Update app.py

app.py

@@ -311,7 +311,7 @@ def transfer_learning_forecasting():
 
 
 def dynamic_forecasting():
-    st.title("Dynamic Forecasting")
+    st.title("Personalized Neural Forecasting")
     st.markdown("""
     Train time series forecasting model from scratch and provide forecasts/visualization by using various deep neural network-based model trained on user data.
     
@@ -414,8 +414,9 @@ def timegpt_fcst():
 
     df = df.drop_duplicates(subset=['ds']).reset_index(drop=True)
     
-    # st.write(df)
+    
     if st.sidebar.button("Submit"):
+        start_time = time.time()
         forecast_df = nixtla_client.forecast(
             df=df,
             h=h,
@@ -424,9 +425,14 @@ def timegpt_fcst():
         )
         st.session_state.forecast_df = forecast_df
 
-    if 'forecast_df' in st.session_state:
-        forecast_df = st.session_state.forecast_df
-        st.pyplot(nixtla_client.plot(df, forecast_df, level=[90]))
+
+        if 'forecast_df' in st.session_state:
+            forecast_df = st.session_state.forecast_df
+            st.pyplot(nixtla_client.plot(df, forecast_df, level=[90]))
+    
+            end_time = time.time()  # End timing
+            time_taken = end_time - start_time
+            st.success(f"Time taken for {model_choice} forecast: {time_taken:.2f} seconds")
 
 
 
@@ -478,6 +484,7 @@ def timegpt_anom():
 
     df = df.drop_duplicates(subset=['ds']).reset_index(drop=True)
     if st.sidebar.button("Submit"):
+        start_time=time.time()
         anom_df = nixtla_client.detect_anomalies(
             df=df,
             freq=freq,
@@ -485,9 +492,13 @@ def timegpt_anom():
         )
         st.session_state.anom_df = anom_df
 
-    if 'anom_df' in st.session_state:
-        anom_df = st.session_state.anom_df
-        st.pyplot(nixtla_client.plot(df, anom_df))
+        if 'anom_df' in st.session_state:
+            anom_df = st.session_state.anom_df
+            st.pyplot(nixtla_client.plot(df, anom_df))
+    
+            end_time = time.time()  # End timing
+            time_taken = end_time - start_time
+            st.success(f"Time taken for {model_choice} forecast: {time_taken:.2f} seconds")
         
     
     
@@ -497,7 +508,7 @@ pg = st.navigation({
     "Neuralforecast": [
         # Load pages from functions
         st.Page(transfer_learning_forecasting, title="Zero-shot Forecasting", default=True, icon=":material/query_stats:"),
-        st.Page(dynamic_forecasting, title="Dynamic Forecasting", icon=":material/monitoring:"),
+        st.Page(dynamic_forecasting, title="Personalized Neural Forecasting", icon=":material/monitoring:"),
     ],
         "TimeGPT": [
         # Load pages from functions