Update app.py

app.py

@@ -16,13 +16,12 @@ from datetime import date, timedelta
 API_TOKEN = os.getenv("LEADFEEDER_API_TOKEN")
 APP_PASSWORD = os.getenv("APP_PASSWORD")
 
-# Fail-safe for local testing if secrets aren't set
 if not API_TOKEN or not APP_PASSWORD:
     print("⚠️ WARNING: Secrets missing. App will launch but API calls will fail.")
     API_TOKEN = "PLACEHOLDER"
     APP_PASSWORD = "password"
 
-ACCOUNT_ID = "255333"  # PREMIUM account
+ACCOUNT_ID = "255333" 
 BASE_URL = "https://api.leadfeeder.com"
 PAGE_SIZE = 100 
 HEADERS = {
@@ -32,11 +31,10 @@ HEADERS = {
 CAMPAIGN_CONFIG_FILE = "campaign_rules.json"
 
 # =====================================================
-# 1. CAMPAIGN MANAGER & BUSINESS LOGIC
+# 1. CAMPAIGN MANAGER & LOGIC
 # =====================================================
-# UPDATED: Renamed "MS Stack" to "MS Tech" as requested
 DEFAULT_CAMPAIGNS = {
-    "MS Stack": [
+    "MS Tech": [
         "microsoft", "power", "dynamics", "crm", "365", "xamarin", "sharepoint", 
         "dot", ".net", "asp.net", "azure", "copilot", "real-estate-website-development", 
         "manufacturing-production", "legacy-hrms", "healthcare-appointment", "eld-fleet",
@@ -71,9 +69,9 @@ def save_campaign_rules(rules_text):
         rules = json.loads(rules_text)
         with open(CAMPAIGN_CONFIG_FILE, "w") as f:
             json.dump(rules, f, indent=4)
-        return "✅ Configuration Saved! (Reload Data to apply changes)", rules
+        return "✅ Configuration Saved!", rules
     except json.JSONDecodeError:
-        return "❌ Error: Invalid JSON format.", None
+        return "❌ Error: Invalid JSON.", None
 
 def categorize_quality(score):
     if pd.isna(score): return "Unknown"
@@ -98,29 +96,22 @@ def assign_campaign(url, 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 (requires landing_page_path)
     rules = load_campaign_rules()
     if "landing_page_path" in df.columns:
         df["Campaign"] = df["landing_page_path"].apply(lambda x: assign_campaign(x, rules))
     else:
         df["Campaign"] = "Uncategorized"
-        
     return df
 
 # =====================================================
 # 2. PRESETS
 # =====================================================
 DASHBOARD_PRESETS = {
-    # -- NEW: TARGETED COMPARISON --
     "Key Campaigns Overview (MS Tech, Fintech, Adtech)": ("SPECIAL_KEY_CAMPAIGNS", None, None),
-    
     "All Campaigns (Multi-Chart)": ("SPECIAL_MULTI", None, None), 
-    
     "Visits by Campaign": ("Campaign", "total_visits", "sum"),
     "Leads by Campaign": ("Campaign", "company_name", "count"),
     "Leads by Quality Group": ("Quality_Group", "company_name", "count"),
@@ -132,20 +123,18 @@ TREND_PRESETS = {
     "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"),
-    
     "Total Visits Trend": ("total_visits", "sum", None),
     "Active Accounts Trend": ("company_name", "count", None),
 }
 
 # =====================================================
-# 3. API HANDLING (FULL DATA PRESERVED)
+# 3. API HANDLING
 # =====================================================
 def make_request(url, params=None):
     retries = 3
     while retries > 0:
         r = requests.get(url, headers=HEADERS, params=params, timeout=45)
         if r.status_code == 429:
-            print("⏳ Rate limit hit. Sleeping for 60 seconds...")
             time.sleep(61)
             retries -= 1
             continue
@@ -154,20 +143,14 @@ def make_request(url, params=None):
     raise Exception("Max retries exceeded")
 
