def init(self, force=False):
base_path = util.path_dataset(self)
idxs = [self.index, self.index_stem, self.doc_store]
self._init_indices_parallel(idxs, self._init_iter_collection(), force)
qrels_file = os.path.join(base_path, 'qrels.robust2004.txt')
if (force or not os.path.exists(qrels_file)) and self._confirm_dua():
util.download(**_FILES['qrels'], file_name=qrels_file)
for fold in FOLDS:
fold_qrels_file = os.path.join(base_path, f'{fold}.qrels')
if (force or not os.path.exists(fold_qrels_file)):
all_qrels = trec.read_qrels_dict(qrels_file)
fold_qrels = {
qid: dids
for qid, dids in all_qrels.items() if qid in FOLDS[fold]
}
trec.write_qrels_dict(fold_qrels_file, fold_qrels)
query_file = os.path.join(base_path, 'topics.txt')
if (force or not os.path.exists(query_file)) and self._confirm_dua():
query_file_stream = util.download_stream(**_FILES['queries'],
encoding='utf8')
with util.finialized_file(query_file, 'wt') as f:
plaintext.write_tsv(f,
trec.parse_query_format(query_file_stream))
def qrels_path(self, fold_qrels_file):
if not fold_qrels_file.is_file():
with self.assessments.path.open("r") as fp:
all_qrels = trec.read_qrels_dict(fp)
fold_qrels = {
qid: dids
for qid, dids in all_qrels.items() if qid in self.qids
}
trec.write_qrels_dict(fold_qrels_file, fold_qrels)
return fold_qrels_file
def wrapped(it):
with util.finialized_file(file, 'wt') as f:
for doc in it:
if is_heldout == (doc.did in _HELD_OUT_IDS):
trec.write_qrels_dict(f, {doc.did: {doc.did: 1}})
def init(self, force=False):
needs_docs = []
for index in [self.index_stem, self.index_stem_2020, self.doc_store]:
if force or not index.built():
needs_docs.append(index)
if needs_docs and self._confirm_dua():
with contextlib.ExitStack() as stack:
doc_iter = self._init_iter_collection()
doc_iter = self.logger.pbar(doc_iter, desc='articles')
doc_iters = util.blocking_tee(doc_iter, len(needs_docs))
for idx, it in zip(needs_docs, doc_iters):
if idx is self.index_stem_2020:
it = (d for d in it if '2020' in d.data['date'])
stack.enter_context(
util.CtxtThread(functools.partial(idx.build, it)))
path = os.path.join(util.path_dataset(self), 'rnd1.tsv')
if not os.path.exists(path) and self._confirm_dua():
with util.download_tmp('https://ir.nist.gov/covidSubmit/data/topics-rnd1.xml', expected_md5="cf1b605222f45f7dbc90ca8e4d9b2c31") as f, \
util.finialized_file(path, 'wt') as fout:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'query', topic.find('query').get_text()),
(qid, 'quest', topic.find('question').get_text()),
(qid, 'narr', topic.find('narrative').get_text()),
])
udel_flag = path + '.includes_udel'
if not os.path.exists(udel_flag):
with open(path,
'at') as fout, util.finialized_file(udel_flag, 'wt'):
with util.download_tmp(
'https://raw.githubusercontent.com/castorini/anserini/master/src/main/resources/topics-and-qrels/topics.covid-round1-udel.xml',
expected_md5="2915cf59ae222f0aa20b2a671f67fd7a") as f:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'udel', topic.find('query').get_text()),
])
path = os.path.join(util.path_dataset(self), 'rnd2.tsv')
if not os.path.exists(path) and self._confirm_dua():
with util.download_tmp('https://ir.nist.gov/covidSubmit/data/topics-rnd2.xml', expected_md5="550129e71c83de3fb4d6d29a172c5842") as f, \
util.finialized_file(path, 'wt') as fout:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'query', topic.find('query').get_text()),
(qid, 'quest', topic.find('question').get_text()),
(qid, 'narr', topic.find('narrative').get_text()),
])
udel_flag = path + '.includes_udel'
if not os.path.exists(udel_flag):
with open(path,
'at') as fout, util.finialized_file(udel_flag, 'wt'):
with util.download_tmp(
'https://raw.githubusercontent.com/castorini/anserini/master/src/main/resources/topics-and-qrels/topics.covid-round2-udel.xml',
expected_md5="a8988734e6f812921d5125249c197985") as f:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'udel', topic.find('query').get_text()),
])
path = os.path.join(util.path_dataset(self), 'rnd5.tsv')
if not os.path.exists(path) and self._confirm_dua():
with util.download_tmp('https://ir.nist.gov/covidSubmit/data/topics-rnd5.xml', expected_md5="0307a37b6b9f1a5f233340a769d538ea") as f, \
util.finialized_file(path, 'wt') as fout:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'query', topic.find('query').get_text()),
(qid, 'quest', topic.find('question').get_text()),
(qid, 'narr', topic.find('narrative').get_text()),
])
udel_flag = path + '.includes_udel'
if not os.path.exists(udel_flag):
with open(path,
'at') as fout, util.finialized_file(udel_flag, 'wt'):
with util.download_tmp(
'https://raw.githubusercontent.com/castorini/anserini/master/src/main/resources/topics-and-qrels/topics.covid-round5-udel.xml',
expected_md5="966a49487348dc853634bcdd0829fd26") as f:
soup = BeautifulSoup(f.read(), 'lxml-xml')
for topic in soup.find_all('topic'):
qid = topic['number']
plaintext.write_tsv(fout, [
(qid, 'udel', topic.find('query').get_text()),
])
qrels_file = os.path.join(util.path_dataset(self), 'rnd5.qrels')
if (force or not os.path.exists(qrels_file)) and self._confirm_dua():
util.download(
'https://raw.githubusercontent.com/castorini/anserini/master/src/main/resources/topics-and-qrels/qrels.covid-round4-cumulative.txt',
qrels_file)
for fold in FOLDS:
fold_qrels_file = os.path.join(util.path_dataset(self),
f'{fold}-rnd5.qrels')
if (force or not os.path.exists(fold_qrels_file)):
all_qrels = trec.read_qrels_dict(qrels_file)
fold_qrels = {
qid: dids
for qid, dids in all_qrels.items()
if str(qid) in FOLDS[fold]
}
trec.write_qrels_dict(fold_qrels_file, fold_qrels)