Unable to reproduce results

[mohit1997]

I have installed scPred and been following the article Intro and executed this code

library("scPred")
library("tidyverse")

download.file("https://scrnaseq-public-datasets.s3.amazonaws.com/scater-objects/pollen.rds", destfile = "~/Downloads/pollen.rds")
require("SingleCellExperiment")
pollen <- readRDS("~/Downloads/pollen.rds")

pollen_counts <- normcounts(pollen)
pollen_cpm  <- apply(pollen_counts, 2, function(x) (x/sum(x))*1000000)
pollen_metadata <- as.data.frame(colData(pollen))

set.seed(1234)
i <- createDataPartition(pollen_metadata$cell_type2, p = 0.70, list = FALSE)
train_data <- pollen_cpm[, i]
test_data <- pollen_cpm[, -i]

train_info <- pollen_metadata[i, , drop = FALSE]
test_info <- pollen_metadata[-i, , drop = FALSE]

set.seed(1234)
scp <- eigenDecompose(train_data, n = 20)

scPred::metadata(scp) <- train_info
scp <- getFeatureSpace(scp, pVar = "cell_type2")

plotEigen(scp, group = "cell_type2")
scp <- trainModel(scp, seed = 66)

Then the results I obtained are different from the ones mentioned in the article, I get the following AUC scores

Training information
      Model: Support Vector Machines with Class Weights
            AUC   Precision Recall F    
blood       0.938 1         0.988  0.994
dermal      0.929 1         1      1    
neural      0.891 1         0.869  0.926
pluripotent 0.7   1         1      1