add dataset info

Author: SarahMuth

run_sbatch_revision.sbatch

@@ -9,7 +9,4 @@
 
 source ~/.bashrc
 conda activate synapse-net
-python /user/muth9/u12095/synapse-net/scripts/cooper/revision/updated_data_analysis/run_data_analysis.py \
- -i /mnt/lustre-emmy-hdd/projects/nim00007/data/synaptic-reconstruction/cooper/20241102_TOMO_DATA_Imig2014/final_Imig2014_seg_autoComp/SNAP25/ \
- -o /mnt/lustre-emmy-hdd/projects/nim00007/data/synaptic-reconstruction/cooper/20241102_TOMO_DATA_Imig2014/afterRevision_analysis/boundaryT0_9_constantins_presynapticFiltering/full_dataset --store \
- -s ./analysis_results/full_dataset
+python scripts/cooper/revision/surface_dice.py -i /mnt/ceph-hdd/cold/nim00007/AZ_prediction_new/endbulb_of_held/ -gt /mnt/ceph-hdd/cold/nim00007/new_AZ_train_data/endbulb_of_held/ -v 7

scripts/cooper/revision/surface_dice.py

@@ -70,6 +70,7 @@ def collect_results(input_folder, gt_folder, version, check=False):
     results = []
     seg_key = f"predictions/az/seg_v{version}"
     gt_key = "/labels/az_merged"
+    input_folder_name = os.path.basename(os.path.normpath(input_folder))
 
     for fname in tqdm(os.listdir(input_folder), desc="Processing segmentations"):
         if not fname.endswith(".h5"):
@@ -84,18 +85,36 @@ def collect_results(input_folder, gt_folder, version, check=False):
 
         result = process_file(pred_path, gt_path, seg_key, gt_key, check)
         if result:
+            result["input_folder"] = input_folder_name
             results.append(result)
 
     return results
 
 
 def save_results(results, output_file):
-    """Save results as an Excel file."""
-    df = pd.DataFrame(results)
-    df.to_excel(output_file, index=False)
+    """Append results to an Excel file, updating rows with matching tomo_name and input_folder."""
+    new_df = pd.DataFrame(results)
+
+    if os.path.exists(output_file):
+        existing_df = pd.read_excel(output_file)
+
+        # Drop rows where tomo_name and input_folder match any in new_df
+        combined_df = existing_df[
+            ~existing_df.set_index(["tomo_name", "input_folder"]).index.isin(
+                new_df.set_index(["tomo_name", "input_folder"]).index
+            )
+        ]
+
+        # Append new data and reset index
+        final_df = pd.concat([combined_df, new_df], ignore_index=True)
+    else:
+        final_df = new_df
+
+    final_df.to_excel(output_file, index=False)
     print(f"Results saved to {output_file}")
 
 
+
 def main():
     parser = argparse.ArgumentParser(description="Compute surface dice for AZ segmentations.")
     parser.add_argument("--input_folder", "-i", required=True, help="Folder with predicted segmentations (.h5)")