def __init__(self, n, observation_sequence=None, default=0):
# In addition to the dictionary of n-tuples, cond_prob is a
# mapping from (w1, ..., wn-1) to P(wn | w1, ... wn-1)
CountingProbDist.__init__(self, default=default)
self.n = n
self.cond_prob = defaultdict()
self.add_sequence(observation_sequence or [])
def __init__(self, observation_sequence=None, default=0):
CountingProbDist.__init__(self, default=default)
self.n = 1
self.cond_prob = defaultdict()
self.add_sequence(observation_sequence or [])
def add_cond_prob(self, ngram):
"""Build the conditional probabilities P(wn | (w1, ..., wn-1)"""
if ngram[:-1] not in self.cond_prob:
self.cond_prob[ngram[:-1]] = CountingProbDist()
self.cond_prob[ngram[:-1]].add(ngram[-1])
def __init__(self, training_text):
training_text = canonicalize(training_text)
self.P2 = CountingProbDist(bigrams(training_text), default=1)