def create_queries_vec(project):
corpus_fname_base = project.full_path + 'Queries'
corpus_fname = corpus_fname_base + '.ordered.gz'
dict_fname = corpus_fname_base + '.dict.gz'
if not os.path.exists(corpus_fname):
pp = GeneralCorpus(lazy_dict=True)
id2word = Dictionary()
with open(os.path.join(project.full_path, 'ids.txt')) as f:
ids = [x.strip() for x in f.readlines()]
queries = list()
for id in ids:
with open(
os.path.join(project.full_path, 'queries',
'ShortDescription' + id + '.txt')) as f:
short = f.read()
with open(
os.path.join(project.full_path, 'queries',
'LongDescription' + id + '.txt')) as f:
long = f.read()
text = ' '.join([short, long])
text = list(pp.preprocess(text))
queries.append((text, (id, 'query')))
OrderedCorpus.serialize(corpus_fname, queries, metadata=True)
corpus = OrderedCorpus(corpus_fname)
return corpus
def create_queries(project):
corpus_fname_base = project.full_path + 'Queries'
corpus_fname = corpus_fname_base + '.ordered.gz'
dict_fname = corpus_fname_base + '.dict.gz'
if not os.path.exists(corpus_fname):
pp = GeneralCorpus(lazy_dict=True)
id2word = Dictionary()
with open(os.path.join(project.full_path, 'ids.txt')) as f:
ids = [x.strip() for x in f.readlines()]
queries = list()
for id in ids:
with open(
os.path.join(project.full_path, 'queries',
'ShortDescription' + id + '.txt')) as f:
short = f.read()
with open(
os.path.join(project.full_path, 'queries',
'LongDescription' + id + '.txt')) as f:
long = f.read()
text = ' '.join([short, long])
text = pp.preprocess(text)
# this step will remove any words not found in the dictionary
bow = id2word.doc2bow(text, allow_update=True)
queries.append((bow, (id, 'query')))
# write the corpus and dictionary to disk. this will take awhile.
MalletCorpus.serialize(corpus_fname,
queries,
id2word=id2word,
metadata=True)
# re-open the compressed versions of the dictionary and corpus
id2word = None
if os.path.exists(dict_fname):
id2word = Dictionary.load(dict_fname)
corpus = MalletCorpus(corpus_fname, id2word=id2word)
return corpus
def create_queries(project):
corpus_fname_base = project.full_path + 'Queries'
corpus_fname = corpus_fname_base + '.mallet.gz'
dict_fname = corpus_fname_base + '.dict.gz'
if not os.path.exists(corpus_fname):
pp = GeneralCorpus(lazy_dict=True)
id2word = Dictionary()
with open(os.path.join(project.full_path, 'ids.txt')) as f:
ids = [x.strip() for x in f.readlines()]
queries = list()
for id in ids:
with open(os.path.join(project.full_path, 'queries',
'ShortDescription' + id + '.txt')) as f:
short = f.read()
with open(os.path.join(project.full_path, 'queries',
'LongDescription' + id + '.txt')) as f:
long = f.read()
text = ' '.join([short, long])
text = pp.preprocess(text)
# this step will remove any words not found in the dictionary
bow = id2word.doc2bow(text, allow_update=True)
queries.append((bow, (id, 'query')))
# write the corpus and dictionary to disk. this will take awhile.
MalletCorpus.serialize(corpus_fname, queries, id2word=id2word,
metadata=True)
# re-open the compressed versions of the dictionary and corpus
id2word = None
if os.path.exists(dict_fname):
id2word = Dictionary.load(dict_fname)
corpus = MalletCorpus(corpus_fname, id2word=id2word)
return corpus
