Machine Learning--第二章--Find-S算法实现

最新推荐文章于 2022-02-14 23:41:13 发布

LZEP2015

最新推荐文章于 2022-02-14 23:41:13 发布

阅读量1.5k

点赞数

CC 4.0 BY-SA版权

分类专栏：机器学习

本文链接：https://blog.csdn.net/LZEP2015/article/details/41790517

机器学习专栏收录该内容

2 篇文章

订阅专栏

本文介绍了一个简单的概念学习算法——Find-S算法，该算法用于寻找训练数据集中的特殊假设，并逐步将其泛化，直到覆盖所有正例。通过具体的天气数据实例演示了如何应用此算法来找出最合适的假设。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Find-S:寻找极大特殊假设

算法流程：1. 将h初始化为H中最特殊的假设；2. 对每个正例x(对于h中的每个属性约束ai),如果x满足ai,那么不做任何处理，否则将h中ai替换为x满足的下一个更一般约束3.输出假设h.

/***************************************************************************
**Mail:zhjkobe2013@live.com
**Find-S.cpp
**@Function: Find appropriate hypthoesis
**Machine learning: chapter 2
**Author:zhangjie
**Create Date: 2014-12-07
**Last Modify:
***************************************************************************/

/*--------------------------------------------------------------------------
Positive Sample & Negative Sample
---------------------------------------------------------------------------
Example   Sky    Airtemp    Humidity   Wind   Water   Forcast  EnjoySports
1        Sunny    Warm       Normal   Strong  Warm     Same      Yes
2        Sunny    Warm       High     Strong  Warm     Same      Yes
3        Rainy    Cold       High     Strong  Warm     Change    No
4        Sunny    Warm       High     Strong  Cool     Change    Yes
---------------------------------------------------------------------------
--------------------------------------------------------------------------*/

#include<iostream>
#include<string>
#include<vector>
using namespace std;
#define NATTRIBUTE 6
#define NSAMPLE 4
void Input_Set(vector< vector<string> >& set)
{
 string s;
 int count;
 char* chs;
 chs=(char*)malloc(255*sizeof(char));
 memset(chs,'0',255*sizeof(char));
 cout<<"Start input"<<endl;
 /*for(int i=0;i<NSAMPLE+1;i++)
   {
  count=0;
    while(cin>>s,s!="end")
    {
     if(count>=(NATTRIBUTE+2))
             {
              break;
             }
             else
             {
              set[i][count]=s;
    count=count+1;
             }
    }
   }*/
 FILE* fp;
 int index,start,len;
 fp=fopen("data.txt","r");
 for(int i=0;i<NSAMPLE+1;i++)
   {
  fscanf(fp,"%s",chs);
  //fgets((char*)&s,SCHAR_MAX,fp);
  s=chs;
  cout<<s<<endl;
     start=0;
  count=0;
  len=s.length();
  cout<<"len="<<len<<endl;
  while(count<(NATTRIBUTE+2))
  {
   index=s.find_first_of("|",start); 
   cout<<"index="<<index<<endl;
   set[i][count]=s.substr(start,index-start);
   start=index+1;
   count=count+1;
  }
  cout<<endl;
   }
 fclose(fp);
 cout<<endl<<"Finish input"<<endl;
 if(chs) free(chs);
}

void Print_Set(vector< vector<string> >& set)
{
 cout<<"Start output"<<endl;
 for(int i=0;i<NSAMPLE+1;i++)
   {
  for(int j=0;j<NATTRIBUTE+2;j++)
   cout<<set[i][j]<<"   ";
  cout<<endl;
   }
  cout<<"Finish output"<<endl;

}

bool Find_S(vector< vector<string> >&set,string* h)
{
 int* count=(int*)malloc(NATTRIBUTE*sizeof(int));
 memset(count,0,NATTRIBUTE*sizeof(int));
 for(int i=1;i<NSAMPLE+1;i++)
 {
    for(int j=1;j<NATTRIBUTE+1;j++)
    {
  if(set[i][NATTRIBUTE+1]=="Yes")
  {
             if(set[i][j]!=h[j-1])
             {
              if(count[j-1]==0)
              {
               h[j-1]=set[i][j];
     count[j-1]+=1;
              }
    else
     count[j-1]+=1;
             }
  }
  else
   continue;
    }
 }

 for(int i=0;i<NATTRIBUTE;i++)
 if(count[i]>=2) h[i]="?";
 if(count) free(count);
 return true;
}
int main(int argc,char* argv[])
{
 vector< vector<string> > m_Set(NSAMPLE+1,vector<string>(NATTRIBUTE+2));
 Input_Set(m_Set);
 Print_Set(m_Set);

 string h[NSAMPLE+2]={"#","#","#","#","#","#"};
 Find_S(m_Set,h);

 cout<<"The hypthoesis is: ";
 for(int i=0;i<NSAMPLE+2;i++)
  cout<<h[i]<<' ';
 cout<<endl;
 return 0;
}

//data.txt的格式为