app.py analyse function fix 5

src/app.py

@@ -42,53 +42,49 @@ st.set_page_config(
     layout="wide"
 )
 
-# Initialize session state variables
-if 'model' not in st.session_state:
-    st.session_state['model'] = None
-if 'tokenizer' not in st.session_state:
-    st.session_state['tokenizer'] = None
-if 'preprocessor' not in st.session_state:
-    st.session_state['preprocessor'] = None
+@st.cache_resource
+def load_model_and_tokenizer():
+    """Load the model and tokenizer (cached)."""
+    # Initialize model
+    model = HybridFakeNewsDetector(
+        bert_model_name=BERT_MODEL_NAME,
+        lstm_hidden_size=LSTM_HIDDEN_SIZE,
+        lstm_num_layers=LSTM_NUM_LAYERS,
+        dropout_rate=DROPOUT_RATE
+    )
+    
+    # Load trained weights
+    state_dict = torch.load(SAVED_MODELS_DIR / "final_model.pt", map_location=torch.device('cpu'))
+    
+    # Filter out unexpected keys
+    model_state_dict = model.state_dict()
+    filtered_state_dict = {k: v for k, v in state_dict.items() if k in model_state_dict}
+    
+    # Load the filtered state dict
+    model.load_state_dict(filtered_state_dict, strict=False)
+    model.eval()
+    
+    # Initialize tokenizer
+    tokenizer = BertTokenizer.from_pretrained(BERT_MODEL_NAME)
+    
+    return model, tokenizer
 
-def load_model():
-    """Load the trained model and tokenizer."""
-    if st.session_state['model'] is None:
-        # Initialize model
-        model = HybridFakeNewsDetector(
-            bert_model_name=BERT_MODEL_NAME,
-            lstm_hidden_size=LSTM_HIDDEN_SIZE,
-            lstm_num_layers=LSTM_NUM_LAYERS,
-            dropout_rate=DROPOUT_RATE
-        )
-        
-        # Load trained weights
-        state_dict = torch.load(SAVED_MODELS_DIR / "final_model.pt", map_location=torch.device('cpu'))
-        
-        # Filter out unexpected keys
-        model_state_dict = model.state_dict()
-        filtered_state_dict = {k: v for k, v in state_dict.items() if k in model_state_dict}
-        
-        # Load the filtered state dict
-        model.load_state_dict(filtered_state_dict, strict=False)
-        model.eval()
-        st.session_state['model'] = model
-        
-        # Initialize tokenizer
-        st.session_state['tokenizer'] = BertTokenizer.from_pretrained(BERT_MODEL_NAME)
-        
-        # Initialize preprocessor
-        st.session_state['preprocessor'] = TextPreprocessor()
+@st.cache_resource
+def get_preprocessor():
+    """Get the text preprocessor (cached)."""
+    return TextPreprocessor()
 
 def predict_news(text):
     """Predict if the given news is fake or real."""
-    if st.session_state['model'] is None:
-        load_model()
+    # Get model, tokenizer, and preprocessor from cache
+    model, tokenizer = load_model_and_tokenizer()
+    preprocessor = get_preprocessor()
     
     # Preprocess text
-    processed_text = st.session_state['preprocessor'].preprocess_text(text)
+    processed_text = preprocessor.preprocess_text(text)
     
     # Tokenize
-    encoding = st.session_state['tokenizer'].encode_plus(
+    encoding = tokenizer.encode_plus(
         processed_text,
         add_special_tokens=True,
         max_length=MAX_SEQUENCE_LENGTH,
@@ -100,7 +96,7 @@ def predict_news(text):
     
     # Get prediction
     with torch.no_grad():
-        outputs = st.session_state['model'](
+        outputs = model(
             encoding['input_ids'],
             encoding['attention_mask']
         )