Update app.py

app.py

@@ -156,6 +156,10 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
     print(f"🕵️ Deep enriching {total} rows ({start_date} to {end_date})...")
     
     for index, row in target_df.iterrows():
+        # Only enrich if data is missing
+        if row.get("landing_page_path") and row.get("exit_page_path"):
+            continue
+
         lead_id = row["lead_id"]
         try:
             visit_data = make_request(
@@ -208,7 +212,7 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
         except Exception as e:
             print(f"Failed to enrich lead {lead_id}: {e}")
             
-        if index % 5 == 0:
+        if max_rows and index % 5 == 0:
             progress(index / total, desc="Enriching...")
             
     return df
@@ -315,42 +319,51 @@ def build_trend(df, preset, grain, filter_values):
     return px.line(ts, x="period", y=val, markers=True, template="plotly_white", title=preset)
 
 # =====================================================
-# ADVANCED ANALYTICS (WITH SEARCH FILTER)
+# ADVANCED ANALYTICS (WITH AUTO-ENRICHMENT)
 # =====================================================
-def build_advanced_plots(df, search_lead_id=None, search_company=None):
+def build_advanced_plots(df, search_lead_id, search_company, start_date, end_date):
     if df is None or df.empty:
         return None, None
     
-    # --- FILTERING LOGIC ---
+    # --- 1. FILTER ---
     filtered_df = df.copy()
-    
     title_suffix = ""
     
-    # 1. Filter by Lead ID (Exact Match)
     if search_lead_id and search_lead_id.strip():
         filtered_df = filtered_df[filtered_df["lead_id"] == search_lead_id.strip()]
         title_suffix = f" (Lead: {search_lead_id})"
         
-    # 2. Filter by Company Name (Partial Match, Case Insensitive)
     if search_company and search_company.strip():
-        # Handle NA values before string search
         filtered_df = filtered_df[filtered_df["company_name"].notna()]
         filtered_df = filtered_df[filtered_df["company_name"].str.contains(search_company, case=False, na=False)]
         title_suffix = f" (Company: {search_company})"
         
     if filtered_df.empty:
-        # Return empty figures or message logic handled by returning None
         return go.Figure(layout=dict(title="No matching data found")), go.Figure(layout=dict(title="No matching data found"))
 
-    # --- 1. SANKEY DIAGRAM ---
+    # --- 2. AUTO-ENRICHMENT ---
+    # Check if the filtered rows are missing landing/exit data. 
+    # If so, fetch it immediately!
+    missing_data = filtered_df[filtered_df["landing_page_path"].isnull()]
+    
+    if not missing_data.empty:
+        # We pass the subset to the enrich function
+        print(f"🔄 Auto-enriching {len(missing_data)} rows for visualization...")
+        
+        # We need to update the original filtered_df with the new data
+        enriched_subset = enrich_leads_with_visits(missing_data, start_date, end_date)
+        
+        # Update the rows in filtered_df using the enriched data
+        filtered_df.update(enriched_subset)
+
+    # --- 3. SANKEY DIAGRAM ---
     flow_df = filtered_df.dropna(subset=["landing_page_path", "exit_page_path"])
     
     if flow_df.empty:
-        sankey_fig = go.Figure(layout=dict(title="No valid Landing/Exit pages found for selection"))
+        sankey_fig = go.Figure(layout=dict(title="No visit data available for selected lead(s)"))
     else:
         flow_counts = flow_df.groupby(["landing_page_path", "exit_page_path"]).size().reset_index(name="count")
         
-        # If searching specific company, we show ALL their flows. Otherwise top 20.
         if not search_lead_id and not search_company:
             flow_counts = flow_counts.sort_values("count", ascending=False).head(20)
         
@@ -367,10 +380,10 @@ def build_advanced_plots(df, search_lead_id=None, search_company=None):
         )])
         sankey_fig.update_layout(title_text=f"User Flow: Landing → Exit{title_suffix}", font_size=10)
 
-    # --- 2. HEATMAP ---
+    # --- 4. HEATMAP ---
     temp_df = filtered_df.dropna(subset=["last_visit_date"]).copy()
     if temp_df.empty:
-        heatmap_fig = go.Figure(layout=dict(title="No visit dates found for selection"))
+        heatmap_fig = go.Figure(layout=dict(title="No visit dates found"))
     else:
         temp_df["day_name"] = temp_df["last_visit_date"].dt.day_name()
         temp_df["hour"] = temp_df["last_visit_date"].dt.hour
@@ -449,7 +462,7 @@ with gr.Blocks(title="Leadfeeder Pro Analytics") as demo:
                 plot
             )
 
-        # --- TAB 4: ADVANCED ANALYTICS (UPDATED WITH SEARCH) ---
+        # --- TAB 4: ADVANCED ANALYTICS ---
         with gr.Tab("🔬 Advanced Analytics"):
             gr.Markdown("Visualize user behavior flows. Leave search blank to see aggregate Top 20 flows.")
             
@@ -463,8 +476,8 @@ with gr.Blocks(title="Leadfeeder Pro Analytics") as demo:
                 sankey_plot = gr.Plot(label="User Flow (Sankey)")
                 heatmap_plot = gr.Plot(label="Activity Heatmap")
             
-            # Pass the new search inputs to the function
-            btn_adv.click(build_advanced_plots, [df_state, search_lead, search_comp], [sankey_plot, heatmap_plot])
+            # NOTE: Passed start/end dates so we can auto-enrich on the fly!
+            btn_adv.click(build_advanced_plots, [df_state, search_lead, search_comp, start, end], [sankey_plot, heatmap_plot])
 
         # --- TAB 5: DEBUGGER ---
         with gr.Tab("🛠️ Debugger"):