def step(self, anneal, model_params, my_data):
""" Perform an EM-step """
# Noisify model parameters
model_params = self.noisify_params(model_params, anneal)
# Sanity check model parameters
model_params = self.check_params(model_params)
# For partial EM-step: select batch
my_pdata = self.select_partial_data(anneal, my_data)
# Annotate partial dataset with hidden-state candidates
my_pdata = self.select_Hprimes(model_params, my_pdata)
# Do E-step and calculate joint-probabilities
my_joint_prob = self.E_step(anneal, model_params, my_pdata)
# Use joint-probabilities to derive new parameter set
new_model_params = self.M_step(
anneal, model_params, my_joint_prob, my_pdata)
# Calculate Objecive Function
#[Q, theo_Q] = self.objective(my_joint_prob, model_params, my_pdata)
#dlog.append('Q', Q)
#dlog.append('theo_Q', theo_Q)
# Log iboth model parameters and annealing parameters
dlog.append_all(new_model_params)
dlog.append_all(anneal.as_dict())
return new_model_params
'sigma_gt')
dlog.set_handler(print_list, TextPrinter)
dlog.set_handler(print_list, StoreToTxt, output_path + '/result.h5')
dlog.set_handler(h5_list, StoreToH5, output_path + '/result.h5')
dlog.append('W_gt', params_gt['W'])
dlog.append('sigma_gt', params_gt['sigma'])
dlog.append('pi_gt', params_gt['pi'])
dlog.append('N', N)
dlog.append('Hprime', Hprime)
dlog.append('H', H)
dlog.append('gamma', gamma)
dlog.append('states', states)
model_params = model.standard_init(my_data)
dlog.append_all(model_params)
for param_name in model_params.keys():
if param_name not in model.to_learn:
model_params[param_name] = params_gt[param_name]
model.s_gt = my_s
# Choose annealing schedule
anneal = LinearAnnealing(100)
anneal['T'] = [(0.0, 2.), (0.1, 2.), (0.4, 1.)]
anneal['Ncut_factor'] = [(0, 0.0), (0.6, 0.0), (0.9, 1.)]
# anneal['W_noise'] = [(0, 5.0), (.6, 0.0)]
# anneal['pi_noise'] = [(0, 0.1), (.6, 0.0)]
anneal['anneal_prior'] = False
# Create and start EM annealing
em = EM(model=model, anneal=anneal)