aveerr = np.mean(errs[learnername])
print('Average error for ' + learnername + ': ' + str(aveerr))
if aveerr < besterr:
besterr = aveerr
best_algorithm = learnername
print('best algorithm is: ', best_algorithm, 'with error: ', besterr)
return best_algorithm
if __name__ == '__main__':
trainsize = 5000
testsize = 5000
numruns = 1
classalgs = {'Random': algs.Classifier(),
'Linear Regression': algs.LinearRegressionClass(),
'Naive Bayes': algs.NaiveBayes({'usecolumnones': False}),
'Naive Bayes Ones': algs.NaiveBayes({'usecolumnones': True}),
'Linear Regression': algs.LinearRegressionClass(),
'Logistic Regression': algs.LogitReg(),
'Neural Network': algs.NeuralNet({'epochs': 100}),
'Neural Network 2': algs.NeuralNet2({'epochs': 100}),
'KernelLogitReg': algs.KernelLogitReg(),
# 'KernelLogitReg': algs.KernelLogitReg({'kernel': 'hamming'})
##################### for calling cross validation use these instead ####################
# 'Neural Network 4 32': algs.NeuralNet({'nh': 4, 'batch_size': 32}),
# 'Neural Network 16 32': algs.NeuralNet({'nh': 16, 'batch_size': 32}),
# 'Neural Network 4 128': algs.NeuralNet({'nh': 4, 'batch_size': 128}),
# 'Neural Network 16 128': algs.NeuralNet({'nh': 16, 'batch_size': 128}),
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
}),
'kernel Logistic Regression':
algs.KernelLogitReg({'k': 30}),
'Hamming kernel Logistic Regression':
algs.KernelLogitReg({
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={}
