def setup_module():
# Need to do this because the dataIterator function depends
# on the BOW file to be generated.
global ac_train
global ac_dev
docsToBOWs(TRAINKEY)
docsToBOWs(DEVKEY)
ac_train = getAllCounts(dataIterator(TRAINKEY))
ac_dev = getAllCounts(dataIterator(DEVKEY))
def setup_module():
# Need to do this because the dataIterator function depends
# on the BOW file to be generated.
global ac_train
global ac_dev
docsToBOWs(TRAINKEY)
docsToBOWs(DEVKEY)
ac_train = getAllCounts (dataIterator (TRAINKEY))
ac_dev = getAllCounts (dataIterator (DEVKEY))
def get_HMM_weights(trainfile):
"""Train a set of of log-prob weights using HMM transition model
Parameters:
trainfile -- The name of the file to train weights
Returns:
weights -- Weights dict with log-prob of transition and emit features
ngrams("I really like", 2)
(I, really)
(really, like)
(end_tag,'N',trans) => q(stop/N) => (N, end_tag)
q(stop/N) = count(stop, N) / count(N)
"""
# compute naive bayes weights
counters = most_common.get_tags(trainfile)
class_counts = most_common.get_class_counts(counters)
allwords = set()
for counts in counters.values():
allwords.update(set(counts.keys()))
nb_weights = naivebayes.learnNBWeights(counters, class_counts, allwords, alpha=0.001)
# convert nb weights to hmm weights
hmm_weights = defaultdict(lambda: -1000.0)
for (tag, word), weight in nb_weights.iteritems():
hmm_weights[(tag, word, EMIT)] = weight
unigram = preproc.getNgrams(trainfile)
bigram = preproc.getNgrams(trainfile, 2)
unigramCount = preproc.getAllCounts(unigram)
bigramCount = preproc.getAllCounts(bigram)
for (tag1, tag2) in bigramCount.keys():
hmm_weights[(tag2, tag1, TRANS)] = np.log(1.0 * bigramCount.get((tag1, tag2), 0)) - np.log(
unigramCount.get(tag1, 0)
)
return hmm_weights
