def penalized_ll(nbcs, data):
ll = 0.0
cluster_priors = [log(1.0 * c.size / len(data)) for c in nbcs]
for inst in data:
vals = [cluster_priors[i] + nbcs[i].fast_ll(inst, float('-inf')) for i in range(len(nbcs))]
ll += logsumexp( vals )
ll -= knobs.cluster_penalty * len(nbcs) * data.shape[1]
return ll
def nbmix_likelihood_from_model(data, lprobs, priors):
nc = lprobs[0].shape[0]
lp = np.zeros(nc)
ll = 0.0
for d in data:
lp[:] = 0.0
for j in range(data.shape[1]):
lp += lprobs[j,:,d[j]]
lp += priors
ll += logsumexp(lp)
return ll
def max_likelihood_qa(data, nvals, qa, approximate=False, smooth=0.1):
nc = qa.max() + 1
sil = np.zeros(nc)
for i in range(nc):
di = data[qa==i].astype(np.int)
total = float(len(di))
si = 0.0
for j in range(di.shape[1]):
bc = np.bincount(di[:,j])
for c in bc:
if c == 0:
continue
si += c*log(c / total)
si += log(total / len(data)) # cluster prior
sil[i] = si
s = sil.sum() if approximate else logsumexp(sil)
return s
