Update app.py

app.py

@@ -82,6 +82,34 @@ def cleanup_model(model, tokenizer):
     except Exception:
         pass
 
+def validate_excel_structure(df):
+    """Validate the structure and content of the Excel file"""
+    validation_messages = []
+    
+    # Check for minimum content
+    if len(df) == 0:
+        validation_messages.append("File contains no data")
+        return False, validation_messages
+    
+    # Check abstract length
+    if df['Abstract'].str.len().min() < 50:
+        validation_messages.append("Some abstracts are too short (less than 50 characters)")
+    
+    # Check publication year format
+    try:
+        df['Publication Year'] = df['Publication Year'].astype(int)
+        if df['Publication Year'].min() < 1900 or df['Publication Year'].max() > 2025:
+            validation_messages.append("Invalid publication years detected")
+    except:
+        validation_messages.append("Invalid format in Publication Year column")
+    
+    # Check if DOIs are in valid format (basic check)
+    if not df['DOI'].str.contains(r'10\.\d{4,}/.+', na=True).all():
+        validation_messages.append("Some DOIs are in invalid format")
+    
+    return len(validation_messages) == 0, validation_messages
+
+
 @st.cache_data
 def process_excel(uploaded_file):
     """Process uploaded Excel file"""
@@ -95,6 +123,25 @@ def process_excel(uploaded_file):
         if missing_columns:
             st.error(f"Missing required columns: {', '.join(missing_columns)}")
             return None
+
+        # Check number of papers
+        if len(df) > 5:
+            st.error("❌ Your file contains more than 5 papers. Please upload a file with maximum 5 papers.")
+            return None
+
+        # Validate structure and content
+        is_valid, messages = validate_excel_structure(df)
+        if not is_valid:
+            for msg in messages:
+                st.error(f"❌ {msg}")
+            return None
+
+
+        # Check for empty required fields
+        for col in required_columns:
+            if df[col].isna().any():
+                st.warning(f"⚠️ Some entries in '{col}' column are empty. This might affect the analysis.")
+        
         
         return df[required_columns]
     except Exception as e:
@@ -318,10 +365,24 @@ def create_filter_controls(df, sort_column):
 
 def main():
     st.title("🔬 Biomedical Papers Analysis")
+
+    st.info("""
+    **📋 File Upload Requirements:**
+    - Excel file (.xlsx or .xls) with **maximum 5 papers**
+    - Must contain these columns:
+      • Abstract
+      • Article Title
+      • Authors
+      • Source Title
+      • Publication Year
+      • DOI
+      • Times Cited, All Databases
+    """)
+
     
     # File upload section
     uploaded_file = st.file_uploader(
-        "Upload Excel file containing papers", 
+        "Upload Excel file containing papers (max 5 papers)", 
         type=['xlsx', 'xls'],
         help="File must contain: Abstract, Article Title, Authors, Source Title, Publication Year, DOI"
     )
@@ -331,12 +392,17 @@ def main():
     question = ""
     
     if uploaded_file is not None:
-        # Process Excel file
+    # Process Excel file
         if st.session_state.processed_data is None:
             with st.spinner("Processing file..."):
                 df = process_excel(uploaded_file)
                 if df is not None:
-                    st.session_state.processed_data = df.dropna(subset=["Abstract"])
+                    df = df.dropna(subset=["Abstract"])
+                    if len(df) > 0:
+                        st.session_state.processed_data = df
+                        st.success(f"✅ Successfully loaded {len(df)} papers with abstracts")
+                    else:
+                        st.error("❌ No valid papers found after processing. Please check your file.")
         
         if st.session_state.processed_data is not None:
             df = st.session_state.processed_data