Package | Description |
---|---|
org.apache.solr.ltr |
This package contains the main logic for performing the reranking using
a Learning to Rank model.
|
Modifier and Type | Method and Description |
---|---|
static LTRScoringQuery.FeatureInfo[] |
LTRRescorer.extractFeaturesInfo(LTRScoringQuery.ModelWeight modelWeight,
int docid,
Float originalDocScore,
List<LeafReaderContext> leafContexts) |
LTRScoringQuery.FeatureInfo[] |
LTRScoringQuery.ModelWeight.getFeaturesInfo() |
Modifier and Type | Method and Description |
---|---|
boolean |
FeatureLogger.log(int docid,
LTRScoringQuery scoringQuery,
SolrIndexSearcher searcher,
LTRScoringQuery.FeatureInfo[] featuresInfo)
Log will be called every time that the model generates the feature values
for a document and a query.
|
abstract String |
FeatureLogger.makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo) |
String |
CSVFeatureLogger.makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo) |
Copyright © 2000-2019 Apache Software Foundation. All Rights Reserved.