Update app.py

app.py

@@ -1985,63 +1985,205 @@ if not df_category.empty:
     # st.markdown(insight_text, unsafe_allow_html=True)
 else:
     st.info("No data available for non-positive issue categories with 100% coverage and positive trend.")
+
+# =================== OBJECTIVE 7 — Insight and Recommendation ===================
 st.markdown("<h3 class='section-title'>OBJECTIVE 7 — Insight and Recommendation</h3>", unsafe_allow_html=True)
 
-# === Ekstraksi Insight (sama seperti Anda) ===
+# ✅ Pastikan df_filtered tersedia
+if 'df_filtered' not in st.session_state:
+    st.error("⚠️ `df_filtered` not found in session state. Please ensure filters are applied.")
+    st.stop()
+df_filtered = st.session_state.df_filtered
+
+# ✅ Definisi fungsi — dipastikan di global scope
+def extract_agentic_insights_v5(df: pd.DataFrame):
+    dev = {
+        "lowest_ratio_9_locs": [],
+        "obj3a_lowest_div": None,
+        "obj3b_slowest_executor": None,
+        "obj3c_lowest_reporter": None,
+        "obj3d_slowest_div": None,
+        "obj4_unsafe_condition_pct": 0.0,
+        "obj4_unsafe_action_pct": 0.0,
+        "obj4_near_miss_pct": 0.0,
+        "obj5_q1_divs": [],
+        "obj5_q2_divs": [],
+        "obj6_top2_categories": [],
+    }
+
+    # === 1. 9 locations with lowest finding-to-reporter ratio ===
+    if {'nama_lokasi_full', 'creator_nid', 'created_at', 'kode_temuan'}.issubset(df.columns):
+        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 = monthly[monthly['reporters'] > 0]
+        monthly['ratio'] = monthly['findings'] / monthly['reporters']
+        loc_avg = monthly.groupby('nama_lokasi_full')['ratio'].mean()
+        lowest_9 = loc_avg.nsmallest(9)
+        dev["lowest_ratio_9_locs"] = [(loc, round(ratio, 2)) for loc, ratio in lowest_9.items()]
+
+    # === 2a: Division — lowest ratio ===
+    if {'nama', 'creator_nid', 'created_at', 'kode_temuan'}.issubset(df.columns):
+        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')
+        )
+        agg = agg[agg['reporters'] > 0].reset_index()
+        agg['ratio'] = agg['findings'] / agg['reporters']
+        div_ratio = agg.groupby('nama')['ratio'].mean()
+        if not div_ratio.empty:
+            name = div_ratio.idxmin()
+            val = round(div_ratio.min(), 2)
+            dev["obj3a_lowest_div"] = (name, val)
+
+    # === 2b: Executor — slowest resolution ===
+    if 'days_to_close' in df.columns:
+        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(), 2)
+                dev["obj3b_slowest_executor"] = (name, val)
+
+    # === 2c: Reporter — lowest frequency ===
+    if {'creator_name', 'created_at'}.issubset(df.columns):
+        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["obj3c_lowest_reporter"] = (name, val)
+
+    # === 2d: Division — slowest resolution ===
+    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(), 2)
+                dev["obj3d_slowest_div"] = (name, val)
+
+    # === 3. Non-Positive composition ===
+    if 'temuan_kategori' in df.columns:
+        cnt = df['temuan_kategori'].value_counts(normalize=True) * 100
+        dev["obj4_unsafe_condition_pct"] = round(cnt.get("Unsafe Condition", 0), 2)
+        dev["obj4_unsafe_action_pct"] = round(cnt.get("Unsafe Action", 0), 2)
+        dev["obj4_near_miss_pct"] = round(cnt.get("Near Miss", 0), 2)
+
+    # === 4. Risk Quadrants ===
+    X_LIMIT, Y_LIMIT = 20, 3
+    if {'nama', 'created_at', 'days_to_close', 'kode_temuan'}.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 = 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_q1_divs"].append(r['nama'])
+            elif r['Finding Count'] < X_LIMIT and r['Avg Lead Time'] >= Y_LIMIT:
+                dev["obj5_q2_divs"].append(r['nama'])
+
+    # === 5. Top 2 non-Positive categories ===
+    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 = (nonpos.groupby('kategori').size() / n_months).sort_values(ascending=False).head(2)
+            dev["obj6_top2_categories"] = [(cat, round(val, 2)) for cat, val in cat_avg.items()]
+
+    return dev
+
+# === Jalankan ekstraksi ===
 dev = extract_agentic_insights_v5(df_filtered)
 
