Update app.py

app.py

@@ -81,6 +81,7 @@ def process_data(file, trade_selection, filter_date):
             return "Error: Attendance column contains non-numeric values", None, None, None, None, None
         
         # Ensure Attendance is positive
+        df['Attendance'] = df['Attendance'].clip(lower=0)
         if (df['Attendance'] <= 0).any():
             logger.error("Attendance contains non-positive values")
             return "Error: Attendance must contain only positive values", None, None, None, None, None
@@ -133,16 +134,17 @@ def process_data(file, trade_selection, filter_date):
         # Parse forecast dates
         forecast_df['Date'] = pd.to_datetime(forecast_df['Date'])
         
-        # Apply date filtering based on manual filter_date
-        date_range_str = "All dates"
-        if filter_date and filter_date.strip():
-            try:
-                selected_date = pd.to_datetime(filter_date.strip(), format='%d-%m-%Y')
-                forecast_df = forecast_df[forecast_df['Date'].dt.date == selected_date.date()]
-                date_range_str = selected_date.strftime('%Y-%m-%d')
-            except ValueError:
-                logger.error(f"Invalid date format: {filter_date}. Use DD-MM-YYYY (e.g., 01-04-2025)")
-                return "Error: Invalid date format. Use DD-MM-YYYY (e.g., 01-04-2025)", None, None, None, None, None
+        # Ensure only positive values for Risk and Attendance in forecast data
+        forecast_df['Risk'] = forecast_df['Risk'].clip(lower=0)
+        forecast_df['Attendance'] = forecast_df['Attendance'].clip(lower=0)
+        
+        # Apply date filtering based on filter_date (daily view only)
+        if filter_date:
+            selected_date = pd.to_datetime(filter_date)
+            forecast_df = forecast_df[forecast_df['Date'].dt.date == selected_date.date()]
+            date_range_str = selected_date.strftime('%Y-%m-%d')
+        else:
+            date_range_str = "All dates"
         
         if forecast_df.empty:
             logger.warning("No data available for the selected date")
@@ -151,20 +153,18 @@ def process_data(file, trade_selection, filter_date):
         # Store the forecast data globally
         latest_forecast_df = forecast_df
         
-        # Create bar graph for risk with enhanced layout and fixed overlapping labels
-        logger.debug("Generating enhanced risk bar graph with fixed overlapping labels")
+        # Create bar graph for risk with enhanced layout
+        logger.debug("Generating enhanced risk bar graph")
         risk_bar_fig = go.Figure()
-        colors = px.colors.qualitative.Plotly
+        colors = px.colors.qualitative.Plotly  # Consistent color palette for trades
         
         for idx, trade in enumerate(trades_to_process):
             trade_forecast = forecast_df[forecast_df['Trade'] == trade]
             risk_bar_fig.add_trace(go.Bar(
                 x=trade_forecast['Date'],
-                y=trade_forecast['Risk'].clip(1, 100),  # Minimum risk set to 1% instead of 0%
+                y=trade_forecast['Risk'].clip(lower=0),  # Cap risk values to zero or above
                 name=trade,
                 marker_color=colors[idx % len(colors)],
-                width=0.3,
-                offset=(idx - (len(trades_to_process) - 1) / 2) * 0.2,
                 hovertemplate=(
                     f"Trade: {trade}<br>" +
                     "Date: %{x}<br>" +
@@ -176,7 +176,7 @@ def process_data(file, trade_selection, filter_date):
             title=f"Shortage Risk Bar Graph ({date_range_str}, Risk in %, {len(trades_to_process)} Trade{'s' if len(trades_to_process) != 1 else ''})",
             xaxis_title="Date",
             yaxis_title="Risk (%)",
-            barmode='group',
+            barmode='group',  # Group bars to avoid overlap
             showlegend=True,
             hovermode="closest",
             legend=dict(
@@ -190,37 +190,26 @@ def process_data(file, trade_selection, filter_date):
                 x=1
             ),
             xaxis=dict(
-                tickangle=60,
+                tickangle=45,  # Rotate for better readability
                 tickformat="%Y-%m-%d",
-                tickmode="auto",
-                nticks=5,
+                tickmode="linear",  # Ensure even spacing
+                nticks=10,  # Adjust number of ticks for clarity
                 gridcolor='lightgrey'
             ),
             yaxis=dict(
-                range=[1, 100],  # Adjusted to start from 1 for strictly positive risks
+                range=[0, 100],  # Set a reasonable range starting from 0
                 gridcolor='lightgrey',
-                zeroline=False,  # Remove zeroline since risks start at 1
-                gridwidth=1
+                zeroline=True,
+                zerolinewidth=2,
+                zerolinecolor='black'
             ),
             plot_bgcolor='white',
             margin=dict(t=80, b=80, l=60, r=60)
         )
         
