plot_k_resolution_corresp {ClustAssess}

Correspondence Between Resolution and the Number of Clusters

Description

For each configuration provided in the res_object_list, display what number of clusters appear for different values of the resolution parameters.

Usage

plot_k_resolution_corresp(
  res_object_list,
  res_object_names = NULL,
  given_height = 0.7
)

Arguments

res_object_list

An object returned by the 'get_resolution_importance' method.

res_object_names

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

given_height

Used for adjusting the vertical position of the boxplot; the value will be passed in the 'width' argument of the 'ggplot::position_dodge' method.

Value

A ggplot2 object. Different shapes of points indicate different parameter configuration, while the color illustrates the frequency of the most common partition. The frequency is calculated as the fraction between the number of total appearances and the number of runs.

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_resolution_corresp(resolution_result)