Update app.py

app.py

@@ -1981,44 +1981,49 @@ if not df_category.empty:
 else:
     st.info("No data available for non-positive issue categories with 100% coverage and positive trend.")
 
-st.markdown("<h3 class='section-title'>OBJECTIVE 7 - Insight and Recommendation</h3>", unsafe_allow_html=True)
-# =================== OBJECTIVE 7 - Insight and Recommendation (Revised per Deviasi Aktual) ===================
 
+# =================== OBJECTIVE 7 - Insight and Recommendation (Revised per Deviasi Aktual) ===================
+# =================== OBJECTIVE 7 - Insight and Recommendation ===================
+st.markdown("<h3 class='section-title'>OBJECTIVE 7 — Insight and Recommendation</h3>", unsafe_allow_html=True)
 
-def extract_critical_deviations(df: pd.DataFrame):
+def extract_deviations_for_insight(df: pd.DataFrame):
+    """Ekstrak nilai aktual dari Obj 2–6 sesuai permintaan: 9 lokasi ratio=1.0, dll."""
     dev = {
-        "obj2_locations_ratio_1": [],
-        "obj3a_lowest_div_ratio": None,
+        "obj2_ratio_1_locs": [],
+        "obj3a_lowest_div": None,
         "obj3b_lowest_reporter": None,
-        "obj3c_slowest_div_leadtime": None,
+        "obj3c_slowest_div": None,
         "obj3d_slowest_executor": None,
-        "obj4_unsafe_share": {},
+        "obj4_unsafe_condition": 0.0,
+        "obj4_unsafe_action": 0.0,
+        "obj4_near_miss": 0.0,
         "obj5_quadrant_I": [],
         "obj5_quadrant_II": [],
-        "obj6_top2_bubbles": []
+        "obj6_top2_categories": []
     }
 
-    # === OBJ 2: 9 lokasi dengan finding ratio ≈ 1.0 (rentang 0.95–1.05) ===
+    # === OBJ 2: 9 lokasi dengan ratio ≈ 1.0 ===
     if {'nama_lokasi_full', 'creator_nid', 'created_at', 'kode_temuan'}.issubset(df.columns):
-        df_calc = df[['nama_lokasi_full', 'creator_nid', 'created_at', 'kode_temuan']].copy()
-        df_calc['created_at'] = pd.to_datetime(df_calc['created_at'], errors='coerce')
-        df_calc = df_calc.dropna(subset=['created_at', 'nama_lokasi_full', 'creator_nid'])
-        df_calc['bulan'] = df_calc['created_at'].dt.to_period('M')
-        monthly_agg = df_calc.groupby(['nama_lokasi_full', 'bulan']).agg(
+        calc = df[['nama_lokasi_full', 'creator_nid', 'created_at', 'kode_temuan']].copy()
+        calc['created_at'] = pd.to_datetime(calc['created_at'], errors='coerce')
+        calc = calc.dropna(subset=['created_at', 'nama_lokasi_full', 'creator_nid'])
+        calc['bulan'] = calc['created_at'].dt.to_period('M')
+        monthly = calc.groupby(['nama_lokasi_full', 'bulan']).agg(
             findings=('kode_temuan', 'size'),
             reporters=('creator_nid', 'nunique')
         ).reset_index()
-        monthly_agg = monthly_agg[monthly_agg['reporters'] > 0]
-        monthly_agg['ratio'] = monthly_agg['findings'] / monthly_agg['reporters']
-        loc_avg = monthly_agg.groupby('nama_lokasi_full')['ratio'].mean().reset_index()
+        monthly = monthly[monthly['reporters'] > 0]
+        monthly['ratio'] = monthly['findings'] / monthly['reporters']
+        loc_avg = monthly.groupby('nama_lokasi_full')['ratio'].mean().reset_index()
         near_1 = loc_avg[(loc_avg['ratio'] >= 0.95) & (loc_avg['ratio'] <= 1.05)]
-        dev["obj2_locations_ratio_1"] = near_1.nlargest(9, 'ratio')['nama_lokasi_full'].tolist()
+        dev["obj2_ratio_1_locs"] = near_1.nlargest(9, 'ratio')['nama_lokasi_full'].tolist()
 
