[Amore-commits] R access to AMORE networks

[Manuel Castejón Limas]

Dear all,
We have gained access from the R terminal to the AMORE C++  classes.
Now, it's only a matter of writing a few lines of code for the predict and
train methods.
Greetings
Manuel


incCode <- paste(readLines( "pkg/AMORE/src/AMORE.h"), collapse = "\n" )

testCode <- ""

testCodefun <- cfunction(sig=signature(), body=testCode,includes=incCode,
otherdefs="using namespace Rcpp;", language="C++", verbose=FALSE,
convention=".Call",Rcpp=TRUE,cppargs=character(), cxxargs=
paste("-I",getwd(),"/pkg/AMORE/src -I/opt/local/include",sep=""),
libargs=character())

modAMORE <- Module("mod_AMORE",  getDynLib(testCodefun))



AMOREnet <- modAMORE$NetworkRinterface

net <- new (AMOREnet)

net$show()

# Uninitialized network. Please use any of the create methods available.



net$createFeedForwardNetwork(c(3,4,5,2))    # This one should be improve to
accept an arbitrary couple of activation functions --- a piece of cake

net$show()

# 

# 

# =========================================================

#          Input Layer

# =========================================================

# 

# -----------------------------------

#  Id: 1

# -----------------------------------

#  output: 0.000000

# -----------------------------------

# 

# -----------------------------------

#  Id: 2

# -----------------------------------

#  output: 0.000000

# -----------------------------------

# 

# -----------------------------------

#  Id: 3

# -----------------------------------

#  output: 0.000000

# -----------------------------------

# 

# =========================================================

#          Hidden Layers

# =========================================================

# 

# -----------------------------------

#  Id: 4

# -----------------------------------

#  bias: 0.075957

#  output: 0.000000

# -----------------------------------

# From:  1  Weight=  0.066707

# From:  2  Weight=  -0.206484

# From:  3  Weight=  -0.105587

# -----------------------------------

# 

# -----------------------------------

#  Id: 5

# -----------------------------------

#  bias: -0.078118

#  output: 0.000000

# -----------------------------------

# From:  1  Weight=  0.029251

# From:  2  Weight=  0.092108

# From:  3  Weight=  0.120308

# -----------------------------------

# 

# -----------------------------------

#  Id: 6

# -----------------------------------

#  bias: -0.072798

#  output: 0.000000

# -----------------------------------

# From:  1  Weight=  0.212599

# From:  2  Weight=  0.228965

# From:  3  Weight=  0.103189

# -----------------------------------

# 

# -----------------------------------

#  Id: 7

# -----------------------------------

#  bias: -0.076561

#  output: 0.000000

# -----------------------------------

# From:  1  Weight=  0.031377

# From:  2  Weight=  -0.090947

# From:  3  Weight=  0.004679

# -----------------------------------

# 

# -----------------------------------

#  Id: 8

# -----------------------------------

#  bias: 0.208192

#  output: 0.000000

# -----------------------------------

# From:  4  Weight=  0.206423

# From:  5  Weight=  0.129576

# From:  6  Weight=  0.145507

# From:  7  Weight=  0.061925

# -----------------------------------

# 

# -----------------------------------

#  Id: 9

# -----------------------------------

#  bias: 0.061735

#  output: 0.000000

# -----------------------------------

# From:  4  Weight=  0.027846

# From:  5  Weight=  -0.159941

# From:  6  Weight=  0.193446

# From:  7  Weight=  -0.149098

# -----------------------------------

# 

# -----------------------------------

#  Id: 10

# -----------------------------------

#  bias: -0.059627

#  output: 0.000000

# -----------------------------------

# From:  4  Weight=  0.092017

# From:  5  Weight=  0.226942

# From:  6  Weight=  0.075113

# From:  7  Weight=  -0.224416

# -----------------------------------

# 

# -----------------------------------

#  Id: 11

# -----------------------------------

#  bias: -0.081444

#  output: 0.000000

# -----------------------------------

# From:  4  Weight=  -0.036672

# From:  5  Weight=  0.155313

# From:  6  Weight=  -0.062914

# From:  7  Weight=  -0.126029

# -----------------------------------

# 

# -----------------------------------

#  Id: 12

# -----------------------------------

#  bias: -0.151271

#  output: 0.000000

# -----------------------------------

# From:  4  Weight=  0.229607

# From:  5  Weight=  0.210131

# From:  6  Weight=  -0.010589

# From:  7  Weight=  -0.194893

# -----------------------------------

# 

# =========================================================

#          Output Layer

# =========================================================

# 

# -----------------------------------

#  Id: 13

# -----------------------------------

#  bias: 0.097918

#  output: 0.000000

# -----------------------------------

# From:  8  Weight=  0.107296

# From:  9  Weight=  -0.171640

# From:  10  Weight=  -0.051762

# From:  11  Weight=  0.039894

# From:  12  Weight=  0.123288

# -----------------------------------

# 

# -----------------------------------

#  Id: 14

# -----------------------------------

#  bias: 0.136566

#  output: 0.000000

# -----------------------------------

# From:  8  Weight=  0.083047

# From:  9  Weight=  -0.129915

# From:  10  Weight=  -0.102014

# From:  11  Weight=  -0.059982

# From:  12  Weight=  -0.193560

# -----------------------------------

# =========================================================






-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/amore-commits/attachments/20110725/42deffd3/attachment-0001.htm>