{"id":"https://openalex.org/W4285019205","doi":"https://doi.org/10.1016/j.simpa.2022.100359","title":"Categorical Attribute traNsformation Environment (CANE): A python module for categorical to numeric data preprocessing","display_name":"Categorical Attribute traNsformation Environment (CANE): A python module for categorical to numeric data preprocessing","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4285019205","doi":"https://doi.org/10.1016/j.simpa.2022.100359"},"language":"en","primary_location":{"id":"doi:10.1016/j.simpa.2022.100359","doi":"https://doi.org/10.1016/j.simpa.2022.100359","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2022.100359","pdf_url":"http://www.softwareimpacts.com/article/S2665963822000720/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.softwareimpacts.com/article/S2665963822000720/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052355746","display_name":"Lu\u00eds Miguel Matos","orcid":"https://orcid.org/0000-0001-5827-9129","observed_orcids":["https://orcid.org/0000-0001-5827-9129"]},"institutions":[{"id":"https://openalex.org/I4405252451","display_name":"Centro ALGORITMI","ror":"https://ror.org/05w8p0566","country_code":"PT","type":"education","lineage":["https://openalex.org/I4405252451"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds Miguel Matos","raw_affiliation_strings":["ALGORITMI Centre, Minho University, Guimar\u00e3es, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-5827-9129","affiliations":[{"raw_affiliation_string":"ALGORITMI Centre, Minho University, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4405252451","https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038313684","display_name":"Jo\u00e3o Azevedo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090193","display_name":"Centro de Computa\u00e7\u00e3o Gr\u00e1fica","ror":"https://ror.org/00aahnw66","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210090193"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Azevedo","raw_affiliation_strings":["EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4210090193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083173537","display_name":"Arthur Matta","orcid":"https://orcid.org/0000-0002-4902-9483","observed_orcids":["https://orcid.org/0000-0002-4902-9483"]},"institutions":[{"id":"https://openalex.org/I4210090193","display_name":"Centro de Computa\u00e7\u00e3o Gr\u00e1fica","ror":"https://ror.org/00aahnw66","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210090193"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Arthur Matta","raw_affiliation_strings":["EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4210090193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014796819","display_name":"Andre Luiz Pilastri","orcid":"https://orcid.org/0000-0002-4380-3220","observed_orcids":["https://orcid.org/0000-0002-4380-3220"]},"institutions":[{"id":"https://openalex.org/I4210090193","display_name":"Centro de Computa\u00e7\u00e3o Gr\u00e1fica","ror":"https://ror.org/00aahnw66","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210090193"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Pilastri","raw_affiliation_strings":["EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPMQ, CCG ZGDV Institute, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4210090193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077829125","display_name":"Paulo Cesar Cortez","orcid":"https://orcid.org/0000-0002-7991-2090","observed_orcids":["https://orcid.org/0000-0002-7991-2090","https://orcid.org/0000-0002-4020-3019"]},"institutions":[{"id":"https://openalex.org/I4405252451","display_name":"Centro ALGORITMI","ror":"https://ror.org/05w8p0566","country_code":"PT","type":"education","lineage":["https://openalex.org/I4405252451"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paulo Cortez","raw_affiliation_strings":["ALGORITMI Centre, Minho University, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Centre, Minho University, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I4405252451","https://openalex.org/I99682543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025777936","display_name":"Rui Mendes","orcid":"https://orcid.org/0000-0002-2433-5193","observed_orcids":["https://orcid.org/0000-0002-2433-5193"]},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Mendes","raw_affiliation_strings":["ALGORITMI Centre, Minho University, Braga, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Centre, Minho University, Braga, Portugal","institution_ids":["https://openalex.org/I99682543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052355746"],"corresponding_institution_ids":["https://openalex.org/I4405252451","https://openalex.org/I99682543"],"apc_list":{"value":250,"currency":"USD","value_usd":250},"apc_paid":{"value":250,"currency":"USD","value_usd":250},"fwci":1.1908,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.78571685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"100359","last_page":"100359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.5386000275611877,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.5386000275611877,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.20900000631809235,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.12330000102519989,"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-library","display_name":"Python library","score":0.7450000047683716},{"id":"https://openalex.org/keywords/one-hot-encoding","display_name":"one-hot encoding","score":0.7799999713897705},{"id":"https://openalex.org/keywords/inverse-document-frequency","display_name":"inverse document frequency","score":0.9490000009536743},{"id":"https://openalex.org/keywords/machine-learning-data-preparation","display_name":"machine