-    # === OBJ 3a: Divisi dengan rasio temuan/orang terendah ===
+    # === OBJ 3a–3d: ekstrem aktual ===
+    # 3a: divisi rasio terendah
     if {'nama', 'creator_nid', 'created_at', 'kode_temuan'}.issubset(df.columns):
-        df_ratio = df[['nama', 'creator_nid', 'created_at', 'kode_temuan']].copy()
-        df_ratio['bulan'] = pd.to_datetime(df_ratio['created_at']).dt.to_period('M')
-        agg = df_ratio.groupby(['nama', 'bulan']).agg(
+        calc = df[['nama', 'creator_nid', 'created_at', 'kode_temuan']].copy()
+        calc['bulan'] = pd.to_datetime(calc['created_at']).dt.to_period('M')
+        agg = calc.groupby(['nama', 'bulan']).agg(
             findings=('kode_temuan', 'size'),
             reporters=('creator_nid', 'nunique')
         )
@@ -2026,148 +2031,198 @@ def extract_critical_deviations(df: pd.DataFrame):
         agg['ratio'] = agg['findings'] / agg['reporters']
         div_ratio = agg.groupby('nama')['ratio'].mean()
         if not div_ratio.empty:
-            lowest = div_ratio.idxmin()
-            dev["obj3a_lowest_div_ratio"] = (lowest, round(div_ratio.min(), 2))
+            name = div_ratio.idxmin()
+            val = round(div_ratio.min(), 2)
+            dev["obj3a_lowest_div"] = (name, val)
 
