def calculate_matches()

in src/evaluation.py [0:0]

• 14 lines of code
• 6 McCabe index (conditional complexity)

def calculate_matches(data: List, workers_num: int):
    """
    Evaluates answers presence in the set of documents. This function is supposed to be used with a large collection of
    documents and results. It internally forks multiple sub-processes for evaluation and then merges results
    :param all_docs: dictionary of the entire documents database. doc_id -> (doc_text, title)
    :param answers: list of answers's list. One list per question
    :param closest_docs: document ids of the top results along with their scores
    :param workers_num: amount of parallel threads to process data
    :param match_type: type of answer matching. Refer to has_answer code for available options
    :return: matching information tuple.
    top_k_hits - a list where the index is the amount of top documents retrieved and the value is the total amount of
    valid matches across an entire dataset.
    questions_doc_hits - more detailed info with answer matches for every question and every retrieved document
    """

    logger.info('Matching answers in top docs...')

    tokenizer = SimpleTokenizer()
    get_score_partial = partial(check_answer, tokenizer=tokenizer)

    processes = ProcessPool(processes=workers_num)
    scores = processes.map(get_score_partial, data)

    logger.info('Per question validation results len=%d', len(scores))

    n_docs = len(data[0]['ctxs'])
    top_k_hits = [0] * n_docs
    for question_hits in scores:
        best_hit = next((i for i, x in enumerate(question_hits) if x), None)
        if best_hit is not None:
            top_k_hits[best_hit:] = [v + 1 for v in top_k_hits[best_hit:]]

    return QAMatchStats(top_k_hits, scores)