最近回顾了下复杂网络中的一下基本知识，记得自己当初入门时候，一个难点是将文字转变为代码的能力，另一个难点是不知道什么是网络。这篇文章给出了ER网络的算法实现，希望能帮助到刚进入复杂网络领域的同学们。
ER随机网络的算法描述与网络性质
对于刚进入复杂网络的同学来说，ER随机网络（Erdös 和 Rényi 提出的 随机网络模型）肯定不会陌生，它将随机性作为基本元素，它的特点是不指定节点，而通过随机性进行连边。
算法实现一：最初的 ER 网络 𝐺(𝑁, 𝑀) 的构造是通过给定网络中节点数量与边数，通过随机种子选取连边，直到给定边数全部连接。值得注意的是，通常我们都在构建网络时拒绝产生重连边与自连边。
算法实现二：ER 网络一个更为人们熟知的变体 𝐺(𝑁, 𝑝) 由 Gilbert 提出，可以描述为通过给定节点数以及每个节点的连边概率 𝑝 (以概率 𝑝 与其它节点相连，以1 - 𝑝 的概率不相连)，遍历所有节点，即可完成 ER 随机网络的构建。当节点数量较少时 𝐺(𝑁, 𝑀) 构建的随机网络与 𝐺(𝑁, 𝑝) 构建的随机网络会有较大差异。但节点数量较大时，两者在统计学中是等价的。
| 参数 | 物理意义 |
| G() | 图或网络 |
| N | 网络中节点总数 |
| M | 网络中总边数 |
| p | 连边概率 |
| k | 度 |
ER随机网络的一个性质是满足泊松分布，即：
度分布服从泊松分布使其度在平均度〈𝑘〉两端呈指数衰减，这表明 ER 随机网络是一种均匀的随机网络，网络中节点的度近似于网络的平均度 𝑘 ≈ 〈𝑘〉。网络的性质不做过度赘述，基本任意一本复杂网络书籍或是综述中都有非常详细的讲解。
算法实现
算法采用C++代码实现，编译软件为Code::Blocks，其中网络使用的是邻接链表进行表示。
算法一C++代码实现：
#include <iostream>
#include <ctime>
#include <stdlib.h>
#include <fstream>
#include <cmath>
#include "mt19937ar.c"
#include <algorithm>
#include <vector>
using namespace std;
int main()
{
int Network_Size = 100000; //网络节点数
double average_degree = 4; //平均度
int edge = 0.5*Network_Size*average_degree; //边数
unsigned long idum; //高精度随机种子生成器初始化
idum=(unsigned long)time(NULL);
init_genrand(idum);
vector<int> degree(Network_Size,0); //节点度
vector<vector<int> > adjlist(Network_Size); //网络邻接链表
ofstream outfile_ER_adjlist;
ofstream outfile_ER_degree;
double r;
outfile_ER_adjlist.open("ER_adjlist.txt");
outfile_ER_degree.open("ER_degree.txt");
for(;;)
{
double judge = 0;
int random_1 = genrand_int32()%Network_Size;
int random_2 = genrand_int32()%Network_Size;
if(random_1 != random_2) //解决重连边自连边问题
{
for(int i = 0; i < adjlist[random_1].size(); i++)
{
if(adjlist[random_1][i] == random_2)
{
judge = 1;
break;
}
}
if(judge == 1)
{
continue;
}
else
{
adjlist[random_1].push_back(random_2);
degree[random_1]++;
adjlist[random_2].push_back(random_1);
degree[random_2]++;
edge--;
}
}
if(edge == 0)
break;
}
for(int i = 0; i < Network_Size; i++)
{
for(int j = 0; j < adjlist[i].size(); j++)
{
outfile_ER_adjlist << adjlist[i][j] << ' ';
}
outfile_ER_adjlist << endl;
}
for(int i = 0; i < Network_Size; i++)
{
outfile_ER_degree << degree[i] << endl;
}
return 0;
}算法二C++代码实现：
#include <iostream>
#include <ctime>
#include <stdlib.h>
#include <fstream>
#include <cmath>
#include "mt19937ar.c"
#include <algorithm>
#include <vector>
using namespace std;
int main()
{
int Network_Size = 100000; //网络节点数
double p = 0.00004; //连边概率
unsigned long idum; //高精度随机种子生成器初始化
idum=(unsigned long)time(NULL);
init_genrand(idum);
vector<int> degree(Network_Size,0); //节点度
vector<vector<int> > adjlist(Network_Size); //网络邻接链表
ofstream outfile_ER_adjlist;
ofstream outfile_ER_degree;
double r;
outfile_ER_adjlist.open("ER_adjlist.txt");