-    # === OBJ 3b: Reporter dengan frekuensi terendah (>0) ===
+    # 3b: reporter frekuensi terendah
     if {'creator_name', 'created_at'}.issubset(df.columns):
-        df_rep = df[['creator_name', 'created_at']].copy()
-        df_rep['bulan'] = pd.to_datetime(df_rep['created_at']).dt.to_period('M')
-        rep_monthly = df_rep.groupby(['creator_name', 'bulan']).size().reset_index(name='count')
-        rep_avg = rep_monthly.groupby('creator_name')['count'].mean()
-        if not rep_avg.empty and rep_avg.min() > 0:
-            lowest = rep_avg.idxmin()
-            dev["obj3b_lowest_reporter"] = (lowest, round(rep_avg.min(), 2))
-
-    # === OBJ 3c & 3d: Lead time terpanjang (divisi & individu) ===
+        calc = df[['creator_name', 'created_at']].copy()
+        calc['bulan'] = pd.to_datetime(calc['created_at']).dt.to_period('M')
+        monthly = calc.groupby(['creator_name', 'bulan']).size().reset_index(name='count')
+        avg = monthly.groupby('creator_name')['count'].mean()
+        avg = avg[avg > 0]
+        if not avg.empty:
+            name = avg.idxmin()
+            val = round(avg.min(), 2)
+            dev["obj3b_lowest_reporter"] = (name, val)
+
+    # 3c: divisi lead time terpanjang
+    if 'days_to_close' in df.columns and 'nama' in df.columns:
+        valid = df[df['days_to_close'].notna() & (df['days_to_close'] >= 0)]
+        if not valid.empty:
+            lead = valid.groupby('nama')['days_to_close'].mean()
+            if not lead.empty:
+                name = lead.idxmax()
+                val = round(lead.max(), 1)
+                dev["obj3c_slowest_div"] = (name, val)
+
+    # 3d: eksekutor lead time terpanjang
     if 'days_to_close' in df.columns:
-        valid_df = df[df['days_to_close'].notna() & (df['days_to_close'] >= 0)]
-
-        # 3c: divisi
-        if 'nama' in valid_df.columns:
-            div_lead = valid_df.groupby('nama')['days_to_close'].mean()
-            if not div_lead.empty:
-                slowest = div_lead.idxmax()
-                dev["obj3c_slowest_div_leadtime"] = (slowest, round(div_lead.max(), 1))
-
-        # 3d: executor (prioritas: nama_pic → creator_name)
-        executor_col = 'nama_pic' if 'nama_pic' in valid_df.columns else 'creator_name'
-        if executor_col in valid_df.columns:
-            exec_lead = valid_df.groupby(executor_col)['days_to_close'].mean()
-            if not exec_lead.empty:
-                slowest = exec_lead.idxmax()
-                dev["obj3d_slowest_executor"] = (slowest, round(exec_lead.max(), 1))
-
-    # === OBJ 4: Pie chart — unsafe share ===
+        valid = df[df['days_to_close'].notna() & (df['days_to_close'] >= 0)]
+        exec_col = 'nama_pic' if 'nama_pic' in valid.columns else 'creator_name'
+        if exec_col in valid.columns:
+            lead = valid.groupby(exec_col)['days_to_close'].mean()
+            if not lead.empty:
+                name = lead.idxmax()
+                val = round(lead.max(), 1)
+                dev["obj3d_slowest_executor"] = (name, val)
+
+    # === OBJ 4: unsafe share ===
     if 'temuan_kategori' in df.columns:
-        cat_counts = df['temuan_kategori'].value_counts(normalize=True) * 100
-        unsafe_cats = ['Unsafe Condition', 'Unsafe Action', 'Near Miss']
-        for cat in unsafe_cats:
-            if cat in cat_counts.index:
-                dev["obj4_unsafe_share"][cat] = round(cat_counts[cat], 1)
-
-    # === OBJ 5: Risk Matrix kuadran (X_LIMIT=20, Y_LIMIT=3) ===
+        total = len(df)
+        if total > 0:
+            cnt = df['temuan_kategori'].value_counts(normalize=True) * 100
+            dev["obj4_unsafe_condition"] = round(cnt.get("Unsafe Condition", 0), 1)
+            dev["obj4_unsafe_action"] = round(cnt.get("Unsafe Action", 0), 1)
+            dev["obj4_near_miss"] = round(cnt.get("Near Miss", 0), 1)
+
+    # === OBJ 5: kuadran risiko (X=20, Y=3) ===
     X_LIMIT, Y_LIMIT = 20, 3
-    if 'nama' in df.columns and 'days_to_close' in df.columns:
-        df_risk = df.copy()
-        df_risk['created_at'] = pd.to_datetime(df_risk['created_at'], errors='coerce')
-        df_risk = df_risk.assign(month=df_risk['created_at'].dt.to_period('M').astype(str))
-        monthly_counts = df_risk.groupby(['nama', 'month'])['kode_temuan'].nunique().reset_index()
+    if {'nama', 'created_at', 'days_to_close'}.issubset(df.columns):
+        calc = df.copy()
+        calc['created_at'] = pd.to_datetime(calc['created_at'], errors='coerce')
+        calc = calc.assign(month=calc['created_at'].dt.to_period('M').astype(str))
+        monthly_counts = calc.groupby(['nama', 'month'])['kode_temuan'].nunique().reset_index()
         avg_count = monthly_counts.groupby('nama')['kode_temuan'].mean().reset_index(name='Finding Count')
-        leadtime = df_risk.groupby('nama')['days_to_close'].mean().reset_index(name='Average Lead Time')
-        risk_mat = avg_count.merge(leadtime, on='nama', how='left').fillna(0)
-        risk_mat['Average Lead Time'] = risk_mat['Average Lead Time'].clip(lower=0)
-
-        for _, row in risk_mat.iterrows():
-            div = row['nama']
-            cnt = row['Finding Count']
-            lt = row['Average Lead Time']
-            if cnt >= X_LIMIT and lt >= Y_LIMIT:
-                dev["obj5_quadrant_I"].append(div)
-            elif cnt < X_LIMIT and lt >= Y_LIMIT:
-                dev["obj5_quadrant_II"].append(div)
-
-    # === OBJ 6: Whiteboard — 2 bubble terbesar (Avg/Month non-Positive) ===
-    if 'kategori' in df.columns and 'temuan_kategori' in df.columns:
-        df_nonpos = df[df['temuan_kategori'] != 'Positive'].copy()
-        if not df_nonpos.empty:
-            start = df['created_at'].min().to_period('M')
-            end = df['created_at'].max().to_period('M')
+        leadtime = calc.groupby('nama')['days_to_close'].mean().reset_index(name='Avg Lead Time')
+        mat = avg_count.merge(leadtime, on='nama', how='left').fillna(0)
+        for _, r in mat.iterrows():
+            if r['Finding Count'] >= X_LIMIT and r['Avg Lead Time'] >= Y_LIMIT:
+                dev["obj5_quadrant_I"].append(r['nama'])
+            elif r['Finding Count'] < X_LIMIT and r['Avg Lead Time'] >= Y_LIMIT:
+                dev["obj5_quadrant_II"].append(r['nama'])
+
+    # === OBJ 6: top 2 bubble (non-Positive, Avg/Month tertinggi) ===
+    if {'kategori', 'temuan_kategori', 'created_at'}.issubset(df.columns):
+        nonpos = df[df['temuan_kategori'] != 'Positive']
+        if not nonpos.empty:
+            start = nonpos['created_at'].min().to_period('M')
+            end = nonpos['created_at'].max().to_period('M')
             n_months = len(pd.period_range(start=start, end=end, freq='M'))
-            cat_avg = (df_nonpos.groupby('kategori').size() / n_months).sort_values(ascending=False).head(2)
-            dev["obj6_top2_bubbles"] = [(cat, round(val, 1)) for cat, val in cat_avg.items()]
+            cat_avg = (nonpos.groupby('kategori').size() / n_months).sort_values(ascending=False).head(2)
+            dev["obj6_top2_categories"] = [(cat, round(val, 1)) for cat, val in cat_avg.items()]
 
