def compute_map()

in utils.py [0:0]

• 41 lines of code
• 9 McCabe index (conditional complexity)

def compute_map(ranks, gnd, kappas=[]):
    """
    Computes the mAP for a given set of returned results.
         Usage:
           map = compute_map (ranks, gnd)
                 computes mean average precsion (map) only
           map, aps, pr, prs = compute_map (ranks, gnd, kappas)
                 computes mean average precision (map), average precision (aps) for each query
                 computes mean precision at kappas (pr), precision at kappas (prs) for each query
         Notes:
         1) ranks starts from 0, ranks.shape = db_size X #queries
         2) The junk results (e.g., the query itself) should be declared in the gnd stuct array
         3) If there are no positive images for some query, that query is excluded from the evaluation
    """

    map = 0.
    nq = len(gnd) # number of queries
    aps = np.zeros(nq)
    pr = np.zeros(len(kappas))
    prs = np.zeros((nq, len(kappas)))
    nempty = 0

    for i in np.arange(nq):
        qgnd = np.array(gnd[i]['ok'])

        # no positive images, skip from the average
        if qgnd.shape[0] == 0:
            aps[i] = float('nan')
            prs[i, :] = float('nan')
            nempty += 1
            continue

        try:
            qgndj = np.array(gnd[i]['junk'])
        except:
            qgndj = np.empty(0)

        # sorted positions of positive and junk images (0 based)
        pos  = np.arange(ranks.shape[0])[np.in1d(ranks[:,i], qgnd)]
        junk = np.arange(ranks.shape[0])[np.in1d(ranks[:,i], qgndj)]

        k = 0;
        ij = 0;
        if len(junk):
            # decrease positions of positives based on the number of
            # junk images appearing before them
            ip = 0
            while (ip < len(pos)):
                while (ij < len(junk) and pos[ip] > junk[ij]):
                    k += 1
                    ij += 1
                pos[ip] = pos[ip] - k
                ip += 1

        # compute ap
        ap = compute_ap(pos, len(qgnd))
        map = map + ap
        aps[i] = ap

        # compute precision @ k
        pos += 1 # get it to 1-based
        for j in np.arange(len(kappas)):
            kq = min(max(pos), kappas[j]); 
            prs[i, j] = (pos <= kq).sum() / kq
        pr = pr + prs[i, :]

    map = map / (nq - nempty)
    pr = pr / (nq - nempty)

    return map, aps, pr, prs