Update app.py

app.py

@@ -232,21 +232,21 @@ def calculate_prediction_with_ltsm(symbol="BTC", period="5d", interval="5m"):
     prices = [(pd.to_datetime(index, unit='m'), price) for index, price in data['Close'].items()] 
     df = pd.DataFrame(prices, columns=['Date', 'Price'])
 
-    st.write("**Preparing data for LTSM Model training......")
+    st.write("**Preparing data for LTSM Model training......(processing)...")
     X, Y, scaler = prepare_lstm_data(df)
 
-    st.write("**Build LTSM Model with X shape data.........")
+    st.write("**Build LTSM Model with X shape data.........(processing)...")
     model = build_lstm_model((X.shape[1], 1))
 
     # Train the model
-    st.write("**Train LTSM Model with X,Y shape data with batch_size(32), epochs(10)............")
+    st.write("**Train LTSM Model with X,Y shape data with batch_size(32), epochs(10)............(processing)...")
     model.fit(X, Y, batch_size=32, epochs=10)
     
     # Predict the next price point
-    st.write("**Sequence LTSM Model with X,Y shape data with batch_size(32), epochs(10)...............")
+    st.write("**Sequence LTSM Model with X,Y shape data with batch_size(32), epochs(10)...............(processing)...")
     last_sequence = X[-1].reshape(1, X.shape[1], 1)
 
-    st.write("**Predict realtime price with  LTSM Model trained with X,Y shape data with batch_size(32), epochs(10)..................")
+    st.write("**Predict realtime price with  LTSM Model trained with X,Y shape data with batch_size(32), epochs(10)..................(processing)...")
     scaled_prediction = model.predict(last_sequence)
     predicted_price = scaler.inverse_transform(scaled_prediction)
 
@@ -396,8 +396,8 @@ symbol = st.sidebar.text_input("Enter Cryptocurrency Symbol (e.g., BTC):", "BTC"
 
 # Add buttons for navigation
 show_news_button = st.sidebar.button("Show Latest News")
-show_data_button = st.sidebar.button("Show Data and Prediction")
-predict_lstm_button = st.sidebar.button("Predict with LSTM Model")
+show_data_button = st.sidebar.button("Show Data and Indicators")
+predict_lstm_button = st.sidebar.button("Predict by training LSTM Model")
 
 
 # Fetch data and news when the button is clicked