     return dev
 
-# Jalankan ekstraksi deviasi
-deviations = extract_critical_deviations(df_filtered)
+# Ekstrak deviasi aktual
+dev = extract_deviations_for_insight(df_filtered)
+
+# Bangun Insight Summary — sesuai struktur: 1, 2 → 2a–2d, 3, 4a, 4b, 5
+insight_lines = []
+
+# 1. Pola umum
+insight_lines.append("1. Analisis deviasi menunjukkan ketidakseimbangan antara aktivitas inspeksi dan kapasitas resolusi.")
+
+# 2. Temuan utama (dipecah)
+if dev["obj2_ratio_1_locs"]:
+    locs = ", ".join(dev["obj2_ratio_1_locs"][:5])
+    insight_lines.append(f"2. Lokasi dengan rasio optimal (~1,0): {locs}, dan 4 lainnya.")
+    insight_lines.append(f"   2a. Sembilan lokasi tersebut menunjukkan beban kerja seimbang dan pelaporan konsisten.")
+if dev["obj3a_lowest_div"] and dev["obj3b_lowest_reporter"]:
+    div, r1 = dev["obj3a_lowest_div"]
+    rep, r2 = dev["obj3b_lowest_reporter"]
+    insight_lines.append("   2b. Aktivitas pelaporan terendah terjadi di:")
+    insight_lines.append(f"       • Divisi: {div} (rasio {r1})")
+    insight_lines.append(f"       • Reporter: {rep} ({r2} temuan/bulan)")
+if dev["obj3c_slowest_div"] and dev["obj3d_slowest_executor"]:
+    div, lt1 = dev["obj3c_slowest_div"]
+    exe, lt2 = dev["obj3d_slowest_executor"]
+    insight_lines.append("   2c. Lead time penyelesaian terpanjang terjadi di:")
+    insight_lines.append(f"       • Divisi: {div} ({lt1} hari)")
+    insight_lines.append(f"       • Eksekutor: {exe} ({lt2} hari)")
+if dev["obj4_unsafe_condition"] or dev["obj4_unsafe_action"] or dev["obj4_near_miss"]:
+    uc, ua, nm = dev["obj4_unsafe_condition"], dev["obj4_unsafe_action"], dev["obj4_near_miss"]
+    insight_lines.append("   2d. Komposisi temuan:")
+    insight_lines.append(f"       • Unsafe Condition: {uc}%")
+    insight_lines.append(f"       • Unsafe Action: {ua}%")
+    insight_lines.append(f"       • Near Miss: {nm}%")
+
+# 3. Objective 6 — top 2 bubble
+if dev["obj6_top2_categories"]:
+    c1, c2 = dev["obj6_top2_categories"]
+    insight_lines.append(f"3. Dua kategori temuan paling sering muncul (non-Positive): {c1[0]} ({c1[1]}/bulan) dan {c2[0]} ({c2[1]}/bulan).")
+
+# 4a & 4b — Kuadran risiko
+if dev["obj5_quadrant_I"]:
+    q1 = ", ".join(dev["obj5_quadrant_I"][:3])
+    insight_lines.append(f"4a. Divisi risiko tinggi (volume tinggi + lead time tinggi): {q1}.")
+if dev["obj5_quadrant_II"]:
+    q2 = ", ".join(dev["obj5_quadrant_II"][:3])
+    insight_lines.append(f"4b. Divisi risiko tersembunyi (volume rendah + lead time tinggi): {q2}.")
+
+# 5. Sintesis
+insight_lines.append("5. Pola utama: aktivitas inspeksi tidak diimbangi kapasitas resolusi, sehingga hazard tetap terbuka lama.")
+
+insight_text = "<br>".join(insight_lines)
+
+# Rekomendasi & Risk Mitigation — per poin insight
+rec_mitigation = []
+
+# Untuk 2a
+if dev["obj2_ratio_1_locs"]:
+    rec_mitigation.append({
+        "point": "2a",
+        "recommendation": "Jadikan 9 lokasi ber-rasio ~1,0 sebagai benchmark operasional: dokumentasikan praktik pelaporan, rotasi, dan validasi lapangan.",
+        "mitigation": "Tetapkan standar beban kerja: 0,8–1,2 temuan/pelapor/bulan. Jika rasio <0,5 atau >1,5 selama 2 bulan → picu capacity review."
+    })
 
