Evaluate cluster

Description

This function evaluate the clusters created by SOM. Each cluster is a neuron or a set of neuron categorized with same label. It produces a sits tibble indicating the percentage of mixture of classes in each cluster.

Usage

sits_som_evaluate_cluster(som_map)

Arguments

Value

A tibble with the cluster and the percentage of classes mixtured in each cluster.

Author(s)

Lorena Santos, lorena.santos@inpe.br

Karine Ferreira. karine.ferreira@inpe.br

Examples

## Not run: 
# Read a set of samples
# Get a new subset of samples evaluated by clustering methods
som_map <- sits_som_map(samples_modis_4bands,
    grid_xdim = 10, grid_ydim = 10,
    distance = "euclidean"
)
cluster_purity <- sits_som_evaluate_cluster(som_map)

## End(Not run)