plot_k_n_partitions {ClustAssess}

Relationship Between the Number of Clusters and the Number of Unique Partitions

Description

For each configuration provided in partition_obj_list, display how many different partitions with the same number of clusters can be obtained by changing the seed.

Usage

plot_k_n_partitions(partition_obj_list, object_names = NULL)

Arguments

partition_obj_list

An object or a concatenation of objects returned by the 'merge_resolutions' method.

object_names

Custom names that the user could assing to each configuration; if not specified, the plot will use the generated configuration names.

Value

A ggplot2 object. The color gradient suggests the frequency of the most common partition relative to the total number of appearances of that specific number of clusters.

Examples

set.seed(2021)
# create an artificial expression matrix
expr_matrix = matrix(runif(500*10), nrow = 500)

# get the PCA embedding of the data
pca_embedding = irlba::irlba(expr_matrix, nv = 2)
pca_embedding = pca_embedding$u %*% diag(pca_embedding$d)
rownames(pca_embedding) = as.character(1:500)

# run the function on the pca embedding
resolution_result = get_resolution_importance(embedding = pca_embedding,
   resolution = c(0.8, 1),
   n_neigh = c(5, 7),
   n_repetitions = 5,
   clustering_method = 1,
   graph_type = 2,
   object_name = "name_example")

plot_k_n_partitions(resolution_result)