o 7ti @s>ddlmZddlmZd ddZeeddZeeddZdS) )partial)Datasetboolcstgdddfdd}|j|fdd|jDd}i}|jD] }d d||D||<q't|S) Ntitleabstractquestionanswer answer_typecSs|dr d}d}||fS|drd}d}||fS|dr&|d}d}||fS|dr4|d}d}||fS|ddurBd }d}||fSdS) N unanswerableyes_noyesrfree_form_answerfree form answerextractive_spansFno) answer_blobr r rrN/home/ubuntu/.local/lib/python3.10/site-packages/lm_eval/tasks/qasper/utils.py_categorise_answer s* z(process_docs.._categorise_answerc sgggggd}|d}|d}t|dd|ddD]B\}}|dD]9}|\}}|kr`|d||d||d||d|t|trYd |}|d|q'q|S) a Given a `doc`, flatten it out so that each JSON blob contains exactly one question and one answer. Logic taken from the reference implementation available at https://github.com/allenai/qasper-led-baseline/blob/main/scripts/evaluator.py rrrqasranswersr r z, )popzipappend isinstancelistjoin) docobs_listrrr answer_listrr r )rset_answer_typerr_flattens,  "     zprocess_docs.._flattencsg|]}|vr|qSrr).0key)FEATURESrr >sz process_docs..)remove_columnscSsg|] }|D]}|qqSrr)r#rowxrrrr&Bs)mapfeatureskeysr from_dict)datasetr!r" new_datasetr$r)r%rr!r process_docss r0)r!rN)r) functoolsrdatasetsrr0process_docs_boolprocess_docs_freeformrrrrs   A