-# Bangun Insight Summary
-insight_parts = []
+# Untuk 2b
+if dev["obj3a_lowest_div"] and dev["obj3b_lowest_reporter"]:
+    rec_mitigation.append({
+        "point": "2b",
+        "recommendation": "Lakukan 1:1 coaching dengan reporter terendah dan silent walkdown di divisi terendah untuk identifikasi hambatan.",
+        "mitigation": "Aktifkan micro-checklist digital (QR code → form 3 pertanyaan). Target: kenaikan temuan/bulan ≥0,5 dalam 30 hari."
+    })
 
-# Obj 2: 9 lokasi ratio ~1.0
-if deviations["obj2_locations_ratio_1"]:
-    locs = ", ".join(deviations["obj2_locations_ratio_1"][:5])
-    insight_parts.append(
-        f"Nine locations show near-optimal finding-to-reporter ratio (~1.0), indicating balanced workload: "
-        f"{locs}, and others."
-    )
+# Untuk 2c
+if dev["obj3c_slowest_div"] and dev["obj3d_slowest_executor"]:
+    rec_mitigation.append({
+        "point": "2c",
+        "recommendation": "Bentuk Rapid Response Task Force untuk divisi dan eksekutor dengan lead time terpanjang: lakukan workflow mapping & integrasi verifikasi foto.",
+        "mitigation": "Terapkan SLA dua tingkat: High Risk ≤3 hari, Medium/Low ≤7 hari. Jika >7 hari → eskalasi otomatis ke Daily Safety Huddle."
+    })
 
