if args.rm3:
search_rankers.append('rm3')
searcher.set_rm3()
# invalid topics name
if topics == {}:
print(f'Topic {args.topics} Not Found')
exit()
# get re-ranker
use_prcl = args.prcl and len(args.prcl) > 0 and args.alpha > 0
if use_prcl is True:
ranker = PseudoRelevanceClassifierReranker(searcher.index_dir,
args.vectorizer,
args.prcl,
r=args.r,
n=args.n,
alpha=args.alpha)
# build output path
output_path = args.output
if output_path is None:
if use_prcl is True:
clf_rankers = []
for t in args.prcl:
if t == ClassifierType.LR:
clf_rankers.append('lr')
elif t == ClassifierType.SVM:
clf_rankers.append('svm')
r_str = f'prcl.r_{args.r}'
print(f'Using whitespace analyzer because of pretokenized topics')
tokenizer = AutoTokenizer.from_pretrained(args.tokenizer)
print(f'Using {args.tokenizer} to preprocess topics')
if args.stopwords:
analyzer = JDefaultEnglishAnalyzer.fromArguments(
'porter', False, args.stopwords)
searcher.set_analyzer(analyzer)
print(f'Using custom stopwords={args.stopwords}')
# get re-ranker
use_prcl = args.prcl and len(args.prcl) > 0 and args.alpha > 0
if use_prcl is True:
ranker = PseudoRelevanceClassifierReranker(searcher.index_dir,
args.vectorizer,
args.prcl,
r=args.r,
n=args.n,
alpha=args.alpha)
# build output path
output_path = args.output
if output_path is None:
if use_prcl is True:
clf_rankers = []
for t in args.prcl:
if t == ClassifierType.LR:
clf_rankers.append('lr')
elif t == ClassifierType.SVM:
clf_rankers.append('svm')
r_str = f'prcl.r_{args.r}'