chore: clean up the graph and add cumulative average graph

app.py

@@ -652,22 +652,31 @@ def create_combined_time_series_graph(df):
     avg_apr_data_with_ma = avg_apr_data.copy()
     avg_apr_data_with_ma['moving_avg'] = None  # Initialize the moving average column
     
-    # Define the time window for the moving average (2 hours)
-    time_window = pd.Timedelta(hours=2)
+    # Define the time window for the moving average (6 hours)
+    time_window = pd.Timedelta(hours=6)
     logger.info(f"Calculating moving average with time window of {time_window}")
     
-    # Calculate the moving average for each timestamp
+    # Calculate two moving averages: one with 2-hour window and one with infinite window
+    avg_apr_data_with_ma['moving_avg'] = None  # 2-hour window
+    avg_apr_data_with_ma['infinite_avg'] = None  # Infinite window (all data up to timestamp)
+    
+    # Calculate the moving averages for each timestamp
     for i, row in avg_apr_data_with_ma.iterrows():
         current_time = row['timestamp']
         window_start = current_time - time_window
         
-        # Get all data points within the time window
+        # Get all data points within the 2-hour time window
         window_data = apr_data_sorted[
             (apr_data_sorted['timestamp'] >= window_start) & 
             (apr_data_sorted['timestamp'] <= current_time)
         ]
         
-        # Calculate the average APR for the time window
+        # Get all data points up to the current timestamp (infinite window)
+        infinite_window_data = apr_data_sorted[
+            apr_data_sorted['timestamp'] <= current_time
+        ]
+        
+        # Calculate the average APR for the 2-hour time window
         if not window_data.empty:
             avg_apr_data_with_ma.at[i, 'moving_avg'] = window_data['apr'].mean()
             logger.debug(f"Time window {window_start} to {current_time}: {len(window_data)} points, avg={window_data['apr'].mean()}")
@@ -675,8 +684,16 @@ def create_combined_time_series_graph(df):
             # If no data points in the window, use the current value
             avg_apr_data_with_ma.at[i, 'moving_avg'] = row['apr']
             logger.debug(f"No data points in time window for {current_time}, using current value {row['apr']}")
+        
+        # Calculate the average APR for the infinite window
+        if not infinite_window_data.empty:
+            avg_apr_data_with_ma.at[i, 'infinite_avg'] = infinite_window_data['apr'].mean()
+            logger.debug(f"Infinite window up to {current_time}: {len(infinite_window_data)} points, avg={infinite_window_data['apr'].mean()}")
+        else:
+            # This should never happen, but just in case
+            avg_apr_data_with_ma.at[i, 'infinite_avg'] = row['apr']
     
-    logger.info(f"Calculated time-based moving average with {len(avg_apr_data_with_ma)} points")
+    logger.info(f"Calculated time-based moving averages with {len(avg_apr_data_with_ma)} points")
     
     # Plot individual agent data points with agent names in hover, but limit display for scalability
     if not apr_data.empty:
@@ -696,56 +713,19 @@ def create_combined_time_series_graph(df):
         
         logger.info(f"Showing {len(top_agents)} agents by default out of {len(unique_agents)} total agents")
         
-        # Add data points for each agent, but only make top agents visible by default
-        for agent_name in unique_agents:
-            agent_data = apr_data[apr_data['agent_name'] == agent_name]
-            
-            # Explicitly convert to Python lists
-            x_values = agent_data['timestamp'].tolist()
-            y_values = agent_data['apr'].tolist()
-            
-            # Determine if this agent should be visible by default
-            is_visible = agent_name in top_agents
-            
-            # Add data points as markers
-            fig.add_trace(
-                go.Scatter(
-                    x=x_values,
-                    y=y_values,
-                    mode='markers',  # Only markers for original data
-                    marker=dict(
-                        color=color_map[agent_name],
-                        symbol='circle',
-                        size=10,
-                        line=dict(width=1, color='black')
-                    ),
-                    name=f'Agent: {agent_name}',
-                    hovertemplate='Time: %{x}<br>APR: %{y:.2f}<br>Agent: ' + agent_name + '<extra></extra>',
-                    visible=is_visible  # Only top agents visible by default
-                )
-            )
-            logger.info(f"Added data points for agent {agent_name} with {len(x_values)} points (visible: {is_visible})")
+        # No longer showing individual agent data points as requested
+        logger.info("Skipping individual agent data points as requested")
         
