[R] problem to get a correct output

Dominique Knockaert knockaert77 at yahoo.com
Thu May 5 12:52:19 CEST 2005


Dear,

I am new user of 'R' (package e1071) and the first
thing I did was reading the manuals. Although it was
not clear for me how it works.
My problem is the following:
I have a data set of customers data of insurances with
variables  Class, Group Distance Claim. The file
called 'xx.dat'. Using the manuals I think I had
entered the data in the program. I used several
function, but I never get an output.
In fact, I want to use the SVM with Vapnik's loss
function for classification for the response variable
'Claim' and discrete explanatory variables Class,
Group, Distance whitout modelling interaction terms
manually. I want to use epsilon = 0.1, cast penalty
constant (C) cost =1, and  a Gaussian radial basis
function kernel with y =1, i.e. k(x,x')=
exp(-y||x-x'||²).
I would like to aply here the classification rule to
the whole data set and construct a 2-by-2 table of
claim and predicted levels of Claim.

I hope you can help me further !!
Many thanks in advance !

best regards,
Dominique




More information about the R-help mailing list