 def fetch_basic_leads(start_date, end_date):
-    """ Fetch ALL company details (No data points missed). """
     page = 1
     rows = []
     print(f"🚀 Fetching full company list for {start_date} to {end_date}...")
-    
     while True:
         try:
             js = make_request(
                 f"{BASE_URL}/accounts/{ACCOUNT_ID}/leads",
-                params={
-                    "start_date": start_date, "end_date": end_date,
-                    "page[number]": page, "page[size]": PAGE_SIZE,
-                    "include": "location"
-                }
+                params={"start_date": start_date, "end_date": end_date, "page[number]": page, "page[size]": PAGE_SIZE, "include": "location"}
             )
             data = js.get("data", [])
             if not data: break
@@ -208,7 +191,7 @@ def fetch_basic_leads(start_date, end_date):
                     "region": loc.get("region"),
                     "city": loc.get("city"),
                     "leadfeeder_url": a.get("view_in_leadfeeder"),
-                    "landing_page_path": None, # Init for Enrichment
+                    "landing_page_path": None,
                     "exit_page_path": None
                 })
             print(f"✅ Page {page} loaded. Rows: {len(rows)}")
@@ -223,25 +206,18 @@ def fetch_basic_leads(start_date, end_date):
     return df
 
 def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=gr.Progress()):
-    """ Step 2: Deep enrich (Restored full logic). """
     if df.empty: return df
     target_df = df.head(max_rows) if max_rows else df
     total = len(target_df)
     
     print(f"🕵️ Deep enriching {total} rows ({start_date} to {end_date})...")
-    
     for index, row in target_df.iterrows():
-        # Skip if already enriched
-        if row.get("landing_page_path") and row.get("exit_page_path"): continue
-        
+        if row.get("landing_page_path"): continue
         lead_id = row["lead_id"]
         try:
             visit_data = make_request(
                 f"{BASE_URL}/accounts/{ACCOUNT_ID}/leads/{lead_id}/visits",
-                params={
-                    "start_date": start_date, "end_date": end_date,
-                    "page[size]": 1, "include": "page_views"
-                }
+                params={"start_date": start_date, "end_date": end_date, "page[size]": 1, "include": "page_views"}
             )
             visits = visit_data.get("data", [])
             included = visit_data.get("included", [])
@@ -251,11 +227,8 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
             if visits:
                 visit = visits[0]
                 v_attrs = visit.get("attributes", {})
-                
-                # A. Direct Attributes
                 landing = v_attrs.get("landing_page_path") or v_attrs.get("landing_page_url")
                 
-                # B. Parse 'visit_route'
                 visit_route = v_attrs.get("visit_route", [])
                 if visit_route and isinstance(visit_route, list):
                     last_step = visit_route[-1]
@@ -264,11 +237,9 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
                         first_step = visit_route[0]
                         landing = first_step.get("page_path") or first_step.get("page_url")
                 
-                # C. Deep Link via 'included' Page Views
                 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", [])]
-                    
                     if pv_ids:
                         if not landing:
                             first_pv = pv_map.get(pv_ids[0])
@@ -281,10 +252,9 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
                 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
 
 # =====================================================
@@ -293,22 +263,16 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
 def load_preview(start, end):
     df = fetch_basic_leads(start, end)
     if df.empty: return df, pd.DataFrame(), "⚠️ No data found."
-    
-    # Enrich top 50 for better preview categorization
     df_preview = df.copy()
     df_preview = enrich_leads_with_visits(df_preview, start, end, max_rows=50)
     df_preview = apply_business_logic(df_preview)
-    
-    status = f"✅ Loaded **{len(df):,} companies**. Preview shows top 50 rows enriched."
-    return df, df_preview.head(50), status
+    return df, df_preview.head(50), f"✅ Loaded {len(df):,} companies. Preview top 50 enriched."
 
