class PoissonUnigramPattern:
def __init__(self, K, morpheme_prior, gamma, delta, pattern_vocabulary):
self.morpheme_model = DirichletMultinomial(K-2, morpheme_prior) # -START, -STOP
self.length_model = GammaPoisson(gamma, delta)
self.vocabulary = pattern_vocabulary
def increment(self, pattern):
morphemes = self.vocabulary[pattern]
for morpheme in morphemes:
self.morpheme_model.increment(morpheme-2)
self.length_model.increment(len(morphemes)-1)
def decrement(self, pattern):
morphemes = self.vocabulary[pattern]
for morpheme in morphemes:
self.morpheme_model.decrement(morpheme-2)
self.length_model.decrement(len(morphemes)-1)
def prob(self, pattern):
morphemes = self.vocabulary[pattern]
return (prod(self.morpheme_model.prob(m) for m in morphemes) *
self.length_model.prob(len(morphemes)-1))
def log_likelihood(self, full=False):
return (self.morpheme_model.log_likelihood(full)
+ self.length_model.log_likelihood(full))
def resample_hyperparemeters(self, n_iter):
return self.morpheme_model.resample_hyperparemeters(n_iter)
def __repr__(self):
return ('PoissonUnigram(length ~ {self.length_model},'
' morph ~ {self.morpheme_model})').format(self=self)
def sample_topics(doc, model, n_iter):
assignments = [None] * len(doc)
doc_topic = DirichletMultinomial(model.n_topics, model.alpha)
for it in xrange(n_iter):
for i, word in enumerate(doc):
if it > 0: doc_topic.decrement(assignments[i])
assignments[i] = mult_sample((k, (doc_topic.prob(k)
* model.topic_word[k].prob(word))) for k in xrange(model.n_topics))
doc_topic.increment(assignments[i])
return topic_vector(doc_topic, model)