def main():
DS = ClassificationDataSet.loadFromFile("ClassifierDataSet")
print DS.calculateStatistics()
print type(DS)
rates = measuredLearning(DS)
# Produce two new datasets, the first one containing the fraction given by proportion of the samples.
# splitWithProportion(proportion=0.5)
# print len(ds)
# tstdata, trndata = alldata.splitWithProportion( 0.25 )
# for input, target in ds:
# print input,target
# print ds['input']
# print ds['target']
#hidden class by default sigmoid
all_data=ClassificationDataSet.loadFromFile("nn-data")
# tstdata, trndata = all_data.splitWithProportion( 0.25 )
tstdata_temp, partdata_temp = all_data.splitWithProportion( 0.25 )
trndata_temp,validata_temp = partdata_temp.splitWithProportion(0.50)
tstdata = ClassificationDataSet(200, 1, nb_classes=2)
for n in xrange(0, tstdata_temp.getLength()):
tstdata.addSample( tstdata_temp.getSample(n)[0], tstdata_temp.getSample(n)[1] )
trndata = ClassificationDataSet(200, 1, nb_classes=2)
for n in xrange(0, trndata_temp.getLength()):
trndata.addSample( trndata_temp.getSample(n)[0], trndata_temp.getSample(n)[1] )
validata= ClassificationDataSet(200, 1, nb_classes=2)
from pybrain.structure import RecurrentNetwork, FeedForwardNetwork
from pybrain.structure import LinearLayer, SigmoidLayer, TanhLayer
from pybrain.structure import FullConnection
from pybrain.datasets import SupervisedDataSet, ClassificationDataSet
from pybrain.utilities import percentError
from pybrain.tools.shortcuts import buildNetwork
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.structure.modules import SoftmaxLayer, BiasUnit
from pylab import ion, ioff, figure, draw, contourf, clf, show, hold, plot
from scipy import diag, arange, meshgrid, where
from numpy.random import multivariate_normal
from numpy import array_equal
import pickle
DSSuperRaw = SupervisedDataSet.loadFromFile("Data/DSSuperRaw")
DSClassRaw = ClassificationDataSet.loadFromFile("Data/DSClassRaw")
DSSuperWhiten = SupervisedDataSet.loadFromFile("Data/DSSuperWhiten")
DSClassWhiten = ClassificationDataSet.loadFromFile("Data/DSClassWhiten")
DSSuperNorm = SupervisedDataSet.loadFromFile("Data/DSSuperNorm")
DSClassNorm = ClassificationDataSet.loadFromFile("Data/DSClassNorm")
layers = (14, 14, 8)
net = buildNetwork(*layers, hiddenclass=TanhLayer, bias=True, outputbias=True, outclass=SoftmaxLayer, recurrent=True)
TrainDS, TestDS = DSSuperNorm.splitWithProportion(0.7)
# TrainDS._convertToOneOfMany()
# TestDS._convertToOneOfMany()
from pybrain.datasets import ClassificationDataSet
print "Reading data set..."
DS = ClassificationDataSet.loadFromFile('dataset.csv')
#Split validation set
TestDS, TrainDS = DS.splitWithProportion( 0.25 )
#train svm
from svm import svm_problem, svm_parameter, libsvm, gen_svm_nodearray
#define problem with data from the pybrain dataset.
# best python explanation for libsvm is here: https://github.com/arnaudsj/libsvm/tree/master/python
#we have to convert the data to ints and lists because of the low-level c interface
prob = svm_problem([int(t) for t in TrainDS['target']],[list(i) for i in TrainDS['input']])
param = svm_parameter()
# option: -t 0: linear kernel. Best for classification.
# option: -c 0.01: regularization parameter. smaller is more regularization
# see below for all options
param.parse_options('-t 0 -c 0.01')
print "Training svm..."
model = libsvm.svm_train(prob,param)
print "Testing svm with three random inputs"
from random import randrange
for j in range(3):
i = randrange(0,len(TestDS))
#again some conversion needed because of low level interface
x0,m_idx = gen_svm_nodearray(list(TestDS['input'][i]))
prediction = libsvm.svm_predict(model, x0)
print("Target:{0}, prediction:{1}".format(TestDS['target'][i],prediction))
def genet(lst):
n, lg, nhide, nhide1, epo, wd = lst
ds = ClassificationDataSet.loadFromFile('r10000_l' + str(lg) + '.dat')
fna = fname1(n, lg, nhide, nhide1, epo, wd)
nt = trainet2(ds, nhide, nhide1, epo, wd, fn=fna)
NetworkWriter.writeToFile(nt, filename=fna + '.xml')
from pybrain.datasets import ClassificationDataSet
print "Reading data set..."
DS = ClassificationDataSet.loadFromFile('dataset.csv')
#Split validation set
TestDS, TrainDS = DS.splitWithProportion(0.25)
#train svm
from svm import svm_problem, svm_parameter, libsvm, gen_svm_nodearray
#define problem with data from the pybrain dataset.
# best python explanation for libsvm is here: https://github.com/arnaudsj/libsvm/tree/master/python
#we have to convert the data to ints and lists because of the low-level c interface
prob = svm_problem([int(t) for t in TrainDS['target']],
[list(i) for i in TrainDS['input']])
param = svm_parameter()
# option: -t 0: linear kernel. Best for classification.
# option: -c 0.01: regularization parameter. smaller is more regularization
# see below for all options
param.parse_options('-t 0 -c 0.01')
print "Training svm..."
model = libsvm.svm_train(prob, param)
print "Testing svm with three random inputs"
from random import randrange
for j in range(3):
i = randrange(0, len(TestDS))
#again some conversion needed because of low level interface
x0, m_idx = gen_svm_nodearray(list(TestDS['input'][i]))
prediction = libsvm.svm_predict(model, x0)
