def extract_multilingual_documents(inv_dict, langs, text_path, out_path):
if not os.path.exists(out_path):
os.makedirs(out_path)
for lang in langs:
if lang not in inv_dict:
raise ValueError("Lang %s is not in the dictionary" % lang)
docs_created = len(list_files(out_path))
print("%d multilingual documents found." % docs_created)
for doc, lang in _doc_generator(text_path, langs):
title = _extract_title(doc)
if title in inv_dict[lang]:
#pass
ids = inv_dict[lang][title]
for id in ids:
target_file = join(out_path, id) + ".xml"
if os.path.exists(target_file):
_append_doc(target_file, doc, lang)
else:
_create_doc(target_file, id, doc, lang)
docs_created += 1
else:
if not re.match('[A-Za-z]+', title):
print("Title <%s> for lang <%s> not in dictionary" %
(title, lang))
def _doc_generator(text_path, langs):
dotspace = re.compile(r'\.(?!\s)')
for l, lang in enumerate(langs):
print("Processing language <%s> (%d/%d)" % (lang, l, len(langs)))
lang_dir = join(text_path, lang)
split_dirs = list_dirs(lang_dir)
for sd, split_dir in enumerate(split_dirs):
print("\tprocessing split_dir <%s> (%d/%d)" %
(split_dir, sd, len(split_dirs)))
split_files = list_files(join(lang_dir, split_dir))
for sf, split_file in enumerate(split_files):
print("\t\tprocessing split_file <%s> (%d/%d)" %
(split_file, sf, len(split_files)))
with BZ2File(join(lang_dir, split_dir, split_file),
'r',
buffering=1024 * 1024) as fi:
while True:
doc_lines = list(islice(fi, 3))
if doc_lines:
# some sentences are not followed by a space after the dot
doc_lines[1] = dotspace.sub('. ', doc_lines[1])
# [workaround] I found html symbol was not treated, and unescaping it now might not help...
doc_lines[1] = escape(doc_lines[1].replace(
" ", " "))
yield doc_lines, lang
else:
break
def fetch_wikipedia_multilingual(wiki_multi_path, langs, min_words=100, deletions=False, max_documents=-1, pickle_name=None):
if pickle_name and os.path.exists(pickle_name):
print("unpickling %s" % pickle_name)
return pickle.load(open(pickle_name, 'rb'))
multi_docs = list_files(wiki_multi_path)
mling_documents = {l:[] for l in langs}
valid_documents = 0
minwords_exception = 0
wrongdoc_exception = 0
for d,multi_doc in enumerate(multi_docs):
print("\rProcessed %d/%d documents, valid %d/%d, few_words=%d, few_langs=%d" %
(d, len(multi_docs), valid_documents, len(multi_docs), minwords_exception, wrongdoc_exception),end="")
doc_path = join(wiki_multi_path, multi_doc)
try:
m_doc = _load_multilang_doc(doc_path, langs, min_words)
valid_documents += 1
for l in langs:
mling_documents[l].append(m_doc[l])
except MinWordsNotReached:
minwords_exception += 1
if deletions: os.remove(doc_path)
except WrongDocumentFormat:
wrongdoc_exception += 1
if deletions: os.remove(doc_path)
if max_documents>0 and valid_documents>=max_documents:
break
if pickle_name:
print("Pickling wikipedia documents object in %s" % pickle_name)
pickle.dump(mling_documents, open(pickle_name, 'wb'), pickle.HIGHEST_PROTOCOL)
return mling_documents
def fetch_RCV1(data_path, split='all'):
assert split in ['train', 'test',
'all'], 'split should be "train", "test", or "all"'
request = []
labels = set()
read_documents = 0
lang = 'en'
training_documents = 23149
test_documents = 781265
if split == 'all':
split_range = (2286, 810596)
expected = training_documents + test_documents
elif split == 'train':
split_range = (2286, 26150)
expected = training_documents
else:
split_range = (26151, 810596)
expected = test_documents
global nwords
nwords = []
for part in list_files(data_path):
if not re.match('\d+\.zip', part): continue
target_file = join(data_path, part)
assert exists(target_file), \
"You don't seem to have the file "+part+" in " + data_path + ", and the RCV1 corpus can not be downloaded"+\
" w/o a formal permission. Please, refer to " + RCV1_BASE_URL + " for more information."