-        # Add moving average as a smooth line
+        # Add 2-hour moving average as a smooth line
         x_values_ma = avg_apr_data_with_ma['timestamp'].tolist()
         y_values_ma = avg_apr_data_with_ma['moving_avg'].tolist()
         
-        # Create a more detailed hover template for the moving average line
-        # that includes information about all agents at each timestamp and the time window
-        hover_data = []
+        # Create hover template for the 2-hour moving average line
+        hover_data_2h = []
         for idx, row in avg_apr_data_with_ma.iterrows():
             timestamp = row['timestamp']
-            window_start = timestamp - time_window
-            
-            # Find all agents with data in the time window
-            agents_in_window = apr_data[
-                (apr_data['timestamp'] >= window_start) & 
-                (apr_data['timestamp'] <= timestamp)
-            ]
-            
-            # Simplified hover text without detailed data points
-            hover_data.append(
-                f"Time: {timestamp}<br>Moving Avg APR (2h window): {row['moving_avg']:.2f}"
+            hover_data_2h.append(
+                f"Time: {timestamp}<br>Moving Avg APR (6h window): {row['moving_avg']:.2f}"
             )
         
         fig.add_trace(
@@ -753,13 +733,37 @@ def create_combined_time_series_graph(df):
                 x=x_values_ma,
                 y=y_values_ma,
                 mode='lines',  # Only lines for moving average
-                line=dict(color='red', width=3),
-                name='Moving Average APR (2h window)',
-                hovertext=hover_data,
+                line=dict(color='red', width=2),  # Thinner line
+                name='Moving Average APR (6h window)',
+                hovertext=hover_data_2h,
                 hoverinfo='text'
             )
         )
-        logger.info(f"Added time-based moving average APR trace with {len(x_values_ma)} points")
+        logger.info(f"Added 2-hour moving average APR trace with {len(x_values_ma)} points")
+        
+        # Add infinite window moving average as another line
+        y_values_infinite = avg_apr_data_with_ma['infinite_avg'].tolist()
+        
+        # Create hover template for the infinite window moving average line
+        hover_data_infinite = []
+        for idx, row in avg_apr_data_with_ma.iterrows():
+            timestamp = row['timestamp']
+            hover_data_infinite.append(
+                f"Time: {timestamp}<br>Cumulative Avg APR (all data): {row['infinite_avg']:.2f}"
+            )
+        
+        fig.add_trace(
+            go.Scatter(
+                x=x_values_ma,
+                y=y_values_infinite,
+                mode='lines',  # Only lines for moving average
+                line=dict(color='green', width=4),  # Thicker solid line
+                name='Cumulative Average APR (all data)',
+                hovertext=hover_data_infinite,
+                hoverinfo='text'
+            )
+        )
+        logger.info(f"Added infinite window moving average APR trace with {len(x_values_ma)} points")
     
     # Update layout - use simple boolean values everywhere
     fig.update_layout(
@@ -781,16 +785,7 @@ def create_combined_time_series_graph(df):
         hovermode="closest"
     )
     
-    # Add a note about hidden agents if there are more than MAX_VISIBLE_AGENTS
-    if len(unique_agents) > MAX_VISIBLE_AGENTS:
-        fig.add_annotation(
-            text=f"Note: Only showing top {MAX_VISIBLE_AGENTS} agents by default. Toggle others in legend.",
-            xref="paper", yref="paper",
-            x=0.5, y=1.05,
-            showarrow=False,
-            font=dict(size=12, color="gray"),
-            align="center"
-        )
+    # No longer need the note about hidden agents since we're not showing individual agents
     
     # FORCE FIXED Y-AXIS RANGE
     fig.update_yaxes(
@@ -855,73 +850,65 @@ def create_combined_time_series_graph(df):
             # Sort by timestamp
             avg_apr_data = avg_apr_data.sort_values('timestamp')
             
-            # Calculate time-based moving average for the fallback graph
+            # Calculate both moving averages for the fallback graph
             avg_apr_data_with_ma = avg_apr_data.copy()
-            avg_apr_data_with_ma['moving_avg'] = None
+            avg_apr_data_with_ma['moving_avg'] = None  # 2-hour window
+            avg_apr_data_with_ma['infinite_avg'] = None  # Infinite window
             
-            # Define the time window (2 hours)
-            time_window = pd.Timedelta(hours=2)
+            # Define the time window (6 hours)
+            time_window = pd.Timedelta(hours=6)
             
