Java: Data Science Made Easy

Using an SVM for camping data

For illustration purposes, we will be using a dataset consisting of age, income, and whether someone camps. We would like to be able to predict whether someone is inclined to camp based on their age and income. The data we use is stored in .arff format and is not based on a survey but has been created to explain the SVM process. The input data is found in the camping.txt file, as shown next. The file extension does not need to be .arff:

@relation camping@attribute age numeric@attribute income numeric@attribute camps {1, 0}@data23,45600,145,65700,172,55600,124,28700,122,34200,128,32800,132,24600,125,36500,126,91000,029,85300,067,76800,086,58900,056,125300,025,125000,022,43600,178,125700,173,56500,129,87600,0 ...