t, p = stats.ttest_ind(NaiveBayes, Logistic, equal_var=False)
print('t-value is: %f, p-vaule is: %f' % (t, p))
if p < alpha:
print("Reject h0,NaiveBayes and Logistic are different!")
else:
print("Fail to reject h0")
if __name__ == '__main__':
trainsize = 90000
testsize = 10000
numruns = 10
classalgs = {
#'Linear Regression': algs.LinearRegressionClass(),
'Naive Bayes': algs.NaiveBayes({'usecolumnones': False}),
'Logistic Regression': algs.LogitReg(),
'Neural Network': algs.NeuralNet({'epochs': 100}),
#'KernelLogitReg': algs.KernelLogitReg({'kernel': 'linear'})
}
numalgs = len(classalgs)
parameters = (
# best parameters for now
{
'regwgt': 0.1,
'nh': 12,
'eta': 0.0001
},
# {'regwgt': 0.1, 'nh': 2,'eta':0.01},
# {'regwgt': 0.01, 'nh': 4,'eta':0.001},
learnername + ': ' +
str(STDeviation(std[learnername], errors[learnername])))
learner = min(errors, key=errors.get)
best_algorithm = learner
return best_algorithm
if __name__ == '__main__':
trainsize = 5000
testsize = 5000
numruns = 3
classalgs = { #'Random': algs.Classifier(),
'Naive Bayes':
algs.NaiveBayes({'usecolumnones': False}),
'Naive Bayes Ones':
algs.NaiveBayes({'usecolumnones': True}),
'Linear Regression':
algs.LinearRegressionClass(),
'Logistic Regression Reg':
algs.LogitReg({
'regularizer': 'l2',
'lamb': 0.001,
'stepsize': 0.001
}),
'Logistic Regression':
algs.LogitReg({
'lamb': 0.001,
'stepsize': 0.001
}),
trainset, testset = loadsusy()
"""The choice of the number of folds should be user-input"""
fold=10
trainlabel=np.reshape(trainset[1],(-1,1))
trset = np.hstack((trainset[0],trainlabel))
numinputs = trset.shape[1]-1
np.random.shuffle(trset)
parts = [trset[i::fold] for i in xrange(fold)]
obj=[]
print('Running on train={0} and test={1} samples').format(trainset[0].shape[0], testset[0].shape[0])
parm_pass={'Neural Network':{'ni': trset.shape[1]-1, 'nh': 0, 'no': 1},
'Logistic Regression':{'regwt':0,'type':"L2"}}
classalgs = {'Linear Regression': algs.LinearRegressionClass(),
'Naive Bayes Ones': algs.NaiveBayes(),
'Logistic Regression': algs.LogitReg(parm_pass['Logistic Regression']),
'Neural Network': algs.NeuralNet(parm_pass['Neural Network'])
}
classalgs1 = collections.OrderedDict(sorted(classalgs.items()))
best_parm=[]
for learnername , learner in classalgs1.iteritems():
print 'Running learner = ' + learnername
# # Train model
parm_accuracy={}
