def qk_candidate_gen(q_res_path: str, doc_score_path, split,
config) -> List[Tuple[QCKQuery, List[KDP]]]:
queries: List[QCKQuery] = get_qck_queries(split)
num_jobs = d_n_claims_per_split2[split]
score_d = load_doc_scores(doc_score_path, num_jobs)
tprint("loading ranked list")
ranked_list: Dict[
str, List[SimpleRankedListEntry]] = load_galago_ranked_list(q_res_path)
query_ids = list(ranked_list.keys())
query_ids.sort()
print("num queries", len(query_ids))
q_id_to_job_id = {q_id: job_id for job_id, q_id in enumerate(query_ids)}
print("Pre loading docs")
top_n = config['top_n']
out_qk: List[Tuple[QCKQuery, List[KnowledgeDocumentPart]]] = []
all_doc_parts = 0
ticker = TimeEstimator(len(queries))
for q in queries:
job_id: int = q_id_to_job_id[q.query_id]
entries: List = score_d[job_id]
entries.sort(key=get_second, reverse=True)
doc_ids = left(entries)
doc_ids = doc_ids[:top_n]
preload_man.preload(TokenizedCluewebDoc, doc_ids)
docs = iterate_docs(doc_ids)
doc_part_list: List[KDP] = iterate_document_parts(
docs, config['window_size'], config['step_size'], 20)
all_doc_parts += len(doc_part_list)
out_qk.append((q, doc_part_list))
ticker.tick()
return out_qk
def main():
save_dir = os.path.join(output_path, "pc_qc")
exist_or_mkdir(save_dir)
for split in splits:
queries = get_qck_queries(split)
eval_candidate = get_eval_candidates_as_qck(split)
save_path = os.path.join(save_dir, split)
make_pc_qc(queries, eval_candidate, is_correct_factory(), save_path)
def main():
for split in splits:
q_res_path = os.path.join(output_path, "perspective_experiments",
"clueweb_qres", "{}.txt".format(split))
qck_queries = get_qck_queries(split)
candidate = get_qk_candidate(config1(), q_res_path, qck_queries)
print("Num candidate : {}", len(candidate))
save_to_pickle(candidate, "pc_qk2_{}".format(split))
def get_qck_gen_dynamic_kdp():
split = "train"
candidate_d: Dict[str, List[QCKCandidate]] = get_extended_eval_candidate_as_qck(split)
train2_claims = load_claims_for_sub_split("val")
target_qids = list([str(c['cId']) for c in train2_claims ])
queries = get_qck_queries(split)
queries = list([q for q in queries if q.query_id in target_qids])
return QCKGenDynamicKDP(queries, candidate_d, get_is_correct_fn())
def main():
save_dir = os.path.join(output_path, "pc_qc2")
exist_or_mkdir(save_dir)
for split in splits:
queries = get_qck_queries(split)
q_res_path = os.path.join("output",
"perspective_experiments",
"q_res_{}.txt".format(split))
eval_candidate = get_qck_candidate_from_ranked_list_path(q_res_path)
save_path = os.path.join(save_dir, split)
make_pc_qc(queries, eval_candidate, is_correct_factory(), save_path)
def make_qcknc_problem(
passage_score_path: FilePath,
info_path: FilePath,
config_path: FilePath,
split: str,
save_name: str,
) -> None:
candidate_dict: Dict[int, List[Dict]] = dict(
get_eval_candidates_from_pickle(split))
queries: List[QCKQuery] = get_qck_queries(split)
config = json.load(open(config_path, "r"))
def get_pids(l: List[Dict]) -> List[str]:
return lmap(lambda x: x['pid'], l)
candidate_id_dict_1: Dict[int, List[str]] = dict_value_map(
get_pids, candidate_dict)
candidate_id_dict: Dict[str,
List[str]] = dict_key_map(str, candidate_id_dict_1)
all_candidate_ids = set(flatten(candidate_id_dict.values()))
candidate_dict: Dict[str, QCKCandidate] = {
cid: get_qck_candidate_from_candidate_id(cid)
for cid in all_candidate_ids
}
data_id_to_info: Dict = load_combine_info_jsons(info_path, qk_convert_map)
print("number of dat info ", len(data_id_to_info))
qk_result: List[Tuple[str, List[QKOutEntry]]] = collect_good_passages(
data_id_to_info, passage_score_path, config)
query_dict = {q.query_id: q for q in queries}
payloads = qck_from_qk_results(qk_result, candidate_id_dict, query_dict,
candidate_dict)
out_dir = os.path.join(output_path, "cppnc")
exist_or_mkdir(out_dir)
save_path = os.path.join(out_dir, save_name + ".tfrecord")
data_id_man = write_qck_as_tfrecord(save_path, payloads)
info_save_path = os.path.join(out_dir, save_name + ".info")
print("Payload size : ", len(data_id_man.id_to_info))
json.dump(data_id_man.id_to_info, open(info_save_path, "w"))
print("tfrecord saved at :", save_path)
print("info saved at :", info_save_path)
def get_candidates(q_res_path, split, config) -> List[QKUnit]:
queries = get_qck_queries(split)
top_n = config['top_n']
candidate: List[Tuple[QCKQuery, List[KDP]]] = qk_candidate_gen(
q_res_path, queries, top_n, config)
return candidate