def init(self, force=False): path = util.path_dataset(self) needs_collection = [] for index in [self.index, self.index_stem, self.doc_store]: if force or not index.built(): needs_collection.append(index.build) for subset in ['main', 'heldout']: is_heldout = (subset == 'heldout') query_file = os.path.join(path, f'{subset}.queries') if force or not os.path.exists(query_file): needs_collection.append( self._init_build_queryfile(query_file, is_heldout)) qrels_file = os.path.join(path, f'{subset}.qrels') if force or not os.path.exists(query_file): needs_collection.append( self._init_build_qrels(qrels_file, is_heldout)) if needs_collection and self._confirm_dua(): with contextlib.ExitStack() as stack: collection_iter = logger.pbar(self._init_iter_corpus(), desc='collection') sub_iters = util.blocking_tee(collection_iter, len(needs_collection)) for fn, it in zip(needs_collection, sub_iters): stack.enter_context( util.CtxtThread(functools.partial(fn, it)))
def init(self, force=False): base_dir = os.path.join(util.path_dataset(self), self.subset) if self.subset == 'dummy': datafile = os.path.join(base_dir, 'datafile.tsv') qrels = os.path.join(base_dir, 'qrels.txt') if not os.path.exists(datafile): os.symlink(os.path.abspath('etc/dummy_datafile.tsv'), datafile) if not os.path.exists(qrels): os.symlink(os.path.abspath('etc/dummy_qrels.txt'), qrels) needs_datafile = [] if force or not self.index.built(): needs_datafile.append(lambda it: self.index.build( indices.RawDoc(did, txt) for t, did, txt in it if t == 'doc')) if force or not self.index_stem.built(): needs_datafile.append(lambda it: self.index_stem.build( indices.RawDoc(did, txt) for t, did, txt in it if t == 'doc')) if force or not self.doc_store.built(): needs_datafile.append(lambda it: self.doc_store.build( indices.RawDoc(did, txt) for t, did, txt in it if t == 'doc')) query_file = os.path.join(base_dir, 'queries.tsv') if force or not os.path.exists(query_file): needs_datafile.append( lambda it: plaintext.write_tsv(query_file, ( (qid, txt) for t, qid, txt in it if t == 'query'))) if needs_datafile: df_glob = os.path.join(base_dir, 'datafile*.tsv') datafiles = glob(df_glob) while not datafiles: c = util.confirm( f'No data files found. Please move/link data files to {df_glob}.\n' 'Data files should contain both queries and documents in the ' 'following format (one per line):\n' '[query|doc] [TAB] [qid/did] [TAB] [text]') if not c: sys.exit(1) datafiles = glob(df_glob) main_iter = itertools.chain(*(plaintext.read_tsv(df) for df in datafiles)) main_iter = tqdm(main_iter, desc='reading datafiles') iters = util.blocking_tee(main_iter, len(needs_datafile)) with contextlib.ExitStack() as stack: for fn, it in zip(needs_datafile, iters): stack.enter_context( util.CtxtThread(functools.partial(fn, it))) qrels_file = os.path.join(base_dir, 'qrels.txt') while not os.path.exists(qrels_file): c = util.confirm( f'No qrels file found. Please move/link qrels file to {qrels_file}.\n' 'Qrels file should be in the TREC format:\n' '[qid] [SPACE] Q0 [SPACE] [did] [SPACE] [score]') if not c: sys.exit(1)
def _init_indices_parallel(self, indices, doc_iter, force): needs_docs = [] for index in indices: if force or not index.built(): needs_docs.append(index) if needs_docs and self._confirm_dua(): with contextlib.ExitStack() as stack: doc_iters = util.blocking_tee(doc_iter, len(needs_docs)) for idx, it in zip(needs_docs, doc_iters): stack.enter_context(util.CtxtThread(functools.partial(idx.build, it)))
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), 'rnd1.qrels') if not os.path.exists(path) and self._confirm_dua(): util.download( 'https://ir.nist.gov/covidSubmit/data/qrels-rnd1.txt', path, expected_md5="d58586df5823e7d1d0b3619a73b31518")
def init(self, force=False): idxs = [self.index_stem, self.doc_store] self._init_indices_parallel(idxs, self._init_iter_collection(), force) base_path = util.path_dataset(self) needs_queries = [] if force or not os.path.exists( os.path.join(base_path, 'train.queries.tsv')): needs_queries.append(lambda it: plaintext.write_tsv( os.path.join(base_path, 'train.queries.tsv'), ((qid, txt) for file, qid, txt in it if file == 'queries.train.tsv' and qid not in MINI_DEV))) if force or not os.path.exists( os.path.join(base_path, 'minidev.queries.tsv')): needs_queries.append(lambda it: plaintext.write_tsv( os.path.join(base_path, 'minidev.queries.tsv'), ((qid, txt) for file, qid, txt in it if file == 'queries.train.tsv' and qid in