0
$\begingroup$

I am new to SVM and Matlab. I would like to have an example how to prepare my data to be as input to the SVM classifer (using libsvm)

let us assume that i have a group of words first i have extracted some attributes such as bigram and trigrams (Average Jaccard index) and I wanted to input these values to a classifier in order to classify them

I know that i have first to train my classifier with initial data (labled) I have these data

60000 words from dictionary and 40000 other terms while I generate 100000 random strings

now i want to classify if the new words are random or not

I have calculated the Jaccard index for each one and also i have calculated some other features such as number of characters and number and some other features.

now how I can convert these data to metrix ? I am a bit confused about the next step

$\endgroup$
1
0
$\begingroup$

you can get the answer in LIBSVM Frequently Asked Questions http://www.csie.ntu.edu.tw/~cjlin/libsvm/faq.html#/Q03:_Data_preparation

$\endgroup$
0
$\begingroup$

This thread is a bit older, but as a new learner to SVM as well, did you ever find a good resource for how to prepare datasets for svm reg or classification?

$\endgroup$
1
  • $\begingroup$ This is not an answer to the question. $\endgroup$ – Michael R. Chernick May 27 '17 at 18:45

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.