matlab 读取txt文件以及进行数据处理_akala啦_新浪博客

      周日做了信息论的小project，差不读熬了一个晚上加周一的早上，终于利用matlab成功的读取了txt文件中的英文单词以及简单的数据处理，现在进行简单的分享。

       百度经验：matlab如何读取txt文件：                     https://jingyan.baidu.com/article/b87fe19e6b478852183568e1.html

      

 代码：

1. function [] = work3()
2. clc
3. clear all
4. close all
5. %% read data
6. ch = fileread('harry1.txt');  
7. ch = strrep(ch,',',' ');   %%将逗号换成空格
8. ch = lower(ch);           %%排成一行
9. ch = reshape(strsplit(ch),[],1);     %%将cell类型的数据转换成char，每个单词一行。
10. %% 1-gram
11. gram1=ch;
12. [words,~,idx] = unique(char(gram1),'rows');
13. numOccurrences = histcounts(idx,length(words));
14. numOccurrences =sort(numOccurrences );
15. [err1,H1]=errH(numOccurrences);
16. %% 2-gram
17. clear words idx numOccurrences
18. gram2=char(ch);
19. [gram2_row,~]=size(gram2);
20. for i=1:gram2_row/2
21.     gram2_reshap(i,:)=[gram2(2*i-1,:) gram2(2*i,:)];
22. end
23. [words,~,idx] = unique(gram2_reshap,'rows');
24. [word_row,~]=size(words);
25. numOccurrences = histcounts(idx,word_row);
26. numOccurrences =sort(numOccurrences );
27. [err2,H2]=errH(numOccurrences);
28. %% 3-gram
29. clear words idx numOccurrences
30. gram3=char(ch);
31. [gram3_row,~]=size(gram3);
32. for i=1:gram3_row/3
33.     gram3_reshap(i,:)=[gram3(3*i-2,:) gram3(3*i-1,:) gram3(3*i,:)];
34. end
35. [words,~,idx] = unique(gram3_reshap,'rows');
36. [word_row,~]=size(words);
37. numOccurrences = histcounts(idx,word_row);
38. numOccurrences =sort(numOccurrences );
39. [err3,H3]=errH(numOccurrences);
40. 
    
41. 
    
42. 
    
43. 
    
44. 
    
45. 
    
46. figure
47. stairs(err1,H1/H1(1),'r')
48. titleName = ['N=',num2str(H1(1))];
49. hold on
50. stairs(err2,H2/H2(1),'b')
51. hold on
52. stairs(err3,H3/H3(1),'k')
53. 
    
54. title(titleName,'fontsize',16,'fontweight','bold');
55. xlabel('误差','fontsize',16,'fontweight','bold');
56. ylabel('H/N','fontsize',16,'fontweight','bold');
57. legend('1-gram','2-gram','3-gram');
58. 
    
59. 
    
60. end
61. 
    
62. %%
63. %% 纠错函数
64. function [err,H]=errH(numOccurrences)
65. x_remain=sum(numOccurrences);
66. p_num=numOccurrences /sum(numOccurrences);
67. num=1;
68. err(1)=0;
69. H(1)=log2(x_remain);
70. for r=1:length(numOccurrences)
71. %     hwait=waitbar(num/sum(numOccurrences),'请等待>>>>>>>>');
72. 
    
73.     for n=1:numOccurrences(r)
74.     num=num+1;
75.     x_remain=x_remain-1;
76.     err(num)=err(num-1)+p_num(r)/numOccurrences(r);
77.     H(num)=log2(x_remain);
78.     end
79. end
80. end
81.