Integration with existing packages
In blocking: Various Blocking Methods for Entity Resolution

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

Setup

library(blocking)
library(reclin2)

Data

In the example we will use the same dataset as in the Blocking records for record linkage vignette.

data(census)
data(cis)
census[, x:=1:.N]
cis[, y:=1:.N]

Integration with the `reclin2` package

The package contains function pair_ann which aims at integration with reclin2 package. This function works as follows.

pair_ann(x = census[1:1000], 
         y = cis[1:1000], 
         on = c("pername1", "pername2", "sex", "dob_day", "dob_mon", "dob_year", "enumcap", "enumpc"), 
         deduplication = FALSE) |>
  head()

Which provides you information on the total number of pairs. This can be further included in the pipeline of the reclin2 package (note that we use a different ANN this time).

pair_ann(x = census[1:1000], 
         y = cis[1:1000], 
         on = c("pername1", "pername2", "sex", "dob_day", "dob_mon", "dob_year", "enumcap", "enumpc"), 
         deduplication = FALSE,
         ann = "hnsw") |>
  compare_pairs(on = c("pername1", "pername2", "sex", "dob_day", "dob_mon", "dob_year", "enumcap", "enumpc"),
                comparators = list(cmp_jarowinkler())) |>
  score_simple("score",
               on = c("pername1", "pername2", "sex", "dob_day", "dob_mon", "dob_year", "enumcap", "enumpc")) |>
  select_threshold("threshold", score = "score", threshold = 6) |>
  link(selection = "threshold") |>
  head()

Usage with `fastLink` package

Just use the block column in the function fastLink::blockData(). As a result you will obtain a list of records blocked for further processing.

Usage with `RecordLinkage` package

Just use the block column in the argument blockfld in the compare.dedup() or compare.linkage() function. Please note that block column for the RecordLinkage package should be stored as a character not a numeric/integer vector.