learning data preparation","score":0.6639999747276306},{"id":"https://openalex.org/keywords/cane","display_name":"cane","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.9482009410858154},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7475212812423706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681450009346008},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6076408624649048},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5503690242767334},{"id":"https://openalex.org/C2776821462","wikidata":"https://www.wikidata.org/wiki/Q406090","display_name":"Cane","level":3,"score":0.5405920743942261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246042013168335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47598138451576233},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4612480700016022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3957335650920868},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3252262473106384},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14276397228240967},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2777108408","wikidata":"https://www.wikidata.org/wiki/Q11002","display_name":"Sugar","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.simpa.2022.100359","doi":"https://doi.org/10.1016/j.simpa.2022.100359","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2022.100359","pdf_url":"http://www.softwareimpacts.com/article/S2665963822000720/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"},{"id":"pmh:oai:repositorium.sdum.uminho.pt:1822/81434","doi":null,"is_oa":true,"landing_page_url":"http://doi.org/10.1016/j.simpa.2022.100359","pdf_url":null,"source":{"id":"https://openalex.org/S4306401240","display_name":"Reposit\u00f3riUM (Universidade do Minho)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I99682543","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/I99682543"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:repositorium.uminho.pt:1822/81434","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1822/81434","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1016/j.simpa.2022.100359","doi":"https://doi.org/10.1016/j.simpa.2022.100359","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.simpa.2022.100359","pdf_url":"http://www.softwareimpacts.com/article/S2665963822000720/pdf","source":{"id":"https://openalex.org/S4210180398","display_name":"Software Impacts","issn_l":"2665-9638","issn":["2665-9638"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Software Impacts","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1269010350","display_name":null,"funder_award_id":"NORTE-01-0247-FEDER-017497","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2913297792","display_name":"Centro de Investiga\u00e7\u00e3o ALGORITMI","funder_award_id":"UID/CEC/00319/2019","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G323769159","display_name":null,"funder_award_id":"PORTUGAL 2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3838636553","display_name":null,"funder_award_id":"-01-0247-","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4316116677","display_name":null,"funder_award_id":"NORTE2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5485649731","display_name":null,"funder_award_id":"PORTUGAL2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G96847669","display_name":null,"funder_award_id":"NORTE-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285019205.pdf","grobid_xml":"https://content.openalex.org/works/W4285019205.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2282861635","https://openalex.org/W2443960221","https://openalex.org/W2558311305","https://openalex.org/W2592128043","https://openalex.org/W2735278706","https://openalex.org/W2944664101","https://openalex.org/W2979111891","https://openalex.org/W3030891763","https://openalex.org/W3102268560","https://openalex.org/W3216883307","https://openalex.org/W4206451024","https://openalex.org/W4224288360","https://openalex.org/W4285177221","https://openalex.org/W4285718886"],"related_works":["https://openalex.org/W4387000860","https://openalex.org/W2785051855","https://openalex.org/W4402979250","https://openalex.org/W2377302194","https://openalex.org/W4312820300","https://openalex.org/W1990836268","https://openalex.org/W4399715481","https://openalex.org/W7127597638","https://openalex.org/W4240055601","https://openalex.org/W7056364739"],"abstract_inverted_index":{"Categorical":[0,67],"Attribute":[1],"traNsformation":[2],"Environment":[3],"(CANE)":[4],"is":[5,17,21,83],"a":[6,23,75],"simpler":[7,76],"but":[8],"powerful":[9],"data":[10,38,54],"categorical":[11,53,60],"preprocessing":[12],"Python":[13],"package.":[14],"The":[15],"package":[16],"valuable":[18],"since":[19],"there":[20],"currently":[22],"large":[24],"range":[25],"of":[26],"Machine":[27],"Learning":[28],"(ML)":[29],"algorithms":[30],"that":[31,90],"can":[32,91],"only":[33],"be":[34],"trained":[35],"using":[36],"numerical":[37],"(e.g.,":[39],"Deep":[40],"Learning,":[41],"Support":[42],"Vector":[43],"Machines)":[44],"and":[45,74],"several":[46,87],"real-world":[47],"ML":[48],"applications":[49],"are":[50],"associated":[51],"with":[52,86],"attributes.":[55],"Currently,":[56],"CANE":[57,81],"offers":[58],"three":[59],"to":[61],"numeric":[62],"transformation":[63],"methods,":[64],"namely:":[65],"Percentage":[66],"Pruned":[68],"(PCP),":[69],"Inverse":[70],"Document":[71],"Frequency":[72],"(IDF)":[73],"One-Hot-Encoding":[77],"method.":[78],"Additionally,":[79],"the":[80],"module":[82],"well":[84],"documented":[85],"code":[88],"examples":[89],"help":[92],"in":[93],"its":[94],"adoption":[95],"by":[96],"non":[97],"expert":[98],"users.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-12T00:00:00"}
