[46],"or":[47],"high":[49],"hard":[53],"specify":[55,78],"more":[56],"fine-grained":[57],"tasks.":[59],"In":[60,115],"response,":[61],"we":[62,117],"propose":[63,103],"DataPrep.EDA,":[64,101],"novel":[66],"task-centric":[67],"system":[69,154],"Python.":[71,156],"DataPrep.EDA":[72,148,161,173],"allows":[73],"declaratively":[77],"wide":[80],"range":[81],"of":[82,97,112,167,180],"different":[86],"granularity":[87],"with":[88,149],"single":[90],"function":[91],"call.":[92],"We":[93,142],"identify":[94],"number":[96],"challenges":[98],"implement":[100],"and":[102,134,170],"effective":[104],"solutions":[105],"improve":[107],"the":[108,113,127,140,151],"scalability,":[109],"usability,":[110],"customizability":[111],"system.":[114],"particular,":[116],"discuss":[118],"some":[119],"lessons":[120],"learned":[121],"from":[122],"using":[123],"Dask":[124],"build":[126],"processing":[129],"pipelines":[130],"describe":[135],"our":[136],"approaches":[137],"accelerate":[139],"pipelines.":[141],"conduct":[143],"extensive":[144],"experiments":[145,158],"compare":[147],"Pandas-profiling,":[150],"state-of-the-art":[152],"The":[157],"show":[159],"that":[160],"significantly":[162],"outperforms":[163],"Pandas-profiling":[164],"terms":[166],"both":[168],"speed":[169],"user":[171],"experience.":[172],"open-sourced":[175],"as":[176],"an":[177],"component":[179],"DataPrep:":[181],"https://github.com/sfu-db/dataprep.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2021-04-13T00:00:00"}