Update app.py

app.py

@@ -3,8 +3,11 @@ import time
 import requests
 import json
 import pandas as pd
+import math
 import gradio as gr
 import plotly.express as px
+from plotly.subplots import make_subplots
+import plotly.graph_objects as go
 from datetime import date, timedelta
 
 # =====================================================
@@ -85,67 +88,77 @@ def get_campaign_match(text, rules):
 def apply_business_logic(df):
     if df is None or df.empty: return df
     
+    # 1. Quality Group
     if "lead_quality_score" in df.columns:
         df["Quality_Group"] = df["lead_quality_score"].apply(categorize_quality)
-    
+        
+    # 2. Campaign Logic (Strict Landing Page Only)
     rules = load_campaign_rules()
     
     def resolve_campaign(row):
         path = row.get("landing_page_path")
-        # Strictly check landing page to avoid generic categorizations
+        
+        # STRICT MATCHING: Only look at landing page. Skip empty or generic homepages.
         if path and path not in ["", "/", "/home"]:
             match = get_campaign_match(path, rules)
-            if match: 
+            if match:
                 return match
+                
         return "Uncategorized"
-
+        
     df["Campaign"] = df.apply(resolve_campaign, axis=1)
     return df
 
 # =====================================================
-# 2. PRESETS (Original structure preserved)
+# 2. PRESETS 
 # =====================================================
 DASHBOARD_PRESETS = {
-    # --- Added New Presets ---
+    # -- SPECIAL VIEWS --
+    "Key Campaigns Bifurcation (MS Tech, Fintech, Adtech)": ("SPECIAL_KEY_BIFURCATION", None, None),
+    "All Campaigns Performance": ("SPECIAL_ALL_PERFORMANCE", None, None),
+    
+    # -- CAMPAIGN & QUALITY --
     "Visits by Campaign": ("Campaign", "total_visits", "sum"),
     "Leads by Campaign": ("Campaign", "company_name", "count"),
     "Leads by Quality Group": ("Quality_Group", "company_name", "count"),
+    
+    # -- GEOGRAPHY --
+    "Visits by Country": ("country", "total_visits", "sum"),
+    "Leads by Country": ("country", "company_name", "count"),
     "Visits by City": ("city", "total_visits", "sum"),
     "Leads by City": ("city", "company_name", "count"),
-    "Leads by Country": ("country", "company_name", "count"),
+    
+    # -- INDUSTRY --
+    "Visits by Industry": ("primary_industry", "total_visits", "sum"),
     "Leads by Industry": ("primary_industry", "company_name", "count"),
     
-    # --- Original Presets ---
-    "Total Visits by Industry": ("primary_industry", "total_visits", "sum"),
-    "Total Visits by Country": ("country", "total_visits", "sum"),
-    "Avg Quality by Industry": ("primary_industry", "lead_quality_score", "mean"),
+    # -- OTHERS --
     "Top Accounts by Visits": ("company_name", "total_visits", "sum"),
-    "Companies by Country": ("country", "company_name", "count"),
-    "Accounts by Assignee": ("assignee", "company_name", "count"),
-    "Visits by Assignee": ("assignee", "total_visits", "sum"),
 }
 
 TREND_PRESETS = {
-    # --- Added New Presets ---
+    # -- CAMPAIGN & QUALITY --
     "Visits Trend by Campaign": ("total_visits", "sum", "Campaign"),
     "Leads Trend by Campaign": ("company_name", "count", "Campaign"),
     "Visits Trend by Quality": ("total_visits", "sum", "Quality_Group"),
+    
+    # -- GEOGRAPHY --
+    "Visits Trend by Country": ("total_visits", "sum", "country"),
+    "Leads Trend by Country": ("company_name", "count", "country"),
     "Visits Trend by City": ("total_visits", "sum", "city"),
     "Leads Trend by City": ("company_name", "count", "city"),
-    "Leads Trend by Country": ("company_name", "count", "country"),
+    
+    # -- INDUSTRY --
+    "Visits Trend by Industry": ("total_visits", "sum", "primary_industry"),
     "Leads Trend by Industry": ("company_name", "count", "primary_industry"),
     
