Windows无法运行FitEnsembleSVM

[AdotaLover]

window无法运行mclapply的并行计算
system.time({
embeddings.df <- FetchData(seu.ref, vars = paste0("UMAP_", 1:2))
batch.size = 5000 # number of subsampled cells for each SVR model
n.models = 20 # number of SVR models trained
umap.model <- FitEnsembleSVM(feature.mat = gss.mat,
emb.mat = embeddings.df,
do.norm = "L2",
batch.size = batch.size,
n.models = n.models
)

})
L2 normalization ...
Creating regression tasks: size=5000, n=20
|++++++++++++++++++++++++++++++++++++++++++++++++++| 100% elapsed=00s
|++++++++++++++++++++++++++++++++++++++++++++++++++| 100% elapsed=00s
|++++++++++++++++++++++++++++++++++++++++++++++++++| 100% elapsed=00s
Regression ...
错误于parallel::mclapply(1:n.models, function(j) .train(coord_i, j), :
Windows不支持'mc.cores' > 1
Timing stopped at: 0.8 0.06 0.9

[JarningGau]

ProjectSVR现在不支持在win平台下的并行计算，这种情况设置mc.cores=1即可。