print("\nImporting training data...")
from pybrain.datasets import ClassificationDataSet
#bring in data from training file
traindata = ClassificationDataSet(16,1,10)
f = open("zipcode.tra") #this file has 3 lines of 5 values, then 1 line of 1 value and the class
i = 0
sample = []
target = []
for line in f.readlines():
    if i == 0:
        #reset lists
        sample = []
        target = []
    if i < 3:
        sample.extend(list(map(float, line.split()))[0:5])
    if i == 3:
        sample.extend(list(map(float, line.split()))[0:1])
        target.append(int(list(map(float, line.split()))[1])-1)
        traindata.appendLinked(sample[0:16],target)
        i = 0
    else:
        i += 1
    #using classification data set this time (subtracting 1 so first class is 0)
    #traindata.appendLinked(list(map(float, line.split()))[0:16],int(list(map(float, line.split()))[16])-1)
    
    
 
print("Training rows: %d " %  len(traindata) )
print("Input dimensions: %d, output dimensions: %d" % ( traindata.indim, traindata.outdim))
#convert to have 1 in column per class
traindata._convertToOneOfMany()
#raw_input("Press Enter to view training data...")
#print(traindata)
print("\nFirst sample: ", traindata['input'][0], traindata['target'][0], traindata['class'][0])

print("\nCreating Neural Network:")
#create the network
from pybrain.tools.shortcuts import buildNetwork
from pybrain.structure.modules import SoftmaxLayer
#change the number below for neurons in hidden layer
hiddenneurons = 13
net = buildNetwork(traindata.indim,hiddenneurons,traindata.outdim, outclass=SoftmaxLayer)
print('Network Structure:')
print('\nInput: ', net['in'])
#can't figure out how to get hidden neuron count, so making it a variable to print
print('Hidden layer 1: ', net['hidden0'], ", Neurons: ", hiddenneurons )
print('Output: ', net['out'])

#raw_input("Press Enter to train network...")
#train neural network
print("\nTraining the neural network...")
from pybrain.supervised.trainers import BackpropTrainer
trainer = BackpropTrainer(net,traindata)
trainer.trainUntilConvergence(dataset = traindata, maxEpochs=100, continueEpochs=10, verbose=True)
#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
trnresult = percentError( trainer.testOnClassData(dataset = traindata),
                              traindata['class'] )
print("  train error: %5.2f%%" % trnresult)
#result for each class [should probably create an array for this!]
#note, "junk" file is to contain "everything but class xx" part of output from splitting by class
trn00, junk =  traindata.splitByClass(0)
trn01, junk =  traindata.splitByClass(1)
trn02, junk =  traindata.splitByClass(2)
trn03, junk =  traindata.splitByClass(3)
trn04, junk =  traindata.splitByClass(4)
trn05, junk =  traindata.splitByClass(5)
trn06, junk =  traindata.splitByClass(6)
trn07, junk =  traindata.splitByClass(7)
trn08, junk =  traindata.splitByClass(8)
trn09, junk =  traindata.splitByClass(9)
trn00result = percentError( trainer.testOnClassData(dataset = trn00), trn00['class'])
trn01result = percentError( trainer.testOnClassData(dataset = trn01), trn01['class'])
trn02result = percentError( trainer.testOnClassData(dataset = trn02), trn02['class'])
trn03result = percentError( trainer.testOnClassData(dataset = trn03), trn03['class'])
trn04result = percentError( trainer.testOnClassData(dataset = trn04), trn04['class'])
trn05result = percentError( trainer.testOnClassData(dataset = trn05), trn05['class'])
trn06result = percentError( trainer.testOnClassData(dataset = trn06), trn06['class'])
trn07result = percentError( trainer.testOnClassData(dataset = trn07), trn07['class'])
trn08result = percentError( trainer.testOnClassData(dataset = trn08), trn08['class'])
trn09result = percentError( trainer.testOnClassData(dataset = trn09), trn09['class'])
print("  train class 1 samples: %d, error: %5.2f%%" % (len(trn00),trn00result))
print("  train class 2 samples: %d, error: %5.2f%%" % (len(trn01),trn01result))
print("  train class 3 samples: %d, error: %5.2f%%" % (len(trn02),trn02result))
print("  train class 4 samples: %d, error: %5.2f%%" % (len(trn03),trn03result))
print("  train class 5 samples: %d, error: %5.2f%%" % (len(trn04),trn04result))
print("  train class 6 samples: %d, error: %5.2f%%" % (len(trn05),trn05result))
print("  train class 7 samples: %d, error: %5.2f%%" % (len(trn06),trn06result))
print("  train class 8 samples: %d, error: %5.2f%%" % (len(trn07),trn07result))
print("  train class 9 samples: %d, error: %5.2f%%" % (len(trn08),trn08result))
print("  train class 10 samples: %d, error: %5.2f%%" % (len(trn09),trn09result))


