General Interface Pairwise Constrained Clustering By Local Search

Model from conclust
This function takes an unlabeled dataset and two lists of must-link and cannot-link constraints as input and produce a clustering as output.

cclsSSLR(
  n_clusters = NULL,
  mustLink = NULL,
  cantLink = NULL,
  max_iter = 1,
  tabuIter = 100,
  tabuLength = 20
)

Arguments

n_clusters	A number of clusters to be considered. Default is NULL (num classes)
mustLink	A list of must-link constraints. NULL Default, constrints same label
cantLink	A list of cannot-link constraints. NULL Default, constrints with different label
max_iter	maximum iterations in KMeans. Default is 1
tabuIter	Number of iteration in Tabu search
tabuLength	The number of elements in the Tabu list

Note

This models only returns labels, not centers

References

Tran Khanh Hiep, Nguyen Minh Duc, Bui Quoc Trung
Pairwise Constrained Clustering by Local Search
2016

Examples

library(tidyverse)
#> -- Attaching packages -------------------------------------------------------------------- tidyverse 1.3.0 --
#> v ggplot2 3.3.2     v purrr   0.3.4
#> v tibble  3.0.3     v dplyr   1.0.2
#> v tidyr   1.1.2     v stringr 1.4.0
#> v readr   1.4.0     v forcats 0.5.0
#> -- Conflicts ----------------------------------------------------------------------- tidyverse_conflicts() --
#> x dplyr::filter() masks stats::filter()
#> x dplyr::lag()    masks stats::lag()
library(caret)
#> Loading required package: lattice
#> 
#> Attaching package: 'caret'
#> The following object is masked from 'package:purrr':
#> 
#>     lift
library(SSLR)
library(tidymodels)
#> -- Attaching packages ------------------------------------------------------------------- tidymodels 0.1.1 --
#> v broom     0.7.1      v recipes   0.1.13
#> v dials     0.0.9      v rsample   0.0.8 
#> v infer     0.5.3      v tune      0.1.1 
#> v modeldata 0.0.2      v workflows 0.2.0 
#> v parsnip   0.1.3      v yardstick 0.0.7 
#> -- Conflicts ---------------------------------------------------------------------- tidymodels_conflicts() --
#> x scales::discard()        masks purrr::discard()
#> x dplyr::filter()          masks stats::filter()
#> x recipes::fixed()         masks stringr::fixed()
#> x dplyr::lag()             masks stats::lag()
#> x caret::lift()            masks purrr::lift()
#> x yardstick::precision()   masks caret::precision()
#> x yardstick::recall()      masks caret::recall()
#> x yardstick::sensitivity() masks caret::sensitivity()
#> x yardstick::spec()        masks readr::spec()
#> x yardstick::specificity() masks caret::specificity()
#> x recipes::step()          masks stats::step()

data <- iris

set.seed(1)
#% LABELED
cls <- which(colnames(iris) == "Species")

labeled.index <- createDataPartition(data$Species, p = .2, list = FALSE)
data[-labeled.index,cls] <- NA


m <- cclsSSLR(max_iter = 1) %>% fit(Species ~ ., data)

#Get labels (assing clusters), type = "raw" return factor
labels <- m %>% cluster_labels()

print(labels)
#> # A tibble: 150 x 1
#>    .pred_class
#>    <fct>      
#>  1 1          
#>  2 1          
#>  3 1          
#>  4 1          
#>  5 1          
#>  6 1          
#>  7 1          
#>  8 1          
#>  9 1          
#> 10 1          
#> # ... with 140 more rows