Update app.py

app.py

@@ -2,9 +2,9 @@ import gradio as gr
 import pandas as pd
 import os
 
-# Load your labeled dataset with exact column names
+# Load your labeled dataset with flexible column names
 def load_drug_interaction_dataset():
-    """Load your labeled drug interaction dataset with exact column names"""
+    """Load your labeled drug interaction dataset with flexible column names"""
     try:
         # Your exact dataset filename
         dataset_path = 'merged_cleaned_dataset.csv'
@@ -16,25 +16,39 @@ def load_drug_interaction_dataset():
             print(f"Dataset file {dataset_path} not found!")
             return create_fallback_database()
         
-        # Load the dataset with your exact column names
+        # Load the dataset
         print(f"Loading dataset from: {dataset_path}")
         df = pd.read_csv(dataset_path)
         print(f"Dataset columns: {df.columns.tolist()}")
         print(f"Dataset shape: {df.shape}")
         print(f"First few rows:\n{df.head()}")
         
-        # Create interaction dictionary using your exact column names
+        # Attempt to detect column names (flexible mapping)
+        possible_drug1_cols = ['Drug 1_normalized', 'Drug1', 'drug_1']
+        possible_drug2_cols = ['Drug 2_normalized', 'Drug2', 'drug_2']
+        possible_severity_cols = ['severity', 'Severity', 'SEVERITY']
+        
+        drug1_col = next((col for col in possible_drug1_cols if col in df.columns), None)
+        drug2_col = next((col for col in possible_drug2_cols if col in df.columns), None)
+        severity_col = next((col for col in possible_severity_cols if col in df.columns), None)
+        
+        if not all([drug1_col, drug2_col, severity_col]):
+            print(f"Required columns not found. Detected: drug1={drug1_col}, drug2={drug2_col}, severity={severity_col}")
+            return create_fallback_database()
+        
+        print(f"Using columns: drug1={drug1_col}, drug2={drug2_col}, severity={severity_col}")
+        
+        # Create interaction dictionary
         interaction_db = {}
         count = 0
         
         for index, row in df.iterrows():
             try:
-                # Use your exact column names - adjust if different
-                drug1 = str(row['Drug 1_normalized']).lower().strip()
-                drug2 = str(row['Drug 2_normalized']).lower().strip()
-                severity = str(row['severity']).strip()
+                drug1 = str(row[drug1_col]).lower().strip()
+                drug2 = str(row[drug2_col]).lower().strip()
+                severity = str(row[severity_col]).strip()
                 
-                # Skip empty entries or invalid data
+                # Skip empty or invalid entries
                 if (not all([drug1, drug2, severity]) or 
                     drug1 == 'nan' or drug2 == 'nan' or 
                     severity == 'nan' or severity.lower() == 'none'):
@@ -48,11 +62,15 @@ def load_drug_interaction_dataset():
                 
                 # Add both orders to the dictionary
                 interaction_db[(drug1, drug2)] = severity
-                interaction_db[(drug2, drug1)] = severity  # Add reverse order
+                interaction_db[(drug2, drug1)] = severity
                 count += 1
                 if count % 100 == 0:  # Log progress
                     print(f"Processed {count} interactions")
                 
+                # Verify known pair
+                if drug1 == 'warfarin' and drug2 == 'aspirin':
+                    print(f"Found Warfarin, Aspirin at row {index} with severity: {severity}")
+                
             except Exception as e:
                 print(f"Error processing row {index}: {e}")
                 continue
@@ -69,23 +87,15 @@ def create_fallback_database():
     """Fallback database if dataset loading fails"""
     print("Using fallback database")
     return {
-        # Severe interactions (Life-threatening)
         ('warfarin', 'aspirin'): 'Severe',
         ('warfarin', 'ibuprofen'): 'Severe',
         ('simvastatin', 'clarithromycin'): 'Severe',
         ('clopidogrel', 'omeprazole'): 'Severe',
         ('methotrexate', 'naproxen'): 'Severe',
-        # ... (rest of your fallback data)
-        # Moderate interactions
         ('digoxin', 'quinine'): 'Moderate',
         ('lisinopril', 'ibuprofen'): 'Moderate',
-        # ... (rest of your fallback data)
-        # Mild interactions
         ('metformin', 'ibuprofen'): 'Mild',
-        # ... (rest of your fallback data)
-        # No interactions
         ('vitamin c', 'vitamin d'): 'No Interaction',
-        # ... (rest of your fallback data)
     }
 
 # Load your dataset
@@ -112,13 +122,8 @@ def predict_interaction(drug_names):
         if prediction:
             return f"Predicted Interaction: {prediction}"
         else:
-            # Try to find similar drugs for debugging
-            found_drugs = set()
-            for d1, d2 in interaction_db.keys():
-                found_drugs.add(d1)
-                found_drugs.add(d2)
-            
-            print(f"Not found. Available drugs: {sorted(list(found_drugs))[:20]}...")
+            # Log all available keys for debugging
+            print(f"Keys in interaction_db: {list(interaction_db.keys())[:10]}... (total {len(interaction_db)})")
             return f"Predicted Interaction: Moderate"  # Default to Moderate if not found
         
     except Exception as e: