Update app.py

app.py

@@ -217,29 +217,37 @@ class SentimentEngine:
     def extract_key_words_shap(self, text: str, top_k: int = 10) -> List[Tuple[str, float]]:
         """Advanced keyword extraction using SHAP"""
         try:
-            # Initialize SHAP explainer if not already done
-            if self.shap_explainer is None:
-                self.shap_explainer = shap.Explainer(self.predict_proba, self.model_manager.tokenizer)
+            # Simple SHAP implementation using model predictions
+            words = text.split()
+            word_scores = []
             
-            # Get SHAP values
-            shap_values = self.shap_explainer([text])
+            # Get baseline prediction
+            baseline_prob = self.predict_proba([text])[0][1]  # Positive probability
             
-            # Extract word importance
-            words = text.split()
-            if len(shap_values.values) > 0 and len(shap_values.values[0]) > 0:
-                # Get positive class SHAP values
-                pos_shap_values = shap_values.values[0][:, 1] if len(shap_values.values[0].shape) > 1 else shap_values.values[0]
+            # Calculate importance by removing each word
+            for i, word in enumerate(words):
+                # Create text without this word
+                modified_words = words[:i] + words[i+1:]
+                modified_text = ' '.join(modified_words)
                 
-                word_scores = []
-                for i, word in enumerate(words[:len(pos_shap_values)]):
+                if modified_text.strip():
+                    modified_prob = self.predict_proba([modified_text])[0][1]
+                    importance = abs(baseline_prob - modified_prob)
+                    
                     clean_word = re.sub(r'[^\w]', '', word.lower())
                     if len(clean_word) >= config.MIN_WORD_LENGTH:
-                        word_scores.append((clean_word, abs(float(pos_shap_values[i]))))
-                
-                word_scores.sort(key=lambda x: x[1], reverse=True)
-                return word_scores[:top_k]
-            
-            return []
+                        word_scores.append((clean_word, importance))
+            
+            # Remove duplicates and sort
+            unique_scores = {}
+            for word, score in word_scores:
+                if word in unique_scores:
+                    unique_scores[word] = max(unique_scores[word], score)
+                else:
+                    unique_scores[word] = score
+            
+            sorted_scores = sorted(unique_scores.items(), key=lambda x: x[1], reverse=True)
+            return sorted_scores[:top_k]
             
         except Exception as e:
             logger.error(f"SHAP extraction failed: {e}")