view release on metacpan or  search on metacpan

lib/AI/DecisionTree.pm  view on Meta::CPAN

    ($best_attr, $best_score) = ($attr, $score) if $score < $best_score;
  }
  
  return $best_attr;
}

sub entropy2 {
  shift;
  my ($counts, $total) = @_;

  # Entropy is defined with log base 2 - we just divide by log(2) at the end to adjust.
  my $sum = 0;
  $sum += $_ * log($_) foreach values %$counts;
  return +(log($total) - $sum/$total)/log(2);
}

sub entropy {
  shift;

  my %count;
  $count{$_}++ foreach @_;

  # Entropy is defined with log base 2 - we just divide by log(2) at the end to adjust.
  my $sum = 0;
  $sum += $_ * log($_) foreach values %count;
  return +(log(@_) - $sum/@_)/log(2);
}

sub prune_tree {
  my $self = shift;

  # We use a minimum-description-length approach.  We calculate the
  # score of each node:
  #  n = number of nodes below
  #  r = number of results (categories) in the entire tree
  #  i = number of instances in the entire tree
  #  e = number of errors below this node

  # Hypothesis description length (MML):
  #  describe tree: number of nodes + number of edges
  #  describe exceptions: num_exceptions * log2(total_num_instances) * log2(total_num_results)
  
  my $r = keys %{ $self->{results} };
  my $i = $self->{tree}{instances};
  my $exception_cost = log($r) * log($i) / log(2)**2;

  # Pruning can turn a branch into a leaf
  my $maybe_prune = sub {
    my ($self, $node) = @_;
    return unless $node->{children};  # Can't prune leaves

    my $nodes_below = $self->nodes_below($node);
    my $tree_cost = 2 * $nodes_below - 1;  # $edges_below == $nodes_below - 1
    
    my $exceptions = $self->exceptions( $node );