def main():
inputs = ReadCSV('./data/input.csv')
outputs = ReadCSV('./data/output.csv')
ids = make_list(outputs)
x = []
y = {}
for i in range(3, 24, 3):
x.append(i)
for hidden_layers in range(
1, 7): #change loop for plot also if you change here
print 'Number of hidden layers', hidden_layers
y[hidden_layers] = []
for i in x:
print 'Number of training tuples', i
y[hidden_layers].append(
find_accuracy(i, ids, hidden_layers, inputs, outputs))
#print x
#print y
#Now plot the graph
for i in range(1, 7):
t = pylab.plot(x,
y[i],
label="Number of hidden layers " + str(i),
linewidth=4,
linestyle='-')
t = pylab.xlabel("Number of training tuples")
t = pylab.ylabel("Accuracy %")
t = pylab.title(
"Random Subset Sampling (Number of training samples vs Accuracy)")
t = pylab.legend(loc='lower right')
t = pylab.grid()
pylab.show()
def main():
inputs = ReadCSV('./data/input.csv')
outputs = ReadCSV('./data/output.csv')
test_set = test.keys()
train_set = []
for k in inputs.keys():
if k not in test_set:
train_set.append(k)
print "Number of training samples", len(train_set)
print "Number of testing samples", len(test_set)
net = buildNetwork(178, 6, 5)
ds=SupervisedDataSet(178,5)
for id in train_set:
ds.addSample(inputs[id],outputs[id])
trainer = BackpropTrainer(net, ds, learningrate=0.001, momentum = 0.001)
trainer.trainUntilConvergence(maxEpochs=1000, validationProportion = 0.5)
for id in test_set:
predicted = net.activate(inputs[id])
actual = outputs[id]
print '-----------------------------'
print test[id]
print '-----------------------------'
print 'Trait\t\tPredicted\tActual\tError'
for i in range(0,5):
error = abs(predicted[i] - actual[i])*100/4.0
print traits[i], '\t', predicted[i], '\t', actual[i], '\t', error,"%"
def main():
inputs = ReadCSV('./data/input.csv')
outputs = ReadCSV('./data/output.csv')
ids = make_list(outputs)
x = []
y = {}
for i in range(2, 11, 2):
x.append(i)
for hidden_layers in range(
1, 6): #change loop for plot also if you change here
print 'Number of hidden layers', hidden_layers
y[hidden_layers] = []
for i in x:
print 'Number of folds', i
y[hidden_layers].append(
find_accuracy(i, ids, hidden_layers, inputs, outputs))
#print x
#print y
#Now plot the graph
for i in range(1, 6):
t = pylab.plot(x,
y[i],
label="Number of hidden layers " + str(i),
linewidth=4,
linestyle='-')
t = pylab.xlabel("Number of folds")
t = pylab.ylabel("Accuracy %")
t = pylab.title("K-Fold cross validation (Number of folds vs Accuracy)")
t = pylab.legend(loc='lower right')
t = pylab.grid()
pylab.show()
def main():
inputs = ReadCSV('./data/input.csv')
outputs = ReadCSV('./data/output.csv')
ids = make_list(outputs)
net = constructNet(ids, inputs, outputs)
pickle.dump(net, open('neuralNet.sl', 'w'))
import sys
sys.path.append('./lib')
from ReadCSV import ReadCSV
print ReadCSV("./data/input.csv")
from ReadCSV import ReadCSV
rs = ReadCSV(
'/home/dgrfi/MEGA/supersymmetry/7TeVxyz.csv').read_matrix_in_dataframe()
from pybrain.tools.shortcuts import buildNetwork
from pybrain.datasets import SupervisedDataSet
from pybrain.structure import TanhLayer
from pybrain.supervised.trainers import BackpropTrainer
import pickle
import sys
sys.path.append('./lib')
from ReadCSV import ReadCSV
new_input = ReadCSV("newinput.csv")
net = pickle.load(open("neuralNet.sl", "r"))
input = new_input[new_input.keys()[0]]
traits = net.activate(input)
text = ""
for trait in traits:
text = text + str(trait) + " "
print text
def createSample(self):
sum_w8 = self.w.sum_weights(self.w.weights)
#print(sum_w8)
rd = ReadCSV()
sample = rd.create_sampleList(self.sample_limit, self.db, sum_w8)
return sample
accuracies = []
for i in range(self.turns):
print(" turn ", i)
validationSet = self.create_validation_set(div_db, i)
#print(len(validationSet))
adaboost_set = []
for j in range(self.turns):
if (j != i):
adaboost_set += div_db[j]
adaboost_set = [self.attr_list] + adaboost_set
fscr, accuracy_per_turn = self.fscr_per_turn(
adaboost_set, validationSet)
#print(fscr)
f1Scores.append(fscr)
accuracies.append(accuracy_per_turn)
#print(len(f1Scores))
fscore = sum(f1Scores) / float(self.turns)
acc_score = sum(accuracies) / float(self.turns)
print("the f1 score of simulation: ", fscore)
print("the accuracy of simulation: ", acc_score)
##################################################################################
rd = ReadCSV()
db_1 = rd.produceDB()
k = KFoldCross(db_1, 5)
#print(k.block_size)
k.validation()
