#from pybrain.structure import FeedForwardNetwork
#n = FeedForwardNetwork()

#from pybrain.structure import LinearLayer, SigmoidLayer
#inLayer = LinearLayer(2)
#hiddenLayer = SigmoidLayer(3)
#outLayer = LinearLayer(1)

#n.addInputModule(inLayer)
#n.addModule(hiddenLayer)
#n.addOutputModule(outLayer)

#from pybrain.structure import FullConnection
#in_to_hidden = FullConnection(inLayer, hiddenLayer)
#hidden_to_out = FullConnection(hiddenLayer, outLayer)

#n.addConnection(in_to_hidden)
#n.addConnection(hidden_to_out)

#n.sortModules()
#print n

#from pybrain.supervised.trainers import BackpropTrainer

#import numpy as np

#create the network
from pybrain.tools.shortcuts import buildNetwork
net = buildNetwork(8,1,7)
print('Network Structure\nInput: ')
print(net['in'])
print('Hidden layer 1: ')
print(net['hidden0'])
print('Output: ')
print(net['out'])

print("\nImporting training data...")
#bring in data from training file
i = 0
inp = [] #inputs x
tar = [] #outputs ty
f = open("regression.tra")
for line in f.readlines():
    #every other line in file is 8 input values or 7 output values
    if i%2 == 0:
       inp.append(list(map(float, line.split())))
    else:
       tar.append(list(map(float, line.split())))
    i=i+1
 
print("Training input rows: %d , Target rows: %d " % (len(inp), len(tar)))
#print(i)
#input("Press Enter to view input data...")
#print('Input Values:')
#print(imp)
#input("Press Enter to view output data...")
#print('Target Values:')
#print(tar)

#set input and target arrays in data set
#raw_input("Press Enter to import training dataset into network...")
from pybrain.datasets import SupervisedDataSet
ds = SupervisedDataSet(8,7)
for index, row in enumerate(inp):
    ds.addSample(inp[index],tar[index])
    #print inp[index], tar[index]

#train neural network
print("\nTraining the neural network...")
from pybrain.supervised.trainers import BackpropTrainer
trainer = BackpropTrainer(net,ds)
trainer.trainUntilConvergence(dataset = ds, maxEpochs=30, continueEpochs=10, verbose=True, validationProportion = .20)
#for i in range(20):
#    print("Training Epoch: %d" % trainer.totalepochs)
#    print(trainer.testOnData())
#    trainer.trainEpochs(1)

print("\n")
for mod in net.modules:
    for conn in net.connections[mod]:
        print conn
        for cc in range(len(conn.params)):
            print conn.whichBuffers(cc), conn.params[cc]

print("\nTraining Epochs: %d" % trainer.totalepochs)
#from pybrain.utilities import percentError
print("\ntestOnData:")
print(trainer.testOnData())
from pybrain.tools.validation import ModuleValidator, Validator
meansq = ModuleValidator()
print("MSE:", meansq.MSE(trainer.module,ds))
#print("\nTraining Percent Error: ")
#print(percentError(trainer.testOnData(),ds))

raw_input("\nPress Enter to start testing...")

print("Importing testing data...")
#bring in data from test file
i = 0
inp_tst = [] #inputs x
tar_tst = [] #outputs ty
f = open("regression.tst")
for line in f.readlines():
    #every other line in file is 8 input values or 7 output values
    if i%2 == 0:
       inp_tst.append(list(map(float, line.split())))
    else:
       tar_tst.append(list(map(float, line.split())))
    i=i+1
 
print("Test input rows: %d , Target rows: %d " % (len(inp_tst), len(tar_tst)))

#test data set
ds_tst = SupervisedDataSet(8,7)
for index, row in enumerate(inp_tst):
    ds_tst.addSample(inp_tst[index],tar_tst[index])
    #print inp_tst[index], tar_tst[index]

#print("\nActivate on test dataset:")
#print(net.activateOnDataset(ds_tst))
print("\ntestOnData ds_tst:")
print(trainer.testOnData(dataset = ds_tst))
meansq = ModuleValidator()
print("MSE:", meansq.MSE(trainer.module,ds_tst))
#print("\nTesting Percent Error: ")
#print(percentError(trainer.testOnData(dataset = ds_tst),ds_tst))

p = net.activateOnDataset(ds_tst)
print(p)


#print('\nActivate:')
#print(net.activate([1,2,3,4,5,6,7,8]))