-        for idx, trade in enumerate(trades_to_process):
-            trade_forecast = forecast_df[forecast_df['Trade'] == trade]
-            for i, (date, risk) in enumerate(zip(trade_forecast['Date'], trade_forecast['Risk'].clip(1, 100))):
-                y_offset = 5
-                risk_bar_fig.add_annotation(
-                    x=date,
-                    y=risk,
-                    text=f"{risk}%",
-                    showarrow=False,
-                    yshift=y_offset,
-                    font=dict(size=10),
-                    align="center"
-                )
-        
+        # Add annotation for capped values
         max_risk = forecast_df['Risk'].max()
+        min_risk = forecast_df['Risk'].min()
         if max_risk > 100:
             risk_bar_fig.add_annotation(
                 text=f"Note: Risk values capped at 100% (Max: {max_risk:.1f}%)",
@@ -230,7 +219,7 @@ def process_data(file, trade_selection, filter_date):
                 font=dict(size=10)
             )
         
-        logger.info("Enhanced risk bar graph with fixed overlapping labels generated")
+        logger.info("Enhanced risk bar graph generated")
         
         # Create line graph for attendance
         logger.debug("Generating attendance line graph")
@@ -239,9 +228,10 @@ def process_data(file, trade_selection, filter_date):
         
         for idx, trade in enumerate(trades_to_process):
             trade_forecast = forecast_df[forecast_df['Trade'] == trade]
+            # Add line for attendance
             line_fig.add_trace(go.Scatter(
                 x=trade_forecast['Date'],
-                y=trade_forecast['Attendance'],
+                y=trade_forecast['Attendance'].clip(lower=0),
                 mode='lines+markers',
                 name=trade,
                 line=dict(color=colors[idx % len(colors)]),
@@ -256,12 +246,13 @@ def process_data(file, trade_selection, filter_date):
                 customdata=trade_forecast[['Risk', 'Alert']].values
             ))
             
+            # Add markers for Warning and Critical alerts
             for alert_type in ['Warning', 'Critical']:
                 alert_data = trade_forecast[trade_forecast['Alert'] == alert_type]
                 if not alert_data.empty:
                     line_fig.add_trace(go.Scatter(
                         x=alert_data['Date'],
-                        y=alert_data['Attendance'],
+                        y=alert_data['Attendance'].clip(lower=0),
                         mode='markers',
                         name=f"{trade} {alert_type}",
                         marker=dict(
@@ -296,6 +287,7 @@ def process_data(file, trade_selection, filter_date):
                 gridcolor='lightgrey'
             ),
             yaxis=dict(
+                range=[0, forecast_df['Attendance'].max() * 1.2],  # Dynamic range starting from 0
                 gridcolor='lightgrey'
             ),
             plot_bgcolor='white',
@@ -310,7 +302,7 @@ def process_data(file, trade_selection, filter_date):
             'Risk': 'mean'
         }).reset_index()
         summary_df['Attendance'] = summary_df['Attendance'].round(1)
-        summary_df['Risk'] = summary_df['Risk'].round(1).clip(1)  # Ensure minimum risk of 1%
+        summary_df['Risk'] = summary_df['Risk'].round(1)
         summary_df = summary_df.rename(columns={'Attendance': 'Average Attendance', 'Risk': 'Average Risk (%)'})
         logger.info(f"Summary statistics generated: {summary_df.to_dict()}")
         
@@ -319,9 +311,9 @@ def process_data(file, trade_selection, filter_date):
         fig = plt.figure(figsize=(12, 20))
         gs = fig.add_gridspec(5, 1, height_ratios=[3, 3, 0.2, 1.5, 0.5], hspace=0.8)
         
-        # Plot bar graph for risk
+        # Plot bar graph for risk with improved text alignment and spacing
         ax1 = fig.add_subplot(gs[0])
-        width = 0.2
+        width = 0.35  # Adjusted width for even spacing
         unique_dates = forecast_df['Date'].unique()
         x_positions = range(len(unique_dates))
         
@@ -330,20 +322,20 @@ def process_data(file, trade_selection, filter_date):
             trade_x = [pos + idx * width for pos in x_positions]
             bars = ax1.bar(
                 trade_x,
-                trade_forecast['Risk'].clip(1, 100),
+                trade_forecast['Risk'].clip(lower=0),
                 width,
                 label=trade,
                 color=colors[idx % len(colors)]
             )
-            for bar in bars:
-                height = bar.get_height()
-                y_offset = 5
+            for bar, x, height in zip(bars, trade_x, trade_forecast['Risk'].clip(lower=0)):
+                # Dynamic vertical offset based on bar height with adjusted padding
+                offset = 5 if abs(height) < 10 else 10  # Adjusted for positive values only
                 ax1.text(
-                    bar.get_x() + bar.get_width() / 2,
-                    height + y_offset,
+                    x + width / 2,  # Center horizontally
+                    height + offset,  # Dynamic vertical offset
                     f'{height:.1f}%',
                     ha='center',
-                    va='bottom',
+                    va='bottom',  # Align text appropriately for positive values
                     fontsize=8
                 )
         
