Learning Decision Trees

The code with the particular input file has been tested on the R2011a MATLAB distribution. For the given data set, the expected output matches the one in the Russel & Norvik's book and is visualized as follows:

tree.png

The circular nodes represent the attributes and the texts on the edge represent the values the attributes can take on. The leaf nodes represent the final decisions given the data. In this restaurant domain, when (1) the patrons are full, (2) you are hungry, (3) the restaurant type is Thai and (4) it is a Friday night, you would decide to wait for the line.

The simpler example input in question 18.6 is also available.

Note that the visualization is with graphviz, which is pretty cool! ;)

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License