Skip to content

fix: use globs and quote paths in cxr label scripts #2090

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Chessing234 wants to merge 2 commits into from
+22 −11
Closed

fix: use globs and quote paths in cxr label scripts #2090

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e453d06
fix: use globs and quote paths in cxr label scripts
Chessing234 Jul 19, 2026
06749c9
fix: glob + quote paths in chexpert runner too
Chessing234 Jul 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 15 additions & 6 deletions mimic-iv-cxr/txt/chexpert/run_chexpert_on_files.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,20 @@ fi
sleep 2

# loop through each .csv file in the section folder
for fn in `ls $REPORT_PATH`; do
echo `date`: $fn
fn_stem=`echo $fn | cut -d. -f 1`
for fn_path in "$REPORT_PATH"/*.csv; do
[ -f "$fn_path" ] || continue
fn=$(basename "$fn_path")
echo "$(date): $fn"
fn_stem=${fn%.csv}
# run chexpert - must be run from chexpert folder
python $CHEXPERT_PATH/label.py --verbose --reports_path $REPORT_PATH/$fn --output_path ${fn_stem}_labeled.csv --mention_phrases_dir $CHEXPERT_PATH/phrases/mention --unmention_phrases_dir $CHEXPERT_PATH/phrases/unmention --pre_negation_uncertainty_path $CHEXPERT_PATH/patterns/pre_negation_uncertainty.txt --negation_path $CHEXPERT_PATH/patterns/negation.txt --post_negation_uncertainty_path $CHEXPERT_PATH/patterns/post_negation_uncertainty.txt
echo `date`: done!
python "$CHEXPERT_PATH/label.py" --verbose \
--reports_path "$fn_path" \
--output_path "${fn_stem}_labeled.csv" \
--mention_phrases_dir "$CHEXPERT_PATH/phrases/mention" \
--unmention_phrases_dir "$CHEXPERT_PATH/phrases/unmention" \
--pre_negation_uncertainty_path "$CHEXPERT_PATH/patterns/pre_negation_uncertainty.txt" \
--negation_path "$CHEXPERT_PATH/patterns/negation.txt" \
--post_negation_uncertainty_path "$CHEXPERT_PATH/patterns/post_negation_uncertainty.txt"
echo "$(date): done!"
echo ''
done
done
12 changes: 7 additions & 5 deletions mimic-iv-cxr/txt/negbio/run_negbio.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,20 +32,22 @@ sleep 2
# mimic_cxr_001.csv
# mimic_cxr_002.csv
# .. etc
for fn in `ls $BASE_FOLDER`;
for fn_path in "$BASE_FOLDER"/mimic_cxr_*.csv;
do
[ -f "$fn_path" ] || continue
fn=$(basename "$fn_path")
echo "Looping through files with mimic_cxr_###.csv pattern."
# validate it's a mimic_cxr sections file
if [[ $fn =~ ^mimic_cxr_[0-9]+.csv$ ]];
then
export INPUT_FILE=${BASE_FOLDER}/$fn
export INPUT_FILE=$fn_path
# remove extension from filename
# sets the folder location to stem of original filename
# all intermediate files will be saved in this folder
export OUTPUT_DIR=${INPUT_FILE::-4}

echo $OUTPUT_DIR - running NegBio..
python $NEGBIO_PATH/negbio/negbio_csv2bioc.py --output $OUTPUT_DIR/report $INPUT_FILE
echo "$OUTPUT_DIR - running NegBio.."
python "$NEGBIO_PATH/negbio/negbio_csv2bioc.py" --output "$OUTPUT_DIR/report" "$INPUT_FILE"
python $NEGBIO_PATH/negbio/negbio_pipeline.py section_split --pattern $NEGBIO_PATH/patterns/section_titles_cxr8.txt --output $OUTPUT_DIR/sections $OUTPUT_DIR/report/* --workers=6
python $NEGBIO_PATH/negbio/negbio_pipeline.py ssplit --output $OUTPUT_DIR/ssplit $OUTPUT_DIR/sections/* --workers=6
python $NEGBIO_PATH/negbio/negbio_pipeline.py parse --output $OUTPUT_DIR/parse $OUTPUT_DIR/ssplit/* --workers=6
Expand All @@ -55,7 +57,7 @@ do

# ultimate filename we save the labels to
export OUTPUT_LABELS=$OUTPUT_DIR/${fn::-4}_labels.csv
python $NEGBIO_PATH/negbio/ext/chexpert_collect_labels.py --phrases_file $NEGBIO_PATH/patterns/chexpert_phrases.yml --output $OUTPUT_LABELS $OUTPUT_DIR/neg/*
python "$NEGBIO_PATH/negbio/ext/chexpert_collect_labels.py" --phrases_file "$NEGBIO_PATH/patterns/chexpert_phrases.yml" --output "$OUTPUT_LABELS" "$OUTPUT_DIR"/neg/*
fi
done
echo "Done looping through files."
Loading