Tutorial (12): Exercise 5
Exercise 5: Evaluating using a testing set
The Holdout (validation) data
Select rows by clicking to move data instances (rows) between tables
The Decision Tree: Interactively build it
- Click on the root node below and start building the tree.
- Non leaf nodes can be "pruned" once they have been chosen (by clicking on the node and selecting "prune node completely")
- The ratios on the branches indicate how well the chosen attribute at a node splits the remaining data based on the target attribute ('outcome').
- Click on any nodes to hilight the rows in the data table that the rule down to that node covers.
- At each node, the entropy of the data at that point in the tree will be given.
- Information gain (entropy reduction) is specified for each attribute.
Reducing entropy to zero is a way of building a decision tree here.
When no more nodes can be expanded, the tree has classified all the training data.
- Move data into the testing set from the training set (by clicking) and then contsruct a tree. Ideally a testing set should have 33% or less of the training data (about 3 or 4 instances here).
- Compare classification errors on the testing data for complex trees compared to simple trees.
Classification Errors (Totals)