rows { options { stream_name: "" physical_type: PHYSICAL_STREAM_TYPE_QUADS generalized_statements: false rdf_star: false max_name_table_size: 128 max_prefix_table_size: 16 max_datatype_table_size: 16 logical_type: LOGICAL_STREAM_TYPE_DATASETS version: 2 } } rows { prefix { id: 0 value: "https://w3id.org/kpxl/ios/ds/np/" } } rows { name { id: 0 value: "RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ" } } rows { namespace { name: "this" value { prefix_id: 1 name_id: 0 } } } rows { prefix { id: 0 value: "https://w3id.org/kpxl/ios/ds/np/RAn08NC9isAMOUJCNaGrh31KHTSet2xemhzqS9YNB49hQ#" } } rows { name { id: 0 value: "" } } rows { namespace { name: "sub" value { prefix_id: 2 name_id: 0 } } } rows { prefix { id: 0 value: "http://www.nanopub.org/nschema#" } } rows { namespace { name: "np" value { prefix_id: 3 name_id: 2 } } } rows { prefix { id: 0 value: "http://purl.org/dc/terms/" } } rows { namespace { name: "dct" value { prefix_id: 4 name_id: 2 } } } rows { prefix { id: 0 value: "http://www.w3.org/1999/02/22-rdf-syntax-ns#" } } rows { namespace { name: "rdf" value { prefix_id: 5 name_id: 2 } } } rows { prefix { id: 0 value: "https://w3id.org/np/o/ntemplate/" } } rows { namespace { name: "nt" value { prefix_id: 6 name_id: 2 } } } rows { prefix { id: 0 value: "http://purl.org/nanopub/x/" } } rows { namespace { name: "npx" value { prefix_id: 7 name_id: 2 } } } rows { prefix { id: 0 value: "http://www.w3.org/2001/XMLSchema#" } } rows { namespace { name: "xsd" value { prefix_id: 8 name_id: 2 } } } rows { prefix { id: 0 value: "http://www.w3.org/2000/01/rdf-schema#" } } rows { namespace { name: "rdfs" value { prefix_id: 9 name_id: 2 } } } rows { prefix { id: 0 value: "https://orcid.org/" } } rows { namespace { name: "orcid" value { prefix_id: 10 name_id: 2 } } } rows { prefix { id: 0 value: "http://purl.org/np/" } } rows { namespace { name: "ns1" value { prefix_id: 11 name_id: 2 } } } rows { prefix { id: 0 value: "http://www.w3.org/ns/prov#" } } rows { namespace { name: "prov" value { prefix_id: 12 name_id: 2 } } } rows { prefix { id: 0 value: "http://xmlns.com/foaf/0.1/" } } rows { namespace { name: "foaf" value { prefix_id: 13 name_id: 2 } } } rows { name { id: 0 value: "hasAssertion" } } rows { name { id: 0 value: "assertion" } } rows { name { id: 0 value: "Head" } } rows { quad { s_iri { prefix_id: 1 name_id: 1 } p_iri { prefix_id: 3 name_id: 3 } o_iri { prefix_id: 2 name_id: 0 } g_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "hasProvenance" } } rows { name { id: 0 value: "provenance" } } rows { quad { p_iri { prefix_id: 3 name_id: 0 } o_iri { prefix_id: 2 name_id: 0 } } } rows { name { id: 0 value: "hasPublicationInfo" } } rows { name { id: 0 value: "pubinfo" } } rows { quad { p_iri { prefix_id: 3 name_id: 0 } o_iri { prefix_id: 2 name_id: 0 } } } rows { name { id: 0 value: "type" } } rows { name { id: 0 value: "Nanopublication" } } rows { quad { p_iri { prefix_id: 5 name_id: 0 } o_iri { prefix_id: 3 name_id: 0 } } } rows { prefix { id: 0 value: "http://id.crossref.org/issn/" } } rows { name { id: 0 value: "2451-8492" } } rows { name { id: 0 value: "title" } } rows { quad { s_iri { prefix_id: 14 name_id: 0 } p_iri { prefix_id: 4 name_id: 0 } o_literal { lex: "Data Science" } g_iri { prefix_id: 2 name_id: 4 } } } rows { prefix { id: 0 value: "https://doi.org/10.3233/" } } rows { name { id: 0 value: "DS-240059" } } rows { name { id: 0 value: "abstract" } } rows { quad { s_iri { prefix_id: 15 name_id: 14 } p_iri { prefix_id: 4 name_id: 0 } o_literal { lex: "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." } } } rows { name { id: 0 value: "date" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_literal { lex: "2024-06-26" } } } rows { name { id: 0 value: "hasPart" } } rows { name { id: 0 value: "RA0XRooQKz2A7aoP0VJLS2NKcvQv-n7RwPoYtcD4wtTPc" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_iri { prefix_id: 1 name_id: 0 } } } rows { name { id: 0 value: "isPartOf" } } rows { quad { p_iri { prefix_id: 4 name_id: 0 } o_iri { prefix_id: 14 name_id: 12 } } } rows { quad { p_iri { prefix_id: 4 name_id: 0 } o_literal { lex: "Measuring Data Drift with the Unstable Population Indicator" } } } rows { prefix { id: 0 value: "http://purl.org/spar/fabio/" } } rows { name { id: 0 value: "ResourcePaper" } } rows { quad { p_iri { prefix_id: 5 name_id: 10 } o_iri { prefix_id: 16 name_id: 20 } } } rows { name { id: 0 value: "0000-0003-2581-8370" } } rows { prefix { id: 6 value: "http://schema.org/" } } rows { name { id: 0 value: "affiliation" } } rows { prefix { id: 0 value: "https://ror.org/" } } rows { name { id: 0 value: "04dkp9463" } } rows { quad { s_iri { prefix_id: 10 name_id: 0 } p_iri { prefix_id: 6 name_id: 0 } o_iri { prefix_id: 7 name_id: 0 } } } rows { name { id: 0 value: "05xvt9f17" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "email" } } rows { quad { p_iri { prefix_id: 6 name_id: 0 } o_literal { lex: "datascience@marcelhaas.com" } } } rows { name { id: 0 value: "name" } } rows { quad { p_iri { prefix_id: 13 name_id: 0 } o_literal { lex: "Marcel R. Haas" } } } rows { name { id: 0 value: "0009-0003-5030-0108" } } rows { name { id: 0 value: "04b8v1s79" } } rows { quad { s_iri { prefix_id: 10 name_id: 0 } p_iri { prefix_id: 6 name_id: 22 } o_iri { prefix_id: 7 name_id: 28 } } } rows { quad { o_iri { prefix_id: 0 name_id: 23 } } } rows { quad { p_iri { prefix_id: 6 name_id: 25 } o_literal { lex: "L.Sibbald@tilburguniversity.edu" } } } rows { quad { p_iri { prefix_id: 13 name_id: 0 } o_literal { lex: "Lisette Sibbald" } } } rows { quad { s_iri { prefix_id: 7 name_id: 28 } o_literal { lex: "Department of Methodology and Statistics and Department of Cognitive Neuropsychology, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands" } } } rows { quad { s_iri { prefix_id: 0 name_id: 23 } o_literal { lex: "Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands" } } } rows { quad { s_iri { prefix_id: 0 name_id: 0 } o_literal { lex: "Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, The Netherlands" } } } rows { name { id: 0 value: "author-list" } } rows { name { id: 0 value: "_1" } } rows { quad { s_iri { prefix_id: 2 name_id: 29 } p_iri { prefix_id: 5 name_id: 0 } o_iri { prefix_id: 10 name_id: 21 } } } rows { name { id: 0 value: "author-list__1" } } rows { name { id: 0 value: "_2" } } rows { quad { s_iri { prefix_id: 2 name_id: 31 } p_iri { prefix_id: 5 name_id: 0 } o_iri { prefix_id: 10 name_id: 27 } } } rows { name { id: 0 value: "wasAttributedTo" } } rows { quad { s_iri { prefix_id: 2 name_id: 4 } p_iri { prefix_id: 12 name_id: 33 } o_iri { prefix_id: 10 name_id: 21 } g_iri { prefix_id: 2 name_id: 7 } } } rows { quad { o_iri { prefix_id: 10 name_id: 27 } } } rows { name { id: 0 value: "0000-0002-1267-0234" } } rows { quad { s_iri { prefix_id: 0 name_id: 34 } p_iri { prefix_id: 13 name_id: 26 } o_literal { lex: "Tobias Kuhn" } g_iri { prefix_id: 2 name_id: 9 } } } rows { quad { s_iri { prefix_id: 10 name_id: 21 } o_literal { lex: "Marcel R. Haas" } } } rows { quad { s_iri { prefix_id: 0 name_id: 27 } o_literal { lex: "Lisette Sibbald" } } } rows { quad { s_iri { prefix_id: 2 name_id: 29 } p_iri { prefix_id: 5 name_id: 0 } o_iri { prefix_id: 10 name_id: 21 } } } rows { quad { p_iri { prefix_id: 5 name_id: 32 } o_iri { prefix_id: 10 name_id: 27 } } } rows { name { id: 0 value: "sig" } } rows { prefix { id: 0 value: "http://purl.org/nanopub/x/" } } rows { name { id: 0 value: "hasAlgorithm" } } rows { quad { s_iri { prefix_id: 2 name_id: 35 } p_iri { prefix_id: 8 name_id: 0 } o_literal { lex: "RSA" } } } rows { name { id: 0 value: "hasPublicKey" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_literal { lex: "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCjDGQCS1S+SRnERDuYDXOugdYUP0efEquHJEEHAbU/uLzBVlga89zqrNPCS7fBE6lArBUWEmT8eLKdMapyqvAzI1J3jUWTMhDJF+XFBkUiuiFfNSc4vJJcmi0yujtnuzXsRIG202jyaP4f5ULoskFwaZOSBZJfiE0dsB3D7DTIAQIDAQAB" } } } rows { name { id: 0 value: "hasSignature" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_literal { lex: "Ox+5X6nHLumNtHd4Ka2ICEWhUX+v6KVWn4UKDEEAixySaGj9TJt/mBFpssxtxcrM29g070GCs1SakxQ2Re3c6lUEEkHh/E4MLDc9ReR2vZoLi2oUzJfKzWC+WuTjML12q88gZUw9uoWThRpPW+j4XOn8dUrPk8DffrF/R1+Hrg8=" } } } rows { name { id: 0 value: "hasSignatureTarget" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_iri { prefix_id: 1 name_id: 1 } } } rows { name { id: 0 value: "signedBy" } } rows { quad { p_iri { prefix_id: 8 name_id: 40 } o_iri { prefix_id: 10 name_id: 34 } } } rows { name { id: 0 value: "created" } } rows { datatype { id: 0 value: "http://www.w3.org/2001/XMLSchema#dateTime" } } rows { quad { s_iri { prefix_id: 1 name_id: 1 } p_iri { prefix_id: 4 name_id: 41 } o_literal { lex: "2024-07-12T09:07:29.273Z" datatype: 1 } } } rows { name { id: 0 value: "creator" } } rows { quad { p_iri { prefix_id: 0 name_id: 0 } o_iri { prefix_id: 10 name_id: 34 } } } rows { quad { p_iri { prefix_id: 4 name_id: 19 } o_iri { prefix_id: 15 name_id: 14 } } } rows { name { id: 0 value: "license" } } rows { prefix { id: 0 value: "https://creativecommons.org/licenses/by/4.0/" } } rows { quad { p_iri { prefix_id: 4 name_id: 43 } o_iri { prefix_id: 9 name_id: 2 } } } rows { name { id: 0 value: "hasNanopubType" } } rows { name { id: 0 value: "ScholarlyWork" } } rows { quad { p_iri { prefix_id: 8 name_id: 44 } o_iri { prefix_id: 16 name_id: 0 } } } rows { prefix { id: 11 value: "https://w3id.org/kpxl/ios/ds/terms/" } } rows { name { id: 0 value: "DataScienceNanopub" } } rows { quad { o_iri { prefix_id: 11 name_id: 0 } } } rows { name { id: 0 value: "introduces" } } rows { quad { p_iri { prefix_id: 8 name_id: 0 } o_iri { prefix_id: 15 name_id: 14 } } } rows { name { id: 0 value: "supersedes" } } rows { name { id: 0 value: "RALO1noJ6z4w0bumoQuKpUVKT7HE_zagqAA8Qy4djeLg0" } } rows { quad { p_iri { prefix_id: 8 name_id: 48 } o_iri { prefix_id: 1 name_id: 0 } } } rows { name { id: 0 value: "wasCreatedAt" } } rows { prefix { id: 3 value: "https://nanodash.petapico.org/" } } rows { quad { p_iri { prefix_id: 8 name_id: 0 } o_iri { prefix_id: 3 name_id: 2 } } } rows { prefix { id: 14 value: "http://purl.org/ontology/bibo/" } } rows { name { id: 0 value: "authorList" } } rows { quad { p_iri { prefix_id: 14 name_id: 51 } o_iri { prefix_id: 2 name_id: 29 } } } rows { prefix { id: 6 value: "http://www.w3.org/2000/01/rdf-schema#" } } rows { name { id: 0 value: "label" } } rows { quad { p_iri { prefix_id: 6 name_id: 52 } o_literal { lex: "Article: Measuring Data Drift with the Unstable Population Indicator" } } } rows { prefix { id: 0 value: "https://w3id.org/np/o/ntemplate/" } } rows { name { id: 0 value: "wasCreatedFromProvenanceTemplate" } } rows { prefix { id: 12 value: "http://purl.org/np/" } } rows { name { id: 0 value: "RAi6zZAwhaJ23Hzg4lIjlPir6Take3ZQp-lS9skfBEwfQ" } } rows { quad { p_iri { prefix_id: 7 name_id: 0 } o_iri { prefix_id: 12 name_id: 0 } } } rows { name { id: 0 value: "wasCreatedFromPubinfoTemplate" } } rows { name { id: 0 value: "RAA2MfqdBCzmz9yVWjKLXNbyfBNcwsMmOqcNUxkk1maIM" } } rows { quad { p_iri { prefix_id: 7 name_id: 0 } o_iri { prefix_id: 12 name_id: 0 } } } rows { name { id: 0 value: "RAh1gm83JiG5M6kDxXhaYT1l49nCzyrckMvTzcPn-iv90" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "RAjpBMlw3owYhJUBo3DtsuDlXsNAJ8cnGeWAutDVjuAuI" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { prefix { id: 0 value: "https://w3id.org/np/" } } rows { name { id: 0 value: "RA5R_qv3VsZIrDKd8Mr37x3HoKCsKkwN5tJVqgQsKhjTE" } } rows { quad { o_iri { prefix_id: 13 name_id: 0 } } } rows { name { id: 0 value: "RAIabr2sRVJ-YOIwZRD__BVMJKnq3QtQw_mjLIGSACPAI" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "RA_JdI7pfDcyvEXLr_gper3h8egmNggeTqkJbyHrlMEdo" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "RAoWx0AJvNw-WqkGgZO4k8udNCg6kMcGZARN3DgO_5TII" } } rows { quad { o_iri { prefix_id: 0 name_id: 0 } } } rows { name { id: 0 value: "wasCreatedFromTemplate" } } rows { name { id: 0 value: "RAeQJfX3lMDqtzyddnRmlBvxSoWohzEKzsaMKWrR8K6J0" } } rows { quad { p_iri { prefix_id: 7 name_id: 0 } o_iri { prefix_id: 13 name_id: 0 } } }