matlab 转 arff,mat格式数据集转换为arff与txt格式

下面的代码给出了将mat格式数据集转换为arff与txt格式的matlab代码。

注意，每个.mat文件中只有一个数据集，其中共有m+1列，最后一列是label。

转为arff: mat2arff.m代码

MATLAB

%

% This function is used to convert the input data to '.arff'

% file format,which is compatible to weka file format ...

%

% Parameters:

% input_filename -- Input file name,only can conversion '.mat','.txt'

% or '.csv' file format ...

% arff_filename -- the output '.arff' file ...

% NOTEs:

%The input 'M*N' file data must be the following format:

% M: sampel numbers;

% N: sample features and label,"1:N-1" -- features, "N" - sample label ...

% 读取文件数据 ...

clear

clc

input_filename = 'GLIOMA-t.mat';

arff_filename = 'GLIOMA.arff';

if strfind(input_filename,'.mat')

matdata = importdata(input_filename);

elseif strfind(input_filename,'.txt')

matdata = textread(input_filename) ;

elseif strfind(input_filename,'.csv')

matdata = csvread(input_filename);

end

[row,col] = size(matdata);

f = fopen(arff_filename,'wt');

if (f < 0)

error(sprintf('Unable to open the file %s',arff_filename));

return

end

fprintf(f,'%s\n',['@relation ',arff_filename]);

for i = 1 : col - 1

st = ['@attribute att_',num2str(i),' numeric'];

fprintf(f,'%s\n',st);

end

% 保存文件头最后一行类别信息

floatformat = '%.16g';

Y = matdata(:,col);

uY = unique(Y); % 得到label类型

st = ['@attribute label {'];

for j = 1 : size(uY) - 1

st = [st sprintf([floatformat ' ,'],uY(j))];

end

st = [st sprintf([floatformat '}'],uY(length(uY)))];

fprintf(f,'%s\n\n',st);

% 开始保存数据 ...

labelformat = [floatformat ' '];

fprintf(f,'@data\n');

for i = 1 : row

Xi = matdata(i,1:col-1);

s = sprintf(labelformat,Y(i));

s = [sprintf([floatformat ' '],[; Xi]) s];

fprintf(f,'%s\n',s);

end

fclose(f);

%

% This function is used to convert the input data to '.arff'

% file format,which is compatible to weka file format ...

%

% Parameters:

% input_filename -- Input file name,only can conversion '.mat','.txt'

% or '.csv' file format ...

% arff_filename -- the output '.arff' file ...

% NOTEs:

%The input 'M*N' file data must be the following format:

% M: sampel numbers;

% N: sample features and label,"1:N-1" -- features, "N" - sample label ...

% 读取文件数据 ...

clear

clc

input_filename = 'GLIOMA-t.mat';

arff_filename = 'GLIOMA.arff';

if strfind(input_filename,'.mat')

matdata = importdata(input_filename);

elseif strfind(input_filename,'.txt')

matdata = textread(input_filename) ;

elseif strfind(input_filename,'.csv')

matdata = csvread(input_filename);

end

[row,col] = size(matdata);

f = fopen(arff_filename,'wt');

if (f < 0)

error(sprintf('Unable to open the file %s',arff_filename));

return

end

fprintf(f,'%s\n',['@relation ',arff_filename]);

for i = 1 : col - 1

st = ['@attribute att_',num2str(i),' numeric'];

fprintf(f,'%s\n',st);

end

% 保存文件头最后一行类别信息

floatformat = '%.16g';

Y = matdata(:,col);

uY = unique(Y); % 得到label类型

st = ['@attribute label {'];

for j = 1 : size(uY) - 1

st = [st sprintf([floatformat ' ,'],uY(j))];

end

st = [st sprintf([floatformat '}'],uY(length(uY)))];

fprintf(f,'%s\n\n',st);

% 开始保存数据 ...

labelformat = [floatformat ' '];

fprintf(f,'@data\n');

for i = 1 : row

Xi = matdata(i,1:col-1);

s = sprintf(labelformat,Y(i));

s = [sprintf([floatformat ' '],[; Xi]) s];

fprintf(f,'%s\n',s);

end

fclose(f);

转为txt: mat2txt.m代码

当然也可用save直接转换，但是会出现每一行开头会空两格的情况。

注意dataName.mat中的数据集名称是data

MATLAB

clc

clear

load('dataName.mat')

fid = fopen('dataName.txt', 'wt');

for i = 1 : size(data, 1)

for j = 1 : size(data, 2) - 1

fprintf(fid,'%e   ',data(i, j));

end

fprintf(fid,'%e\n',data(i, size(data, 2)));

end

fclose(fid);

clc

clear

load('dataName.mat')

fid = fopen('dataName.txt', 'wt');

for i = 1 : size(data, 1)

for j = 1 : size(data, 2) - 1

fprintf(fid,'%e   ',data(i, j));

end

fprintf(fid,'%e\n',data(i, size(data, 2)));

end

fclose(fid);

标签： mat

顶一下

(0)

0%

踩一下

(0)

0%