def getAllBoW(self):
"""Return unigram, bigram words as bag of words."""
fname = 'cache/word_ngrams.%s.set%d.dom%d.pickle' % (
self.getFilename(), self.getEssaySet(), self.getDomain())
try:
f = open(fname, 'rb')
bow = pickle.load(f)
except:
bigram_measures = nltk.collocations.BigramAssocMeasures()
bow = list()
for line in self.getRawText():
cur = LanguageUtils.tokenize(line)
finder = BigramCollocationFinder.from_words(cur)
scored = finder.score_ngrams(bigram_measures.pmi)
for bigram, score in scored:
cur.append(bigram)
bow.append(cur)
pickle.dump(bow, open(fname, 'w'))
return bow
def getPOS(self):
if len(self.pos_tags) > 0:
return self.pos_tags
fname = 'cache/pos.%s.set%d.pickle' % (self.file_name, self.essay_set)
try:
f = open(fname, 'rb')
self.pos_tags = pickle.load(f)
except:
pos_lines = list()
tot_ln = self.size()
prog = 0
hunpos = nltk.tag.HunposTagger("en_wsj.model")
for line in self.getRawText():
tokens = LanguageUtils.punkt_tokenize(line)
pos_tags = hunpos.tag(tokens)
tags_only = [tag for w, tag in pos_tags]
pos_lines.append(tags_only)
prog += 1
if prog % 100 == 0:
print "POS Tagging %d of %d" % (prog, tot_ln)
self.pos_tags = pos_lines
f = open(fname, 'w')
pickle.dump(self.pos_tags, f)
return self.pos_tags
def extractFeatures(self, ds, corpus):
"""Extracts features from a DataSet ds"""
# load into memory the string from data/essay_set_desc_?.txt
f = open('data/essay_set_desc_%d.txt' % ds.getEssaySet(), 'r')
prompt = f.read()
# tokenize into unigrams & bigrams
tokens = LanguageUtils.tokenize(prompt)
bigram_measures = nltk.collocations.BigramAssocMeasures()
finder = BigramCollocationFinder.from_words(tokens)
scored = finder.score_ngrams(bigram_measures.raw_freq)
for bigram, score in scored:
tokens.append(bigram)
# Get feature bows for projection into LSI
dictionary = corpus.getWordDictionary()
# get lsi
lsi = corpus.getLSA()
tfidf = corpus.getTfidf()
mm_corpus = ds.getGensimCorpus()
# project into lsi space
vec_bow = dictionary.doc2bow(tokens)
vec_lsi = lsi[tfidf[vec_bow]]
index = gensim.similarities.MatrixSimilarity(lsi[tfidf[ds.getGensimCorpus()]])
sims = index[vec_lsi]
feats = list()
for sim in sims:
cur_feat = list()
cur_feat.append(sim)
feats.append(cur_feat)
self.features = np.asarray(feats)
return
