Hello everyone! I have problem at line 8 and it states Wrong input format at line 1. Hope you could help me thank you! Godbless

Question

Elbert Abrea 2019-11-26

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/493215-hello-everyone-i-have-problem-at-line-8-and-it-states-wrong-input-format-at-line-1-hope-you-could

编辑： Rik 2019-11-26

ThesisDataW1v3.csv

Here is my code:

SPECTF = csvread('ThesisDataW1v3.csv');
labels = SPECTF(:,1);
features = SPECTF(:,2:end);
features_sparse = sparse(features);
libsvmwrite('ThesisDataW1v3SPARSE.csv', labels, features_sparse);
clear all;clc
[label, features] = libsvmread('ThesisDataW1v3.csv');
[N,D] = size(features);
labelList = unique(label(:));
NClass = length(labelList);

And attach also is my data that I want to train(Numbers 1 and 3 there specefies my two labels):

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Rik 2019-11-26

编辑：Rik 2019-11-26

I would also argue against the use of clear all, if you want to use that at all you should use clearvars.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Walter Roberson 2019-11-26

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/493215-hello-everyone-i-have-problem-at-line-8-and-it-states-wrong-input-format-at-line-1-hope-you-could#answer_403371

You use libsvmwrite() to carefully write out data with proper labels and features, but then you use libsvmread() to read in the original data rather than the label + feature data that you just wrote out.