def modified_process(filename):
''' Serial processing of abstracts, no topic modeling. '''
abstracts = []
dictionary = []
# load stop words
stops = set()
stop_file = 'stopwords.txt'
with open(stop_file, 'rU') as stopFile:
for row in stopFile.readlines():
stops.add(row.replace('\n', ''))
dictlist = Process.load(filename, abstracts, stops)
# create dictionary
Process.create_dict(dictlist, dictionary)
# clean text of words not in dictionary
for abstract in abstracts:
abstext = [word for word in abstract.Get('cleantext') if word in dictionary]
abstract.Set('cleantext', abstext)
dictlength = len(dictionary)
bigramdict = []
termbow = defaultdict(float)
termbigram = defaultdict(float)
for abstract in abstracts:
# create dict of word frequency (bag of words)
bow = Process.create_bagofwords(abstract, dictionary)
abstract.Set('bow', bow)
abstract.Set('bownum', dictlength)
for ind in bow.keys():
termbow[ind] += 1.0
# create dict of bigram frequency
bigram, bigramdict = Process.create_bigram(abstract, dictionary, bigramdict)
abstract.Set('bigram', bigram)
for pair in bigram.keys():
termbigram[pair] += 1.0
# create dict of tfidf
Process.serial_tfidf(abstracts, 'bow', termbow, len(bigramdict))
Process.serial_tfidf(abstracts, 'bigram', termbigram)
return abstracts
scleanend = time.time()
sfreqstart = time.time()
dictlength = len(dictionary)
bigramdict = []
termbow = defaultdict(float)
termbigram = defaultdict(float)
for abstract in abstracts:
# create dict of word frequency (bag of words)
bow = Process.create_bagofwords(abstract, dictionary)
abstract.Set('bow', bow)
abstract.Set('bownum', dictlength)
for ind in bow.keys():
termbow[ind] += 1.0
# create dict of bigram frequency
bigram, bigramdict = Process.create_bigram(abstract, dictionary, bigramdict)
abstract.Set('bigram', bigram)
for pair in bigram.keys():
termbigram[pair] += 1.0
sfreqend = time.time()
# create dict of tfidf
stfidfstart = time.time()
Process.serial_tfidf(abstracts, 'bow', termbow, len(bigramdict))
Process.serial_tfidf(abstracts, 'bigram', termbigram)
stfidfend = time.time()
# do some topic modeling
stopicstart = time.time()
Process.serial_topics(abstracts, Process.numtopics)
stopicend = time.time()
def process(filename):
''' Serial processing of abstracts, for evaluation purposes. '''
abstracts = []
dictionary = []
# load stop words
stops = set()
stop_file = 'stopwords.txt'
with open(stop_file, 'rU') as stopFile:
for row in stopFile.readlines():
stops.add(row.replace('\n', ''))
dictlist = Process.load(filename, abstracts, stops)
# create dictionary
Process.create_dict(dictlist, dictionary)
# clean text of words not in dictionary
for abstract in abstracts:
abstext = [word for word in abstract.Get('cleantext') if word in dictionary]
abstract.Set('cleantext', abstext)
dictlength = len(dictionary)
bigramdict = []
termbow = defaultdict(float)
termbigram = defaultdict(float)
for abstract in abstracts:
# create dict of word frequency (bag of words)
bow = Process.create_bagofwords(abstract, dictionary)
abstract.Set('bow', bow)
abstract.Set('bownum', dictlength)
for ind in bow.keys():
termbow[ind] += 1.0
# create dict of bigram frequency
bigram, bigramdict = Process.create_bigram(abstract, dictionary, bigramdict)
abstract.Set('bigram', bigram)
for pair in bigram.keys():
termbigram[pair] += 1.0
# create dict of tfidf
Process.serial_tfidf(abstracts, 'bow', termbow, len(bigramdict))
Process.serial_tfidf(abstracts, 'bigram', termbigram)
##### TOPICS
# prepare dictionary and corpora for topic modeling
docs = [abstract.Get('cleantext') for abstract in abstracts]
dictionary = corpora.Dictionary(docs)
dictionary.save('abstracts.dict')
corpus = [dictionary.doc2bow(doc) for doc in docs]
corpora.MmCorpus.serialize('abstracts.mm', corpus)
# use gensim tfidf to transform
tfidf = models.TfidfModel(corpus)
corpus_tfidf = tfidf[corpus]
# load lsa and lda models
numtopics = 10 # this can be adjusted
lsaModel = Lsa.serial(corpus_tfidf, dictionary, numtopics)
ldaModel = Lda.serial(corpus_tfidf, dictionary, numtopics, alpha=50.0/numtopics, eta=2.0/numtopics)
# store lda and lsa representation in all abstracts
for i in xrange(len(abstracts)):
lsaVec = lsaModel[tfidf[corpus[i]]]
ldaVec = ldaModel[tfidf[corpus[i]]]
lsaVector = defaultdict(float)
ldaVector = defaultdict(float)
for v in lsaVec:
lsaVector[v[0]] = v[1]
for v in ldaVec:
ldaVector[v[0]] = v[1]
abstracts[i].Set('lsa', lsaVector)
abstracts[i].Set('lda', ldaVector)
abstracts[i].Set('numtopics', numtopics)
return abstracts