zipfile = ZipFile(target_file)
for xmlfile in zipfile.namelist():
xmlcontent = zipfile.open(xmlfile).read()
try:
doc = parse_document(xmlcontent,
assert_lang=lang,
valid_id_range=split_range)
labels.update(doc.categories)
request.append(doc)
read_documents += 1
except ValueError:
print(
'\n\tskipping document {} with inconsistent language label: expected language {}'
.format(part + '/' + xmlfile, lang))
except (IDRangeException, ExpectedLanguageException) as e:
pass
print('\r[{}] read {} documents'.format(part, len(request)),
end='')
if read_documents == expected: break
if read_documents == expected: break
print()
print('ave:{} std {} min {} max {}'.format(np.mean(nwords), np.std(nwords),
np.min(nwords), np.max(nwords)))
return request, list(labels)
def fetch_RCV2(data_path, languages=None):
if not languages:
languages = list(RCV2_LANG_DIR.keys())
else:
assert set(languages).issubset(set(
RCV2_LANG_DIR.keys())), 'languages not in scope'
request = []
labels = set()
global nwords
nwords = []
for lang in languages:
path = join(data_path, RCV2_LANG_DIR[lang])
lang_docs_read = 0
for part in list_files(path):
target_file = join(path, part)
assert exists(target_file), \
"You don't seem to have the file "+part+" in " + path + ", and the RCV2 corpus can not be downloaded"+\
" w/o a formal permission. Please, refer to " + RCV2_BASE_URL + " for more information."
zipfile = ZipFile(target_file)
for xmlfile in zipfile.namelist():
xmlcontent = zipfile.open(xmlfile).read()
try:
doc = parse_document(xmlcontent, assert_lang=lang)
labels.update(doc.categories)
request.append(doc)
lang_docs_read += 1
except ValueError:
print(
'\n\tskipping document {} with inconsistent language label: expected language {}'
.format(
RCV2_LANG_DIR[lang] + '/' + part + '/' + xmlfile,
lang))
except (IDRangeException, ExpectedLanguageException) as e:
pass
print('\r[{}] read {} documents, {} for language {}'.format(
RCV2_LANG_DIR[lang] + '/' + part, len(request),
lang_docs_read, lang),
end='')
print()
print('ave:{} std {} min {} max {}'.format(np.mean(nwords), np.std(nwords),
np.min(nwords), np.max(nwords)))
return request, list(labels)
def fetch_jrcacquis(
langs=None,
data_path=None,
years=None,
ignore_unclassified=True,
cat_filter=None,
cat_threshold=0,
parallel=None,
most_frequent=-1,
DOWNLOAD_URL_BASE='http://optima.jrc.it/Acquis/JRC-Acquis.3.0/corpus/'
):
assert parallel in [None, 'force', 'avoid'], 'parallel mode not supported'
if not langs:
langs = JRC_LANGS
else:
if isinstance(langs, str): langs = [langs]
for l in langs:
if l not in JRC_LANGS:
raise ValueError(
'Language %s is not among the valid languages in JRC-Acquis v3'
% l)
if not data_path:
data_path = get_data_home()
if not os.path.exists(data_path):
os.mkdir(data_path)
request = []
total_read = 0
for l in langs:
file_name = 'jrc-' + l + '.tgz'
archive_path = join(data_path, file_name)
if not os.path.exists(archive_path):
print(
"downloading language-specific dataset (once and for all) into %s"
% data_path)
DOWNLOAD_URL = join(DOWNLOAD_URL_BASE, file_name)
download_file(DOWNLOAD_URL, archive_path)
print("untarring dataset...")
tarfile.open(archive_path, 'r:gz').extractall(data_path)
documents_dir = join(data_path, l)
print("Reading documents...")
read = 0
for dir in list_dirs(documents_dir):
year = int(dir)
if years == None or year in years:
year_dir = join(documents_dir, dir)
pickle_name = join(data_path,
'jrc_' + l + '_' + dir + '.pickle')
if os.path.exists(pickle_name):
print("loading from file %s" % pickle_name)
l_y_documents = pickle.load(open(pickle_name, "rb"))
read += len(l_y_documents)
else:
l_y_documents = []
all_documents = list_files(year_dir)
empty = 0
for i, doc_file in enumerate(all_documents):
try:
jrc_doc = parse_document(join(year_dir, doc_file),
year)
except ValueError:
jrc_doc = None
if jrc_doc and (not ignore_unclassified
or jrc_doc.categories):
l_y_documents.append(jrc_doc)
else:
empty += 1
if len(all_documents) > 50 and (
(i + 1) % (len(all_documents) / 50) == 0):
print('\r\tfrom %s: completed %d%%' %
(year_dir,
int((i + 1) * 100.0 / len(all_documents))),
end='')
read += 1
print(
'\r\tfrom %s: completed 100%% read %d documents (discarded %d without categories or empty fields)\n'
% (year_dir, i + 1, empty),
end='')
print("\t\t(Pickling object for future runs in %s)" %
pickle_name)
pickle.dump(l_y_documents, open(pickle_name, 'wb'),
pickle.HIGHEST_PROTOCOL)
request += l_y_documents
print("Read %d documents for language %s\n" % (read, l))
total_read += read
print("Read %d documents in total" % (total_read))
if parallel == 'force':
request = _force_parallel(request, langs)
elif parallel == 'avoid':
request = random_sampling_avoiding_parallel(request)
final_cats = _get_categories(request)
if cat_filter:
request = _filter_by_category(request, cat_filter)
final_cats = _get_categories(request)
if cat_threshold > 0:
request, final_cats = _filter_by_frequency(request, cat_threshold)
if most_frequent != -1 and len(final_cats) > most_frequent:
request, final_cats = _most_common(request, most_frequent)
return request, final_cats
