def xml_train_test_prep(field='body', relevance='TACM'):
train_file = os.path.join(args.data_dir, 'qd.xml.seg.train')
test_file = os.path.join(args.data_dir, 'qd.xml.seg.test')
max_vocab_size = args.max_vocab_size
train_word_file = os.path.join(args.data_dir, 'train.pointwise')
test_word_file = os.path.join(args.data_dir, 'test.pointwise')
train_prep_file = os.path.join(args.data_dir, 'train.prep.pointwise')
test_prep_file = os.path.join(args.data_dir, 'test.prep.pointwise')
vocab_file = os.path.join(args.data_dir, 'vocab')
field_in_xml = xml_field_maping(field)
print('build vocab ...')
vocab = Vocab(max_size=max_vocab_size)
for i, qd in enumerate(qd_xml_iterator(train_file)):
'''
query = qd.find('./query').text
words = query.split(' ')
for doc in qd.findall('./doc/{}'.format(field_in_xml)):
words.extend(doc.text.split(' '))
'''
if i % 10000 == 0:
print('{}w'.format(i // 10000))
query = qd['query']
words = query.split(' ')
for doc in qd['doc']:
words.extend(doc[field_in_xml].split(' '))
for w in words:
vocab.add(w)
vocab.build()
vocab.save_to_file(vocab_file)
for from_file, word_file, prep_file in \
[(train_file, train_word_file, train_prep_file), (test_file, test_word_file, test_prep_file)]:
qd_xml_to_prep(from_file,
prep_file,
vocab,
field_in_xml=field_in_xml,
relevance=relevance)
def preprocess():
binary = args.binary_html
data_dir = args.data_dir
max_vocab_size = args.max_vocab_size
docs_dir = os.path.join(data_dir, 'docs')
query_filepath = os.path.join(data_dir, 'query')
train_filepath = os.path.join(data_dir, 'train.pointwise')
test_filepath = os.path.join(data_dir, 'test.pointwise')
vocab = Vocab(max_size=max_vocab_size)
train_query_ids, train_doc_ids = get_query_doc_ids(train_filepath)
test_query_ids, test_doc_ids = get_query_doc_ids(test_filepath)
query_ids = train_query_ids | test_query_ids
doc_ids = train_doc_ids | test_doc_ids
print('total query: {}, total doc: {}'.format(len(query_ids),
len(doc_ids)))
query_dict = load_from_query_file(query_filepath)
doc_dict = {}
for qid in sorted(train_query_ids):
for term in query_dict[qid].split():
vocab.add(term)
count = 0
for docid in sorted(train_doc_ids):
count += 1
if count % 10000 == 0:
print('processed {}w docs'.format(count // 10000))
doc_body = load_from_html_cascade(os.path.join(docs_dir,
docid + '.html'),
binary=binary)['body']
doc_dict[docid] = doc_body
#print(docid)
#print(' '.join(doc_body))
#input()
for term in doc_body:
vocab.add(term)
vocab.build()
vocab.save_to_file(os.path.join(data_dir, 'vocab'))
empty_qid, empty_docid = set(), set()
with open(os.path.join(data_dir, 'query.prep'), 'w') as fp:
for qid in sorted(query_ids):
qt = query_dict[qid].split()
if len(qt) == 0:
empty_qid.add(qid)
continue
fp.write('{}\t{}\n'.format(
qid, ' '.join(map(lambda x: str(x), vocab.encode(qt)))))
with open(os.path.join(data_dir, 'docs.prep'), 'w') as fp:
for docid in sorted(doc_ids):
if docid in doc_dict:
doc_body = doc_dict[docid]
else:
doc_body = load_from_html_cascade(os.path.join(
docs_dir, docid + '.html'),
binary=binary)['body']
if len(doc_body) == 0:
empty_docid.add(docid)
continue
fp.write('{}\t{}\n'.format(
docid, ' '.join(map(lambda x: str(x),
vocab.encode(doc_body)))))
print('have {} empty query, have {} empty doc'.format(
len(empty_qid), len(empty_docid)))
filter_samples(train_filepath,
'{}.prep.{}'.format(*train_filepath.rsplit('.', 1)),
empty_qid, empty_docid)
filter_samples(test_filepath,
'{}.prep.{}'.format(*test_filepath.rsplit('.', 1)),
empty_qid, empty_docid)
