confHist

#!/bin/bash
usage()
{
	echo "Usage: confHist (output_dir target_dir) | fileList -gs|--graphSize <value>"
	echo -e "\t\t[-m|--minCount <value>] [-s|--strokes] [-i|--lgimgDir <directory>]"
	echo -e "\t\t[-p|--dotpdfDir <directory>] [--split] [--filter] [-h|--help]"
	echo ""
  echo "------- Required Arguments -------"
  echo "output_dir    				Output lg files directory"
  echo "target_dir    				Ground truth lg files directory"
	echo "fileList      				File whose each line contains outputfile_path targetfile_path"
	echo -e "\t\t\t\t\tis used for comparison."
	echo "Note: Use either the 2 directories or the fileList"
	echo -e "-gs or --graphSize <value> \t\tThe number of objects/primitives in targets to analyze"
  echo "" 
  echo "------- Optional Arguments -------"
	echo -e "-m or --minCount <value> \tThe minimum number of times an error should occur before"
	echo -e "\t\t\t\tdetailed information is provided in the confusion histogram"
	echo -e "\t\t\t\tBy default, all errors are shown (minCount = 1)"
	echo -e "-s or --strokes \t\tConstruct stroke(primitive) confusion histograms in addition"
	echo -e "\t\t\t\tto object confusion histograms"
	echo -e "-i or --lgimgDir <directory> \tThe directory containing the expression images of the lg files"
	echo -e "-p or --dotpdfDir <directory> \tThe directory containing the lg2dot comparison pdf outputs"
	echo -e "\t\t\t\t If not provided, new lg2dot comparison outputs are generated and used"
	echo -e "-sp or --split \t\t\tSeparate the more frequent(>minCount) errors and (<=minCount)"
	echo -e "\t\t\t\terrors"
	echo -e "-f or --filter \t\t\tIgnore the less frequent(<=minCount) errors"
	echo -e "-h or --help \t\t\tPrint usage and this help message and exit"
}

if [ $# -eq 0 ]
then
	echo "LgEval confHist: Structure Confusion Histogram Generator"
	echo "Copyright (c) R. Zanibbi, H. Mouchere, 2013-2014"
	echo ""
	echo "Usage: confHist (output_dir target_dir) | fileList -gs|--graphSize <value>"
	echo -e "\t\t[-m|--minCount <value>] [-s|--strokes] [-i|--lgimgDir <directory>]"
	echo -e "\t\t[-p|--dotpdfDir <directory>] [--split] [--filter] [-h|--help]"
	echo "For details on arguments usage: confHist -h or confHist --help"
	echo ""
	echo "Creates an .html file containing structure confusion histograms"
	echo "at the object level. The histograms visualize errors by their"
	echo "frequency when comparing files in output_dir vs. target_dir (target_dir is 'ground truth')."
	echo "It is assumed that every .lg file in output_dir exists in target_dir, and a file"
	echo "output_dir_vs_target_dir is created as output."
	echo ""
	echo "Output is written to the file confHist_outputs/CH_<output_dir_vs_target_dir>.html"
	echo "or confHist_outputs/CH_<fileList>.html, depending upon the arguments used."
	exit 0
fi

GRAPH_SIZE=""
MIN_COUNT=1
STROKES=0
LGIMG_DIR="../"
DOTPDF_DIR="../"
SPLIT=0
FILTER=1
POSITIONAL=()
while [[ $# -gt 0 ]]
do
key="$1"

case $key in
    -h|--help) usage
    exit 0 
    ;;
    -gs|--graphSize)
    GRAPH_SIZE="$2"
    shift # past argument
    shift # past value
    ;;
    -m|--minCount)
    MIN_COUNT="$2"
    shift # past argument
    shift # past value
    ;;
    -s|--strokes)
    STROKES=1
    shift # past argument
    ;;
    -i|--lgimgDir)
    LGIMG_DIR="$2"
    shift # past argument
    shift # past value
    ;;
    -p|--dotpdfDir)
    DOTPDF_DIR="$2"
    shift # past argument
    shift # past value
    ;;
    -sp|--split)
    SPLIT=1
    shift # past argument
    ;;
    -f|--filter)
    FILTER=1
    shift # past argument
    ;;
    *)    # unknown option
    POSITIONAL+=("$1") # save it in an array for later
    shift # past argument
    ;;
esac
done
set -- "${POSITIONAL[@]}" # restore positional parameters

if [[ -z "$GRAPH_SIZE" ]]
then
	echo "Error: Please enter graph size using -gs value OR --graphSize value"
	exit 1
fi

OUT_DIR="confHist_outputs"
if [ ! -d $OUT_DIR ]
then
	mkdir $OUT_DIR
fi	

if [ -d $1 ]
then
	# Remove trailing slashes.
	output_dir=${1%/}
	target_dir=${2%/}
	base1=`basename $output_dir`
	base2=`basename $target_dir`
	INFILE="$OUT_DIR/${base1}_vs_${base2}"
	
	# Two directories passed (hopefully).
	# NOTE: Assumes same number of .lg files with
	#       matching names.
	ls $output_dir/*.lg > _f1
	ls $target_dir/*.lg > _f2

	L1=`wc -l _f1 | awk '{print $1}'`
	L2=`wc -l _f2 | awk '{print $1}'`
	if [ "$L1" != "$L2" ]
	then
		echo "  !! Error: differing number of .lg files:"
		echo "     ($L1) $output_dir"
		echo "     ($L2) $target_dir"
		rm -f _f1 _f2
		exit 1
	fi

	paste -d" " _f1 _f2 > $INFILE
	rm -f _f1 _f2 
	
	# HACK: ${@:3} selects args starting from the third.
	python $LgEvalDir/src/confHists.py --fileList $INFILE --graphSize $GRAPH_SIZE \
		--minCount $MIN_COUNT --strokes $STROKES --lgimgDir $LGIMG_DIR \
		--dotpdfDir $DOTPDF_DIR --split $SPLIT --filter $FILTER
	#rm $INFILE
else
	# User-provided file list.
	python $LgEvalDir/src/confHists.py --fileList $@ --graphSize $GRAPH_SIZE \
		--minCount $MIN_COUNT --strokes $STROKES --lgimgDir $LGIMG_DIR \
		--dotpdfDir $DOTPDF_DIR --split $SPLIT --filter $FILTER
fi

exit 0