{"id":"https://openalex.org/W2963049780","doi":"https://doi.org/10.1145/3331076.3331110","title":"Chi squared feature selection over Apache Spark","display_name":"Chi squared feature selection over Apache Spark","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963049780","doi":"https://doi.org/10.1145/3331076.3331110","mag":"2963049780"},"language":"en","primary_location":{"id":"doi:10.1145/3331076.3331110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331076.3331110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Database Applications & Engineering Symposium on   - IDEAS '19","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/A5043344581","display_name":"Mohamed Nassar","orcid":"https://orcid.org/0000-0001-8857-4436"},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Mohamed Nassar","raw_affiliation_strings":["American University of Beirut (AUB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB)","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108526386","display_name":"Ha\u0131\u0308dar Safa","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Haidar Safa","raw_affiliation_strings":["American University of Beirut (AUB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB)","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085788792","display_name":"Alaa Al Mutawa","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Alaa Al Mutawa","raw_affiliation_strings":["American University of Beirut (AUB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB)","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016430217","display_name":"Helal Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Ahmed Helal","raw_affiliation_strings":["American University of Beirut (AUB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB)","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040626441","display_name":"Iskander Gaba","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Iskander Gaba","raw_affiliation_strings":["American University of Beirut (AUB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut (AUB)","institution_ids":["https://openalex.org/I98635879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4338,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.71616065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9983000159263611,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9941999912261963,"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/feature-selection","display_name":"Feature selection","score":0.7257522344589233},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7080972790718079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6283343434333801},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5704883337020874},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5454862117767334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45768558979034424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.355247437953949},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07810142636299133}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7257522344589233},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7080972790718079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283343434333801},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5704883337020874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5454862117767334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45768558979034424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.355247437953949},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07810142636299133},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3331076.3331110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331076.3331110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Database Applications & Engineering Symposium on   - IDEAS '19","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3737756367","display_name":null,"funder_award_id":"URB-AUB-2018/2019","funder_id":"https://openalex.org/F4320309999","funder_display_name":"American University of Beirut"}],"funders":[{"id":"https://openalex.org/F4320309999","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21"},{"id":"https://openalex.org/F4320336463","display_name":"University Research Board, American University of Beirut","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1993320880","https://openalex.org/W2038412523","https://openalex.org/W2216541755","https://openalex.org/W2294884429","https://openalex.org/W2295764711","https://openalex.org/W2435251607","https://openalex.org/W2484802798","https://openalex.org/W2521265831","https://openalex.org/W2542459869","https://openalex.org/W2620834380","https://openalex.org/W2800545970","https://openalex.org/W2949941707"],"related_works":["https://openalex.org/W4307883119","https://openalex.org/W2345184372","https://openalex.org/W2374344280","https://openalex.org/W2159220931","https://openalex.org/W2013349038","https://openalex.org/W2015538044","https://openalex.org/W27971500","https://openalex.org/W2316780152","https://openalex.org/W2052253960","https://openalex.org/W2480412556"],"abstract_inverted_index":{"We":[0,174,187],"live":[1],"in":[2,42,66,89,103,123,176],"the":[3,87,104,112,130,133,143,147,189,194,197,207],"age":[4],"of":[5,29,36,47,71,84,86,115,132,157,180,193,200],"big":[6],"data":[7,88,195],"and":[8,68,74,91,196],"distributed":[9],"computing.":[10],"The":[11,152],"current":[12],"large":[13],"scale":[14],"computation":[15],"frameworks":[16,38],"are":[17,204],"based":[18],"on":[19],"a":[20,27,54,63,69,82,101],"scaling-out":[21],"approach":[22],"for":[23,171],"distributing":[24],"tasks":[25],"over":[26,51,206],"cluster":[28,72],"commodity":[30],"machines.":[31],"Apache":[32],"Spark":[33,52,148,153],"is":[34,53,78,98,120,140,168],"one":[35],"these":[37],"that":[39],"has":[40],"excelled":[41],"many":[43],"computational":[44],"tasks.":[45],"Implementation":[46],"statistical":[48],"learning":[49,125,137,150],"algorithms":[50],"challenging":[55],"task.":[56],"A":[57],"bad":[58],"implementation":[59,128,156,167],"may":[60],"lead":[61],"to":[62,81,100],"significant":[64],"decrease":[65],"performance":[67,77],"waste":[70],"time":[73],"money.":[75],"Poor":[76],"mostly":[79],"due":[80,99],"lack":[83],"understanding":[85],"hand":[90],"Spark's":[92],"underlying":[93],"mechanisms":[94],"more":[95,169],"than":[96,142],"it":[97],"deficit":[102],"framework":[105],"itself.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110],"consider":[111],"use":[113],"case":[114],"X2":[116,158],"feature":[117,159],"selection":[118,160],"which":[119,139],"very":[121],"popular":[122],"supervised":[124],"pipelines.":[126],"Our":[127,165,202],"follows":[129],"algorithm":[131,144],"Scikit-learn":[134],"Python":[135],"machine":[136,149],"library":[138,155],"different":[141],"used":[145],"by":[146],"library.":[151],"ML":[154],"accepts":[161],"only":[162],"categorical":[163],"features.":[164,173],"alternative":[166],"suitable":[170],"numerical":[172],"experiment":[175],"particular":[177],"with":[178],"features":[179],"high":[181],"sparsity":[182],"such":[183],"as":[184],"n-gram":[185],"counts.":[186],"study":[188],"best":[190],"partitioning":[191],"scheme":[192],"optimal":[198],"number":[199],"partitions.":[201],"experiments":[203],"run":[205],"Databricks":[208],"platform.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}