-# === Buat List Insight & Rekomendasi Spesifik (perbaiki duplikasi) ===
+# === Siapkan entri tabel ===
 entries = []
 
 # 1. Low-ratio locations
 if dev["lowest_ratio_9_locs"]:
-    loc_list = ", ".join([f"<strong>{loc}</strong> ({ratio:.2f})" for loc, ratio in dev["lowest_ratio_9_locs"]])
-    insight = f"Nine locations with the <em>lowest</em> finding-to-reporter ratio: {loc_list}."
-    rec = "Launch <em>Agency Activation Sprint</em>: assign Safety Champions to conduct ≥1 spot inspection/week per site."
-    mit = "Deploy QR-code checklists + automated WhatsApp reminders. Target: ratio ≥0.5 within 45 days."
-    entries.append({"Risk Category": "Reporting Coverage Risk", "Insight": insight, "Recommendation": rec, "Mitigation": mit})
+    loc_list = ", ".join([f"{loc} ({ratio:.2f})" for loc, ratio in dev["lowest_ratio_9_locs"]])
+    entries.append({
+        "Risk Category": "Reporting Coverage Risk",
+        "Insight": f"Nine locations with the lowest finding-to-reporter ratio: {loc_list}.",
+        "Recommendation": "Launch <em>Agency Activation Sprint</em>: assign Safety Champions to conduct ≥1 spot inspection/week per site.",
+        "Mitigation": "Deploy QR-code checklists + automated WhatsApp reminders. Target: ratio ≥0.5 within 45 days."
+    })
 
 # 2. Capacity imbalance
 parts = []
 if dev["obj3a_lowest_div"]:
-    parts.append(f"division <strong>{dev['obj3a_lowest_div'][0]}</strong> (ratio: {dev['obj3a_lowest_div'][1]:.2f})")
+    name, val = dev["obj3a_lowest_div"]
+    parts.append(f"division <strong>{name}</strong> (ratio: {val:.2f})")
 if dev["obj3c_lowest_reporter"]:
-    parts.append(f"reporter <strong>{dev['obj3c_lowest_reporter'][0]}</strong> ({dev['obj3c_lowest_reporter'][1]:.2f}/month)")
+    name, val = dev["obj3c_lowest_reporter"]
+    parts.append(f"reporter <strong>{name}</strong> ({val:.2f} findings/month)")
 if dev["obj3d_slowest_div"]:
-    parts.append(f"division <strong>{dev['obj3d_slowest_div'][0]}</strong> (avg. resolution: {dev['obj3d_slowest_div'][1]:.2f} days)")
+    name, val = dev["obj3d_slowest_div"]
+    parts.append(f"division <strong>{name}</strong> (avg. resolution: {val:.2f} days)")
 if dev["obj3b_slowest_executor"]:
-    parts.append(f"executor <strong>{dev['obj3b_slowest_executor'][0]}</strong> (avg. resolution: {dev['obj3b_slowest_executor'][1]:.2f} days)")
+    name, val = dev["obj3b_slowest_executor"]
+    parts.append(f"executor <strong>{name}</strong> (avg. resolution: {val:.2f} days)")
 
 if parts:
-    insight = f"Uneven operational capacity: {'; '.join(parts)}."
-    rec = "Activate <em>Agentic Capacity Dashboard</em> for real-time monitoring of reporting & resolution KPIs."
-    mit = "Auto-trigger coaching alerts to Area PICs if deviation >20% from baseline, with peer benchmarking."
-    entries.append({"Risk Category": "Capacity Imbalance Risk", "Insight": insight, "Recommendation": rec, "Mitigation": mit})
+    insight = f"Uneven operational capacity detected: {'; '.join(parts)}."
+    entries.append({
+        "Risk Category": "Capacity Imbalance Risk",
+        "Insight": insight,
+        "Recommendation": "Activate <em>Agentic Capacity Dashboard</em> for real-time monitoring of reporting & resolution KPIs.",
+        "Mitigation": "Auto-trigger coaching alerts to Area PICs if deviation >20% from baseline, with peer benchmarking."
+    })
 
