view release on metacpan or  search on metacpan

lib/LiteratureBasedDiscovery/TimeSlicing.pm  view on Meta::CPAN

# ALBD::TimeSlicing
#
# Library module of time slicing methods for LBD
#
# Copyright (c) 2017
#
# Sam Henry
# henryst at vcu.edu
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to
#
# The Free Software Foundation, Inc.,
# 59 Temple Place - Suite 330,
# Boston, MA  02111-1307, USA.

package TimeSlicing;
use strict;
use warnings;

use LiteratureBasedDiscovery::Discovery;


#
# Calculates and outputs to STDOUT Time Slicing evaluation stats of
# precision and recall at $numIntervals intervals, Mean Average Precision
# (MAP), precision at k, and frequency at k
# input:  $trueMatrixRef <- a ref to a hash of true discoveries
#         $rowRanksRef <- a ref to a hash of arrays of ranked predictions. 
#                         Each hash key is a cui,  each hash element is an 
#                         array of ranked predictions for that cui. The ranked 
#                         predictions are cuis are ordered in descending order 
#                         based on association. (from Rank::RankDescending)
#         $numIntervals <- the number of recall intervals to generate
sub outputTimeSlicingResults {
    #grab the input
    my $goldMatrixRef = shift;
    my $rowRanksRef = shift;
    my $numIntervals = shift;


#calculate and output stats
#------------------------------------------

 #calculate precision and recall
    print "calculating precision and recall\n";
    my ($precisionRef, $recallRef) = &calculatePrecisionAndRecall_implicit(
	 $goldMatrixRef, $rowRanksRef, $numIntervals);

    #output precision and recall
    print "----- average precision at 10% recall intervals (i recall precision) ----> \n";
    foreach my $i (sort {$a <=> $b} keys %{$precisionRef}) {
	print "      $i ${$recallRef}{$i} ${$precisionRef}{$i}\n";
    }
    print "\n";
    
#-------------------------------------------
    
    #calculate mean average precision
    my $map = &calculateMeanAveragePrecision(
	$goldMatrixRef, $rowRanksRef);
    #output mean average precision
    print "---------- mean average precision ---------------> \n";
    print "      MAP = $map\n";
    print "\n";

#-------------------------------------------
    
    #calculate precision at k
    print "calculating precision at k\n";
    my $precisionAtKRef = &calculatePrecisionAtK($goldMatrixRef, $rowRanksRef);
    #output precision at k
    print "---------- mean precision at k intervals ---------------> \n";
    foreach my $k (sort {$a <=> $b} keys %{$precisionAtKRef}) {
	print "      $k ${$precisionAtKRef}{$k}\n";
    }
    print "\n";

#-------------------------------------------
    
    #calculate cooccurrences at k
    print "calculating mean cooccurrences at k\n";
    my $cooccurrencesAtKRef = &calculateMeanCooccurrencesAtK($goldMatrixRef, $rowRanksRef);
    #output cooccurrences at k
    print "---------- mean cooccurrences at k intervals ---------------> \n";