 def download_full_excel(df, start, end):
     if df is None or df.empty: return None
     print("⏳ Starting full enrichment for Excel export...")
-    
     enriched_df = enrich_leads_with_visits(df.copy(), start, end)
     final_df = apply_business_logic(enriched_df)
-    
     path = "/tmp/leadfeeder_campaign_data.xlsx"
     final_df.to_excel(path, index=False)
     return path
@@ -324,14 +288,11 @@ def inspect_raw_json(lead_id, start_date, end_date):
         return str(e)
 
 # =====================================================
-# 5. CHART ENGINES (IMPROVED UI)
+# 5. CHART ENGINES
 # =====================================================
 def build_kpis(df):
     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)
-        
+    if "Quality_Group" not in df.columns: df = apply_business_logic(df)
     return (
         len(df),
         df["total_visits"].gt(0).sum(),
@@ -346,99 +307,50 @@ 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)
 
-    # --- 1. NEW KEY CAMPAIGNS COMPARISON (MS Tech, Fintech, Adtech) ---
     if preset == "Key Campaigns Overview (MS Tech, Fintech, Adtech)":
-        target_campaigns = ["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")
         
-        # Filter Data
-        filtered_df = df[df["Campaign"].isin(target_campaigns)].copy()
+        visits = filtered.groupby("Campaign")["total_visits"].sum().reset_index()
+        leads = filtered.groupby("Campaign")["company_name"].count().reset_index()
         
-        if filtered_df.empty:
-            return px.bar(title="No data found for MS Tech, Fintech, or Adtech. Try 'Download Excel' to enrich more rows.")
-
-        # Create Aggregates
-        visits = filtered_df.groupby("Campaign")["total_visits"].sum().reset_index()
-        leads = filtered_df.groupby("Campaign")["company_name"].count().reset_index()
-
-        # Subplots: Left=Visits, Right=Leads
-        fig = make_subplots(rows=1, cols=2, subplot_titles=("Total Visits", "Total Leads (Count)"))
-
-        fig.add_trace(
-            go.Bar(x=visits["Campaign"], y=visits["total_visits"], name="Visits", marker_color='indigo'),
-            row=1, col=1
-        )
-        fig.add_trace(
-            go.Bar(x=leads["Campaign"], y=leads["company_name"], name="Leads", marker_color='teal'),
-            row=1, col=2
-        )
+        fig = make_subplots(rows=1, cols=2, subplot_titles=("Total Visits", "Total Leads"))
+        fig.add_trace(go.Bar(x=visits["Campaign"], y=visits["total_visits"], name="Visits"), row=1, col=1)
+        fig.add_trace(go.Bar(x=leads["Campaign"], y=leads["company_name"], name="Leads"), row=1, col=2)
         fig.update_layout(title_text="Key Campaigns Comparison", showlegend=False)
         return fig
 
-    # --- 2. ALL CAMPAIGNS MULTI-CHART ---
     if preset == "All Campaigns (Multi-Chart)":
-        campaigns = df["Campaign"].dropna().unique().tolist()
-        if not campaigns: return px.bar(title="No Campaigns Found")
-        
-        # Sort so key campaigns appear first if possible, or A-Z
-        campaigns.sort()
-        
-        num_cams = len(campaigns)
-        cols = 2 
-        rows = math.ceil(num_cams / cols)
-        
-        fig = make_subplots(rows=rows, cols=cols, subplot_titles=campaigns, vertical_spacing=0.15)
-
+        campaigns = sorted(df["Campaign"].dropna().unique().tolist())
+        rows = math.ceil(len(campaigns) / 2)
+        fig = make_subplots(rows=rows, cols=2, subplot_titles=campaigns, vertical_spacing=0.15)
         for i, camp in enumerate(campaigns):
-            r = (i // cols) + 1
-            c = (i % cols) + 1
-            
+            r, c = (i // 2) + 1, (i % 2) + 1
             camp_df = df[df["Campaign"] == camp]
-            grouped = camp_df.groupby("company_name")["total_visits"].sum().reset_index()
-            grouped = grouped.sort_values("total_visits", ascending=False).head(top_n)
-            
+            grouped = camp_df.groupby("company_name")["total_visits"].sum().reset_index().sort_values("total_visits", ascending=False).head(top_n)
             fig.add_trace(go.Bar(x=grouped["company_name"], y=grouped["total_visits"], name=camp), row=r, col=c)
-
-        fig.update_layout(title_text=f"Top Companies by Campaign (All {num_cams})", height=350 * rows, showlegend=False)
+        fig.update_layout(height=350*rows, showlegend=False, title_text="Top Companies by Campaign")
         return fig
 