-            # Calculate the moving average for each timestamp
+            # Calculate the moving averages for each timestamp
             for i, row in avg_apr_data_with_ma.iterrows():
                 current_time = row['timestamp']
                 window_start = current_time - time_window
                 
-                # Get all data points within the time window
+                # Get all data points within the 2-hour time window
                 window_data = apr_data[
                     (apr_data['timestamp'] >= window_start) & 
                     (apr_data['timestamp'] <= current_time)
                 ]
                 
-                # Calculate the average APR for the time window
+                # Get all data points up to the current timestamp (infinite window)
+                infinite_window_data = apr_data[
+                    apr_data['timestamp'] <= current_time
+                ]
+                
+                # Calculate the average APR for the 2-hour time window
                 if not window_data.empty:
                     avg_apr_data_with_ma.at[i, 'moving_avg'] = window_data['apr'].mean()
                 else:
                     # If no data points in the window, use the current value
                     avg_apr_data_with_ma.at[i, 'moving_avg'] = row['apr']
+                
+                # Calculate the average APR for the infinite window
+                if not infinite_window_data.empty:
+                    avg_apr_data_with_ma.at[i, 'infinite_avg'] = infinite_window_data['apr'].mean()
+                else:
+                    avg_apr_data_with_ma.at[i, 'infinite_avg'] = row['apr']
             
-            # Add data points for each agent, but only make top agents visible by default
-            unique_agents = apr_data['agent_name'].unique()
-            colors = px.colors.qualitative.Plotly[:len(unique_agents)]
-            color_map = {agent: colors[i % len(colors)] for i, agent in enumerate(unique_agents)}
-            
-            # Calculate the total number of data points per agent
-            agent_counts = apr_data['agent_name'].value_counts()
-            
-            # Determine how many agents to show individually (limit to top 5 most active)
-            MAX_VISIBLE_AGENTS = 5
-            top_agents = agent_counts.nlargest(min(MAX_VISIBLE_AGENTS, len(agent_counts))).index.tolist()
+            # No longer showing individual agent data points in fallback graph as requested
+            logger.info("Skipping individual agent data points in fallback graph as requested")
             
-            for agent_name in unique_agents:
-                agent_data = apr_data[apr_data['agent_name'] == agent_name]
-                
-                # Determine if this agent should be visible by default
-                is_visible = agent_name in top_agents
-                
-                # Add data points as markers
-                simple_fig.add_trace(
-                    go.Scatter(
-                        x=agent_data['timestamp'],
-                        y=agent_data['apr'],
-                        mode='markers',
-                        name=f'Agent: {agent_name}',
-                        marker=dict(
-                            size=10, 
-                            color=color_map[agent_name]
-                        ),
-                        hovertemplate='Time: %{x}<br>APR: %{y:.2f}<br>Agent: ' + agent_name + '<extra></extra>',
-                        visible=is_visible  # Only top agents visible by default
-                    )
+            # Add 2-hour moving average as a line
+            simple_fig.add_trace(
+                go.Scatter(
+                    x=avg_apr_data_with_ma['timestamp'],
+                    y=avg_apr_data_with_ma['moving_avg'],
+                    mode='lines',
+                    name='Moving Average APR (6h window)',
+                    line=dict(width=2, color='red')  # Thinner line
                 )
+            )
             
-            # Add moving average as a line
+            # Add infinite window moving average as another line
             simple_fig.add_trace(
                 go.Scatter(
                     x=avg_apr_data_with_ma['timestamp'],
-                    y=avg_apr_data_with_ma['moving_avg'],
+                    y=avg_apr_data_with_ma['infinite_avg'],
                     mode='lines',
-                    name='Moving Average APR (2h window)',
-                    line=dict(width=3, color='red')
+                    name='Cumulative Average APR (all data)',
+                    line=dict(width=4, color='green')  # Thicker solid line
                 )
             )
         
@@ -935,16 +922,7 @@ def create_combined_time_series_graph(df):
             width=1000
         )
         
-        # Add a note about hidden agents if there are more than MAX_VISIBLE_AGENTS
-        if len(unique_agents) > MAX_VISIBLE_AGENTS:
-            simple_fig.add_annotation(
-                text=f"Note: Only showing top {MAX_VISIBLE_AGENTS} agents by default. Toggle others in legend.",
-                xref="paper", yref="paper",
-                x=0.5, y=1.05,
-                showarrow=False,
-                font=dict(size=12, color="gray"),
-                align="center"
-            )
+        # No longer need the note about hidden agents since we're not showing individual agents
         
         # Return the simple figure
         return simple_fig