## ---- eval=FALSE-----------------------------------------------------------
#  if (!requireNamespace("BiocManager"))
#      install.packages("BiocManager")
#  BiocManager::install("mbkmeans")

## ----options, include=FALSE, message=FALSE, warning=FALSE------------------
knitr::opts_chunk$set(cache=FALSE, error=FALSE, message=FALSE, warning=FALSE)
library(TENxPBMCData)
library(scater)
library(SingleCellExperiment)
library(mbkmeans)
library(DelayedMatrixStats)
library(ClusterR)

## --------------------------------------------------------------------------
tenx_pbmc4k <- TENxPBMCData(dataset = "pbmc4k")

set.seed(1034)
idx <- sample(seq_len(NCOL(tenx_pbmc4k)), 100)
sce <- tenx_pbmc4k[, idx]

#normalization
sce <- normalize(sce)

vars <- rowVars(logcounts(sce))
names(vars) <- rownames(sce)
vars <- sort(vars, decreasing = TRUE)

sce1000 <- sce[names(vars)[1:1000],]

sce1000

## --------------------------------------------------------------------------
res <- mbkmeans(sce1000, clusters = 5,
                reduceMethod = NA,
                whichAssay = "logcounts")

## --------------------------------------------------------------------------
batchsize <- blocksize(sce1000)
batchsize

## --------------------------------------------------------------------------
res_random <- mbkmeans(sce1000, clusters = 5, 
                reduceMethod = NA,
                whichAssay = "logcounts",
                initializer = "random")
table(res$Clusters, res_random$Clusters)

## --------------------------------------------------------------------------
res_full <- mbkmeans(sce1000, clusters = 5,
                     reduceMethod = NA,
                     whichAssay = "logcounts",
                     initializer = "random",
                     batch_size = ncol(sce1000))
res_classic <- kmeans(t(logcounts(sce1000)), centers = 5)
table(res_full$Clusters, res_classic$cluster)