matlab例程

开发平台：

Matlab

danwenben.m：源码内容

							%提取单词并小写...................................................................
text=textread('lpin.txt','%s');           %提取文本中的单词
stopword=textread('stopword.txt','%s');   %提取stopword中的单词
a=struct('word',[],'count',[]);           %定义一个结构体函数，word存放单词，count存放单词出现的次数
a(1).word=lower(text);                    %将文本中单词小写
%去掉stopword................................................................
k=1;
result=[];
flag=0;
for i=1:length(a(1).word)
    for j=1:length(stopword)
         if strcmp(a(1).word{i},stopword{j})==1
             flag=1;
         end
     end
    if flag==0;
    result{k}=a(1).word{i};
    k=k+1;
    end
    flag=0;
end
%提取词干....................................................................
k=1;s=[];
for i=1:length(result)
   s{k}=porterStemmer(result{i});
   k=k+1;
end
%将与处理的单词写入 lpout.txt.................................................
for i=1:length(s)
    fid=fopen('lpout.txt','a');
    fprintf(fid,'%s n',s{i});
    fclose(fid);
end
%对单词进行计数并提取出来......................................................
m=textread('lpout.txt','%s');
a(2).word=m;
for i=1:length(m)
    a(2).count(i)=1;          %将未计数前的所有单词数置为1
end
for i=1:length(m)                   %如果有相同的单词，则将后面的单词数置0，将本单词数加1
    for j=(i+1):length(m)
        if (strcmp(a(2).word{i},a(2).word{j})==1)&&(a(2).count(i)~=0)
            a(2).count(i)=a(2).count(i)+1;
            a(2).count(j)=0;
        else
            continue;
        end
    end
end
k=1;
for i=1:length(a(2).word)                   %如果单词数非0，则将单词和次数写入结构体数组
    if a(2).count(i)~=0
        a(3).word{k}=a(2).word{i};
        a(3).count(k)=a(2).count(i);
        k=k+1;
    else
        continue;
    end
end
    
%将单词存入word.txt,将次数存入count.txt......................................
for i=1:length(a(3).word)
    fid=fopen('word.txt','a');
    fprintf(fid,'%s n',a(3).word{i});
    fclose(fid);
end
    
for j=1:length(a(3).count) 
    fid=fopen('count.txt','a');
    fprintf(fid,'%d n',a(3).count(j));
    fclose(fid);
end

						