view release on metacpan or  search on metacpan

lib/ALBD.pm  view on Meta::CPAN

	$implicitMatrixRef 
	    = Discovery::removeExplicit($startingMatrixRef, $implicitMatrixRef);

	#apply a semantic type filter to the implicit matrix
	if ((scalar keys %{$targetAcceptTypesRef}) > 0) {
	    Filters::semanticTypeFilter_columns(
		$implicitMatrixRef, $targetAcceptTypesRef, $umls_interface);
	}

	#calculate precision and recall
	my ($precision, $recall) = TimeSlicing::calculatePrecisionRecall(
	    $implicitMatrixRef, $postCutoffMatrixRef);
	print "precision = $precision, recall = $recall\n";

	#calculate averages/min/max only for $i= $numIntervals, which is all terms
	if ($i == $numIntervals) {
	    #average over all terms
	    foreach my $rowKey(keys %{$implicitMatrixRef}) {
		#get the counts true and predicted for this term (row of matrix)
		my $numPredicted = scalar keys %{${$implicitMatrixRef}{$rowKey}};
		my $numTrue = scalar keys %{${$postCutoffMatrixRef}{$rowKey}};

		#sum counts
		$predictedAverage += $numPredicted;
		$trueAverage += $numTrue;
		
		#update min and max
		if ($numPredicted < $predictedMin) {
		    $predictedMin = $numPredicted;
		}
		if ($numPredicted > $predictedMax) {
		    $predictedMax = $numPredicted;
		}
		if ($numTrue < $trueMin) {
		    $predictedMin = $numTrue;
		}
		if ($numTrue > $trueMax) {
		    $predictedMax = $numTrue;
		}

		$predictedTotal += $numPredicted;
		$trueTotal += $numTrue;
	    }
	    #take the average, both true and predicted matrices
	    # have the same number of rows.
	    $predictedAverage /= (scalar keys %{$implicitMatrixRef});
	    $trueAverage /= (scalar keys %{$implicitMatrixRef});
	}
    } 

    #output stats
    print "predicted - total, min, max, average = $predictedTotal, $predictedMin, $predictedMax, $predictedAverage\n";
    print "true - total, min, max, average = $trueTotal, $trueMin, $trueMax, $trueAverage\n";
}


# generates precision and recall values by varying the threshold
# of the A->C ranking measure. Also generates precision at k, and
# mean average precision
# input:  none
# output: none, but precision, recall, precision at k, and map values
#         output to STDOUT
sub timeSlicing_generatePrecisionAndRecall_implicit {
    my $NUM_SAMPLES = 200; #TODO, read fomr file number of samples to average over for timeslicing
    my $self = shift;
    my $start; #used to record run times
    print "In timeSlicing_generatePrecisionAndRecall_implicit\n";

    #Get inputs
    my $startAcceptTypesRef = $self->_getAcceptTypes('start');
    my $linkingAcceptTypesRef = $self->_getAcceptTypes('linking');
    my $targetAcceptTypesRef = $self->_getAcceptTypes('target');

#-----------
# Starting Matrix Creation
#-----------
    #Get the Explicit Matrix
    print "loading explicit\n";
    my $explicitMatrixRef;
    if(!defined $lbdOptions{'explicitInputFile'}) {
	die ("ERROR: explicitInputFile must be defined in LBD config file\n");
    }
    $explicitMatrixRef = Discovery::fileToSparseMatrix($lbdOptions{'explicitInputFile'});

    #create the starting matrix
    print "generating starting\n";
    my $startingMatrixRef 
	= TimeSlicing::generateStartingMatrix($explicitMatrixRef, \%lbdOptions, $startAcceptTypesRef, $NUM_SAMPLES, $umls_interface);
#----------
    

#--------
# Gold Loading/Creation
#--------
    #load or create the gold matrix
    my $goldMatrixRef;
    if (exists $lbdOptions{'goldInputFile'}) {
	print "inputting gold\n";
	$goldMatrixRef = Discovery::fileToSparseMatrix($lbdOptions{'goldInputFile'});
    }
    else {
	print "loading post cutoff\n";
	$goldMatrixRef = TimeSlicing::loadPostCutOffMatrix($startingMatrixRef, $explicitMatrixRef, $lbdOptions{'postCutoffFileName'});

	#remove explicit knowledge from the post cutoff matrix
	$goldMatrixRef = Discovery::removeExplicit($startingMatrixRef, $goldMatrixRef);

	#apply a semantic type filter to the post cutoff matrix
	print "applying semantic filter to post-cutoff matrix\n";
	if ((scalar keys %{$targetAcceptTypesRef}) > 0) {
	    Filters::semanticTypeFilter_columns(
		$goldMatrixRef, $targetAcceptTypesRef, $umls_interface);
	}

	#TODO why is the gold matrix outputting with an extra line between samples?
	#output the gold matrix
	if (exists $lbdOptions{'goldOutputFile'}) {
	    print "outputting gold\n";
	    Discovery::outputMatrixToFile($lbdOptions{'goldOutputFile'}, $goldMatrixRef); 
	}
    }