Update app.py

app.py

@@ -185,7 +185,10 @@ def calculate_threshold_metrics(df, threshold_minutes, scope="all"):
     # Cancellation metrics - now much more accurate
     current_cancellations = int(df_with_prev["cancelled_due_to_previous_delay"].sum())
     cancellations_prevented = int(df_with_prev["cancellation_prevented"].sum())
-    cancellation_rate = (current_cancellations / rentals_with_previous) * 100 if rentals_with_previous > 0 else 0
+    
+    # Remaining cancellation rate after implementing threshold
+    remaining_cancellations = current_cancellations - cancellations_prevented
+    cancellation_rate = (remaining_cancellations / rentals_with_previous) * 100 if rentals_with_previous > 0 else 0
     
     return {
         "total_rentals": total_rentals,
@@ -317,22 +320,21 @@ if selected == "📊 Data Overview":
     col1, col2 = st.columns(2)
     
     with col1:
-        # Delay status distribution
-        df["delay_status"] = df["delay_at_checkout_in_minutes"].apply(
-            lambda x: "Early Return" if pd.notnull(x) and x < 0 else 
-                     "On Time" if pd.notnull(x) and x == 0 else 
-                     "Late Return" if pd.notnull(x) and x > 0 else "Missing Data"
+        # Delay status distribution (excluding missing data)
+        df_with_delay_data = df[df["delay_at_checkout_in_minutes"].notnull()].copy()
+        df_with_delay_data["delay_status"] = df_with_delay_data["delay_at_checkout_in_minutes"].apply(
+            lambda x: "Early Return" if x < 0 else "On Time" if x == 0 else "Late Return"
         )
         
-        delay_counts = df["delay_status"].value_counts()
+        delay_counts = df_with_delay_data["delay_status"].value_counts()
         fig_delay_status = px.pie(
             values=delay_counts.values, 
             names=delay_counts.index,
-            title="Return Status Distribution",
+            title="Return Status Distribution (Data Available Only)",
             color_discrete_sequence=px.colors.qualitative.Bold
         )
         fig_delay_status.update_layout(
-            annotations=[dict(text="Missing Data = no checkout delay recorded", 
+            annotations=[dict(text=f"Based on {len(df_with_delay_data):,} rentals with delay data", 
                             x=0.5, y=-0.1, xref="paper", yref="paper", 
                             showarrow=False, font=dict(size=10))]
         )
@@ -440,18 +442,24 @@ if selected == "📊 Data Overview":
         )
         
         delay_related_cancels = df_analysis["cancelled_due_to_previous_delay"].sum()
-        total_cancels = (df_analysis["state"] == "canceled").sum()
+        total_cancels_with_prev = (df_analysis["state"] == "canceled").sum()
+        total_cancels_all = (df["state"] == "canceled").sum()
         
         col2_1, col2_2 = st.columns(2)
         with col2_1:
-            st.metric("Total Cancellations", f"{total_cancels:,}")
+            st.metric("Total Cancellations (All)", f"{total_cancels_all:,}",
+                     help="All cancelled rentals in the dataset")
         with col2_2:
             st.metric("Due to Previous Delay", f"{delay_related_cancels:,}",
                      help="Cancelled rentals where the previous rental on same car was late")
         
-        if total_cancels > 0:
-            delay_cancel_rate = (delay_related_cancels / total_cancels * 100)
-            st.metric("% of Cancellations Due to Previous Delays", f"{delay_cancel_rate:.1f}%")
+        if total_cancels_all > 0:
+            delay_cancel_rate = (delay_related_cancels / total_cancels_all * 100)
+            st.metric("% of All Cancellations Due to Previous Delays", f"{delay_cancel_rate:.1f}%")
+            
+        # Additional context
+        st.info(f"Note: {total_cancels_with_prev:,} cancellations had previous rentals (analyzed for delay impact)")
+
     
     # Problem cases analysis (including cancellations)
     st.markdown('<div class="section-header">🚨 Current Problem Cases Analysis</div>', unsafe_allow_html=True)
@@ -702,7 +710,7 @@ elif selected == "🕐 Threshold Analysis":
             "Cancellations Prevented vs Threshold",
             "Efficiency (Solve Rate) vs Threshold", 
             "Revenue Impact vs Threshold",
-            "Cancellation Rate vs Threshold"
+            "Remaining Cancellation Rate vs Threshold"
         )
     )
     
@@ -749,7 +757,7 @@ elif selected == "🕐 Threshold Analysis":
     # Cancellation rate
     fig.add_trace(
         go.Scatter(x=sweep_df["threshold"], y=sweep_df["cancellation_rate"],
-                  mode="lines+markers", name="Cancellation Rate (%)", 
+                  mode="lines+markers", name="Remaining Cancellation Rate (%)", 
                   line=dict(color="#e67e22"), showlegend=False),
         row=2, col=3
     )
@@ -877,7 +885,7 @@ elif selected == "🎯 Scope Analysis":
             "Cancellations Prevented by Scope",
             "Efficiency by Scope", 
             "Revenue Impact by Scope",
-            "Cancellation Rate by Scope"
+            "Remaining Cancellation Rate by Scope"
         )
     )
     
@@ -926,7 +934,7 @@ elif selected == "🎯 Scope Analysis":
             row=2, col=2
         )
         
-        # Cancellation rate
+        # Remaining cancellation rate  
         fig.add_trace(
             go.Scatter(x=scope_data["threshold"], y=scope_data["cancellation_rate"],
                       mode="lines+markers", name=f"{scope_name}",