Alias sampling 算法用Python实现

Line论文中采用了alias 采样算法进行优化，其源码为c++，现用Python实现一遍，加深一下印象

网上有人已经用C++ 脱离LINE算法，单独实现了这个算法并且测试，可以先看看。

而alias算法的原理可以看我的上一篇博客，其中包括C++源码的分析，所以Python就不加注释了。 。

python代码:

from gensim.models import  Word2Vecimport  numpy as npedg_num=0u = []#开始边v = []#目标边w = []#权重数组def readdata():    f = open("weight.txt", "r", encoding='utf-8')#测试用的文本边集合，每行为 u v weight    weights = f.readlines()    edg_num = len(weights)  # 边数目    for i in range(len(weights)):        u.append(int(weights[i].split()[0]))        v.append(int(weights[i].split()[1]))        w.append(int(weights[i].split()[2]))    return  edg_numdef initAliasTable():    alias=[-1 for i in range(edg_num)]    prob=[0.0 for i in range(edg_num)]    norm_prob = [0.0 for i in range(edg_num)]    large = []    small= []    w_sum=0    for i in range(edg_num):        w_sum+=w[i]    for i in range(edg_num):        norm_prob[i]=w[i]*edg_num/w_sum   # print(norm_prob)    small_num=0    large_num=0    for i in range(edg_num):        if norm_prob[edg_num-i-1]<1:            small.append(edg_num-i-1)            small_num=small_num+1        else:            large.append(edg_num-i-1)            large_num=large_num+1    #print(small,small_num)   # print(large,large_num)    for l in large:        prob[l]=1.0    while(large_num and small_num):        small_num = small_num - 1        small_cur=small[small_num]        large_num = large_num - 1        large_cur=large[large_num]        if(norm_prob[large_cur]==1):            prob[large_cur] = 1.0            large_num=large_num-1            large_cur=large[large_num]       # print(small_cur,large_cur)        prob[small_cur]=norm_prob[small_cur]        alias[small_cur]=large_cur        norm_prob[large_cur]=norm_prob[large_cur]+norm_prob[small_cur]-1.0       # print(prob)        #print(alias)        if norm_prob[large_cur]<1:            small[small_num]=large_cur            small_num=small_num+1        elif norm_prob[large_cur]==1:            prob[large_cur] = 1.0        else:            large[large_num]=large_cur            large_num=large_num+1        #print(small,small_num)       # print(large,large_num )    return prob,aliasdef sampleanedg(prob,alias):    rand1=np.random.uniform(0,1)    rand2=np.random.uniform(0,1)    k=int(rand1*edg_num)    return k if rand2<prob[k] else alias[k]if __name__ == '__main__':    edg_num=readdata()    prob,alias=initAliasTable()    print("prob=",prob)    print("alias=",alias)    i=60    while(i):        edg_cur=sampleanedg(prob,alias)        i=i-1        print("采样的边序号为",edg_cur+1)        #print("采样边为:",u[edg_cur],v[edg_cur],w[edg_cur])

采样了60次，其中18次为权重最大的边，权重越大越可能被采样。。