evelinag / clusternomics Goto Github PK

library(clusternomics)
library(ggplot2)
library(dplyr)
set.seed(1)

# Number of elements in each cluster, follows the table given above
groupCounts <- c(50, 10, 40, 60)
# Centers of clusters
means <- c(-10.5,1.5)
# Helper function to generate test data
testData <- generateTestData_2D(groupCounts, means)
datasets <- testData$data

# Setup of the algorithm
dataDistributions <- 'diagNormal'
# Pre-specify number of clusters
clusterCounts <- list(global=10, context=c(3,3))
# Set number of iterations
# The following is ONLY FOR SIMULATION PURPOSES 
# Use larger number of iterations for real-life data
maxIter <- 300  
burnin <- 200
lag <- 2  # Thinning of samples

# Run context-dependent clustering
results <- contextCluster(datasets, clusterCounts, 
                          maxIter = maxIter, burnin = burnin, lag = lag,
                          dataDistributions = 'diagNormal',
                          verbose = F)

# Extract resulting cluster assignments
samples <- results$samples  

# Extract global cluster assignments for each MCMC sample
clusters <- lapply(1:length(samples), function(i) samples[[i]]$Global) 

cc <- numberOfClusters(clusters)

cc <- lapply(1:length(clusters), function(i) unique(clusters[[i]]) %>% length)