-    # --- Original Presets ---
+    # -- GENERAL --
     "Total Visits Trend": ("total_visits", "sum", None),
     "Active Accounts Trend": ("company_name", "count", None),
-    "Avg Lead Quality Trend": ("lead_quality_score", "mean", None),
-    "Visits Trend by Industry": ("total_visits", "sum", "primary_industry"),
-    "Visits Trend by Country": ("total_visits", "sum", "country"),
-    "Visits Trend by Assignee": ("total_visits", "sum", "assignee"),
 }
 
 # =====================================================
-# 3. API HANDLING (Original structure preserved)
+# 3. API HANDLING
 # =====================================================
 def make_request(url, params=None):
     retries = 3
@@ -253,7 +266,7 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
                     if not landing:
                         first_step = visit_route[0]
                         landing = first_step.get("page_path") or first_step.get("page_url")
-                
+                        
                 if not landing or not exit_p:
                     pv_map = {p["id"]: p["attributes"] for p in included if p["type"] == "page_views"}
                     pv_ids = [r["id"] for r in visit.get("relationships", {}).get("page_views", {}).get("data", [])]
@@ -264,14 +277,15 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
                         if not exit_p:
                             last_pv = pv_map.get(pv_ids[-1])
                             if last_pv: exit_p = last_pv.get("url") or last_pv.get("path")
-                
+                            
                 df.at[index, "landing_page_path"] = landing
                 df.at[index, "exit_page_path"] = exit_p
         except Exception as e:
             print(f"Failed to enrich lead {lead_id}: {e}")
-        
+            
         if max_rows and index % 5 == 0:
             progress(index / total, desc="Enriching...")
+            
     return df
 
 # =====================================================
@@ -305,10 +319,11 @@ def inspect_raw_json(lead_id, start_date, end_date):
         return str(e)
 
 # =====================================================
-# 5. CHART ENGINES (Restored to exact original logic)
+# 5. CHART ENGINES
 # =====================================================
 def build_kpis(df):
-    if df is None or df.empty: return 0, 0, 0, 0, 0, 0
+    if df is None or df.empty: return 0, 0, 0, 0, 0, 0, 0
+    if "Quality_Group" not in df.columns: df = apply_business_logic(df)
     return (
         len(df),
         df["total_visits"].gt(0).sum(),
@@ -316,60 +331,92 @@ def build_kpis(df):
         round(df["lead_quality_score"].mean(), 2),
         round(df["crm_organization_id"].notna().mean() * 100, 1),
         round(df["linkedin_url"].notna().mean() * 100, 1),
+        df[df["Quality_Group"] == "High Quality (8-10)"].shape[0],
     )
 
 def build_dashboard(df, preset, top_n):
     if df is None or df.empty: return px.bar(title="No Data")
     if "Campaign" not in df.columns: df = apply_business_logic(df)
     
+    if preset == "Key Campaigns Bifurcation (MS Tech, Fintech, Adtech)":
+        target = ["MS Tech", "Fintech", "Adtech"]
+        filtered = df[df["Campaign"].isin(target)].copy()
+        if filtered.empty: return px.bar(title="No Data for Key Campaigns")
+        agg = filtered.groupby("Campaign").agg(
+            Leads_Count=("company_name", "count"),
+            Total_Visits=("total_visits", "sum")
+        ).reset_index()
+        fig = go.Figure()
+        fig.add_trace(go.Bar(x=agg["Campaign"], y=agg["Leads_Count"], name="No. of Leads", marker_color="#00C49F"))
+        fig.add_trace(go.Bar(x=agg["Campaign"], y=agg["Total_Visits"], name="Total Visits", marker_color="#FFBB28"))
+        fig.update_layout(title="Key Campaigns: Leads vs Visits", barmode='group')
+        return fig
+        
+    if preset == "All Campaigns Performance":
+        agg = df.groupby("Campaign").agg(
+            Leads_Count=("company_name", "count"),
+            Total_Visits=("total_visits", "sum")
+        ).reset_index().sort_values("Leads_Count", ascending=False)
+        fig = make_subplots(specs=[[{"secondary_y": True}]])
+        fig.add_trace(go.Bar(x=agg["Campaign"], y=agg["Leads_Count"], name="Leads", marker_color="indigo"), secondary_y=False)
+        fig.add_trace(go.Scatter(x=agg["Campaign"], y=agg["Total_Visits"], name="Visits", mode="lines+markers", line=dict(color="orange", width=3)), secondary_y=True)
+        fig.update_layout(title_text="All Campaigns Performance")
+        return fig
+        
     dim, metric, agg = DASHBOARD_PRESETS[preset]
     if agg == "count":
         grouped = df.groupby(dim, dropna=False).size().reset_index(name="value")
     else:
         grouped = df.groupby(dim, dropna=False)[metric].agg(agg).reset_index(name="value")
-    return px.bar(grouped.sort_values("value", ascending=False).head(top_n), x=dim, y="value", title=preset)
+    return px.bar(grouped.sort_values("value", ascending=False).head(top_n), x=dim, y="value", title=preset, color=dim)
 
