def main():
data = scipy.io.loadmat('spamData.mat')
xtrain = preprocess.log_transform(data['Xtrain'])
# xtrain = data['Xtrain']
ytrain = data['ytrain']
xtest = preprocess.log_transform(data['Xtest'])
ytest = data['ytest']
threshold = 0.1
reg_learn_pairs = [(0.1, 0.0001), (0.001, 0.001), (0.001, 0.0001), (0.0001, 0.001), (0.0001, 0.0001)]
for regularization_weight, learning_rate in reg_learn_pairs:
print 'Regularization_weight %s learning_rate %s' % (regularization_weight, learning_rate)
xplot = []
yplot = []
beta = batch(xtrain, ytrain, threshold, regularization_weight, learning_rate, xplot, yplot)
train = test_error(xtrain, ytrain, beta)
test = test_error(xtest, ytest, beta)
with open('res.txt', 'a') as f:
f.write('%s\t%s\t%s\t%s\n' % (regularization_weight, learning_rate, train, test))
f.flush()
# plot xplot vs yplot
pyplot.plot(xplot, yplot)
pyplot.title('Training Loss vs Number of Iterations.\nregularization_weight %s learning_rate %s' % (
regularization_weight, learning_rate))
pyplot.xlabel("Number of Iterations")
pyplot.ylabel("Negative Log Likelihood")
pyplot.show()
def main():
if len(sys.argv) != 2:
print 'Missing args. Usage: python crossval.py [regularization weight]'
return
the_file, regularization_weight = sys.argv
regularization_weight = float(regularization_weight)
data = scipy.io.loadmat('spamData.mat')
xtrain = preprocess.log_transform(data['Xtrain'])
ytrain = data['ytrain']
shuffled_xtrain, shuffled_ytrain = shuffle(xtrain, ytrain)
threshold = 0.0001
learning_rate = 0.0001
print 'Regularization_weight %s learning_rate %s' % (regularization_weight, learning_rate)
train = 0
test = 0
for i in range(5):
xtest, ytest, xtrain, ytrain = partition(shuffled_xtrain, shuffled_ytrain, i)
beta, xp, yp = batch(xtrain, ytrain, threshold, regularization_weight, learning_rate)
train += test_error(xtrain, ytrain, beta)
test += test_error(xtest, ytest, beta)
train = train / 5
test = test / 5
print '%s\t%s\t%s\t%s' % (regularization_weight, learning_rate, train, test)
with open('res%s.txt' % regularization_weight, 'a') as f:
f.write('%s\t%s\t%s\t%s\n' % (regularization_weight, learning_rate, train, test))
f.flush()