Problem $3,$ Part $($i$)$

Download the dataset MorderGE.RData and then load it into your RStudio workspace. It contains a data frame Morder and a factor type. The data frame Morder contains gene expression measurements for $156$ genes from the T cells of $3$ types $($naive$,$ effector, memory$)$ of $10$ patients $($Holmes et al$.2005).$ Each column represents a gene. Each row represents a sample of T cells; there are $30$ samples since $10($patients$)3($types$)=30.$ Run the following code to perform the k$-$means clustering of the $30$ samples. The output is attached $($you should be able to see exactly the same output, but be sure not to run kmeans multiple times$).$##type##effectormemorynaive##$1092$##$2009$#$31000$

According to the above contingency table, how many samples are in the first cluster of the k$-$means output?

$11$

$9$

$10$

$30$

$6$

$4$ points

Problem $3,$ Part $($ii$)$

The type vector contains the true T cell type of each sample. We expect that the three clusters obtained from k$-$means should match the three cell types. According to the above contigency table, how many samples are wrongly clustered?

$9$

$2$

$11$

None of the above