Update app.py

app.py

@@ -49,13 +49,17 @@ with st.sidebar:
     st.write("Select the date range to calculate the metrics for the predictions. This will influence the accuracy metrics displayed below. The complete dataset ranges from 10/03/2024 until today.")
     start_date_pred, end_date_pred = st.date_input("Select Date Range for Metrics Calculation:", [min_date_allowed_pred, max_date_allowed_pred])
 
+    st.write("### Model Selection for Scatter Plot")
+    model_selection = st.selectbox("Select which model's predictions to display:", options=['DNN', 'LEAR', 'Persistence'], index=0)  # Default to 'DNN'
+
+
 # Main content
 if not selected_variables:
     st.warning("Please select at least one variable to display.")
 else:
     # Plotting
     st.write("## Belgian Day-Ahead Electricity Prices")
-    temp_df = df[(df['Date'] >= pd.Timestamp(start_date))]# & (df['Date'] <= pd.Timestamp(end_date))]
+    temp_df = df[(df['Date'] >= pd.Timestamp(start_date))] #& (df['Date'] <= pd.Timestamp(end_date))]
     fig = go.Figure()
 
     # Updated labels for each variable
@@ -71,18 +75,40 @@ else:
 
     fig.update_layout(xaxis_title="Date", yaxis_title="Price [EUR/MWh]")
     st.plotly_chart(fig, use_container_width=True)
-    st.write("The graph presented here illustrates the day-ahead electricity price forecasts for Belgium, covering the period from one week ago up to tomorrow. It incorporates predictions from three distinct models: DNN (Deep Neural Networks), LEAR (Lasso Estimated AutoRegressive), and Persistence, alongside the actual electricity prices up until today. The Persistence model, a seasonal naive forecaster, bases its predictions on the prices from one week ago. More information regarding the DNN and LEAR models can be found in  article titled: Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark, published in Applied Energy, volume 293, pages 116983, in 2021. Authored by Jesus Lago, Grzegorz Marcjasz, Bart De Schutter, and Rafał Weron.")
+    st.write("The graph presented here illustrates the day-ahead electricity price forecasts for Belgium, covering the period from one week ago up to tomorrow. It incorporates predictions from three distinct models: DNN (Deep Neural Networks), LEAR (Lasso Estimated AutoRegressive), and Persistence, alongside the actual electricity prices up until today.")
+
+
+if not selected_variables:
+    st.warning("Please select at least one variable to display.")
+else:
+    # Plotting
+    st.write("## Scatter Plot: Real Price vs Model Predictions")
+    # Filter based on the selected date range for plotting
+    plot_df = df[(df['Date'] >= pd.Timestamp(min_date_allowed_pred)) & (df['Date'] <= pd.Timestamp(max_date_allowed_pred))]
+    
+    model_column = model_selection
+    if model_selection == 'Persistence':
+        model_column = 'Persis'  # Assuming the DataFrame uses 'Persis' as the column name
+
+    # Create the scatter plot
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=plot_df['Price'], y=plot_df[model_column], mode='markers', name=f"Real Price vs {model_selection} Predictions"))
+
+    # Calculate the line of best fit
+    m, b = np.polyfit(plot_df['Price'], plot_df[model_column], 1)
+    # Calculate the y-values based on the line of best fit
+    regression_line = m * plot_df['Price'] + b
+
+    # Format the equation to display as the legend name
+    equation = f"y = {m:.2f}x + {b:.2f}"
+
+    # Add the line of best fit to the figure with the equation as the legend name
+    fig.add_trace(go.Scatter(x=plot_df['Price'], y=regression_line, mode='lines', name=equation, line=dict(color='black')))
+
+    # Update layout with appropriate titles
+    fig.update_layout(xaxis_title="Real Price [EUR/MWh]", yaxis_title=f"{model_selection} Predictions [EUR/MWh]", title=f"Scatter Plot of Real Price vs {model_selection} Predictions")
+    st.plotly_chart(fig, use_container_width=True)
 
-# Download Predictions Button
-st.write("## Download Predictions")
-st.write("Download Day-Ahead Price & Model Predictions: Receive a detailed CSV file comprising the actual day-ahead electricity prices and the corresponding LEAR and DNN model forecasts. This data enables you to compare performance and accuracy.")
-csv = convert_df_to_csv(df)
-st.download_button(
-    label="Download Predictions CSV",
-    data=csv,
-    file_name='predictions.csv',
-    mime='text/csv',
-)
 
 # Calculating and displaying metrics
 if start_date_pred and end_date_pred:
@@ -102,18 +128,25 @@ if start_date_pred and end_date_pred:
     smape_dnn = 100 * np.mean(np.abs(p_real - p_pred_dnn) / ((np.abs(p_real) + np.abs(p_pred_dnn)) / 2))
     rmse_dnn = np.sqrt(np.mean((p_real - p_pred_dnn) ** 2))
   
+
     mae_lear = np.mean(np.abs(p_real - p_pred_lear))
     smape_lear = 100 * np.mean(np.abs(p_real - p_pred_lear) / ((np.abs(p_real) + np.abs(p_pred_lear)) / 2))
     rmse_lear = np.sqrt(np.mean((p_real - p_pred_lear) ** 2))
 
+
     mae_persis = np.mean(np.abs(p_real - p_pred_persis))
     smape_persis = 100 * np.mean(np.abs(p_real - p_pred_persis) / ((np.abs(p_real) + np.abs(p_pred_persis)) / 2))
     rmse_persis = np.sqrt(np.mean((p_real - p_pred_persis) ** 2))
 
+
     new_metrics_df = pd.DataFrame({
         'Metric': ['MAE', 'SMAPE', 'RMSE'],
         'Persistence': [f"{mae_persis:.2f}", f"{smape_persis:.2f}%", f"{rmse_persis:.2f}"],
         'DNN': [f"{mae_dnn:.2f}", f"{smape_dnn:.2f}%", f"{rmse_dnn:.2f}"],
         'LEAR': [f"{mae_lear:.2f}", f"{smape_lear:.2f}%", f"{rmse_lear:.2f}"]
     })
-    st.dataframe(new_metrics_df, hide_index=True)
+    st.dataframe(new_metrics_df, hide_index=True)
+
+# Download Predictions Button
+st.write("## Access Predictions")
+st.write("If you are interested in accessing the predictions made by the models, please contact Margarida Mascarenhas (KU Leuven PhD Student) at margarida.mascarenhas@kuleuven.be")