def cluster(data, k, mode='full'):
d = data.shape[1]
gm = GM(d, k, mode)
gmm = GMM(gm, 'random')
em = RegularizedEM(pcnt=pcnt, pval=pval)
em.train(data, gmm, maxiter=20)
return gm, gmm.bic(data)
def cluster(data, k, mode = 'full'):
d = data.shape[1]
gm = GM(d, k, mode)
gmm = GMM(gm)
em = EM()
em.train(data, gmm, maxiter = 20)
return gm, gmm.bic(data)
def cluster(data, k, mode = 'full'):
d = data.shape[1]
gm = GM(d, k, mode)
gmm = GMM(gm, 'random')
em = RegularizedEM(pcnt = pcnt, pval = pval)
em.train(data, gmm, maxiter = 20)
return gm, gmm.bic(data)
def cluster(data, k):
d = data.shape[1]
gm = GM(d, k)
gmm = GMM(gm)
em = EM()
em.train(data, gmm, maxiter=20)
return gm, gmm.bic(data)
#++++++++++++++++++++++++
# Learn the model with EM
#++++++++++++++++++++++++
# List of learned mixtures lgm[i] is a mixture with i+1 components
lgm = []
kmax = 6
bics = N.zeros(kmax)
em = EM()
for i in range(kmax):
lgm.append(GM(d, i+1, mode))
gmm = GMM(lgm[i], 'kmean')
em.train(data, gmm, maxiter = 30, thresh = 1e-10)
bics[i] = gmm.bic(data)
print "Original model has %d clusters, bics says %d" % (k, N.argmax(bics)+1)
#+++++++++++++++
# Draw the model
#+++++++++++++++
import pylab as P
P.subplot(3, 2, 1)
for k in range(kmax):
P.subplot(3, 2, k+1)
level = 0.9
P.plot(data[:, 0], data[:, 1], '.', label = '_nolegend_')
# h keeps the handles of the plot, so that you can modify