 # 3. Non-Positive composition
 uc, ua, nm = dev["obj4_unsafe_condition_pct"], dev["obj4_unsafe_action_pct"], dev["obj4_near_miss_pct"]
 if uc + ua + nm > 0:
     insight = f"Non-Positive finding composition: Unsafe Condition ({uc:.2f}%), Unsafe Action ({ua:.2f}%), Near Miss ({nm:.2f}%)."
-    rec = "Enforce photo-based validation for all Unsafe Condition/Action/Near Miss submissions."
-    mit = "System blocks submission if photo evidence or justification is missing."
-    entries.append({"Risk Category": "Data Quality & Categorization Risk", "Insight": insight, "Recommendation": rec, "Mitigation": mit})
+    entries.append({
+        "Risk Category": "Data Quality & Categorization Risk",
+        "Insight": insight,
+        "Recommendation": "Enforce photo-based validation for all Unsafe Condition/Action/Near Miss submissions.",
+        "Mitigation": "System blocks submission if photo evidence or justification is missing."
+    })
 
 # 4. Risk Quadrants
 if dev["obj5_q1_divs"] or dev["obj5_q2_divs"]:
-    q1 = ", ".join([f"<strong>{d}</strong>" for d in dev["obj5_q1_divs"][:3]]) or "—"
-    q2 = ", ".join([f"<strong>{d}</strong>" for d in dev["obj5_q2_divs"][:3]]) or "—"
+    q1 = ", ".join([f"{d}" for d in dev["obj5_q1_divs"][:3]]) or "—"
+    q2 = ", ".join([f"{d}" for d in dev["obj5_q2_divs"][:3]]) or "—"
     insight = f"High-risk divisions (Q1): {q1}; Hidden-risk divisions (Q2): {q2}."
-    rec = "Assign dedicated safety crews to QI divisions; enforce <em>One Finding, One Day</em> closure for QII."
-    mit = "Auto-generate executive escalation reports to VP Ops if any division remains in QI/QII ≥2 months."
-    entries.append({"Risk Category": "SLA & Backlog Risk", "Insight": insight, "Recommendation": rec, "Mitigation": mit})
+    entries.append({
+        "Risk Category": "SLA & Backlog Risk",
+        "Insight": insight,
+        "Recommendation": "Assign dedicated safety crews to QI divisions; enforce <em>One Finding, One Day</em> closure for QII.",
+        "Mitigation": "Auto-generate executive escalation reports to VP Ops if any division remains in QI/QII ≥2 months."
+    })
 
 # 5. Top categories
 if dev["obj6_top2_categories"]:
     c1, c2 = dev["obj6_top2_categories"]
     insight = f"Top recurring non-Positive categories: <strong>{c1[0]}</strong> ({c1[1]:.2f}/month) and <strong>{c2[0]}</strong> ({c2[1]:.2f}/month)."
-    rec = f"Form cross-functional <em>RCA Task Force</em> (Civil, Electrical, HSE, Contractors) for <strong>{c1[0]}</strong> and <strong>{c2[0]}</strong>."
-    mit = "Update tender templates: all bids must include mitigations for these historical finding categories."
-    entries.append({"Risk Category": "Recurring Hazard Risk", "Insight": insight, "Recommendation": rec, "Mitigation": mit})
+    entries.append({
+        "Risk Category": "Recurring Hazard Risk",
+        "Insight": insight,
+        "Recommendation": f"Form cross-functional <em>RCA Task Force</em> (Civil, Electrical, HSE, Contractors) for <strong>{c1[0]}</strong> and <strong>{c2[0]}</strong>.",
+        "Mitigation": "Update tender templates: all bids must include historical mitigations for these categories."
+    })
 
 # === RENDER TABEL TERPADU ===
 if entries:
@@ -2083,4 +2225,4 @@ if entries:
     """
     st.markdown(table_html, unsafe_allow_html=True)
 else:
-    st.info("ℹ️ No actionable insights generated. Ensure required columns exist.")
+    st.info("ℹ️ No actionable insights generated. Ensure required columns exist.")