Update app.py

app.py

@@ -1,39 +1,65 @@
-
-
 import gradio as gr
 import pandas as pd
-import numpy as np
+import os
 
-# Load your labeled dataset
+# Load your labeled dataset with exact column names
 def load_drug_interaction_dataset():
-    """Load your labeled drug interaction dataset"""
+    """Load your labeled drug interaction dataset with exact column names"""
     try:
-        # Replace with your actual dataset path or URL
-        dataset_path = "merged_cleaned_dataset.csv"  # Update this path
+        # Your exact dataset filename
+        dataset_path = 'merged_cleaned_dataset.csv'
+        
+        print(f"Looking for dataset: {dataset_path}")
+        print("Files in directory:", os.listdir('.'))
         
-        # Load the dataset
+        if not os.path.exists(dataset_path):
+            print(f"Dataset file {dataset_path} not found!")
+            return create_fallback_database()
+        
+        # Load the dataset with your exact column names
+        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 from your labeled data
+        # Create interaction dictionary using your exact column names
         interaction_db = {}
+        count = 0
         
-        # Assuming your dataset has columns: Drug1, Drug2, Severity, Confidence
         for _, row in df.iterrows():
-            drug1 = str(row['Drug1']).lower().strip()
-            drug2 = str(row['Drug2']).lower().strip()
-            severity = str(row['Severity']).strip()
-            confidence = float(row.get('Confidence', 0.7))  # Default confidence if not provided
-            
-            # Add both orders to the dictionary
-            interaction_db[(drug1, drug2)] = (severity, confidence)
-            interaction_db[(drug2, drug1)] = (severity, confidence)  # Add reverse order
+            try:
+                # Use your exact column names
+                drug1 = str(row['Drug 1_normalized']).lower().strip()
+                drug2 = str(row['Drug 2_normalized']).lower().strip()
+                severity = str(row['severity']).strip()
+                
+                # Skip empty entries or invalid data
+                if (not all([drug1, drug2, severity]) or 
+                    drug1 == 'nan' or drug2 == 'nan' or 
+                    severity == 'nan' or severity.lower() == 'none'):
+                    continue
+                
+                # Clean up severity labels
+                severity = severity.capitalize()
+                if severity == 'No interaction':
+                    severity = 'No Interaction'
+                
+                # Add both orders to the dictionary
+                interaction_db[(drug1, drug2)] = severity
+                interaction_db[(drug2, drug1)] = severity  # Add reverse order
+                count += 1
+                
+            except Exception as e:
+                print(f"Error processing row {_}: {e}")
+                continue
         
-        print(f"✅ Loaded {len(interaction_db)//2} drug interactions from dataset")
+        print(f"✅ Successfully loaded {count} drug interactions from dataset")
+        print(f"Sample interactions: {list(interaction_db.items())[:5]}")
         return interaction_db
         
     except Exception as e:
         print(f"Error loading dataset: {e}")
-        # Fallback to a basic database if dataset loading fails
         return create_fallback_database()
 
 def create_fallback_database():
@@ -88,9 +114,9 @@ def create_fallback_database():
             ('lisinopril', 'potassium'): ('No Interaction', 0.84),
             ('simvastatin', 'vitamin e'): ('No Interaction', 0.83),
         }
-    
 
 # Load your dataset
+print("Loading drug interaction dataset...")
 interaction_db = load_drug_interaction_dataset()
 
 def predict_interaction(drug_names):
@@ -105,16 +131,22 @@ def predict_interaction(drug_names):
             return "Enter exactly two drug names separated by comma"
         
         drug1, drug2 = drugs[0].lower(), drugs[1].lower()
+        print(f"Looking up: '{drug1}' + '{drug2}'")
         
         # Check if this interaction exists in your dataset
         prediction = interaction_db.get((drug1, drug2))
         
         if prediction:
-            severity, confidence = prediction
-            return f"Severity: {severity} (Confidence: {confidence:.0%}) - From your dataset"
+            return f"Severity: {prediction}"
         else:
-            # Not found in dataset - use moderate as default
-            return "Severity: Moderate (Confidence: 70%) - Not in dataset"
+            # 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]}...")
+            return f"Severity: Moderate - ({drug1}, {drug2} not found in dataset)"
         
     except Exception as e:
         return f"Error: {str(e)}"
@@ -122,7 +154,7 @@ def predict_interaction(drug_names):
 # Create interface
 with gr.Blocks() as demo:
     gr.Markdown("## Drug Interaction Predictor")
-    gr.Markdown("**Using your labeled dataset for predictions**")
+    gr.Markdown("**Using your merged_cleaned_dataset.csv**")
     
     drug_input = gr.Textbox(
         label="Enter two drug names separated by comma",
@@ -133,10 +165,23 @@ with gr.Blocks() as demo:
     predict_btn = gr.Button("Predict")
     output = gr.Textbox(label="Prediction")
     
+    # Show dataset info
+    gr.Markdown(f"*Dataset: merged_cleaned_dataset.csv*")
+    gr.Markdown(f"*Loaded {len(interaction_db)//2} interactions*")
+    
+    # Examples from your dataset
+    gr.Examples(
+        examples=[
+            "warfarin, aspirin",
+            "simvastatin, clarithromycin",
+            "digoxin, quinine",
+            "metformin, alcohol"
+        ],
+        inputs=drug_input,
+        label="Try these examples:"
+    )
+    
     predict_btn.click(predict_interaction, drug_input, output)
 
 if __name__ == "__main__":
-    demo.launch()
-
-    
-       
+    demo.launch()