MINI_DEV))) if force or not os.path.exists( os.path.join(base_path, 'dev.queries.tsv')): needs_queries.append(lambda it: plaintext.write_tsv( os.path.join(base_path, 'dev.queries.tsv'), ((qid, txt) for file, qid, txt in it if file == 'queries.dev.tsv'))) if force or not os.path.exists( os.path.join(base_path, 'eval.queries.tsv')): needs_queries.append(lambda it: plaintext.write_tsv( os.path.join(base_path, 'eval.queries.tsv'), ((qid, txt) for file, qid, txt in it if file == 'queries.eval.tsv'))) if needs_queries and self._confirm_dua(): with util.download_tmp(_SOURCES['queries']) as f, \ tarfile.open(fileobj=f) as tarf, \ contextlib.ExitStack() as ctxt: def _extr_subf(subf): for qid, txt in plaintext.read_tsv( io.TextIOWrapper(tarf.extractfile(subf))): yield subf, qid, txt query_iter = [ _extr_subf('queries.train.tsv'), _extr_subf('queries.dev.tsv'), _extr_subf('queries.eval.tsv') ] query_iter = tqdm(itertools.chain(*query_iter), desc='queries') query_iters = util.blocking_tee(query_iter, len(needs_queries)) for fn, it in zip(needs_queries, query_iters): ctxt.enter_context( util.CtxtThread(functools.partial(fn, it))) file = os.path.join(base_path, 'train.qrels') if (force or not os.path.exists(file)) and self._confirm_dua(): stream = util.download_stream(_SOURCES['train-qrels'], 'utf8') with util.finialized_file(file, 'wt') as out: for qid, _, did, score in plaintext.read_tsv(stream): if qid not in MINI_DEV: trec.write_qrels(out, [(qid, did, score)]) file = os.path.join(base_path, 'minidev.qrels') if (force or not os.path.exists(file)) and self._confirm_dua(): stream = util.download_stream(_SOURCES['train-qrels'], 'utf8') with util.finialized_file(file, 'wt') as out: for qid, _, did, score in plaintext.read_tsv(stream): if qid in MINI_DEV: trec.write_qrels(out, [(qid, did, score)]) file = os.path.join(base_path, 'dev.qrels') if (force or not os.path.exists(file)) and self._confirm_dua(): stream = util.download_stream(_SOURCES['dev-qrels'], 'utf8') with util.finialized_file(file, 'wt') as out: for qid, _, did, score in plaintext.read_tsv(stream): trec.write_qrels(out, [(qid, did, score)]) file = os.path.join(base_path, 'train.mspairs.gz') if not os.path.exists(file) and os.path.exists( os.path.join(base_path, 'qidpidtriples.train.full')): # legacy os.rename(os.path.join(base_path, 'qidpidtriples.train.full'), file) if (force or not os.path.exists(file)) and self._confirm_dua(): util.download(_SOURCES['qidpidtriples.train.full'], file) if not self.config['init_skip_msrun']: for file_name, subf in [('dev.msrun', 'top1000.dev'), ('eval.msrun', 'top1000.eval'), ('train.msrun', 'top1000.train.txt')]: file = os.path.join(base_path, file_name) if (force or not os.path.exists(file)) and self._confirm_dua(): run = {} with util.download_tmp(_SOURCES[file_name]) as f, \ tarfile.open(fileobj=f) as tarf: for qid, did, _, _ in tqdm( plaintext.read_tsv( io.TextIOWrapper(tarf.extractfile(subf)))): if qid not in run: run[qid] = {} run[qid][did] = 0. if file_name == 'train.msrun': minidev = { qid: dids for qid, dids in run.items() if qid in MINI_DEV } with self.logger.duration('writing minidev.msrun'): trec.write_run_dict( os.path.join(base_path, 'minidev.msrun'), minidev) run = { qid: dids for qid, dids in run.items() if qid not in MINI_DEV } with self.logger.duration(f'writing {file_name}'): trec.write_run_dict(file, run) query_path = os.path.join(base_path, 'trec2019.queries.tsv') if (force or not os.path.exists(query_path)) and self._confirm_dua(): stream = util.download_stream(_SOURCES['trec2019.queries'], 'utf8') plaintext.write_tsv(query_path, plaintext.read_tsv(stream)) msrun_path = os.path.join(base_path, 'trec2019.msrun') if (force or not os.path.exists(msrun_path)) and self._confirm_dua(): run = {} with util.download_stream(_SOURCES['trec2019.msrun'], 'utf8') as stream: for qid, did, _, _ in plaintext.read_tsv(stream): if qid not in run: run[qid] = {} run[qid][did] = 0. with util.finialized_file(msrun_path, 'wt') as f: trec.write_run_dict(f, run) qrels_path = os.path.join(base_path, 'trec2019.qrels') if not os.path.exists(qrels_path) and self._confirm_dua(): util.download(_SOURCES['trec2019.qrels'], qrels_path) qrels_path = os.path.join(base_path, 'judgedtrec2019.qrels') if not os.path.exists(qrels_path): os.symlink('trec2019.qrels', qrels_path) query_path = os.path.join(base_path, 'judgedtrec2019.queries.tsv') judged_qids = util.Lazy( lambda: trec.read_qrels_dict(qrels_path).keys()) if (force or not os.path.exists(query_path)): with util.finialized_file(query_path, 'wt') as f: for qid, qtext in plaintext.read_tsv( os.path.join(base_path, 'trec2019.queries.tsv')): if qid in judged_qids(): plaintext.write_tsv(f, [(qid, qtext)]) msrun_path = os.path.join(base_path, 'judgedtrec2019.msrun') if (force or not os.path.exists(msrun_path)) and self._confirm_dua(): with util.finialized_file(msrun_path, 'wt') as f: for qid, dids in trec.read_run_dict( os.path.join(base_path, 'trec2019.msrun')).items(): if qid in judged_qids(): trec.write_run_dict(f, {qid: dids}) # A subset of dev that only contains queries that have relevance judgments judgeddev_path = os.path.join(base_path, 'judgeddev') judged_qids = util.Lazy(lambda: trec.read_qrels_dict( os.path.join(base_path, 'dev.qrels')).keys()) if not os.path.exists(f'{judgeddev_path}.qrels'): os.symlink('dev.qrels', f'{judgeddev_path}.qrels') if not os.path.exists(f'{judgeddev_path}.queries.tsv'): with util.finialized_file(f'{judgeddev_path}.queries.tsv', 'wt') as f: for qid, qtext in plaintext.read_tsv( os.path.join(base_path, 'dev.queries.tsv')): if qid in judged_qids(): plaintext.write_tsv(f, [(qid, qtext)]) if self.config['init_skip_msrun']: if not os.path.exists(f'{judgeddev_path}.msrun'): with util.finialized_file(f'{judgeddev_path}.msrun', 'wt') as f: for qid, dids in trec.read_run_dict( os.path.join(base_path, 'dev.msrun')).items(): if qid in judged_qids(): trec.write_run_dict(f, {qid: dids}) if not self.config['init_skip_train10']: file = os.path.join(base_path, 'train10.queries.tsv') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout: for qid, qtext in self.logger.pbar( plaintext.read_tsv( os.path.join(base_path, 'train.queries.tsv')), desc='filtering queries for train10'): if int(qid) % 10 == 0: plaintext.write_tsv(fout, [(qid, qtext)]) file = os.path.join(base_path, 'train10.qrels') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout, open( os.path.join(base_path, 'train.qrels'), 'rt') as fin: for line in self.logger.pbar( fin, desc='filtering qrels for train10'): qid = line.split()[0] if int(qid) % 10 == 0: fout.write(line) if not self.config['init_skip_msrun']: file = os.path.join(base_path, 'train10.msrun') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout, open( os.path.join(base_path, 'train.msrun'), 'rt') as fin: for line in self.logger.pbar( fin, desc='filtering msrun for train10'): qid = line.split()[0] if int(qid) % 10 == 0: fout.write(line) file = os.path.join(base_path, 'train10.mspairs.gz') if not os.path.exists(file): with gzip.open(file, 'wt') as fout, gzip.open( os.path.join(base_path, 'train.mspairs.gz'), 'rt') as fin: for qid, did1, did2 in self.logger.pbar( plaintext.read_tsv(fin), desc='filtering mspairs for train10'): if int(qid) % 10 == 0: plaintext.write_tsv(fout, [(qid, did1, did2)]) if not self.config['init_skip_train_med']: med_qids = util.Lazy( lambda: { qid.strip() for qid in util.download_stream( 'https://raw.githubusercontent.com/Georgetown-IR-Lab/covid-neural-ir/master/med-msmarco-train.txt', 'utf8', expected_md5="dc5199de7d4a872c361f89f08b1163ef") }) file = os.path.join(base_path, 'train_med.queries.tsv') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout: for qid, qtext in self.logger.pbar( plaintext.read_tsv( os.path.join(base_path, 'train.queries.tsv')), desc='filtering queries for train_med'): if qid in med_qids(): plaintext.write_tsv(fout, [(qid, qtext)]) file = os.path.join(base_path, 'train_med.qrels') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout, open( os.path.join(base_path, 'train.qrels'), 'rt') as fin: for line in self.logger.pbar( fin, desc='filtering qrels for train_med'): qid = line.split()[0] if qid in med_qids(): fout.write(line) if not self.config['init_skip_msrun']: file = os.path.join(base_path, 'train_med.msrun') if not os.path.exists(file): with util.finialized_file(file, 'wt') as fout, open( os.path.join(base_path, 'train.msrun'), 'rt') as fin: for line in self.logger.pbar( fin, desc='filtering msrun for train_med'): qid = line.split()[0] if qid in med_qids(): fout.write(line) file = os.path.join(base_path, 'train_med.mspairs.gz') if not os.path.exists(file): with gzip.open(file, 'wt') as fout, gzip.open( os.path.join(base_path, 'train.mspairs.gz'), 'rt') as fin: for qid, did1, did2 in self.logger.pbar( plaintext.read_tsv(fin), desc='filtering mspairs for train_med'): if qid in med_qids(): plaintext.write_tsv(fout, [(qid, did1, did2)])