def optimize_with_bic(self,data, kvals=None, maxiter = 300,
delta = 0.001, ninit=1,verbose = 0):
"""
Find the optimal GMM using bic criterion.
The method is run with all the values in kmax for k
Parameters
----------
data : (n,p) feature array, n = nb items, p=feature dimension
kvals=None : range of values for k.
if kvals==None, self.k is used
maxiter=300 : max number of iterations of the EM algorithm
delta = 0.001 : criterion on the log-likelihood
increments to declare converegence
ninit=1 : number of possible iterations of the GMM estimation
verbsose=0: verbosity mode
Returns
-------
Labels : array of shape(n), type np.int,
discrete labelling of the data items into clusters
LL : array of shape(n): log-likelihood of the data
bic : (float) associated bic criterion
"""
data = self.check_x(data)
if kvals==None:
LogLike, Labels, bic = self.estimate(data,None, maxiter,\
delta, ninit)
return Labels, LogLike, self.bic(LogLike)
bic_ref = -np.infty
for k in kvals:
self.k = k
nit = 10
mean, label,J = fc.kmeans(data, k, Labels=None)
Lab,LL, bic = self.estimate(data, label, maxiter, delta, ninit)
if bic>bic_ref:
kopt = k
C = self.means.copy()
P = self.precisions.copy()
W = self.weights.copy()
bic_ref = bic
if verbose:
print k,LL,bic,kopt
self.means = C
self.precisions = P
self.weights = W
self.k = kopt
if self.prec_type=='full':
precisions = np.reshape(self.precisions,(self.k,self.dim*self.dim))
else:
precisions = self.precisions
Labels, LogLike = fc.gmm_partition(data,self.means,precisions,\
self.weights)
return Labels, LogLike, self.bic_from_ll(LogLike)
def testpartition(self):
X = nr.randn(10000,2)
A = np.concatenate([np.ones((7000,2)),np.zeros((3000,2))])
X = X+3*A
C = np.array([[0,0],[3,3]])
P = np.array([[1,1],[1,1]])
W = np.array([0.5, 0.5])
L,G = fc.gmm_partition(X,C,P,W)
l = L[:7000].astype('d')
self.assert_(np.mean(l)>0.5)
def sample(self,gd,x,verbose=0):
"""
Evaluating the GMM on some new data
Parameters
----------
data : (n*p) feature array, n = nb items, p=feature dimension
Returns
-------
LL : array of shape (n) log-likelihood of the data
"""
data = gd.make_grid()
if self.prec_type=='full':
precisions = np.reshape(self.precisions,(self.k,self.dim*self.dim))
else:
precisions = self.precisions
Labels, LogLike = fc.gmm_partition(\
data,self.means,precisions, self.weights)
if verbose:
self.show(x,gd,np.exp(LogLike))
return LogLike
