Update app.py

app.py

@@ -84,20 +84,62 @@ max_date_allowed_pred = df_filtered['Date'].max().date()
 end_date = df['Date'].max().date()
 start_date = end_date - pd.Timedelta(days=7)
 
-models_corr_matrix = ['Neural Network 1', 'Neural Network 2', 'Neural Network 3', 
+models_corr_matrix = ['Persistence Model', 'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 
                'Neural Network 4', 'Regularized Linear Model 1', 
                'Regularized Linear Model 2', 'Regularized Linear Model 3', 
-               'Regularized Linear Model 4']
+               'Regularized Linear Model 4', 'Hybrid Ensemble']
+
+def conformal_predictions(data):
+    data['Residuals'] = data['Hybrid Ensemble'] - data['Real Price']
+    data.set_index('Date', inplace=True)
+    data['Hour'] = data.index.hour
+    min_date = data.index.min()
+    for date in data.index.normalize().unique():
+        if date >= min_date + pd.DateOffset(days=30):
+            start_date = date - pd.DateOffset(days=30)
+            end_date = date
+            calculation_window = data[start_date:end_date-pd.DateOffset(hours=1)]
+            quantiles = calculation_window.groupby('Hour')['Residuals'].quantile(0.9)
+            # Use .loc to safely access and modify data
+            if date in data.index:
+                current_day_data = data.loc[date.strftime('%Y-%m-%d')]
+                for hour in current_day_data['Hour'].unique():
+                    if hour in quantiles.index:
+                        hour_quantile = quantiles[hour]
+                        idx = (data.index.normalize() == date) & (data.Hour == hour)
+                        data.loc[idx, 'Quantile_90'] = hour_quantile
+                        data.loc[idx, 'Lower_Interval'] = data.loc[idx, 'Hybrid Ensemble'] - hour_quantile
+                        data.loc[idx, 'Upper_Interval'] = data.loc[idx, 'Hybrid Ensemble'] + hour_quantile
+    data.reset_index(inplace=True)
+    return data
+
+# Main layout of the app
+col1, col2 = st.columns([5, 2])  # Adjust the ratio to better fit your layout needs
+with col1:
+    st.title("Belgium: Electricity Price Forecasting")
+
+with col2:
+    upper_space = col2.empty()
+    upper_space = col2.empty()
+    col2_1, col2_2 = st.columns(2)  # Create two columns within the right column for side-by-side images
+    with col2_1:
+        st.image("C:/Users/mmascare/Documents/KU_Leuven_logo.png", width=100)   # Adjust the path and width as needed
+    with col2_2:
+        st.image("C:/Users/mmascare/Documents/energyville_logo.png", width=100) 
+
+upper_space.markdown("""
+   
+   
+""", unsafe_allow_html=True)
 
-st.title("Belgium: Electricity Price Forecasting")
 
 # Sidebar for inputs
 with st.sidebar:
     st.write("### Variables Selection for Graph")
     st.write("Select which variables you'd like to include in the graph. This will affect the displayed charts and available data for download.")
-    selected_variables = st.multiselect("Select variables to display:", ['Real Price', 'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4', 'Hybrid Ensemble', 'Persistence Model'], default=['Real Price','Neural Network 4', 'Regularized Linear Model 4', 'Persistence Model'])#options=['Real Price', 'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Neural Network Ensemble', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4', 'Regularized Linear Model Ensemble', 'Hybrid Ensemble', 'Persistence Model'], default=['Real Price', 'Neural Network Ensemble', 'Regularized Linear Model Ensemble', 'Persistence Model'])
+    selected_variables = st.multiselect("Select variables to display:", options=['Real Price', 'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4', 'Hybrid Ensemble', 'Persistence Model'], default=['Real Price', 'Hybrid Ensemble'])
     st.write("### Model Selection for Scatter Plot")
-    model_selection = st.selectbox("Select which model's predictions to display:", options=['Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4',  'Hybrid Ensemble', 'Persistence Model'], index=8)#options=['Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Neural Network Ensemble', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4', 'Regularized Linear Model Ensemble', 'Hybrid Ensemble', 'Persistence Model'], index=10) # Adjust the index as needed to default to your desired option
+    model_selection = st.selectbox("Select which model's predictions to display:", options=['Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Regularized Linear Model 1', 'Regularized Linear Model 2','Regularized Linear Model 3', 'Regularized Linear Model 4', 'Hybrid Ensemble', 'Persistence Model'], index=8) # Adjust the index as needed to default to your desired option
 
