AI-DecisionTree

 view release on metacpan or  search on metacpan

Instance/Instance.xs  view on Meta::CPAN

    int         attribute
    int         value
  PPCODE:
    {
      int *new_values;
      int i;
    
      if (attribute >= instance->num_values) {
        if (!value) return; /* Nothing to do */
        
        printf("Expanding from %d to %d places\n", instance->num_values, attribute);
	Renew(instance->values, attribute, int);
        if (!instance->values)
          croak("Couldn't grab new memory to expand instance");
        
        for (i=instance->num_values; i<attribute-1; i++)
          instance->values[i] = 0;
        instance->num_values = 1 + attribute;
      }
    
      instance->values[attribute] = value;

LICENSE  view on Meta::CPAN

    b) cause the whole of any work that you distribute or publish, that
    in whole or in part contains the Program or any part thereof, either
    with or without modifications, to be licensed at no charge to all
    third parties under the terms of this General Public License (except
    that you may choose to grant warranty protection to some or all
    third parties, at your option).

    c) If the modified program normally reads commands interactively when
    run, you must cause it, when started running for such interactive use
    in the simplest and most usual way, to print or display an
    announcement including an appropriate copyright notice and a notice
    that there is no warranty (or else, saying that you provide a
    warranty) and that users may redistribute the program under these
    conditions, and telling the user how to view a copy of this General
    Public License.

    d) You may charge a fee for the physical act of transferring a
    copy, and you may at your option offer warranty protection in
    exchange for a fee.

eg/example.pl  view on Meta::CPAN

my $result;
# Try one of the training examples
$result = $dtree->get_result( attributes => {
					     outlook   => 'rain',
					     temperature => 'mild',
					     humidity => 'high',
					     wind => 'strong',
					    } );
print "Result 1: $result\n";  # no

# Try a new unseen example
$result = $dtree->get_result( attributes => {
					     outlook => 'sunny',
					     temperature => 'hot',
					     humidity => 'normal',
					     wind => 'strong',
					    } );
print "Result 2: $result\n";  # yes



# Show the created tree structure as rules
print map "$_\n", $dtree->rule_statements;


# Will barf on inconsistent data
my $t2 = new AI::DecisionTree;
$t2->add_instance( attributes => { foo => 'bar' },
		   result => 1 );
$t2->add_instance( attributes => { foo => 'bar' },
		   result => 0 );
eval {$t2->train};
print "$@\n";

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

#  { split_on => $attr_name,
#    children => { $attr_value1 => $node1,
#                  $attr_value2 => $node2, ... }
#  }
# or
#  { result => $result }

sub _expand_node {
  my ($self, %args) = @_;
  my $instances = $args{instances};
  print STDERR '.' if $self->{verbose};
  
  $self->{depth} = $self->{curr_depth} if $self->{curr_depth} > $self->{depth};
  local $self->{curr_depth} = $self->{curr_depth} + 1;
  $self->{nodes}++;

  my %results;
  $results{$self->_result($_)}++ foreach @$instances;
  my @results = map {$_,$results{$_}} sort {$results{$b} <=> $results{$a}} keys %results;
  my %node = ( distribution => \@results, instances => scalar @$instances );

t/01-simple.t  view on Meta::CPAN

		    temperature => 'mild',
		    humidity => 'high',
		    wind => 'strong',
		   );

  my $result  = $dtree->get_result( callback => sub { $attributes{$_[0]} } );
  ok $result, 'no';
}


#print map "$_\n", $dtree->rule_statements;
#use YAML; print Dump $dtree;

if (eval "use GraphViz; 1") {
  my $graphviz = $dtree->as_graphviz;
  ok $graphviz;

  if (0) {
    # Only works on Mac OS X
    my $file = '/tmp/tree.png';
    open my($fh), "> $file" or die "$file: $!";
    print $fh $graphviz->as_png;
    close $fh;
    system('open', $file);
  }
} else {
  skip("Skipping: GraphViz is not installed", 0);
}

# Make sure there are 8 nodes
ok $dtree->nodes, 8;

t/02-noisy.t  view on Meta::CPAN

#########################

my $dtree = AI::DecisionTree->new(noise_mode => 'pick_best');
ok $dtree;

my @names = split /, /, <DATA>;
chomp $names[-1];

# Train on first 600 instances
printf "Loading 600 training instances with %d attribute types each\n", scalar @names;
while (<DATA>) {
  last unless 2..601;
  
  chomp;
  my @values = split /, /, $_;
  my $result = pop @values;
  my %pairs = map {$names[$_], $values[$_]} 0..$#names;

  $dtree->add_instance(attributes => \%pairs,
		       result => $result,
		      );
}
print "Building decision tree\n";
$dtree->train;
ok(1);

# Test on rest of data, get at least 80%
print "Testing on remainder of data\n";
my ($good, $bad) = (0,0);
while (<DATA>) {
  chomp;
  my @values = split /, /, $_;
  my $result = pop @values;
  my %pairs = map {$names[$_], $values[$_]} 0..$#names;

  my ($guess, $confidence) = $dtree->get_result(attributes => \%pairs);
  $guess ||= '';  $confidence ||= '';
  ($guess eq $result ? $good : $bad)++;
  
  #print "$guess : $result : $confidence\n";
}
my $accuracy = $good/($good + $bad);
ok $accuracy > .8;
print "Accuracy=$accuracy\n";

#use YAML; print Dump($dtree->rule_tree);
#print map "$_\n", $dtree->rule_statements;

if (eval "use GraphViz; 1") {
  my $graphviz = $dtree->as_graphviz;
  ok $graphviz;

  if (0) {
    # Only works on Mac OS X
    my $file = '/tmp/tree2.png';
    open my($fh), "> $file" or die "$file: $!";
    print $fh $graphviz->as_png;
    close $fh;
    system('open', $file);
  }
} else {
  skip("Skipping: GraphViz is not installed", 0);
}

# The following data comes from the "C4.5" software package, in the
# "soybean.data" data file.  It is somewhat noisy.  I chose it because
# it was a pretty big data set, and because there are published