POJ 2778 DNA Sequence (AC自動機 + dp),poj自動機
DNA Sequence題意:DNA的序列由ACTG四個字母組成,現在給定m個不可行的序列。問隨機構成的長度為n的序列中,有多少種序列是可行的(只要包含一個不可行序列便不可行)。個數很大,對100000模數。
思路:推薦一個部落格,講的非常清楚。這種題目,n很大,首先想到的就是用矩陣來最佳化。那麼如何構造轉移方程呢:首先建立一棵Trie,然後按照AC自動機的方式構造fail指標,然後會發現,當一個狀態分別添加ACTG之後,會得到另一個狀態。 (具體解釋見代碼)
代碼:
/*ID: wuqi9395@126.comPROG:LANG: C++*/#include<map>#include<set>#include<queue>#include<stack>#include<cmath>#include<cstdio>#include<vector>#include<string>#include<fstream>#include<cstring>#include<ctype.h>#include<iostream>#include<algorithm>#define INF (1<<30)#define PI acos(-1.0)#define mem(a, b) memset(a, b, sizeof(a))#define rep(i, n) for (int i = 0; i < n; i++)#define debug puts("===============")typedef long long ll;using namespace std;const int maxn = 110;const int maxm = 110;ll mod = 100000;struct Matrix { int n, m; ll a[maxn][maxm]; void clear() { n = m = 0; memset(a, 0, sizeof(a)); } Matrix operator * (const Matrix &b) const { //實現矩陣乘法 Matrix tmp; tmp.clear(); tmp.n = n; tmp.m = b.m; for (int i = 0; i < n; i++) for (int j = 0; j < m; j++) { if (!a[i][j]) continue; for (int k = 0; k < b.m; k++) tmp.a[i][k] += a[i][j] * b.a[j][k], tmp.a[i][k] %= mod; } return tmp; }}A, res;const int maxnode = 11 * 11;const int charset = 4;struct ACAutomaton { int ch[maxnode][charset]; int fail[maxnode]; int Q[maxnode]; int val[maxnode]; int sz; int id(char ch) { if (ch == 'A') return 0; else if (ch == 'C') return 1; else if (ch == 'T') return 2; return 3; } void init() { fail[0] = 0; //for (int i = 0; i < charset; i++) ID[i] = i; } void reset() { sz = 1; memset(ch[0], 0, sizeof(ch[0])); } void Insert(char* s, int key) { int u = 0; for (; *s; s++) { int c = id(*s); if (!ch[u][c]) { memset(ch[sz], 0, sizeof(ch[sz])); val[sz] = 0; ch[u][c] = sz++; } u = ch[u][c]; } val[u] = key; } void Construct () { int *s = Q, *e = Q; for (int i = 0; i < charset; i++) { if (ch[0][i]) { *e++ = ch[0][i]; fail[ch[0][i]] = 0; } } while(s != e) { int u = *s++; if (val[fail[u]]) val[u] = 1; for (int i = 0; i < charset; i++) { int &v = ch[u][i]; if (v) { *e++ = v; fail[v] = ch[fail[u]][i]; } else { v = ch[fail[u]][i]; } } } } /* dp[i][j]表示長度為i,尾碼為j的狀態 最多就只有10*10個尾碼 所以可以通過dp[n][j] = a0 * dp[n-1][0] + ... + ak * dp[n - 1][k]得到狀態轉移的矩陣 */ void work() { for (int i = 0; i < sz; i++) { for (int j = 0; j < charset; j++) { //對於i狀態,通過添加ACTG能夠得到新的狀態(且之前已經構造過AC自動機,ch[i][j]便表示新狀態) if (!val[i] && !val[ch[i][j]]) { //兩個狀態都必須是可行的,轉化才有意義 A.a[i][ch[i][j]]++; } } } }} AC;Matrix Matrix_pow(Matrix A, ll k, ll mod) { res.clear(); res.n = res.m = AC.sz; for (int i = 0; i < AC.sz; i++) res.a[i][i] = 1; while(k) { if (k & 1) res = res * A; A = A * A; k >>= 1; } return res;}int main () { int m, n; A.clear(); AC.init(); AC.reset(); char str[15]; scanf("%d%d", &m, &n); for (int i = 0; i < m; i++) { scanf("%s", str); AC.Insert(str, 1); } A.n = A.m = AC.sz; AC.Construct(); //之前的都是AC自動機構造部分 AC.work(); //得到狀態轉移的矩陣 res = Matrix_pow(A, n, mod); int ans = 0; rep(i, AC.sz) ans += res.a[0][i]; printf("%d\n", ans % mod); return 0;}
助POJ2778 DNA Sequence
謝謝一個C或者C++版的,兄弟就給你看一下!