ggplot R plot after k means clustering

Question

I did clustering on my dataset and it works so far.

Now I want to plot the clustering and with this code:

ggplot(mydata, aes(SalesRank, PageRank, colour= booksCluster$cluster))+ geom_point()

I get this result:

Now I want instead of the numbers of the clusters the third column of my origin dataset (e.g. 'XY').

How can I achieve this?

Edit:

Here is my data

 $ SalesRank: int  18083 9284 15794 14630 -1 23395 12095 991 653 33717 ...
 $ PageRank : num  0.01 0.01241 0.00753 0.00454 0.00301 ...
 $ Verlag   : Factor w/ 58 levels "-1TION-Z","A-1conda",..: 40 33 33 33 33 57 33

score 0 · Answer 1 · answered Nov 26 '16 at 09:04

0

You will have to change the level names of booksCluster$cluster. If this is not a factor yet, you will have to coerce it to one. You can use levels(bookClusters$cluster) <- c(...) where ... is a vector of new names.

answered Nov 26 '16 at 09:04

Roman Luštrik

69,533
24
154
197

Sorry I'm totally new to r and don't understand your advice. – moses Nov 26 '16 at 10:06
@NicoHoppel Read more about factors [here](https://www.stat.berkeley.edu/classes/s133/factors.html) and [here](http://stackoverflow.com/questions/29711067/r-how-to-change-name-of-factor-levels). – Roman Luštrik Nov 26 '16 at 12:28
Ah okay I understand. Now I have to type 20 names as a vector? – moses Nov 26 '16 at 17:31
@NicoHoppel Please edit your question and show all the data structures in question. You can use `str()`. – Roman Luštrik Nov 27 '16 at 14:58

ggplot R plot after k means clustering

1 Answers1