Learning Decision Trees

Material:

Tasks:

  1. Change the existing code, so that it prints (the necessary data) for a learning curve.
  2. Plot the learning curves for all three data sets (monk-1, monk-2, monk-3) and interpret them.
  3. Are the trees that are learned consistent with the training data? If not, what could be the reason?
  4. Look at the true functions for the three data sets in monk.names (Section 9). Design a good decision tree for each of the concepts by hand.
  5. Compare these decision trees to the ones that were learned by the algorithm (on the whole training data).

Hand In:

  1. Learning curves for the three data sets.
  2. Interpretation of the learning curves.
  3. Answer to 3.
  4. Decision trees for 4.
  5. Interpretation of your findings for 5.