Package: bstrl 1.0.2

bstrl: Bayesian Streaming Record Linkage

Perform record linkage on streaming files using recursive Bayesian updating.

Authors:Brenda Betancourt [aut], Andee Kaplan [aut], Ian Taylor [aut, cre]

# Install 'bstrl' in R:

install.packages('bstrl', repos = c('https://ianmtaylor1.r-universe.dev', 'https://cloud.r-project.org'))

Datasets:

On CRAN:

Last updated from:00872f4aa5. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel	OK	98
source / vignettes	OK	217
linux-release	OK	100
macos-release	OK	157
macos-oldrel	OK	194
windows-devel	OK	78
windows-release	OK	83
windows-oldrel	OK	64
wasm-release	OK	81

Last update: 2022-11-07
Started: 2022-08-02

Help page	Topics
Return a list of all linked pairs (directly or transitively)	alllinks
Perform baseline bipartite record linkage before streaming updates	bipartiteRL
Extract the links from a bstrlstate object into a list of streaminglinks objects.	extractlinks
Create a streaming link object from known record entity id's	fromentities
Simulated Noisy Records	geco_30over_3err
Simulated Noisy Records (smaller set)	geco_small
Example linkage result object for small dataset	geco_small_result
Return True/False whether the two record are coreferent	islinked
Perform multifile record linkage via Gibbs sampling "from scratch"	multifileRL
Perform a PPRB update of record linkage with a new file	PPRBupdate
Calculate the precision of estimated links relative to true links	precision
Calculate the recall of estimated links relative to true links	recall
Perform an SMCMC update of record linkage with a new file	SMCMCupdate
Thin a bstrlstate object	thinsamples