 def build_trend(df, preset, grain, filter_values):
-    if df is None or df.empty: return px.line(title="No Data Loaded")
-    if "Campaign" not in df.columns: df = apply_business_logic(df)
-    
+    if df is None or df.empty: return px.line(title="No Data")
     metric, agg, segment = TREND_PRESETS[preset]
-    df = df.dropna(subset=["last_visit_date"]).copy()
+    df_t = df.dropna(subset=["last_visit_date"]).copy()
+    
+    if segment and segment not in df_t.columns: 
+        df_t = apply_business_logic(df_t)
+        
+    if segment and filter_values: 
+        df_t = df_t[df_t[segment].isin(filter_values)]
         
-    if segment and filter_values:
-        df = df[df[segment].isin(filter_values)]
-        if df.empty: return px.line(title="No data for selected filters")
-
     if grain == "Weekly":
-        df["period"] = df["last_visit_date"].dt.to_period("W").astype(str)
-    elif grain == "Monthly":
-        df["period"] = df["last_visit_date"].dt.to_period("M").astype(str)
+        df_t["period"] = df_t["last_visit_date"].dt.to_period("W").astype(str)
     else:
-        df["period"] = df["last_visit_date"].dt.date
-            
+        df_t["period"] = df_t["last_visit_date"].dt.date
+        
     val = metric
     if agg == "count":
-        df["_v"] = df[metric].notna().astype(int)
+        df_t["_v"] = 1
         val = "_v"
-            
+        
     if segment:
-        ts = df.groupby(["period", segment])[val].agg(agg).reset_index()
-        title = f"{preset} (Filtered)" if filter_values else preset
-        return px.line(ts, x="period", y=val, color=segment, template="plotly_white", title=title)
+        ts = df_t.groupby(["period", segment])[val].agg(agg).reset_index()
+        return px.line(ts, x="period", y=val, color=segment, title=preset, markers=True)
         
-    ts = df.groupby("period")[val].agg(agg).reset_index()
-    return px.line(ts, x="period", y=val, markers=True, template="plotly_white", title=preset)
+    ts = df_t.groupby("period")[val].agg(agg).reset_index()
+    return px.line(ts, x="period", y=val, markers=True, title=preset)
 
 def get_trend_filter_options(df, preset):
     if df is None or df.empty: return gr.update(choices=[], value=None, visible=False)
-    if "Campaign" not in df.columns: df = apply_business_logic(df)
-    
     metric, agg, segment = TREND_PRESETS[preset]
     if not segment: return gr.update(choices=[], value=None, visible=False)
     
+    # FORCE LOGIC
+    if segment not in df.columns: 
+        df = apply_business_logic(df)
+        
     options = sorted(df[segment].astype(str).unique().tolist())
-    top_5 = df[segment].value_counts().head(5).index.tolist()
-    return gr.update(choices=options, value=top_5, visible=True, label=f"Filter {segment}")
+    
+    # Smart Defaults for specific columns
+    if segment == "Campaign":
+        defaults = [o for o in options if o in ["MS Tech", "Fintech", "Adtech"]]
+    else:
+        defaults = options[:5] # Top 5 for City/Country/Industry
+        
+    if not defaults: defaults = options[:5]
+    return gr.update(choices=options, value=defaults, visible=True, label=f"Filter {segment}")
 
