somhca (version 0.3.0)

clusterSOM: Perform Clustering on SOM Nodes

Description

Groups similar nodes of a SOM using hierarchical clustering. By default, the optimal number of clusters is determined automatically using the KGS penalty function, but the user can also specify a fixed number of clusters.

Usage

clusterSOM(
  model,
  n_clusters = NULL,
  validity_indices = TRUE,
  plot_result = TRUE,
  input = NULL
)

Value

Invisibly returns `NULL`. If `plot_result = TRUE`, a plot of the clusters on the SOM grid is produced. If `input` is provided, the clustered dataset is stored in the package environment and can be retrieved with `getClusterData()`.

Arguments

model

A trained SOM model object.

n_clusters

Optional integer. If provided, specifies the number of clusters to cut the SOM dendrogram into. If NULL (default), the optimal number of clusters is determined automatically using the KGS penalty function.

validity_indices

A logical value indicating whether to compute and print popular clustering validity indices (Silhouette, Dunn, CH, Pearson Gamma). Default is `TRUE`.

plot_result

A logical value indicating whether to plot the clustering result. Default is `TRUE`.

input

An optional input specifying either:

File Path

A string specifying the path to a CSV file.

In-Memory Data

A data frame or matrix containing numeric data.

If provided, clusters are assigned to the observations in the original dataset, and the updated data is stored in a package environment as 'DataAndClusters'.

Examples

# Create a toy matrix with 9 columns and 100 rows
data <- matrix(rnorm(900), ncol = 9, nrow = 100)  # 900 random numbers, 100 rows, 9 columns

# Run the finalSOM function with the mock data
model <- finalSOM(data, dimension = 6, iterations = 700)

# Example 1: Perform clustering using the mock model
clusterSOM(model, plot_result = TRUE)

# Example 2: Assign SOM-based clusters to an in-memory data frame
df <- data.frame(
  ID = paste0("Sample", 1:100), # Character column for row headings
  matrix(rnorm(900), ncol = 9, nrow = 100) # Numeric data
)
clusterSOM(model, plot_result = FALSE, input = df)
getClusterData()

# Example 3: Load toy data from a CSV file, perform clustering, and retrieve the clustered dataset
file_path <- system.file("extdata", "toy_data.csv", package = "somhca")
clusterSOM(model, plot_result = FALSE, input = file_path)
getClusterData()