outfile_ER_degree.open("ER_degree.txt");
for(int i = 0; i < Network_Size; ++i)
{
for(int j = i + 1; j < Network_Size; ++j)
{
r = genrand_real2();
if(r < p)
{
adjlist[i].push_back(j);
degree[i]++;
adjlist[j].push_back(i);
degree[j]++;
}
}
}
for(int i = 0; i < Network_Size; i++)
{
for(int j = 0; j < adjlist[i].size(); j++)
{
outfile_ER_adjlist << adjlist[i][j] << ' ';
}
outfile_ER_adjlist << endl;
}
for(int i = 0; i < Network_Size; i++)
{
outfile_ER_degree << degree[i] << endl;
}
return 0;
}"mt19937ar.c"高精度随机种子生成器
/*
A C-program for MT19937, with initialization improved 2002/1/26.
Coded by Takuji Nishimura and Makoto Matsumoto.
Before using, initialize the state by using init_genrand(seed)
or init_by_array(init_key, key_length).
Copyright (C) 1997 - 2002, Makoto Matsumoto and Takuji Nishimura,
All rights reserved.
Copyright (C) 2005, Mutsuo Saito,
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
3. The names of its contributors may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Any feedback is very welcome.
http://www.math.sci.hiroshima-u.ac.jp/~m-mat/MT/emt.html
email: m-mat @ math.sci.hiroshima-u.ac.jp (remove space)
*/
//#include <stdio.h>
//#include "mt19937ar.h"
/* Period parameters */
#define NN 624
#define M 397
#define MATRIX_A 0x9908b0dfUL /* constant vector a */
#define UPPER_MASK 0x80000000UL /* most significant w-r bits */
#define LOWER_MASK 0x7fffffffUL /* least significant r bits */
static unsigned long mt[NN]; /* the array for the state vector */
static int mti=NN+1; /* mti==N+1 means mt[N] is not initialized */
/* initializes mt[N] with a seed */
void init_genrand(unsigned long s)
{
mt[0]= s & 0xffffffffUL;
for (mti=1; mti<NN; mti++) {
mt[mti] =
(1812433253UL * (mt[mti-1] ^ (mt[mti-1] >> 30)) + mti);
/* See Knuth TAOCP Vol2. 3rd Ed. P.106 for multiplier. */
/* In the previous versions, MSBs of the seed affect */
/* only MSBs of the array mt[]. */
/* 2002/01/09 modified by Makoto Matsumoto */
mt[mti] &= 0xffffffffUL;
/* for >32 bit machines */
}
}
/* initialize by an array with array-length */
/* init_key is the array for initializing keys */
/* key_length is its length */
/* slight change for C++, 2004/2/26 */
void init_by_array(unsigned long init_key[], int key_length)
{
int i, j, k;
init_genrand(19650218UL);
i=1; j=0;
k = (NN>key_length ? NN : key_length);
for (; k; k--) {
mt[i] = (mt[i] ^ ((mt[i-1] ^ (mt[i-1] >> 30)) * 1664525UL))
+ init_key[j] + j; /* non linear */
mt[i] &= 0xffffffffUL; /* for WORDSIZE > 32 machines */
i++; j++;
if (i>=NN) { mt[0] = mt[NN-1]; i=1; }
if (j>=key_length) j=0;
}
for (k=NN-1; k; k--) {
mt[i] = (mt[i] ^ ((mt[i-1] ^ (mt[i-1] >> 30)) * 1566083941UL))
- i; /* non linear */
