Update app.py

app.py

@@ -78,8 +78,16 @@ def extract_section_from_pdf(full_text: str, section_title: str) -> str:
     """
     return gpt_call("You are an HR expert working for IOM.", user_prompt)
 
-def classify_job_family(responsibilities: List[str]) -> str:
-    job_families_df = pd.read_csv("job_families1.csv")
+def classify_job_family(responsibilities: List[str]) -> str:    
+
+    try:
+        job_families_df = pd.read_csv("job_families1.csv", on_bad_lines='skip')
+    except Exception as e:
+        print(f"Error reading job_families1.csv: {e}")
+        job_families_df = pd.DataFrame()  # Fallback to an empty DataFrame or handle the error appropriately
+
+
+    
     job_family_list = "\n".join(f"- {row['Job_family']}: {row['Job_subfamily']}" for _, row in job_families_df.iterrows())
     user_prompt = f"""
     Here is a list of job responsibilities:
@@ -117,7 +125,13 @@ def code_sanitize(input_string, valid_codes):
     return None
 
 def classify_occupational_group_by_level(responsibilities: List[str]) -> dict:
-    occupational_groups_df = pd.read_csv("occupational_groups.csv")
+
+    try:
+        occupational_groups_df = pd.read_csv("occupational_groups.csv", on_bad_lines='skip')
+    except Exception as e:
+        print(f"Error reading occupational_groups.csv: {e}")
+        occupational_groups_df = pd.DataFrame()  # Fallback to an empty DataFrame or handle the error appropriately
+     
     result = {}
     try:
         for level in range(1, 5):
@@ -147,13 +161,32 @@ def classify_occupational_group_by_level(responsibilities: List[str]) -> dict:
     return result
 
 def get_skills_info_esco(Level_5_code):
-    esco_level5_df = pd.read_csv("occupations_en.csv", dtype={'code': str, 'iscoGroup': str})
+ 
+    try:
+        esco_level5_df = pd.read_csv("occupations_en.csv", on_bad_lines='skip', dtype={'code': str, 'iscoGroup': str})
+    except Exception as e:
+        print(f"Error reading occupations_en.csv: {e}")
+        esco_level5_df = pd.DataFrame()  # Fallback to an empty DataFrame or handle the error appropriately
+    
     matches = esco_level5_df[esco_level5_df['code'] == Level_5_code]
     conceptUris = matches['conceptUri'].values.tolist()
-    esco_skill_map_df = pd.read_csv("occupationSkillRelations_en.csv")
+     
+    try:
+        esco_skill_map_df = pd.read_csv("occupationSkillRelations_en.csv", on_bad_lines='skip')
+    except Exception as e:
+        print(f"Error reading occupationSkillRelations_en.csv: {e}")
+        esco_skill_map_df = pd.DataFrame()  # Fallback to an empty DataFrame or handle the error appropriately
+    
     skills = esco_skill_map_df[esco_skill_map_df['occupationUri'].isin(conceptUris)]
     skillUris = skills['skillUri'].values.tolist()
-    esco_skill_df = pd.read_csv("skills_en.csv")
+
+
+    try:
+        esco_skill_df = pd.read_csv("skills_en.csv", on_bad_lines='skip')
+    except Exception as e:
+        print(f"Error reading skills_en.csv: {e}")
+        esco_skill_df = pd.DataFrame()  # Fallback to an empty DataFrame or handle the error appropriately
+    
     thisskillslist = esco_skill_df[esco_skill_df['conceptUri'].isin(skillUris)]
     result = thisskillslist[['preferredLabel', 'conceptUri', 'description']].drop_duplicates()
     result = result.rename(columns={'preferredLabel': 'skill_name', 'description': 'skill_description', 'conceptUri': 'skill_code'})