decision_tree_manual_classifier.py 文件源码

def prune(tree, mingain):
    # If the branches aren't leaves, then prune them
    if tree.tb.results == None:
        prune(tree.tb, mingain)
    if tree.fb.results == None:
        prune(tree.fb, mingain)

    # If both the subbranches are now leaves, see if they
    # should merged
    if tree.tb.results != None and tree.fb.results != None:
        # Build a combined dataset
        tb, fb = [], []
        for v, c in tree.tb.results.items():
            tb += [[v]] * c
        for v, c in tree.fb.results.items():
            fb += [[v]] * c

        # Test the reduction in entropy
        delta = entropy(tb + fb) - (entropy(tb) + entropy(fb) / 2)

        if delta < mingain:
            # Merge the branches
            tree.tb, tree.fb = None, None
            tree.results = uniquecounts(tb + fb)