统计英文文本每个字母出现概率不分大小写并进行哈夫曼，香农编码

只统计英文文本的26个字母（不分大小写）出现概率，并对这26个字母进行哈夫曼编码，香农编码，主程序在CalculateLetters_Number.m中。

clc
clear
 %导入pages.txt文件，获取文章中的字符串
fid = fopen（‘a.txt‘）;               
tline = fgetl（fid）;
%变量初始化
i = 1;
test = [];
j = 1;
str1 = ‘‘;

while ischar（tline）
    disp（tline）;                    %显示每一行
    pages{i} = tline;               %将文章中的每一行的字符串存在数据类型为元包（cell）变量中
    tline = fgetl（fid）;
    i=i+1;
end
fclose（fid）;

%for循环?实现pages中的所有行字符串存储在同一个名为：str的字符串变量中
for i=1:length（pages）
    str = strcat（str1pages{i}）;
    str1 = str;
end
str;                               %拿str字符串，自行与文章全文进行校对
a = lower（str）;                    %大写字母转小写
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%
%滤除其他字符，只计算英文字符
for i=1:length（a）
    if（a（i）>=‘a‘）
        if（a（i）<=‘z‘）
        test（j） = a（i）;
        j = j + 1;
        end
    end
end
st=sprintf（‘%c‘test）              %显示最终要统计的英文字符
%%
char = unique（st）;                 %计算有多少个不重复的字符串

for i = 1:length（char）
    char（i）;
    number（i） = length（strfind（stchar（i）））; %统计字符的数目
end
char                               %显示字符
number                             %显示个数

%计算频率frequency
frequency = number/sum（number）     %这里进行一个计算只为了与上面的number现实的个数相对应（这个frequency与下面那个frequency只是顺序不同）
%分别将所有出现过的字符：char每个char出现的次数：number每个char出现的频率：frequency
number = sort（number2‘descend‘） ; %做一个降序，方便下面进行编码
frequency = number/sum（number）;     %再次计算频率
%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%哈夫曼编码%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%
%哈夫曼编码主程序    
disp（‘%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%哈夫曼编码%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%‘）
r=2;                                %r代表r元码
Huffman_CLQ（frequencyr）
disp（‘%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%香农编码%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%‘）
%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%香农编码%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
shannon_result = shannon（frequency）

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        145  2018-01-11 14:55  上传文件\a.txt

     文件       2265  2018-01-12 01:15  上传文件\CalculateLetters_Number.m

     文件        276  2018-01-11 15:25  上传文件\check.m

     文件        253  2018-01-11 15:27  上传文件\first_S.m

     文件       2407  2018-01-11 15:58  上传文件\Huffman_CLQ.m

     文件       1661  2018-01-12 01:16  上传文件\shannon.m

     文件        919  2018-01-11 15:46  上传文件\yasuo_pp.m

     目录          0  2018-01-11 15:58  上传文件

----------- ---------  ---------- -----  ----

                 7926                    8