@@ -351,10 +343,12 @@ def process_data(file, trade_selection, filter_date):
         ax1.set_xlabel('Date', fontsize=12)
         ax1.set_ylabel('Risk (%)', fontsize=12)
         ax1.set_xticks([pos + (len(trades_to_process) - 1) * width / 2 for pos in x_positions])
-        ax1.set_xticklabels([date.strftime('%Y-%m-%d') for date in unique_dates], rotation=45, fontsize=8)
+        ax1.set_xticklabels([date.strftime('%Y-%m-%d') for date in unique_dates], rotation=45, ha='right', fontsize=8)
+        ax1.set_yticks(range(0, 125, 25))  # Balanced y-axis scale with 25% increments starting from 0
         ax1.grid(True, axis='y', linestyle='--', alpha=0.7)
-        ax1.legend(title="Trades", fontsize=10, loc='upper left')
-        ax1.set_ylim(1, 100)  # Adjusted to start from 1 for strictly positive risks
+        ax1.legend(title="Trades", fontsize=10, loc='upper right', bbox_to_anchor=(1.15, 1))  # Moved legend outside
+        ax1.set_ylim(0, 100)  # Cap y-axis to positive values only
+        ax1.tick_params(axis='x', pad=10)  # Increase padding to prevent overlap
         
         # Plot line graph for attendance
         ax2 = fig.add_subplot(gs[1])
@@ -362,7 +356,7 @@ def process_data(file, trade_selection, filter_date):
             trade_forecast = forecast_df[forecast_df['Trade'] == trade]
             ax2.plot(
                 trade_forecast['Date'],
-                trade_forecast['Attendance'],
+                trade_forecast['Attendance'].clip(lower=0),
                 label=trade,
                 color=colors[idx % len(colors)],
                 marker='o',
@@ -374,7 +368,7 @@ def process_data(file, trade_selection, filter_date):
                 if not alert_data.empty:
                     ax2.scatter(
                         alert_data['Date'],
-                        alert_data['Attendance'],
+                        alert_data['Attendance'].clip(lower=0),
                         label=f"{trade} {alert_type}",
                         color=alert_colors[alert_type],
                         marker='D',
@@ -389,6 +383,7 @@ def process_data(file, trade_selection, filter_date):
         ax2.grid(True, linestyle='--', alpha=0.7)
         ax2.legend(title="Trades & Alerts", fontsize=10, loc='upper left', bbox_to_anchor=(0, -0.1), ncol=2)
         ax2.tick_params(axis='x', rotation=45, labelsize=8)
+        ax2.set_ylim(bottom=0)  # Ensure y-axis starts at 0
         
         # Empty spacer subplot for small gap
         ax_spacer = fig.add_subplot(gs[2])
@@ -399,9 +394,8 @@ def process_data(file, trade_selection, filter_date):
         ax3.axis('off')
         table_data = [summary_df.columns.tolist()] + summary_df.values.tolist()
         table = ax3.table(cellText=table_data, cellLoc='center', loc='center', colWidths=[0.3, 0.35, 0.35])
-        table.auto_set_font_size(False)
-        table.set_fontsize(12)
-        table.scale(1.2, 1.2)
+        table.set_fontsize(12)  # Set font size manually
+        table.scale(1.2, 1.2)  # Keep the scaling
         ax3.set_title('Summary Statistics (Risk in %)', fontsize=14, pad=10)
         
         # Add legend for alerts
@@ -414,7 +408,7 @@ def process_data(file, trade_selection, filter_date):
         ]
         ax4.legend(handles=legend_elements, loc='center', ncol=3, title='Alert Types', fontsize=12, title_fontsize=12)
         
-        plt.subplots_adjust(top=0.9, bottom=0.1, left=0.1, right=0.9, hspace=0.6)
+        plt.subplots_adjust(top=0.9, bottom=0.1, left=0.1, right=1.2, hspace=0.6)  # Adjusted right margin for legend
         buf = io.BytesIO()
         plt.savefig(buf, format='pdf', dpi=300, bbox_inches='tight')
         plt.close()
@@ -460,8 +454,10 @@ def notify_contractor():
         logger.warning("No forecast data for notifications")
         return message, history_display
     
+    # Calculate average risk per trade
     risk_summary = latest_forecast_df.groupby('Trade')['Risk'].mean().round(1).to_dict()
     
+    # Generate notifications for each trade
     timestamp = datetime.now().strftime("%Y-%m-%d %I:%M:%S %p")
     notifications = []
     for trade, avg_risk in risk_summary.items():
@@ -513,7 +509,7 @@ with gr.Blocks() as demo:
         trade_dropdown = gr.Dropdown(label="Select Trade", choices=["All"])
     
     with gr.Row():
-        filter_date = gr.Textbox(label="Enter Date (DD-MM-YYYY)", placeholder="e.g., 01-04-2025", value="")
+        filter_date = gr.DateTime(label="Site Calendar Date", value=None)
     
     with gr.Row():
         submit_button = gr.Button("Generate Forecast")