#offset = 0
Xtrain = data[train, 0:-1]
#Xtrain = Xtrain[1,:,:]
ytrain = data[train, -1]
#ytrain = ytrain.ravel()
Xtest = data[test, 0:-1]
ytest = data[test, -1]
#ytest = ytest.ravel()
# trainset, testset = splitdataset(dataset)
# print('Split {0} rows into train={1} and test={2} rows').format(len(dataset), trainset[0].shape[0], testset[0].shape[0])
# nnparams = {'ni': trainset[0].shape[1], 'nh': 32, 'no': 1}
#Add comments here for testing purpose.
classalgs = {
'Random': algs.Classifier(),
'Linear Regression': algs.LinearRegressionClass(),
# 'Naive Bayes': algs.NaiveBayes({'usecolumnones': False})
'Logistic Regression': algs.LogitReg()
}
for learnername, learner in classalgs.iteritems():
#print 'Running learner = ' + learnername
# Train model
learner.learn(Xtrain, ytrain)
# Test model
#print ytest
predictions = learner.predict(Xtest)
#print
accuracy = getaccuracy(ytest, predictions)
if learnername == 'Random':
def cross_validate(K, X, Y, classalgs):
for k in range(K):
for learnername in classalgs:
print('make this work')
best_algorithm = classalgs[learnername]
return best_algorithm
if __name__ == '__main__':
trainsize = 5000
testsize = 5000
numruns = 10
classalgs = {'Random': algs.Classifier(),
# '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})
}
numalgs = len(classalgs)
parameters = (
{'regwgt': 0.0, 'nh': 4},
{'regwgt': 0.01, 'nh': 8},
{'regwgt': 0.05, 'nh': 16},
{'regwgt': 0.1, 'nh': 32},
)
numparams = len(parameters)
besterror = aveerror
bestparams = p
best_algorithm = classalgs[p]
return best_algorithm
if __name__ == '__main__':
trainsize = 5000
testsize = 5000
numruns = 10
classalgs = {
'Random':
algs.Classifier(),
'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}),
'LinearKernelLogitReg':
algs.KernelLogitReg({
'kernel': 'linear',
'regwgt': 0.01,
'regularizer': 'None'