mt[i] &= 0xffffffffUL; /* for WORDSIZE > 32 machines */
i++;
if (i>=NN) { mt[0] = mt[NN-1]; i=1; }
}
mt[0] = 0x80000000UL; /* MSB is 1; assuring non-zero initial array */
}
/* generates a random number on [0,0xffffffff]-interval */
unsigned long genrand_int32(void)
{
unsigned long y;
static unsigned long mag01[2]={0x0UL, MATRIX_A};
/* mag01[x] = x * MATRIX_A for x=0,1 */
if (mti >= NN) { /* generate N words at one time */
int kk;
if (mti == NN+1) /* if init_genrand() has not been called, */
init_genrand(5489UL); /* a default initial seed is used */
for (kk=0;kk<NN-M;kk++) {
y = (mt[kk]&UPPER_MASK)|(mt[kk+1]&LOWER_MASK);
mt[kk] = mt[kk+M] ^ (y >> 1) ^ mag01[y & 0x1UL];
}
for (;kk<NN-1;kk++) {
y = (mt[kk]&UPPER_MASK)|(mt[kk+1]&LOWER_MASK);
mt[kk] = mt[kk+(M-NN)] ^ (y >> 1) ^ mag01[y & 0x1UL];
}
y = (mt[NN-1]&UPPER_MASK)|(mt[0]&LOWER_MASK);
mt[NN-1] = mt[M-1] ^ (y >> 1) ^ mag01[y & 0x1UL];
mti = 0;
}
y = mt[mti++];
/* Tempering */
y ^= (y >> 11);
y ^= (y << 7) & 0x9d2c5680UL;
y ^= (y << 15) & 0xefc60000UL;
y ^= (y >> 18);
return y;
}
/* generates a random number on [0,0x7fffffff]-interval */
long genrand_int31(void)
{
return (long)(genrand_int32()>>1);
}
/* generates a random number on [0,1]-real-interval */
double genrand_real1(void)
{
return genrand_int32()*(1.0/4294967295.0);
/* divided by 2^32-1 */
}
/* generates a random number on [0,1)-real-interval */
double genrand_real2(void)
{
return genrand_int32()*(1.0/4294967296.0);
/* divided by 2^32 */
}
/* generates a random number on (0,1)-real-interval */
double genrand_real3(void)
{
return (((double)genrand_int32()) + 0.5)*(1.0/4294967296.0);
/* divided by 2^32 */
}
/* generates a random number on [0,1) with 53-bit resolution*/
double genrand_res53(void)
{
unsigned long a=genrand_int32()>>5, b=genrand_int32()>>6;
return(a*67108864.0+b)*(1.0/9007199254740992.0);
}
/* These real versions are due to Isaku Wada, 2002/01/09 added */"mt19937ar.c"使用方法
#include <stdio.h>
#include <time.h>
#include "mt19937ar.c"
#define N 1000
int main(void)
{
int i;
// idum 为随机数发生器的种子
unsigned long idum;
idum=(unsigned long)time(NULL);
init_genrand(idum); // 随机数发生器初始化
// genrand_int32() 函数生成一个0到2^31之间的整数
// genrand_int32()%N 则生成一个 [0,N) 之间的整数
printf(" 10 outputs of genrand_int32()\n");
for (i=0; i<100; i++) {
printf("%10lu ", genrand_int32()%N);
if (i%5==4) printf("\n");
}
// genrand_real2() 函数生成一个 [0,1) 之间的双精度随机数
printf("\n 10 outputs of genrand_real2()\n");
for (i=0; i<10; i++) {
printf("%10.8f ", genrand_real2());
if (i%5==4) printf("\n");
}
return 0;
}结语
在科学研究中，往往算法二生成的ER随机网络更为常用。尽管两种算法存在很大差异，但在网络尺度非常大时，两者是等价的。这篇文章使用的代码较为简单，希望能够帮助刚进入复杂网络领域的小伙伴理解ER随机网络的实现。同时若文章有错误处，请指正，感谢大家。
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
