Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-
 import gradio as gr
 import tensorflow as tf
 import joblib
@@ -12,9 +11,8 @@ from huggingface_hub import hf_hub_download
 os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
 
 # --- 1. Download Model and Scalers from Hugging Face Hub ---
-# FIX #1: Ensured the repository name is 100% correct.
 MODEL_REPO = "munem420/stock-forecaster-lstm"
-MODEL_FILENAME = "model_lstm.h5"
+MODEL_FILENAME = "model_lstm.keras"
 SCALER_FILENAME = "scalers.joblib"
 
 print("--- Downloading model and scalers ---")
@@ -32,7 +30,11 @@ loaded_scalers = None
 
 if model_path and os.path.exists(model_path):
     try:
-        loaded_model_lstm = tf.keras.models.load_model(model_path)
+        # FIX #1: Added custom_objects to handle the 'mse' metric during loading
+        loaded_model_lstm = tf.keras.models.load_model(
+            model_path,
+            custom_objects={"mse": tf.keras.losses.MeanSquaredError()}
+        )
         print("✅ Model loaded successfully.")
     except Exception as e:
         print(f"❌ Error loading model: {e}")
@@ -44,20 +46,19 @@ if scalers_path and os.path.exists(scalers_path):
     except Exception as e:
         print(f"❌ Error loading scalers: {e}")
 
+# ... (The rest of the file is unchanged) ...
+
 ticker_to_name = {'ZURVY': 'Zurich Insurance Group AG'}
 
 def get_ticker_from_input(input_name):
     return input_name.upper()
 
-# --- 3. The Main Forecasting Function ---
 def forecast_stock(input_name, model, scalers_dict, input_width=60):
     if not model or not scalers_dict:
         return "Error: Model or scalers not loaded. The backend may have failed to start."
-    # ... (The rest of the function is the same)
     ticker = get_ticker_from_input(input_name)
     if not ticker:
         return "Error: Invalid stock ticker."
-
     print(f"\n--- Generating forecast for {ticker} ---")
     try:
         data_df = yf.download(ticker, period="1y", progress=False)
@@ -65,26 +66,20 @@ def forecast_stock(input_name, model, scalers_dict, input_width=60):
              return f"Error: No data found for ticker {ticker}. It may be delisted or invalid."
     except Exception as e:
         return f"Error fetching data for {ticker}: {e}"
-
     if len(data_df) < input_width:
         return f"Error: Not enough historical data. Need {input_width} days, but only have {len(data_df)}."
-
     recent_data = data_df.tail(input_width)
     close_prices = recent_data['Close'].values.reshape(-1, 1)
-
     scaler = scalers_dict.get(ticker)
     if not scaler:
         print(f"Warning: No specific scaler found for {ticker}. Using ZURVY's scaler as a fallback.")
         scaler = scalers_dict.get('ZURVY')
         if not scaler:
             return "Error: Default scaler 'ZURVY' not found."
-
     scaled_data = scaler.transform(close_prices)
     X_pred = scaled_data.reshape(1, input_width, 1)
-
     prediction_scaled = model.predict(X_pred, verbose=0)[0][0]
     prediction_actual = scaler.inverse_transform(np.array([[prediction_scaled]]))[0][0]
-
     last_close = recent_data['Close'].iloc[-1]
     result = (
         f"Last known close for {ticker}: ${last_close:.2f}\n"
@@ -93,7 +88,6 @@ def forecast_stock(input_name, model, scalers_dict, input_width=60):
     print(result)
     return result
 
-# --- 4. Create the Gradio Interface ---
 def predict_api(ticker_symbol):
     return forecast_stock(ticker_symbol, loaded_model_lstm, loaded_scalers)
 
@@ -103,10 +97,7 @@ with gr.Blocks() as app:
     output_text = gr.Textbox(label="Forecast", visible=False)
     ticker_input.submit(predict_api, inputs=[ticker_input], outputs=[output_text], api_name="predict")
 
-# --- 5. Mount and Serve the React App's Static Files ---
-# This function requires a modern version of Gradio, specified in README.md
 app = gr.mount_static_directory(app, "build")
 
-# Launch the server
 if __name__ == "__main__":
     app.launch()