Update app.py

app.py

@@ -86,6 +86,43 @@ class TweetPreprocessor:
         """Normalize popularity scores using min-max scaling."""
         popularity = self.data['Retweets'] + self.data['Likes']
         return (popularity - popularity.min()) / (popularity.max() - popularity.min() + 1e-6)
+class FakeNewsClassifier:
+    def __init__(self, model_name: str):
+        """Initialize the fake news classifier."""
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model_name = model_name
+        self.model, self.tokenizer = self._load_model()
+        
+    def _load_model(self) -> Tuple[AutoModelForSequenceClassification, AutoTokenizer]:
+        """Load the model and tokenizer."""
+        try:
+            tokenizer = AutoTokenizer.from_pretrained(self.model_name)
+            model = AutoModelForSequenceClassification.from_pretrained(self.model_name).to(self.device)
+            return model, tokenizer
+        except Exception as e:
+            logger.error(f"Error loading model: {e}")
+            raise
+
+    @torch.no_grad()
+    def predict_batch(self, texts: List[str], batch_size: int = 32) -> np.ndarray:
+        """Predict fake news probability for a batch of texts."""
+        predictions = []
+        
+        for i in range(0, len(texts), batch_size):
+            batch_texts = texts[i:i + batch_size]
+            inputs = self.tokenizer(
+                batch_texts,
+                return_tensors="pt",
+                padding=True,
+                truncation=True,
+                max_length=128
+            ).to(self.device)
+            
+            outputs = self.model(**inputs)
+            batch_predictions = outputs.logits.argmax(dim=1).cpu().numpy()
+            predictions.extend(batch_predictions)
+            
+        return np.array(predictions)     
 
 class RecommendationSystem:
     def __init__(self, data_path: Path, model_name: str):