How to use weka for predict results

Prabodha Dissanayake picture Prabodha Dissanayake · Nov 17, 2012 · Viewed 28.2k times · Source

Im new to weka and I'm confused with the tool. What I needed to do is im having a data set about fruit price and relating attributes and im trying to predict the specific fruit price using the data set. Since I'm new to weka I couldn't figure out how to do this task. Please help me or guide me to a tutorial about how to do predictions and what is the best method or the algorithm to do this task.

Thank You.

Answer

alphaGeek picture alphaGeek · Jan 9, 2013

If you want to know more about how to save a trained classifier and load the same later on to predict, please refer the following.

With the assumption that you want to use the Weka GUI, you have to go through 2 steps as below:

  1. First using some pre-labelled data train a classifier[use your fruit prices data]. Make sure it is in ARFF format. After training save the model to your disk. More on this can be found here: http://weka.wikispaces.com/Saving+and+loading+models

  2. In the second step, you have use the already trained model[done in step 1]. Precisely you have to load the model file[saved in step 1] and then use the 'supplied test set" option on the "Classifiers" tab. In "supplied test set" option select the un-labelled data. More on this can be found here: http://weka.wikispaces.com/Making+predictions

I would suggest first playing around with the already provided ARFF data with your Weka install [these ARFF files basically sitting under your Weka install directory, In my case it is under: C:\Program Files\Weka-3-7\data].

Some more useful URLS:

  1. http://www.ibm.com/developerworks/opensource/library/os-weka1/index.html
  2. http://ortho.clmed.ncku.edu.tw/~emba/2006EMBA_MIS/3_16_2006/WekaIntro.pdf

Hope that helps.