dnet-dedup/dnet-pace-core/src/test/resources/eu/dnetlib/pace/config/author.fdup.conf.json

134 lines
3.3 KiB
JSON

{
"wf": {
"threshold": "0.99",
"dedupRun": "001",
"entityType": "author",
"subEntityType": "author",
"subEntityValue": "author",
"orderField": "fullname",
"queueMaxSize": "200",
"groupMaxSize": "100",
"maxChildren": "100",
"slidingWindowSize": "50",
"rootBuilder": [
"result",
"resultProject_outcome_isProducedBy",
"resultResult_publicationDataset_isRelatedTo",
"resultResult_similarity_isAmongTopNSimilarDocuments",
"resultResult_similarity_hasAmongTopNSimilarDocuments",
"resultOrganization_affiliation_isAffiliatedWith",
"resultResult_part_hasPart",
"resultResult_part_isPartOf",
"resultResult_supplement_isSupplementTo",
"resultResult_supplement_isSupplementedBy",
"resultResult_version_isVersionOf"
],
"includeChildren": "true",
"maxIterations": 20,
"idPath": "$.id"
},
"pace": {
"clustering" : [
{ "name" : "lnfi", "fields" : [ "fullname" ], "params" : {} }
],
"decisionTree": {
"start": {
"fields": [
{
"field": "orcid",
"comparator": "exactMatch",
"weight": 1.0,
"countIfUndefined": "true",
"params": {}
}
],
"threshold": 1.0,
"aggregation": "MAX",
"positive": "MATCH",
"negative": "NO_MATCH",
"undefined": "orcids",
"ignoreUndefined": "true"
},
"orcids": {
"fields": [
{
"field": "orcids",
"comparator": "stringListMatch",
"weight": 1.0,
"countIfUndefined": "true",
"params": {"type": "count"}
}
],
"threshold": 3.0,
"aggregation": "MAX",
"positive": "MATCH",
"negative": "coauthors",
"undefined": "coauthors",
"ignoreUndefined": "true"
},
"coauthors": {
"fields": [
{
"field": "coauthors",
"comparator": "authorsMatch",
"weight": 1.0,
"countIfUndefined": "true",
"params": {"type": "count"}
}
],
"threshold": 1.0,
"aggregation": "MAX",
"positive": "topicsMatch",
"negative": "NO_MATCH",
"undefined": "topicsMatch",
"ignoreUndefined": "true"
},
"topicsMatch": {
"fields": [
{
"field": "topics",
"comparator": "cosineSimilarity",
"weight": 1.0,
"countIfUndefined": "true",
"params": {}
}
],
"threshold": 1.0,
"aggregation": "MAX",
"positive": "MATCH",
"negative": "NO_MATCH",
"undefined": "NO_MATCH",
"ignoreUndefined": "false"
}
},
"model": [
{
"name": "topics",
"type": "DoubleArray",
"path": "$.topics"
},
{
"name": "fullname",
"type": "String",
"path": "$.fullname"
},
{
"name": "orcid",
"type": "String",
"path": "$.orcid"
},
{
"name": "coauthors",
"type": "List",
"path": "$.coAuthors[*].fullname"
},
{
"name": "orcids",
"type": "List",
"path": "$.coAuthors[*].orcid"
}
],
"blacklists": {},
"synonyms": {}
}
}