#!/usr/bin/perl -w
## construct_dt_and_classify_one_sample_case4.pl
## This example script is for purely nemeric features generated by the
## TrainingDataGeneratorNumeric class using the information in the
## parameter file param_numeric.txt The training data was generated by
## script generate_training_data_numeric.pl
## Now how we tell the module that the class labels are placed in column
## indexed 1 and that the features are in columns indexed 2 and 3 of the
## csv file.
## Remember that column indexing of the csv file is zero-based.
use strict;
use Algorithm::DecisionTree;
my $training_datafile = "training4.csv";
my $dt = Algorithm::DecisionTree->new(
training_datafile => $training_datafile,
csv_class_column_index => 1,
csv_columns_for_features => [2,3],
entropy_threshold => 0.01,
max_depth_desired => 3,
symbolic_to_numeric_cardinality_threshold => 10,
);
$dt->get_training_data();
$dt->calculate_first_order_probabilities();
$dt->calculate_class_priors();
# UNCOMMENT THE NEXT STATEMENT if you would like to see the
# training data that was read from the disk file:
#$dt->show_training_data();
my $root_node = $dt->construct_decision_tree_classifier();
# UNCOMMENT THE NEXT TWO STATEMENTs if you would like to see the
# decision tree displayed in your terminal window:
print "\n\nThe Decision Tree:\n\n";
$root_node->display_decision_tree(" ");
my @test_sample = qw / gdp=50.0 return_on_invest=45 /;
# The classifiy() in the call below returns a reference to a hash
# whose keys are the class labels and the values the associated
# probabilities:
my %classification = %{$dt->classify($root_node, \@test_sample)};
my @solution_path = @{$classification{'solution_path'}};
delete $classification{'solution_path'};
my @which_classes = keys %classification;
@which_classes = sort {$classification{$b} <=> $classification{$a}}
@which_classes;
print "\nClassification:\n\n";
print " class probability\n";
print " ---------- -----------\n";
foreach my $which_class (@which_classes) {
my $classstring = sprintf("%-30s", $which_class);
my $valuestring = sprintf("%-30s", $classification{$which_class});
print " $classstring $valuestring\n";
}
print "\nSolution path in the decision tree: @solution_path\n";
print "\nNumber of nodes created: " . $root_node->how_many_nodes() . "\n";