isp_data_pollution.py 文件源码

def draw_links(self,n=1,log_sampling=False):
        """ Draw multiple random links. """
        urls = []
        domain_array = np.array([dmn for dmn in self.domain_links])
        domain_count = np.array([len(self.domain_links[domain_array[k]]) for k in range(domain_array.shape[0])])
        p = np.array([np.float(c) for c in domain_count])
        count_total = p.sum()
        if log_sampling:  # log-sampling [log(x+1)] to bias lower count domains
            p = np.fromiter((np.log1p(x) for x in p), dtype=p.dtype)
        if count_total > 0:
            p = p/p.sum()
            cnts = npr.multinomial(n, pvals=p)
            if n > 1:
                for k in range(cnts.shape[0]):
                    domain = domain_array[k]
                    cnt = min(cnts[k],domain_count[k])
                    for url in random.sample(self.domain_links[domain],cnt):
                        urls.append(url)
            else:
                k = int(np.nonzero(cnts)[0])
                domain = domain_array[k]
                url = random.sample(self.domain_links[domain],1)[0]
                urls.append(url)
        return urls