def __init__(self, split):
query_group: List[List[QueryID]] = load_query_group(split)
qrel: SimpleQrel = load_msmarco_simple_qrels(split)
self.split = split
self.queires = dict(load_queries(split))
self.query_group = query_group
self.tokenizer = get_tokenizer()
self.qrel = qrel
def __init__(self, split, load_candidate_doc_list_fn):
query_group: List[List[QueryID]] = load_query_group(split)
candidate_docs_d: Dict[QueryID, List[str]] = load_candidate_doc_list_fn(split)
qrel: SimpleQrel = load_msmarco_simple_qrels(split)
self.split = split
self.queires = dict(load_queries(split))
self.query_group = query_group
self.tokenizer = get_tokenizer()
self.candidate_doc_d: Dict[QueryID, List[str]] = candidate_docs_d
self.qrel = qrel
self.tokenizer = get_tokenizer()
def __init__(self, split):
super(ProcessedResource10doc, self).__init__(split)
query_group: List[List[QueryID]] = load_query_group(split)
candidate_docs_d: Dict[QueryID, List[str]] = load_candidate_doc_list_10(split)
qrel: SimpleQrel = load_msmarco_simple_qrels(split)
self.split = split
self.queires = dict(load_queries(split))
self.query_group = query_group
self.tokenizer = get_tokenizer()
self.candidate_doc_d: Dict[QueryID, List[str]] = candidate_docs_d
self.qrel = qrel
self.tokenizer = get_tokenizer()
def main():
split = "dev"
query_d = dict(load_queries(split))
bm25_module = get_bm25_module()
ranked_list_path = at_working_dir("msmarco-doc{}-top100".format(split))
run_name = "BM25_df100"
rlg = load_ranked_list_grouped(ranked_list_path)
save_path = at_output_dir("ranked_list", "mmd_dev_{}.txt".format(run_name))
te = TimeEstimator(100)
out_entries = []
for query_id, entries in rlg.items():
doc_ids = list([e.doc_id for e in entries])
docs = load_per_query_docs(query_id, None)
found_doc_ids = list([d.doc_id for d in docs])
not_found_doc_ids = list(
[doc_id for doc_id in doc_ids if doc_id not in found_doc_ids])
doc_id_len = len(not_found_doc_ids)
if doc_id_len:
print("{} docs not found".format(doc_id_len))
query_text = query_d[QueryID(query_id)]
def score(doc: MSMarcoDoc):
content = doc.title + " " + doc.body
return bm25_module.score(query_text, content)
scored_docs = list([(d, score(d)) for d in docs])
scored_docs.sort(key=get_second, reverse=True)
reranked_entries = []
for rank, (doc, score) in enumerate(scored_docs):
e = TrecRankedListEntry(query_id, doc.doc_id, rank, score,
run_name)
reranked_entries.append(e)
out_entries.extend(reranked_entries)
te.tick()
if len(out_entries) > 100 * 100:
break
write_trec_ranked_list_entry(out_entries, save_path)