def train_transitions(labelled_sequences,
additional_transitions,
estimator=None):
# default to the MLE estimate
if estimator is None:
estimator = lambda fdist, bins: MLEProbDist(fdist)
# count occurrences of starting states, transitions out of each state
# and output symbols observed in each state
known_symbols = []
known_states = []
starting = FreqDist()
transitions = ConditionalFreqDist()
outputs = ConditionalFreqDist()
for sequence in labelled_sequences:
lasts = None
for token in sequence:
state = token[0]
symbol = token[1]
if lasts is None:
starting[state] += 1
else:
transitions[lasts][state] += 1
outputs[state][symbol] += 1
lasts = state
# update the state and symbol lists
if state not in known_states:
known_states.append(state)
if symbol not in known_symbols:
known_symbols.append(symbol)
# create probability distributions (with smoothing)
N = len(known_states)
pi = estimator(starting, N)
A = ConditionalProbDist(
ConditionalFreqDist.__add__(transitions, additional_transitions),
estimator, N)
B = ConditionalProbDist(outputs, estimator, len(known_symbols))
return hmm.HiddenMarkovModelTagger(known_states, known_symbols, A, B, pi)
