R help - Mar 2012 - how to cluster rows of words in a text file

Hi:

I am trying to cluster the rows of a text file with kmeans:

I load the data as follows
file1 <- read.csv("somefile.csv")

and the file can be viewed having the following line of
words
> file1
1   word1 word3 word4 word1
2   word1 word4 word3 word1
3   word4 word2 word4 word3
4   word4 word2 word1 word3
5   word2 word2 word4 word2

file_as_matrix <- as.matrix(file1);

Now, I want to apply some clustering algorithm such as kmeans to
cluster the rows  in the file to get the following output:

Cluster1
  word1 word3 word4 word1
  word1 word4 word3 word1


Cluster2
   word4 word2 word4 word3
   word4 word2 word1 word3
   word2 word2 word4 word2

 But as kmeans takes as input numeric matrix of data, it cannot be
used to cluster the rows in this case.
Is there any simple way to cluster the rows of such a text file? An
example code would be really useful.


Thanks and regards:
debb

Hello, I didn't quite understand what you need, but maybe you can have a
look here:
www.slideshare.net/whitish/textmining-with-r

R code fragments are in appendixes of the presentation.

Hope this will help,
-Alex
________________________________________
From: r-help-bounces at r-project.org [r-help-bounces at r-project.org] on
behalf of mail me [mailme842 at googlemail.com]
Sent: 23 March 2012 20:03
To: r-help
Subject: [R] how to cluster rows of words in a text file

Hi:

I am trying to cluster the rows of a text file with kmeans:

I load the data as follows
file1 <- read.csv("somefile.csv")

and the file can be viewed having the following line of
words
> file1
1   word1 word3 word4 word1
2   word1 word4 word3 word1
3   word4 word2 word4 word3
4   word4 word2 word1 word3
5   word2 word2 word4 word2

file_as_matrix <- as.matrix(file1);

Now, I want to apply some clustering algorithm such as kmeans to
cluster the rows  in the file to get the following output:

Cluster1
  word1 word3 word4 word1
  word1 word4 word3 word1


Cluster2
   word4 word2 word4 word3
   word4 word2 word1 word3
   word2 word2 word4 word2

 But as kmeans takes as input numeric matrix of data, it cannot be
used to cluster the rows in this case.
Is there any simple way to cluster the rows of such a text file? An
example code would be really useful.


Thanks and regards:
debb

______________________________________________
R-help at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.