Decision Tree Prunning 편집하기 (부분)

==Types of Pruning==
There are two main types of pruning: pre-pruning and post-pruning.
*'''Pre-Pruning (Early Stopping)''': Stops the growth of the tree early by setting conditions on the splitting process. The model halts tree expansion when splits do not meet certain criteria, such as minimum information gain, minimum samples per leaf, or maximum tree depth.
**Example: Setting a maximum depth limit for the tree or requiring a minimum number of samples for each split.

*'''Post-Pruning (Backward Pruning)''': Allows the tree to grow fully and then removes branches that do not contribute significantly to the model’s accuracy. Post-pruning examines each node after tree construction and removes nodes that increase generalization error.
**Example: Cost Complexity Pruning, where nodes are removed based on their contribution to the error, balancing accuracy with model complexity.