corrneighbours.py 文件源码

def predict(otrain):
    binary = (otrain > 0)
    norm = NormalizePositive(axis=1)
    train = norm.fit_transform(otrain)

    dists = distance.pdist(binary, 'correlation')
    dists = distance.squareform(dists)

    neighbors = dists.argsort(axis=1)
    filled = train.copy()
    for u in range(filled.shape[0]):
        # n_u are the neighbors of user
        n_u = neighbors[u, 1:]
        for m in range(filled.shape[1]):
            # This code could be faster using numpy indexing trickery as the
            # cost of readibility (this is left as an exercise to the reader):
            revs = [train[neigh, m]
                    for neigh in n_u
                    if binary[neigh, m]]
            if len(revs):
                n = len(revs)
                n //= 2
                n += 1
                revs = revs[:n]
                filled[u,m] = np.mean(revs)

    return norm.inverse_transform(filled)