[R] nnet plot

RMSOPS ricardosousa2000 at clix.pt
Sun Nov 27 02:35:04 CET 2011


good night

   Again I ask for help to the community, as I am new at this, I have some
basic questions.

 I am looking for packages on neural networks and so you can search found
these two that I think are the most used, neuralnet, nnet.

 So you can test, and correct me if I'm wrong the neuralnet only accepts as
input values ​​nomer, did a little test

 data (iris)
 library (neuralnet)
 Species.numeric <- as.numeric (iris $ Species)
 iris.df <- data.frame (iris, Species.numeric)
 net <- neuralnet (~ Species.numeric Sepal.Width Sepal.Length + + +
Petal.Width Petal.Length, iris.df, hidden = 2)
 options (device = "windows")
 plot (net)
 net

 I think the net library supports all type of data.

 library (nnet)
 library ("nnet")
 RN <- nnet (iris $ Species ~., Data = iris, size = 3, rang = 0.1, decay =
0.01, maxit = 20)
 plot (RN)

 my question is how this package can enter all the input attributes. and how
can I draw a sketch of the network similar to that of neuralnet, or how I
can put all the attributes not transform in the numeric neuralnet.

    Is there a more effective package of neural networks.

 thank you

--
View this message in context: http://r.789695.n4.nabble.com/nnet-plot-tp4111620p4111620.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list