-    # --- STANDARD CHARTS ---
     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, color=dim)
 
-def get_trend_filter_options(df, preset):
-    if df is None or df.empty: return gr.update(choices=[], value=None, visible=False)
-    
-    metric, agg, segment = TREND_PRESETS[preset]
-    if not segment: return gr.update(choices=[], value=None, visible=False)
-    if segment not in df.columns: df = apply_business_logic(df)
-        
-    options = sorted(df[segment].astype(str).unique().tolist())
-    # Default select key campaigns if available
-    defaults = [o for o in options if o in ["MS Tech", "Fintech", "Adtech"]]
-    if not defaults: defaults = options[:5]
-    
-    return gr.update(choices=options, value=defaults, visible=True, label=f"Filter {segment}")
-
 def build_trend(df, preset, grain, filter_values):
     if df is None or df.empty: return px.line(title="No Data")
-    
     metric, agg, segment = TREND_PRESETS[preset]
     df_t = df.dropna(subset=["last_visit_date"]).copy()
     
     if segment:
         if segment not in df_t.columns: df_t = apply_business_logic(df_t)
-        if filter_values:
-            df_t = df_t[df_t[segment].isin(filter_values)]
+        if filter_values: df_t = df_t[df_t[segment].isin(filter_values)]
             
     if grain == "Weekly":
         df_t["period"] = df_t["last_visit_date"].dt.to_period("W").astype(str)
-    elif grain == "Monthly":
-        df_t["period"] = df_t["last_visit_date"].dt.to_period("M").astype(str)
     else:
         df_t["period"] = df_t["last_visit_date"].dt.date
         
@@ -454,8 +366,17 @@ def build_trend(df, preset, grain, filter_values):
     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)
+    metric, agg, segment = TREND_PRESETS[preset]
+    if not segment: return gr.update(choices=[], value=None, visible=False)
+    if segment not in df.columns: df = apply_business_logic(df)
+    options = sorted(df[segment].astype(str).unique().tolist())
+    defaults = [o for o in options if o in ["MS Tech", "Fintech", "Adtech"]] or options[:5]
+    return gr.update(choices=options, value=defaults, visible=True, label=f"Filter {segment}")
+
 # =====================================================
-# 6. UI LAYOUT (STABLE & CLEAN)
+# 6. UI LAYOUT
 # =====================================================
 with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
     gr.Markdown("## 🚀 Leadfeeder Analytics & Campaign Manager")
@@ -473,28 +394,24 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
             with gr.Row():
                 start = gr.Textbox(label="Start Date", value=(date.today()-timedelta(days=30)).isoformat())
                 end = gr.Textbox(label="End Date", value=date.today().isoformat())
-            
             with gr.Row():
                 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, height=400)
+            # Removed height=400 to fix TypeError in older Gradio versions
+            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"):
-            with gr.Row():
-                # KPIs in a row
-                kpis = [gr.Number(label=l) for l in ["Companies", "Active", "Visits", "Avg Quality", "CRM %", "LinkedIn %", "High Quality (8-10)"]]
+            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="Key Campaigns Overview (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)
 
@@ -503,10 +420,8 @@ with gr.Blocks(title="Leadfeeder Campaign Pro") as demo:
             with gr.Row():
                 trend_view = gr.Dropdown(choices=list(TREND_PRESETS.keys()), label="Select Trend", value="Visits Trend by Campaign")
                 grain = gr.Radio(["Daily", "Weekly", "Monthly"], value="Daily", label="Granularity")
-            
             filter_dropdown = gr.Dropdown(multiselect=True, visible=False, label="Filter Segments")
             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)