R Under development (unstable) (2023-07-19 r84711 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2023 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(reclin2)
Loading required package: data.table

Attaching package: 'reclin2'

The following object is masked from 'package:base':

    identical

> source("helpers.R")
> 
> 
> data("linkexample1", "linkexample2")
> linkexample1$id2 <- c(1,1,3,3,5,6)
> linkexample2$id2 <- c(2,3,3,6,7)
> 
> pairs <- pair_blocking(linkexample1, linkexample2, "postcode")
> pairs[, score := runif(nrow(pairs))]
  First data set:  6 records
  Second data set: 5 records
  Total number of pairs: 17 pairs
  Blocking on: 'postcode'

    .x .y      score
 1:  1  1 0.26620705
 2:  1  2 0.53517799
 3:  1  3 0.15675725
 4:  2  1 0.24971265
 5:  2  2 0.71774280
 6:  2  3 0.39375684
 7:  3  1 0.27842934
 8:  3  2 0.93067480
 9:  3  3 0.51133765
10:  4  1 0.25484900
11:  4  2 0.97827497
12:  4  3 0.03870225
13:  5  1 0.67335571
14:  5  2 0.58496315
15:  5  3 0.61462588
16:  6  4 0.61759480
17:  6  5 0.48179762
> pairs[, select := score > 0.5]
  First data set:  6 records
  Second data set: 5 records
  Total number of pairs: 17 pairs
  Blocking on: 'postcode'

    .x .y      score select
 1:  1  1 0.26620705  FALSE
 2:  1  2 0.53517799   TRUE
 3:  1  3 0.15675725  FALSE
 4:  2  1 0.24971265  FALSE
 5:  2  2 0.71774280   TRUE
 6:  2  3 0.39375684  FALSE
 7:  3  1 0.27842934  FALSE
 8:  3  2 0.93067480   TRUE
 9:  3  3 0.51133765   TRUE
10:  4  1 0.25484900  FALSE
11:  4  2 0.97827497   TRUE
12:  4  3 0.03870225  FALSE
13:  5  1 0.67335571   TRUE
14:  5  2 0.58496315   TRUE
15:  5  3 0.61462588   TRUE
16:  6  4 0.61759480   TRUE
17:  6  5 0.48179762  FALSE
> pairs[, select2 := FALSE]
  First data set:  6 records
  Second data set: 5 records
  Total number of pairs: 17 pairs
  Blocking on: 'postcode'

    .x .y      score select select2
 1:  1  1 0.26620705  FALSE   FALSE
 2:  1  2 0.53517799   TRUE   FALSE
 3:  1  3 0.15675725  FALSE   FALSE
 4:  2  1 0.24971265  FALSE   FALSE
 5:  2  2 0.71774280   TRUE   FALSE
 6:  2  3 0.39375684  FALSE   FALSE
 7:  3  1 0.27842934  FALSE   FALSE
 8:  3  2 0.93067480   TRUE   FALSE
 9:  3  3 0.51133765   TRUE   FALSE
10:  4  1 0.25484900  FALSE   FALSE
11:  4  2 0.97827497   TRUE   FALSE
12:  4  3 0.03870225  FALSE   FALSE
13:  5  1 0.67335571   TRUE   FALSE
14:  5  2 0.58496315   TRUE   FALSE
15:  5  3 0.61462588   TRUE   FALSE
16:  6  4 0.61759480   TRUE   FALSE
17:  6  5 0.48179762  FALSE   FALSE
> 
> 
> # === TESTS FOR ID_X AND ID_Y ARGUMENTS
> 
> test <- reclin2:::select_preprocess(pairs, score = "score", id_x = "id", id_y = "id")
> expect_equal(test$.x, linkexample1$id[pairs$.x])
> expect_equal(test$.y, linkexample2$id[pairs$.y])
> 
> test <- reclin2:::select_preprocess(pairs, score = "score", id_x = "id2", id_y = "id2")
> expect_equal(test$.x, linkexample1$id2[pairs$.x])
> expect_equal(test$.y, linkexample2$id2[pairs$.y])
> 
> test <- reclin2:::select_preprocess(pairs, score = "score", id_x = "id2", id_y = "id2",
+   preselect = "select")
> expect_equal(sort(test$.x), sort(linkexample1$id2[pairs$.x[pairs$select]]))
> expect_equal(sort(test$.y), sort(linkexample2$id2[pairs$.y[pairs$select]]))
> 
> test <- reclin2:::select_preprocess(pairs, score = "score", id_x = "id2", id_y = "id2",
+   preselect = "select2")
> expect_equal(nrow(test), 0)
> expect_equal(names(test), c(".x", ".y", "score", "index"))
> 
> expect_error(
+   test <- reclin2:::select_preprocess(pairs, score = "score", id_x = 1:3, id_y = 1:3,
+     preselect = "select")
+ )
> 
> proc.time()
   user  system elapsed 
   0.31    0.07    0.37