"""
 Multilayer perceptron neural network. It can be used for deep learning by
 creating muptiple hidden layers. 
 This MLP consists of several layers of nodes, interconnected through weighted
 acyclic arcs from each preceding layer to the following, without lateral or
 feedback connections. 
 It has many input and output layers. Add additional layers iin line 45
 This example shows the error rate.
"""

from smile.data import AttributeDataset,NominalAttribute
from smile.data.parser import DelimitedTextParser,IOUtils
from smile.classification import NeuralNetwork 
from smile.math import Math
from jarray import zeros,array
from jhplot import *
import java

# this function extract x[][] and y[] array from datasets
def getJavaArrays(dataset):
    rows=dataset.size()
    lst = [0.0]*rows
    twoDimArr = array([lst,[]], java.lang.Class.forName('[D'))
    x = dataset.toArray(twoDimArr)
    y = dataset.toArray(zeros(rows, "i"))
    return x,y

parser =DelimitedTextParser()
parser.setDelimiter("[\t ]+")
parser.setResponseIndex(NominalAttribute("class"), 0)

http="http://datamelt.org/examples/data/usps/"
datasource="zip.train"
print "Reading ",datasource," from from",http
print Web.get(http+datasource)
train=parser.parse("Train",java.io.File(datasource))
x,y=getJavaArrays(train)

print "Normalize data.."
p = len(x[0])
mu = Math.colMeans(x);
sd = Math.colSds(x);
for i in range(len(x)):
   for j in range(p):
       x[i][j] = (x[i][j] - mu[j]) / sd[j];

nin=len(x[0]);  nout=Math.max(y)+1 
print "Training: Nr input layers=",nin," Nr of output layers=",nout

nn=[nin,50,nout] # 50 hidden layers. Need another layer? Add integer after 50 
print "NN layout=",nn
net = NeuralNetwork(NeuralNetwork.ErrorFunction.LEAST_MEAN_SQUARES, NeuralNetwork.ActivationFunction.LOGISTIC_SIGMOID,nn)

c1 = SPlot()
c1.visible()
c1.setGTitle("Neural Network output error")
c1.setAutoRange()
c1.setMarksStyle('various')
c1.setConnected(1, 0)
c1.setNameX('Epoch')
c1.setNameY('Error')

for j in range(70):
  net.learn(x, y)
  error=0.0
  for i in range(len(x)):
       if (net.predict(x[i]) != y[i]): error +=1 
  error=error / len(x)
  c1.addPoint(0,j,error,1)
  c1.update()
  print "Epoch=",j," Error=",error 

datasource="zip.test"
print Web.get(http+datasource)
print "Testing ",datasource," from from",http
test=parser.parse("Test",java.io.File(datasource))
testx,testy=getJavaArrays(test)
for i in range(len(testx)):
   for j in range(p):
      testx[i][j] = (testx[i][j] - mu[j]) / sd[j];

error=0.0
for i in range(len(testx)):
   if (net.predict(testx[i]) != testy[i]):  error +=1

print "Error rate =", 100.0 * error / len(testx),"%"