-# Obj 3a–d
-if deviations["obj3a_lowest_div_ratio"]:
-    div, ratio = deviations["obj3a_lowest_div_ratio"]
-    insight_parts.append(f"Division {div} has the lowest reporting ratio ({ratio}), suggesting potential under-utilization or resource gaps.")
-if deviations["obj3b_lowest_reporter"]:
-    name, rate = deviations["obj3b_lowest_reporter"]
-    insight_parts.append(f"Reporter {name} averages only {rate} finding(s) per month — the lowest among active staff.")
-if deviations["obj3c_slowest_div_leadtime"]:
-    div, lt = deviations["obj3c_slowest_div_leadtime"]
-    insight_parts.append(f"Division {div} takes longest to resolve findings (avg {lt} days), risking SLA breach.")
-if deviations["obj3d_slowest_executor"]:
-    name, lt = deviations["obj3d_slowest_executor"]
-    insight_parts.append(f"Executor {name} has the longest lead time ({lt} days), requiring workflow review.")
-
-# Obj 4: Unsafe share
-if deviations["obj4_unsafe_share"]:
-    unsafe_list = [f"{cat} ({pct}%)" for cat, pct in deviations["obj4_unsafe_share"].items()]
-    unsafe_str = "; ".join(unsafe_list)
-    insight_parts.append(f"Unsafe issues dominate: {unsafe_str} of all findings.")
-
-# Obj 5: Kuadran risiko
-if deviations["obj5_quadrant_I"]:
-    q1 = ", ".join(deviations["obj5_quadrant_I"][:3])
-    insight_parts.append(f"High-risk divisions (high volume + slow resolution): {q1}.")
-if deviations["obj5_quadrant_II"]:
-    q2 = ", ".join(deviations["obj5_quadrant_II"][:3])
-    insight_parts.append(f"Hidden-risk divisions (low volume but very slow): {q2} — may indicate capacity or priority issues.")
-
-# Obj 6: Top 2 bubble
-if deviations["obj6_top2_bubbles"]:
-    bub1, bub2 = deviations["obj6_top2_bubbles"]
-    insight_parts.append(
-        f"The two most frequently recurring unsafe issues are {bub1[0]} ({bub1[1]}/month) "
-        f"and {bub2[0]} ({bub2[1]}/month), indicating systemic root causes."
-    )
+# Untuk 2d
+if dev["obj4_unsafe_condition"] or dev["obj4_unsafe_action"] or dev["obj4_near_miss"]:
+    rec_mitigation.append({
+        "point": "2d",
+        "recommendation": "Luncurkan Positive Hunt Sprint selama 1 bulan: wajibkan 1 temuan Positive/reporter/minggu dan berikan reward.",
+        "mitigation": "Ubah default form digital dari Unsafe Condition → Positive. Target: kenaikan Near Miss & Unsafe Action ≥3× dalam 60 hari."
+    })
 
-insight_text = " ".join(insight_parts) if insight_parts else "No significant deviations detected based on current filters."
+# Untuk 3
+if dev["obj6_top2_categories"]:
+    rec_mitigation.append({
+        "point": "3",
+        "recommendation": "Bentuk Cross-Functional RCA Team (SIPIL, ELEKTRIKAL, Kontraktor, Safety) untuk analisis akar masalah desain/spesifikasi.",
+        "mitigation": "Perbarui spesifikasi tender: wajibkan mitigasi berbasis temuan historis (misal: double insulation untuk kabel outdoor)."
+    })
 
-# Rekomendasi & Risk Mitigation Strategy
-rec_parts = [
-    "Prioritize capacity assessment and coaching for divisions and individuals with lowest activity or longest resolution times.",
-    "Initiate root-cause analysis on top two high-frequency unsafe categories to prevent recurrence.",
-    "Review workload distribution for locations with ratio ≈1.0 — they represent a benchmark for sustainable inspection load."
-]
+# Untuk 4a
+if dev["obj5_quadrant_I"]:
+    rec_mitigation.append({
+        "point": "4a",
+        "recommendation": "Alokasikan dedicated safety crew (2 orang) hanya untuk menutup temuan High Risk dari divisi kuadran I.",
+        "mitigation": "Aktifkan predictive alert: jika divisi masuk Kuadran I ≥2 bulan berturut-turut → notifikasi otomatis ke Manajer Area."
+    })
 
