def compute_metrics_from_files()

in ms_marco_eval.py [0:0]

• 7 lines of code
• 3 McCabe index (conditional complexity)

def compute_metrics_from_files(path_to_reference, path_to_candidate, perform_checks=True):
    """Compute MRR metric
    Args:    
    p_path_to_reference_file (str): path to reference file.
        Reference file should contain lines in the following format:
            QUERYID\tPASSAGEID
            Where PASSAGEID is a relevant passage for a query. Note QUERYID can repeat on different lines with different PASSAGEIDs
    p_path_to_candidate_file (str): path to candidate file.
        Candidate file sould contain lines in the following format:
            QUERYID\tPASSAGEID1\tRank
            If a user wishes to use the TREC format please run the script with a -t flag at the end. If this flag is used the expected format is 
            QUERYID\tITER\tDOCNO\tRANK\tSIM\tRUNID 
            Where the values are separated by tabs and ranked in order of relevance 
    Returns:
        dict: dictionary of metrics {'MRR': <MRR Score>}
    """
    
    qids_to_relevant_passageids = load_reference(path_to_reference)
    qids_to_ranked_candidate_passages = load_candidate(path_to_candidate)
    if perform_checks:
        allowed, message = quality_checks_qids(qids_to_relevant_passageids, qids_to_ranked_candidate_passages)
        if message != '': print(message)

    return compute_metrics(qids_to_relevant_passageids, qids_to_ranked_candidate_passages)