Update app.py

app.py

@@ -7,6 +7,7 @@ from neuralforecast.models import NHITS, TimesNet, LSTM, TFT
 from neuralforecast.losses.pytorch import HuberMQLoss
 from neuralforecast.utils import AirPassengersDF
 import time
+from st_aggrid import AgGrid
 
 @st.cache_resource
 def load_model(path, freq):
@@ -225,6 +226,15 @@ def transfer_learning_forecasting():
     frequency = determine_frequency(df)
     st.sidebar.write(f"Detected frequency: {frequency}")
 
+    df_grid = df.drop(columns="unique_id")
+    grid_table = AgGrid(
+                    df_grid,
+                    editable=False,
+                    theme="streamlit",
+                    fit_columns_on_grid_load=True,
+                    height=360,
+                )
+
     # Load pre-trained models
     nhits_model, timesnet_model, lstm_model, tft_model = select_model_based_on_frequency(frequency, nhits_models, timesnet_models, lstm_models, tft_models)
     forecast_results = {}
@@ -239,6 +249,14 @@ def transfer_learning_forecasting():
     elif model_choice == "TFT":
         forecast_results['TFT'] = generate_forecast(tft_model, df)
 
+    df_grid = df.drop(columns="unique_id")
+    grid_table = AgGrid(
+                    df_grid,
+                    editable=False,
+                    theme="streamlit",
+                    fit_columns_on_grid_load=True,
+                    height=360,
+                )
     for model_name, forecast_df in forecast_results.items():
         plot_forecasts(forecast_df, df, f'{model_name} Forecast for {y_col}')