RecordLinkage (version 0.2-0)

epiClassify: Classify record pairs with EpiLink weights

Description

Classifies record pairs as link, non-link or possible link based on weights computed by epiWeights and the thresholds passed as arguments.

Usage

epiClassify(rpairs, threshold.upper, threshold.lower = threshold.upper)

Arguments

rpairs

RecLinkData object. Record pairs to be classified.

threshold.upper

A numeric value between 0 and 1. Threshold for links.

threshold.lower

A numeric value between 0 and 1. Threshold for possible links.

Value

• A RecLinkResult object with classification results stored in component prediction, otherwise a copy of rpairs.

Details

The object rpairs must have weights calculated by epiWeights, stored in component Wdata. All record pairs with weights greater or equal threshold.upper are classified as links. Record pairs with weights smaller than threshold.upper and greater or equal threshold.lower are classified as possible links. All remaining records are classified as non-links.

See Also

epiWeights

Examples

# generate record pairs
data(RLdata500)
p=compare.dedup(RLdata500,strcmp=TRUE ,strcmpfun=levenshteinSim,
  identity=identity.RLdata500)

# calculate weights
p=epiWeights(p)

# classify and show results
summary(epiClassify(p,0.6))