Machine Learning in Java - Second Edition

Learning algorithms

We have loaded our data and selected the best features, and we are ready to learn some classification models. Let's begin with basic decision trees.

In Weka, a decision tree is implemented within the J48 class, which is a reimplementation of Quinlan's famous C4.5 decision tree learner (Quinlan, 1993).

We will make a decision tree by using the following steps:

1. We initialize a new J48 decision tree learner. We can pass additional parameters with a string table—for instance, the tree pruning that controls the model complexity (refer to Chapter 1, Applied Machine Learning Quick Start). In our case, we will build an un-pruned tree; hence, we will pass a single -U parameter, as follows:

J48 tree = new J48(); String[] options ...