def load_candidate_from_stream()

in ms_marco_eval.py [0:0]

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

def load_candidate_from_stream(f):
    """Load candidate data from a stream.
    Args:f (stream): stream to load.
    Returns:qid_to_ranked_candidate_passages (dict): dictionary mapping from query_id (int) to a list of 1000 passage ids(int) ranked by relevance and importance
    """
    qid_to_ranked_candidate_passages = {}
    for l in f:
        try:
            l = l.strip().split('\t')
            qid = int(l[0])
            pid = int(l[1])
            rank = int(l[2])
            if qid in qid_to_ranked_candidate_passages:
                pass    
            else:
                # By default, all PIDs in the list of 1000 are 0. Only override those that are given
                tmp = [0] * 1000
                qid_to_ranked_candidate_passages[qid] = tmp
            qid_to_ranked_candidate_passages[qid][rank-1]=pid
        except:
            raise IOError('\"%s\" is not valid format' % l)
    return qid_to_ranked_candidate_passages