     st.write("### Date Range for Metrics Calculation")
     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.")
@@ -107,14 +149,42 @@ with st.sidebar:
 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))]
+
+    # Call conformal_predictions if 'Hybrid Ensemble' is selected
+    if 'Hybrid Ensemble' in selected_variables:
+        df = conformal_predictions(df)  # Make sure this function modifies df correctly
+
+    temp_df = df[(df['Date'] >= pd.Timestamp(start_date))]  # Ensure correct date filtering
+
+    # Initialize Plotly figure
     fig = go.Figure()
 
     for variable in selected_variables:
         fig.add_trace(go.Scatter(x=temp_df['Date'], y=temp_df[variable], mode='lines', name=variable))
 
+        # Check if conformal predictions should be added for Hybrid Ensemble
+        if variable == 'Hybrid Ensemble' and 'Quantile_90' in df.columns:
+            # Add the lower interval trace
+            fig.add_trace(go.Scatter(
+                x=temp_df['Date'],
+                y=temp_df['Lower_Interval'],
+                mode='lines',
+                line=dict(width=0),
+                showlegend=False
+            ))
+
+            # Add the upper interval trace and fill to the lower interval
+            fig.add_trace(go.Scatter(
+                x=temp_df['Date'],
+                y=temp_df['Upper_Interval'],
+                mode='lines',
+                line=dict(width=0),
+                fill='tonexty',  # Fill between this trace and the previous one
+                fillcolor='rgba(68, 68, 68, 0.3)',
+                name='Conformal Prediction'
+            ))
+
     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: a Neural Network, a Regularized Linear Model, and Persistence, alongside the actual electricity prices up until today.")
@@ -146,7 +216,13 @@ else:
     fig.add_trace(go.Scatter(x=plot_df['Real 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 from {min_date_allowed_pred} to {max_date_allowed_pred}")
+    fig.update_layout(
+        title=f"Scatter Plot of Real Price vs {model_selection} Predictions from {min_date_allowed_pred} to {max_date_allowed_pred}",
+        xaxis_title="Real Price [EUR/MWh]",
+        yaxis_title=f"{model_selection} Predictions [EUR/MWh]",
+        xaxis=dict(range=[-160, 160]),  # Setting the x-axis range
+        yaxis=dict(range=[-150, 150])   # Setting the y-axis range
+    )
     st.plotly_chart(fig, use_container_width=True)
 
 
@@ -158,11 +234,6 @@ if start_date_pred and end_date_pred:
     filtered_df = df_filtered[(df_filtered['Date'] >= pd.Timestamp(start_date_pred)) & (df_filtered['Date'] <= pd.Timestamp(end_date_pred))]
     
     # List of models for convenience
-    #models = [
-    #    'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4', 'Neural Network Ensemble',
-    #    'Regularized Linear Model 1', 'Regularized Linear Model 2', 'Regularized Linear Model 3', 'Regularized Linear Model 4', 'Regularized Linear Model Ensemble',
-    #    'Persistence Model', 'Hybrid Ensemble'
-    #]
     models = [
         'Neural Network 1', 'Neural Network 2', 'Neural Network 3', 'Neural Network 4',
         'Regularized Linear Model 1', 'Regularized Linear Model 2', 'Regularized Linear Model 3', 'Regularized Linear Model 4',