def anneal_clusters(vbParam):
N, K = vbParam.rhat.shape
stability = calculate_stability(vbParam.rhat)
if np.all(stability > 0.8):
cc = [[k] for k in range(K)]
return vbParam.rhat.argmax(1), stability, cc
maha = mfm.calc_mahalonobis(vbParam, vbParam.muhat.transpose((1, 0, 2)))
maha = np.maximum(maha, maha.T)
maha_thresh_min = 0
for k_target in range(K - 1, 0, -1):
# get connected components with k_target number of them
cc, maha_thresh_min = get_k_cc(maha, maha_thresh_min, k_target)
# calculate soft assignment for each cc
rhat_cc = np.zeros([N, len(cc)])
for i, units in enumerate(cc):
rhat_cc[:, i] = np.sum(vbParam.rhat[:, units], axis=1)
rhat_cc[rhat_cc < 0.001] = 0.0
rhat_cc = rhat_cc / np.sum(rhat_cc, axis=1, keepdims=True)
# calculate stability for each component
# and make decision
stability = calculate_stability(rhat_cc)
if np.all(stability > 0.8) or k_target == 1:
return rhat_cc.argmax(1), stability, cc
def recover_spikes(self, vbParam, pca, maha_dist=1):
N, D = pca.shape
# Cat: TODO: check if this maha thresholding recovering distance is good
threshold = np.sqrt(chi2.ppf(0.99, D))
# update rhat on full data
maskedData = mfm.maskData(pca[:,:,np.newaxis], np.ones([N, 1]), np.arange(N))
vbParam.update_local(maskedData)
# calculate mahalanobis distance
maha = mfm.calc_mahalonobis(vbParam, pca[:,:,np.newaxis])
idx_recovered = np.where(~np.all(maha >= threshold, axis=1))[0]
vbParam.rhat = vbParam.rhat[idx_recovered]
# zero out low assignment vals
if True:
vbParam.rhat[vbParam.rhat < self.assignment_delete_threshold] = 0
vbParam.rhat = vbParam.rhat/np.sum(vbParam.rhat,
1, keepdims=True)
return idx_recovered, vbParam
def cluster_annealing(self, vbParam):
N, K = vbParam.rhat.shape
stability = self.calculate_stability(vbParam.rhat)
if (K == 2) or np.all(stability > 0.8):
cc = [[k] for k in range(K)]
return vbParam.rhat.argmax(1), stability, cc
maha = mfm.calc_mahalonobis(vbParam, vbParam.muhat.transpose(
(1, 0, 2)))
maha = np.maximum(maha, maha.T)
#N, K = vbParam.rhat.shape
#mu = np.copy(vbParam.muhat[:,:,0].T)
#mudiff = mu[:,np.newaxis] - mu
#prec = vbParam.Vhat[:,:,:,0].T * vbParam.nuhat[:,np.newaxis, np.newaxis]
#maha = np.matmul(np.matmul(mudiff[:, :, np.newaxis], prec[:, np.newaxis]), mudiff[:, :, :, np.newaxis])[:, :, 0, 0]
# decrease number of connected components one at a time.
# in any step if all components are stables, stop and return
# otherwise, go until there are only two connected components and return it
maha_thresh_min = 0
for k_target in range(K - 1, 1, -1):
# get connected components with k_target number of them
cc, maha_thresh_min = self.get_k_cc(maha, maha_thresh_min,
k_target)
# calculate soft assignment for each cc
rhat_cc = np.zeros([N, len(cc)])
for i, units in enumerate(cc):
rhat_cc[:, i] = np.sum(vbParam.rhat[:, units], axis=1)
rhat_cc[rhat_cc < 0.001] = 0.0
rhat_cc = rhat_cc / np.sum(rhat_cc, axis=1, keepdims=True)
# calculate stability for each component
# and make decision
stability = self.calculate_stability(rhat_cc)
if np.all(stability > 0.8) or k_target == 2:
return rhat_cc.argmax(1), stability, cc