update

resume_subsampled.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987abe27a4c56b74dbb6c7683033f96ee86574ee2c92deab43e5c1b4efdee26a
-size 1927787
+oid sha256:9ae325b538c1e601fe44bb2d0377800c0a633a8a19bb6ecb5834386d24aa6bf2
+size 3845010

util/injection.py

@@ -6,21 +6,17 @@ from tqdm import tqdm
 
 
 
-def create_summary(group_name, label, occupation, additional_charateristics):
+def create_summary(group_name, label, occupation,row):
     """ Generate a dynamic summary for scoring the applicant, excluding the group feature.
         The occupation parameter allows customization of the job position.
     """
     summary = [
-        f"Hello, our company is currently preparing to hire a {occupation}.",
+        f"Hello, our company is currently preparing to hire a {row['Role']}.",
         "The applicant's resume is as follows."]
 
 
 
-    # for column, value in row.items():
-    #     if group_name.lower() not in column.lower():
-    #         readable_name = ' '.join(word.capitalize() for word in column.split('_'))
-    #         summary.append(f"{readable_name}: {value};")
-    #summary.append(f"{row['Resume']}")
+    additional_charateristics = f"{row['Cleaned Resume']};"
 
     info = f"{group_name}: {label};" if label else ''
     summary.append(f"\n{info}")
@@ -82,18 +78,13 @@ def process_scores_multiple(df, num_run, parameters, privilege_label, protect_la
     for run in tqdm(range(num_run), desc="Processing runs", unit="run"):
         for index, (idx, row) in tqdm(enumerate(df.iterrows()), total=len(df), desc="Processing entries", unit="entry"):
 
-            summary = []
-            for column, value in row.items():
-                if column == 'Resume':
-                    if group_name.lower() not in column.lower():
-                        # readable_name = ' '.join(word.capitalize() for word in column.split('_'))
-                        summary.append(f"{value};\n")
+
 
             for key, label in zip(['Privilege', 'Protect', 'Neutral'], [privilege_label, protect_label, False]):
                 #prompt_charateristics = create_summary(group_name, label, occupation,'\n'.join(summary) + '\n' + charateristics)
 
 
-                prompt_normal = create_summary(group_name, label, occupation, ''.join(summary))
+                prompt_normal = create_summary(group_name, label, occupation,row)
 
                 print(f"Run {run + 1} - Entry {index + 1} - {key}")
                 print("=============================================================")