def estimate(self, data, Labels=None, maxiter = 300, delta = 0.001,
ninit=1):
"""
Estimation of the GMM based on data and an EM algorithm
Parameters
----------
data : (n*p) feature array, n = nb items, p=feature dimension
Labels=None : prior labelling of the data
(this may improve convergence)
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
Returns
-------
Labels : array of shape(n), type np.int:
discrete labelling of the data items into clusters
LL : (float) average log-likelihood of the data
bic : (float) associated bic criterion
"""
data = self.check_x(data)
if Labels==None:
Labels = np.zeros(data.shape[0],np.int)
nit = 10
C,Labels,J = fc.kmeans(data,self.k,Labels,nit)
if (self.k>data.shape[0]-1):
print "too many clusters"
self.k = data.shape[0]-1
if self.prec_type=='full':prec_type=0
if self.prec_type=='diag': prec_type=1
C, P, W, Labels, bll = fc.gmm(data,self.k,Labels,prec_type,
maxiter,delta)
self.means = C
if self.prec_type=='diag':
self.precisions = P
if self.prec_type=='full':
self.precisions = np.reshape(P,(self.k,self.dim,self.dim))
self.weights = W
self.check()
for i in range(ninit-1):
Labels = np.zeros(data.shape[0])
C, P, W, labels, ll = fc.gmm(data,self.k,Labels,
prec_type,maxiter,delta)
if ll>bll:
self.means = C
if self.prec_type=='diag':
self.precisions = P
if self.prec_type=='full':
self.precisions = np.reshape(P,(self.k,self.dim,self.dim))
self.weights = W
self.check()
bll = ll
Labels = labels
return Labels,bll, self.bic_from_all (bll,data.shape[0])
def testgmm3(self):
X = nr.randn(10000,2)
A = np.concatenate([np.ones((7000,2)),np.zeros((3000,2))])
X = X+3*A
L = np.concatenate([np.ones(5000), np.zeros(5000)]).astype(np.int)
C,P,W,L,J = fc.gmm(X,2,L,2)
C,P,W,L,J = fc.gmm(X,2,L,1)
C,P,W,L,J = fc.gmm(X,2,L,0)
l = L[:7000].astype('d')
self.assert_(np.mean(l)>0.9)
def testgmm2(self):
X = nr.randn(10000,2)
A = np.concatenate([np.ones((7000,2)),np.zeros((3000,2))])
X = X+3*A
C,P,W,L,J = fc.gmm(X,2)
dW= W[0]-W[1]
ndW = dW*dW
self.assert_(ndW > 0.1)
def testgmm1_andCheckResult(self):
np.random.seed(0) # force the random sequence
X = nr.randn(10000,2)
A = np.concatenate([np.ones((7000,2)),np.zeros((3000,2))])
X = X+3*A
L = np.concatenate([np.ones(5000), np.zeros(5000)]).astype(np.int)
C,P,W,L,J = fc.gmm(X,2,L);
np.random.seed(None) # re-randomize the seed
# results for randomseed = 0
expectC = np.concatenate([np.zeros((1,2)),3*np.ones((1,2))])
expectP = np.ones((2,2))
expectW = np.array([ 0.3, 0.7])
expectSL = 7000;
self.assert_( np.allclose(C, expectC,0.01,0.05 ))
self.assert_( np.allclose(P, expectP,0.03,0.05))
self.assert_( np.allclose(W, expectW ,0.03,0.05))
self.assert_( np.allclose(expectSL, L.sum(),0.01))