[ { "@graph" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ", "@type" : [ "http://www.nanopub.org/nschema#Nanopublication" ], "http://www.nanopub.org/nschema#hasAssertion" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#assertion" } ], "http://www.nanopub.org/nschema#hasProvenance" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#provenance" } ], "http://www.nanopub.org/nschema#hasPublicationInfo" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#pubinfo" } ] } ], "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#Head" }, { "@graph" : [ { "@id" : "http://id.crossref.org/issn/2451-8492", "http://purl.org/dc/terms/title" : [ { "@value" : "Data Science" } ] }, { "@id" : "https://doi.org/10.3233/DS-240059", "@type" : [ "http://purl.org/spar/fabio/ResourcePaper" ], "http://purl.org/dc/terms/abstract" : [ { "@value" : "Measuring data drift is essential in machine learning applications where model scoring (evaluation) is done on data samples that differ from those used in training. The Kullback-Leibler divergence is a common measure of shifted probability distributions, for which discretized versions are invented to deal with binned or categorical data. We present the Unstable Population Indicator, a robust, flexible and numerically stable, discretized implementation of Jeffrey's divergence, along with an implementation in a Python package that can deal with continuous, discrete, ordinal and nominal data in a variety of popular data types. We show the numerical and statistical properties in controlled experiments. It is not advised to employ a common cut-off to distinguish stable from unstable populations, but rather to let that cut-off depend on the use case." } ], "http://purl.org/dc/terms/date" : [ { "@value" : "2024-06-26" } ], "http://purl.org/dc/terms/hasPart" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RA0XRooQKz2A7aoP0VJLS2NKcvQv-n7RwPoYtcD4wtTPc" } ], "http://purl.org/dc/terms/isPartOf" : [ { "@id" : "http://id.crossref.org/issn/2451-8492" } ], "http://purl.org/dc/terms/title" : [ { "@value" : "Measuring Data Drift with the Unstable Population Indicator" } ] }, { "@id" : "https://orcid.org/0000-0003-2581-8370", "http://schema.org/affiliation" : [ { "@id" : "https://ror.org/04dkp9463" }, { "@id" : "https://ror.org/05xvt9f17" } ], "http://schema.org/email" : [ { "@value" : "datascience@marcelhaas.com" } ], "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Marcel R. Haas" } ] }, { "@id" : "https://orcid.org/0009-0003-5030-0108", "http://schema.org/affiliation" : [ { "@id" : "https://ror.org/04b8v1s79" }, { "@id" : "https://ror.org/04dkp9463" } ], "http://schema.org/email" : [ { "@value" : "L.Sibbald@tilburguniversity.edu" } ], "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Lisette Sibbald" } ] }, { "@id" : "https://ror.org/04b8v1s79", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Department of Methodology and Statistics and Department of Cognitive Neuropsychology, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands" } ] }, { "@id" : "https://ror.org/04dkp9463", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands" } ] }, { "@id" : "https://ror.org/05xvt9f17", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, The Netherlands" } ] }, { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#author-list", "http://www.w3.org/1999/02/22-rdf-syntax-ns#_1" : [ { "@id" : "https://orcid.org/0000-0003-2581-8370" } ] }, { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#author-list__1", "http://www.w3.org/1999/02/22-rdf-syntax-ns#_2" : [ { "@id" : "https://orcid.org/0009-0003-5030-0108" } ] } ], "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#assertion" }, { "@graph" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#assertion", "http://www.w3.org/ns/prov#wasAttributedTo" : [ { "@id" : "https://orcid.org/0000-0003-2581-8370" }, { "@id" : "https://orcid.org/0009-0003-5030-0108" } ] } ], "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#provenance" }, { "@graph" : [ { "@id" : "https://orcid.org/0000-0002-1267-0234", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Tobias Kuhn" } ] }, { "@id" : "https://orcid.org/0000-0003-2581-8370", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Marcel R. Haas" } ] }, { "@id" : "https://orcid.org/0009-0003-5030-0108", "http://xmlns.com/foaf/0.1/name" : [ { "@value" : "Lisette Sibbald" } ] }, { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ", "http://purl.org/dc/terms/created" : [ { "@type" : "http://www.w3.org/2001/XMLSchema#dateTime", "@value" : "2024-07-12T09:07:29.273Z" } ], "http://purl.org/dc/terms/creator" : [ { "@id" : "https://orcid.org/0000-0002-1267-0234" } ], "http://purl.org/dc/terms/isPartOf" : [ { "@id" : "https://doi.org/10.3233/DS-240059" } ], "http://purl.org/dc/terms/license" : [ { "@id" : "https://creativecommons.org/licenses/by/4.0/" } ], "http://purl.org/nanopub/x/hasNanopubType" : [ { "@id" : "http://purl.org/spar/fabio/ScholarlyWork" }, { "@id" : "https://w3id.org/kpxl/ios/ds/terms/DataScienceNanopub" } ], "http://purl.org/nanopub/x/introduces" : [ { "@id" : "https://doi.org/10.3233/DS-240059" } ], "http://purl.org/nanopub/x/supersedes" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RALO1noJ6z4w0bumoQuKpUVKT7HE_zagqAA8Qy4djeLg0" } ], "http://purl.org/nanopub/x/wasCreatedAt" : [ { "@id" : "https://nanodash.petapico.org/" } ], "http://purl.org/ontology/bibo/authorList" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#author-list" } ], "http://www.w3.org/2000/01/rdf-schema#label" : [ { "@value" : "Article: Measuring Data Drift with the Unstable Population Indicator" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromProvenanceTemplate" : [ { "@id" : "http://purl.org/np/RAi6zZAwhaJ23Hzg4lIjlPir6Take3ZQp-lS9skfBEwfQ" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromPubinfoTemplate" : [ { "@id" : "http://purl.org/np/RAA2MfqdBCzmz9yVWjKLXNbyfBNcwsMmOqcNUxkk1maIM" }, { "@id" : "http://purl.org/np/RAh1gm83JiG5M6kDxXhaYT1l49nCzyrckMvTzcPn-iv90" }, { "@id" : "http://purl.org/np/RAjpBMlw3owYhJUBo3DtsuDlXsNAJ8cnGeWAutDVjuAuI" }, { "@id" : "https://w3id.org/np/RA5R_qv3VsZIrDKd8Mr37x3HoKCsKkwN5tJVqgQsKhjTE" }, { "@id" : "https://w3id.org/np/RAIabr2sRVJ-YOIwZRD__BVMJKnq3QtQw_mjLIGSACPAI" }, { "@id" : "https://w3id.org/np/RA_JdI7pfDcyvEXLr_gper3h8egmNggeTqkJbyHrlMEdo" }, { "@id" : "https://w3id.org/np/RAoWx0AJvNw-WqkGgZO4k8udNCg6kMcGZARN3DgO_5TII" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate" : [ { "@id" : "https://w3id.org/np/RAeQJfX3lMDqtzyddnRmlBvxSoWohzEKzsaMKWrR8K6J0" } ] }, { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#author-list", "http://www.w3.org/1999/02/22-rdf-syntax-ns#_1" : [ { "@id" : "https://orcid.org/0000-0003-2581-8370" } ], "http://www.w3.org/1999/02/22-rdf-syntax-ns#_2" : [ { "@id" : "https://orcid.org/0009-0003-5030-0108" } ] }, { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#sig", "http://purl.org/nanopub/x/hasAlgorithm" : [ { "@value" : "RSA" } ], "http://purl.org/nanopub/x/hasPublicKey" : [ { "@value" : "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCjDGQCS1S+SRnERDuYDXOugdYUP0efEquHJEEHAbU/uLzBVlga89zqrNPCS7fBE6lArBUWEmT8eLKdMapyqvAzI1J3jUWTMhDJF+XFBkUiuiFfNSc4vJJcmi0yujtnuzXsRIG202jyaP4f5ULoskFwaZOSBZJfiE0dsB3D7DTIAQIDAQAB" } ], "http://purl.org/nanopub/x/hasSignature" : [ { "@value" : "Ox+5X6nHLumNtHd4Ka2ICEWhUX+v6KVWn4UKDEEAixySaGj9TJt/mBFpssxtxcrM29g070GCs1SakxQ2Re3c6lUEEkHh/E4MLDc9ReR2vZoLi2oUzJfKzWC+WuTjML12q88gZUw9uoWThRpPW+j4XOn8dUrPk8DffrF/R1+Hrg8=" } ], "http://purl.org/nanopub/x/hasSignatureTarget" : [ { "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ" } ], "http://purl.org/nanopub/x/signedBy" : [ { "@id" : "https://orcid.org/0000-0002-1267-0234" } ] } ], "@id" : "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#pubinfo" } ]