Update app.py

app.py

@@ -257,27 +257,22 @@ elif page == "Price Prediction":
         past_sales = st.slider("Past Sales", 100, 1000, 500)
         
         # Prepare input for prediction
-        input_data = np.array([[
+        input_data = np.array([
             le_genre.transform([genre])[0],
             le_region.transform([region])[0],
             demand_index,
             competitor_price,
             past_sales
-        ]])
+        ])
         
-        input_scaled = scaler.transform(input_data)
-        input_reshaped = input_scaled.reshape((1, 1, input_scaled.shape[1]))
+        input_scaled = scaler.transform(input_data.reshape(1, -1)).flatten()
+        input_with_step = np.append(input_scaled, 0)  # Add a step value (0 for prediction)
         
         # Make predictions
         if st.button("Predict Price"):
-            lstm_price = lstm_model.predict(input_reshaped)[0][0]
-            transformer_price = transformer_model.predict(input_reshaped)[0][0]
-            rl_price = rl_model.predict(input_scaled)[0][0]
-            
-            # Get LLM analysis
-            game_info = f"Genre: {genre}, Region: {region}, Past Sales: {past_sales}"
-            market_info = f"Demand Index: {demand_index}, Competitor Price: {competitor_price}"
-            llm_analysis = get_llm_analysis(game_info, market_info)
+            lstm_price = lstm_model.predict(input_scaled.reshape(1, 1, -1))[0][0]
+            transformer_price = transformer_model.predict(input_scaled.reshape(1, 1, -1))[0][0]
+            rl_price = rl_model.predict(input_with_step)[0]
             
             # Display results
             st.success(f"LSTM Predicted Price: ${lstm_price:.2f}")