-mitigation_parts = [
-    "Establish SLA thresholds: max 7 days lead time, min 0.5 findings/reporter/month for active status.",
-    "Deploy predictive alerts when a division enters Quadrant I or II in the risk matrix.",
-    "Integrate category-level trend monitoring into monthly safety meetings to catch emerging risks early."
-]
+# Untuk 4b
+if dev["obj5_quadrant_II"]:
+    rec_mitigation.append({
+        "point": "4b",
+        "recommendation": "Terapkan One Finding, One Day untuk divisi kuadran II: jika ≤3 temuan/bulan, wajib selesai dalam 24 jam.",
+        "mitigation": "Jadikan KPI supervisor: 100% closure <24 jam. Luncurkan Zero Backlog Challenge tiap bulan."
+    })
 
-recommendation_text = " ".join(rec_parts)
-mitigation_text = " ".join(mitigation_parts)
+# Untuk 5 (sintesis)
+rec_mitigation.append({
+    "point": "5",
+    "recommendation": "Integrasikan modul kapasitas resolusi ke dalam perencanaan inspeksi: verifikasi lead time historis sebelum jadwalkan inspeksi.",
+    "mitigation": "Bangun closed-loop system: setiap temuan baru harus diverifikasi capacity to close terlebih dahulu."
+})
 
-# Tampilkan — dua card terpisah
+# Tampilkan — Insight (1 card), Rekomendasi (1 card, tabel rapi)
 st.markdown(
     f"""
     <div class="card" style="
@@ -2179,14 +2234,24 @@ st.markdown(
         box-shadow: 0 2px 4px rgba(0,0,0,0.05);
     ">
         <h4 style="margin-top: 0; color: #1976d2;">Insight Summary</h4>
-        <p style="margin-bottom: 0;">{insight_text}</p>
+        <p style="margin-bottom: 0; line-height: 1.6;">{insight_text}</p>
     </div>
     """,
     unsafe_allow_html=True
 )
 
-st.markdown(
-    f"""
+# Rekomendasi dalam tabel rapi
+if rec_mitigation:
+    rows = []
+    for item in rec_mitigation:
+        rows.append(
+            f"<tr>"
+            f"<td style='text-align:center; font-weight:bold;'>{item['point']}</td>"
+            f"<td>{item['recommendation']}</td>"
+            f"<td>{item['mitigation']}</td>"
+            f"</tr>"
+        )
+    table_html = f"""
     <div class="card" style="
         background-color: #f0f7ff;
         border-left: 4px solid #4caf50;
@@ -2196,9 +2261,26 @@ st.markdown(
         box-shadow: 0 2px 4px rgba(0,0,0,0.05);
     ">
         <h4 style="margin-top: 0; color: #2e7d32;">Recommended Actions and Risk Mitigation Strategy</h4>
-        <p><strong>Recommended Actions:</strong> {recommendation_text}</p>
-        <p><strong>Risk Mitigation Strategy:</strong> {mitigation_text}</p>
+        <table style="width:100%; border-collapse:collapse; font-size:0.95em; margin-top:12px;">
+            <thead>
+                <tr style="background-color:#e3f2fd;">
+                    <th style="padding:10px; text-align:center; border:1px solid #ccc;">Point</th>
+                    <th style="padding:10px; text-align:left; border:1px solid #ccc;">Recommended Actions</th>
+                    <th style="padding:10px; text-align:left; border:1px solid #ccc;">Risk Mitigation Strategy</th>
+                </tr>
+            </thead>
+            <tbody>
+                {"".join(rows)}
+            </tbody>
+        </table>
     </div>
-    """,
-    unsafe_allow_html=True
-)
+    """
+    st.markdown(table_html, unsafe_allow_html=True)
+else:
+    st.markdown(
+        "<div class='card' style='background-color:#f0f7ff; border-left:4px solid #4caf50; padding:16px; margin-bottom:20px;'>"
+        "<h4 style='margin-top:0; color:#2e7d32;'>Recommended Actions and Risk Mitigation Strategy</h4>"
+        "<p>No actionable insights generated. Ensure data contains required columns.</p>"
+        "</div>",
+        unsafe_allow_html=True
+    )