def snll(data, nums, means, covs, prior):
return gmm.calcresps(data, nums, means, covs, True)[1] - np.log(prior)
hard = False
# Load data
data, classes, labels = readData(os.path.join('..','data','wine.data'))
lda = dimred.LDA(data, classes, labels, center=True, scale=True)
projData = lda.transform(data)
x = projData[0,:]
y = projData[1,:]
points = splitClasses(data,classes,labels)
gaussians = [density.Gaussian(data=p) for p in points]
means = np.array([g.mean() for g in gaussians]).T
covs = np.array([g.cov() for g in gaussians])
nums = np.array([ p.shape[1] for p in points ])
weights,nll = gmm.calcresps(data, nums, means, covs, hard=hard)
nums, means, covs, nll = gmm.gmm(data, weights, K=3, hard=hard, diagcov=False)
numsd,meansd,covsd,nlld = gmm.gmm(data, weights, K=3, hard=hard, diagcov=True)
print 'Question 2'
print 'NLL for diagcov=False: ', nll
print 'NLL for diagcov=True: ', nlld
print 'The diagcov=False seems to be the better choice.'
print 'Because we have enough data per class we can use a full estimate '
print 'of the covariance matrix without over-fitting. '
print 'These extra parameters allow us to make a better model which is '
print 'evident in the differance in negative-log-likelihood(NNL).\n'
weights,nll = gmm.calcresps(data, nums, means, covs, hard=hard)
def snll(data, nums, means, covs, prior):
return gmm.calcresps(data, nums, means, covs, True)[1] - np.log(prior)
hard = False
# Load data
data, classes, labels = readData(os.path.join('..', 'data', 'wine.data'))
lda = dimred.LDA(data, classes, labels, center=True, scale=True)
projData = lda.transform(data)
x = projData[0, :]
y = projData[1, :]
points = splitClasses(data, classes, labels)
gaussians = [density.Gaussian(data=p) for p in points]
means = np.array([g.mean() for g in gaussians]).T
covs = np.array([g.cov() for g in gaussians])
nums = np.array([p.shape[1] for p in points])
weights, nll = gmm.calcresps(data, nums, means, covs, hard=hard)
nums, means, covs, nll = gmm.gmm(data,
weights,
K=3,
hard=hard,
diagcov=False)
numsd, meansd, covsd, nlld = gmm.gmm(data,
weights,
K=3,
hard=hard,
diagcov=True)
print 'Question 2'
print 'NLL for diagcov=False: ', nll
print 'NLL for diagcov=True: ', nlld