def _help_do_mstep(self, stats):
#add pseudo counts for nan entries
help_denum = _add_pseudo_counts( stats['post'] )
self.p[0] = stats['post_emission'][0] / (self.n[0] * help_denum)
self.p[1] = stats['post_emission'][1] / (self.n[1] * help_denum)
self.p[0] = _add_pseudo_counts(self.p[0])
self.p[1] = _add_pseudo_counts(self.p[1])
self.merge_distr()
def _help_do_mstep(self, stats):
#add pseudo counts for nan entries
help_denum = _add_pseudo_counts(stats['post'])
self.p[0] = stats['post_emission'][0] / (self.n[0] * help_denum)
self.p[1] = stats['post_emission'][1] / (self.n[1] * help_denum)
self.p[0] = _add_pseudo_counts(self.p[0])
self.p[1] = _add_pseudo_counts(self.p[1])
self.merge_distr()
def _help_do_mstep(self, stats):
for dim in range(self.n_features):
for comp in range(self.distr_magnitude):
for state in range(self.n_components):
self.c[dim][comp][state] = stats['post_sum_l'][dim][comp][
state] / _add_pseudo_counts(stats['post'][state])
if comp == 0:
self.p[dim][comp][state] = stats['post_sum_l_emisson'][
dim][comp][state] / (_add_pseudo_counts(
stats['post_sum_l_factor'][dim][comp][state]))
self.p[dim][comp][state] = _add_pseudo_counts(
self.p[dim][comp][state])
else:
self.p[dim][comp][
state] = self.factors[comp] * self.p[dim][0][state]
self.merge_distr(stats['weights'])
def _help_do_mstep(self, stats):
#add pseudo counts for nan entries
for dim in range(self.n_features):
for state in range(self.n_components):
for comp in range(self.distr_magnitude):
self.p[dim][state][comp] = stats['post_sum_l_emisson'][dim][state][comp] / (self.n[dim] * _add_pseudo_counts(stats['post_sum_l'][dim][state][comp]))
self.p[dim][state][comp] = _add_pseudo_counts(self.p[dim][state][comp])
self.c[dim][state][comp] = stats['post_sum_l'][dim][state][comp] / stats['post'][state]
def _help_do_mstep(self, stats):
#add pseudo counts for nan entries
for dim in range(self.n_features):
for state in range(self.n_components):
for comp in range(self.distr_magnitude):
self.p[dim][state][comp] = stats['post_sum_l_emisson'][dim][state][comp] / (self.n[dim] * _add_pseudo_counts(stats['post_sum_l'][dim][state][comp]))
self.p[dim][state][comp] = _add_pseudo_counts(self.p[dim][state][comp])
self.c[dim][state][comp] = stats['post_sum_l'][dim][state][comp] / stats['post'][state]
def _help_accumulate_sufficient_statistics(self, obs, stats, posteriors):
posteriors = _valid_posteriors(posteriors, obs)
i = 0
print("run...! start at " + str(time()), file=sys.stderr)
for t, symbol in enumerate(obs):
stats['post'] += posteriors[t]
for dim in range(self.n_features):
for comp in range(self.distr_magnitude):
#lookup
index = (symbol[dim],
tuple([
self.p[dim][comp][state]
for state in range(self.n_components)
]))
if index not in lookup_poisson_state:
tmp = np.array([
self._get_poisson(symbol[dim],
self.p[dim][comp][state])
for state in range(self.n_components)
])
lookup_poisson_state[index] = tmp
h = lookup_poisson_state[index]
enum = self.c[dim][comp] * h
denum = np.array([
self._get_value(state, symbol, dim)
for state in range(self.n_components)
])
i += 1
try:
help = posteriors[t] * enum / _add_pseudo_counts(denum)
except:
print("%s \n" % i, file=sys.stderr)
print("%s %s %s \n" % (denum, symbol, dim),
file=sys.stderr)
print("%s \n" % (self.c), file=sys.stderr)
print("%s \n" % (self.p), file=sys.stderr)
print("%s \n" % (posteriors[t]), file=sys.stderr)
print("%s \n" % (enum), file=sys.stderr)
help = np.array([
1.0 / self.distr_magnitude,
1.0 / self.distr_magnitude,
1.0 / self.distr_magnitude
])
stats['post_sum_l'][dim][comp] += help
stats['post_sum_l_emisson'][dim][
comp] += help * symbol[dim]
stats['post_sum_l_factor'][dim][
comp] += help * self.factors[comp]
if posteriors[t][1] > 0.5 or posteriors[t][2] > 0.5:
if posteriors[t][1] >= posteriors[t][2]:
stats['weights'][dim][state][0] += 1
if posteriors[t][2] > posteriors[t][1]:
stats['weights'][dim][state][1] += 1
#print(self.p)
stats['posterior'] = np.copy(posteriors)
def _help_do_mstep(self, stats):
for dim in range(self.n_features):
for comp in range(self.distr_magnitude):
for state in range(self.n_components):
self.c[dim][comp][state] = stats['post_sum_l'][dim][comp][state] / _add_pseudo_counts(stats['post'][state])
# if comp == 0:
self.p[dim][comp][state] = stats['post_sum_l_emisson'][dim][comp][state] / (_add_pseudo_counts(stats['post_sum_l_factor'][dim][comp][state]))
self.p[dim][comp][state] = _add_pseudo_counts(self.p[dim][comp][state])
# else:
# self.p[dim][comp][state] = self.factors[comp] * self.p[dim][0][state]
self.merge_distr(stats['weights'])
def _help_accumulate_sufficient_statistics(self, obs, stats, posteriors):
posteriors = _valid_posteriors(posteriors, obs)
i = 0
print("run...! start at " + str(time()), file=sys.stderr)
for t, symbol in enumerate(obs):
stats['post'] += posteriors[t]
for dim in range(self.n_features):
for comp in range(self.distr_magnitude):
#lookup
index = (symbol[dim], tuple([self.p[dim][comp][state] for state in range(self.n_components)]))
if index not in lookup_poisson_state:
tmp = np.array([self._get_poisson(symbol[dim], self.p[dim][comp][state]) for state in range(self.n_components)])
lookup_poisson_state[index] = tmp
h = lookup_poisson_state[index]
enum = self.c[dim][comp] * h
denum = np.array([self._get_value(state, symbol, dim) for state in range(self.n_components)])
i += 1
try:
help = posteriors[t] * enum / _add_pseudo_counts(denum)
except:
print("%s \n" %i, file=sys.stderr)
print("%s %s %s \n" %(denum, symbol, dim), file=sys.stderr)
print("%s \n" %(self.c), file=sys.stderr)
print("%s \n" %(self.p), file=sys.stderr)
print("%s \n" %(posteriors[t]), file=sys.stderr)
print("%s \n" %(enum), file=sys.stderr)
help = np.array([1.0/self.distr_magnitude, 1.0/self.distr_magnitude, 1.0/self.distr_magnitude])
stats['post_sum_l'][dim][comp] += help
stats['post_sum_l_emisson'][dim][comp] += help * symbol[dim]
stats['post_sum_l_factor'][dim][comp] += help * self.factors[comp]
if posteriors[t][1] > 0.5 or posteriors[t][2] > 0.5:
if posteriors[t][1] >= posteriors[t][2]:
stats['weights'][dim][state][0] += 1
if posteriors[t][2] > posteriors[t][1]:
stats['weights'][dim][state][1] += 1
#print(self.p)
stats['posterior'] = np.copy(posteriors)