Update app.py

app.py

@@ -431,24 +431,32 @@ class B2BCustomerAnalytics:
     
     def create_visualizations(self):
         """Create comprehensive visualizations"""
-        if self.processed_df is None:
+        if self.processed_df is None or len(self.processed_df) == 0:
+            print("No processed data available for visualization")
             return None, None, None, None
         
         try:
+            print(f"Creating visualizations with {len(self.processed_df)} rows")
+            
             # 1. Customer Segment Distribution
             segment_data = self.processed_df.groupby('customer_id')['Segment'].first().value_counts().reset_index()
             segment_data.columns = ['Segment', 'Count']
+            print(f"Segment data: {segment_data}")
             
-            fig1 = px.pie(
-                segment_data, 
-                values='Count', 
-                names='Segment',
-                title='Customer Segment Distribution',
-                hole=0.4,
-                color_discrete_sequence=['#6366f1', '#10b981', '#f59e0b', '#ef4444', '#8b5cf6', '#ec4899']
-            )
-            fig1.update_traces(textposition='inside', textinfo='percent+label')
-            fig1.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
+            if len(segment_data) == 0:
+                print("No segment data found")
+                fig1 = None
+            else:
+                fig1 = px.pie(
+                    segment_data, 
+                    values='Count', 
+                    names='Segment',
+                    title='Customer Segment Distribution',
+                    hole=0.4,
+                    color_discrete_sequence=['#6366f1', '#10b981', '#f59e0b', '#ef4444', '#8b5cf6', '#ec4899']
+                )
+                fig1.update_traces(textposition='inside', textinfo='percent+label')
+                fig1.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
             
             # 2. RFM Analysis
             customer_rfm = self.processed_df.groupby('customer_id').agg({
@@ -457,67 +465,89 @@ class B2BCustomerAnalytics:
                 'monetary': 'first',
                 'Segment': 'first'
             }).reset_index()
+            print(f"RFM data shape: {customer_rfm.shape}")
             
-            fig2 = px.scatter(
-                customer_rfm, 
-                x='recency_days', 
-                y='frequency', 
-                size='monetary',
-                color='Segment', 
-                title='RFM Customer Behavior Matrix',
-                labels={
-                    'recency_days': 'Days Since Last Purchase',
-                    'frequency': 'Purchase Frequency',
-                    'monetary': 'Total Revenue'
-                }
-            )
-            fig2.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
+            if len(customer_rfm) == 0:
+                print("No RFM data found")
+                fig2 = None
+            else:
+                fig2 = px.scatter(
+                    customer_rfm, 
+                    x='recency_days', 
+                    y='frequency', 
+                    size='monetary',
+                    color='Segment', 
+                    title='RFM Customer Behavior Matrix',
+                    labels={
+                        'recency_days': 'Days Since Last Purchase',
+                        'frequency': 'Purchase Frequency',
+                        'monetary': 'Total Revenue'
+                    }
+                )
+                fig2.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
             
             # 3. Churn Risk Distribution
-            if self.predictions is not None:
+            if self.predictions is not None and len(self.predictions) > 0:
+                print(f"Using predictions data with {len(self.predictions)} rows")
                 fig3 = px.histogram(
                     self.predictions, 
                     x='churn_probability', 
                     nbins=20,
                     title='Churn Probability Distribution',
-                    labels={'churn_probability': 'Churn Probability', 'count': 'Number of Customers'}
+                    labels={'churn_probability': 'Churn Probability', 'count': 'Number of Customers'},
+                    color_discrete_sequence=['#6366f1']
                 )
                 fig3.add_vline(x=0.5, line_dash="dash", line_color="red", 
                               annotation_text="High Risk Threshold")
             else:
                 risk_data = self.processed_df.groupby('customer_id')['Churn_Risk'].first().value_counts().reset_index()
                 risk_data.columns = ['Risk_Level', 'Count']
-                colors_map = {'High': '#ef4444', 'Medium': '#f59e0b', 'Low': '#10b981'}
-                fig3 = px.bar(
-                    risk_data, 
-                    x='Risk_Level', 
-                    y='Count',
-                    title='Customer Churn Risk Distribution',
-                    color='Risk_Level', 
-                    color_discrete_map=colors_map
-                )
-            
-            fig3.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
+                print(f"Risk data: {risk_data}")
+                
+                if len(risk_data) == 0:
+                    print("No risk data found")
+                    fig3 = None
+                else:
+                    colors_map = {'High': '#ef4444', 'Medium': '#f59e0b', 'Low': '#10b981'}
+                    fig3 = px.bar(
+                        risk_data, 
+                        x='Risk_Level', 
+                        y='Count',
+                        title='Customer Churn Risk Distribution',
+                        color='Risk_Level', 
+                        color_discrete_map=colors_map
+                    )
+                    fig3.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'}, showlegend=False)
             
             # 4. Revenue Trends
-            self.processed_df['order_month'] = self.processed_df['order_date'].dt.to_period('M')
-            monthly_revenue = self.processed_df.groupby('order_month')['amount'].sum().reset_index()
-            monthly_revenue['order_month'] = monthly_revenue['order_month'].astype(str)
-            
-            fig4 = px.line(
-                monthly_revenue, 
-                x='order_month', 
-                y='amount',
-                title='Monthly Revenue Trends',
-                labels={'amount': 'Revenue ($)', 'order_month': 'Month'}
-            )
-            fig4.update_traces(line_color='#6366f1', line_width=3)
-            fig4.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
+            try:
+                self.processed_df['order_month'] = self.processed_df['order_date'].dt.to_period('M')
+                monthly_revenue = self.processed_df.groupby('order_month')['amount'].sum().reset_index()
+                monthly_revenue['order_month'] = monthly_revenue['order_month'].astype(str)
+                print(f"Monthly revenue data: {monthly_revenue.head()}")
+                
+                if len(monthly_revenue) == 0:
+                    fig4 = None
+                else:
+                    fig4 = px.line(
+                        monthly_revenue, 
+                        x='order_month', 
+                        y='amount',
+                        title='Monthly Revenue Trends',
+                        labels={'amount': 'Revenue ($)', 'order_month': 'Month'}
+                    )
+                    fig4.update_traces(line_color='#6366f1', line_width=3)
+                    fig4.update_layout(height=400, title={'x': 0.5, 'xanchor': 'center'})
+            except Exception as e:
+                print(f"Error creating revenue chart: {e}")
+                fig4 = None
             
             return fig1, fig2, fig3, fig4
             
         except Exception as e:
             print(f"Error creating visualizations: {e}")
+            import traceback
+            traceback.print_exc()
             return None, None, None, None
     
     def create_customer_table(self):