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

print("\nImporting testing data...")
#bring in data from testing file
testdata = ClassificationDataSet(16,1,10)
f = open("zipcode.tst")
i = 0
sample = []
target = []
for line in f.readlines():
    if i == 0:
        #reset lists
        sample = []
        target = []
    if i < 3:
        sample.extend(list(map(float, line.split()))[0:5])
    if i == 3:
        sample.extend(list(map(float, line.split()))[0:1])
        target.append(int(list(map(float, line.split()))[1])-1)
        testdata.appendLinked(sample[0:16],target)
        i = 0
    else:
        i += 1
    

print("Test rows: %d " %  len(testdata) )
print("Input dimensions: %d, output dimensions: %d" % ( testdata.indim, testdata.outdim))
#convert to have 1 in column per class
testdata._convertToOneOfMany()
#raw_input("Press Enter to view training data...")
#print(traindata)
print("\nFirst sample: ", testdata['input'][0], testdata['target'][0], testdata['class'][0])

print("\nTesting...")
tstresult = percentError( trainer.testOnClassData(dataset = testdata),
                              testdata['class'] )
print("  test error: %5.2f%%" % tstresult)
#result for each class [should probably create an array for this!]
#note, "junk" file is to contain "everything but class xx" part of output from splitting by class
tst00, junk =  testdata.splitByClass(0)
tst01, junk =  testdata.splitByClass(1)
tst02, junk =  testdata.splitByClass(2)
tst03, junk =  testdata.splitByClass(3)
tst04, junk =  testdata.splitByClass(4)
tst05, junk =  testdata.splitByClass(5)
tst06, junk =  testdata.splitByClass(6)
tst07, junk =  testdata.splitByClass(7)
tst08, junk =  testdata.splitByClass(8)
tst09, junk =  testdata.splitByClass(9)
tst00result = percentError( trainer.testOnClassData(dataset = tst00), tst00['class'])
tst01result = percentError( trainer.testOnClassData(dataset = tst01), tst01['class'])
tst02result = percentError( trainer.testOnClassData(dataset = tst02), tst02['class'])
tst03result = percentError( trainer.testOnClassData(dataset = tst03), tst03['class'])
tst04result = percentError( trainer.testOnClassData(dataset = tst04), tst04['class'])
tst05result = percentError( trainer.testOnClassData(dataset = tst05), tst05['class'])
tst06result = percentError( trainer.testOnClassData(dataset = tst06), tst06['class'])
tst07result = percentError( trainer.testOnClassData(dataset = tst07), tst07['class'])
tst08result = percentError( trainer.testOnClassData(dataset = tst08), tst08['class'])
tst09result = percentError( trainer.testOnClassData(dataset = tst09), tst09['class'])
print("  test class 1 samples: %d, error: %5.2f%%" % (len(tst00),tst00result))
print("  test class 2 samples: %d, error: %5.2f%%" % (len(tst01),tst01result))
print("  test class 3 samples: %d, error: %5.2f%%" % (len(tst02),tst02result))
print("  test class 4 samples: %d, error: %5.2f%%" % (len(tst03),tst03result))
print("  test class 5 samples: %d, error: %5.2f%%" % (len(tst04),tst04result))
print("  test class 6 samples: %d, error: %5.2f%%" % (len(tst05),tst05result))
print("  test class 7 samples: %d, error: %5.2f%%" % (len(tst06),tst06result))
print("  test class 8 samples: %d, error: %5.2f%%" % (len(tst07),tst07result))
print("  test class 9 samples: %d, error: %5.2f%%" % (len(tst08),tst08result))
print("  test class 10 samples: %d, error: %5.2f%%" % (len(tst09),tst09result))