General Interface Constrained KMeans — constrained

The initialization is the same as seeded kmeans, the difference is that in the following steps the allocation of the clusters in the labelled data does not change

constrained_kmeans(max_iter = 10, method = "euclidean")

Arguments

max_iter	maximum iterations in KMeans. Default is 10
method	distance method in KMeans: "euclidean", "maximum", "manhattan", "canberra", "binary" or "minkowski"

References

Sugato Basu, Arindam Banerjee, Raymond Mooney
Semi-supervised clustering by seeding
July 2002 In Proceedings of 19th International Conference on Machine Learning

Examples

library(tidyverse)
library(caret)
library(SSLR)
library(tidymodels)

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 <- constrained_kmeans() %>% 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


#Get centers
centers <- m %>% get_centers()

print(centers)
#>          [,1]     [,2]     [,3]     [,4]
#> [1,] 5.006000 3.428000 1.462000 0.246000
#> [2,] 5.850909 2.747273 4.320000 1.400000
#> [3,] 6.764444 3.024444 5.622222 2.013333