 # =====================================================
 # 6. UI LAYOUT
@@ -393,22 +440,23 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
                 btn_load = gr.Button("1. Load Data (Preview)", variant="primary")
                 btn_dl = gr.Button("2. Enrich & Download Full Excel")
                 file_dl = gr.File(label="Download Excel")
-                        
+                
             table = gr.Dataframe(label="Preview (Top 50 Enriched)", interactive=True)
             btn_load.click(load_preview, [start, end], [df_state, table, status])
             btn_dl.click(download_full_excel, [df_state, start, end], file_dl)
-
+            
         # --- TAB 2: DASHBOARD ---
         with gr.Tab("📊 Dashboard"):
-            kpis = [gr.Number(label=l) for l in ["Total Companies", "Active Companies", "Total Visits", "Avg Quality", "CRM %", "LinkedIn %"]]
+            kpis = [gr.Number(label=l) for l in ["Companies", "Active", "Visits", "Avg Quality", "CRM %", "LinkedIn %", "High Quality (8-10)"]]
             gr.Button("Refresh KPIs").click(build_kpis, df_state, kpis)
             
+            gr.Markdown("### 📊 Charts")
             with gr.Row():
-                preset = gr.Dropdown(choices=list(DASHBOARD_PRESETS.keys()), label="Chart View", value="Visits by Campaign")
+                preset = gr.Dropdown(choices=list(DASHBOARD_PRESETS.keys()), label="Chart View", value="Key Campaigns Bifurcation (MS Tech, Fintech, Adtech)")
                 top_n = gr.Slider(5, 50, value=10, label="Top N Items")
             chart = gr.Plot()
             gr.Button("Build View").click(build_dashboard, [df_state, preset, top_n], chart)
-
+            
         # --- TAB 3: TRENDS ---
         with gr.Tab("📈 Trends"):
             with gr.Row():
@@ -418,21 +466,24 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
             plot = gr.Plot()
             trend_view.change(get_trend_filter_options, [df_state, trend_view], filter_dropdown)
             gr.Button("Show Trend", variant="primary").click(build_trend, [df_state, trend_view, grain, filter_dropdown], plot)
-
-        # --- TAB 4: SETTINGS ---
+            
+        # --- TAB 4: SETTINGS (EASY TEXT-BASED UI) ---
         with gr.Tab("⚙️ Campaign Settings"):
             gr.Markdown("### Manage Campaign Groups")
-            gr.Markdown("Select a campaign below and paste your keywords separated by commas.")
+            gr.Markdown("Select a campaign below and paste your keywords separated by commas. Changes take effect on the next data load.")
             
+            # Initial Load
             init_rules = load_campaign_rules()
             camp_choices = list(init_rules.keys()) + ["+ Create New Campaign"]
+            default_kws = ", ".join(init_rules.get(camp_choices[0], [])) if init_rules else ""
             
             with gr.Row():
                 camp_dropdown = gr.Dropdown(choices=camp_choices, label="Select Campaign to Edit", value=camp_choices[0])
                 new_camp_name = gr.Textbox(label="New Campaign Name", visible=False)
                 
-            kw_input = gr.Textbox(label="Keywords (comma separated)", lines=5, value=", ".join(init_rules.get(camp_choices[0], [])))
+            kw_input = gr.Textbox(label="Keywords (comma separated)", lines=5, value=default_kws)
             
+            # Switch views dynamically
             def update_ui_on_select(selected_camp):
                 rules = load_campaign_rules()
                 if selected_camp == "+ Create New Campaign":
@@ -446,11 +497,16 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
             save_config_btn = gr.Button("💾 Save Configuration", variant="primary")
             config_status = gr.Markdown()
             
+            # Save Logic
             def save_easy_config(selected_camp, new_name, kw_string):
                 rules = load_campaign_rules()
+                
+                # Split by comma and clean whitespace
                 raw_kws = kw_string.split(",")
                 clean_kws = [k.strip().lower() for k in raw_kws if k.strip()]
+                
                 target_camp = new_name.strip() if selected_camp == "+ Create New Campaign" else selected_camp
+                
                 if not target_camp:
                     return "❌ Error: Campaign name cannot be empty.", gr.update()
                 
@@ -462,7 +518,7 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
                 return f"✅ Saved successfully! Updated keywords for '{target_camp}'.", gr.update(choices=updated_choices, value=target_camp)
 
             save_config_btn.click(save_easy_config, inputs=[camp_dropdown, new_camp_name, kw_input], outputs=[config_status, camp_dropdown])
-
+            
         # --- TAB 5: DEBUGGER ---
         with gr.Tab("🛠️ Debugger"):
             dbg_id = gr.Textbox(label="Lead ID")