Update app.py

app.py

@@ -1985,337 +1985,102 @@ 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 (Agentic AI LLM Style — Final) ===================
-# =================== OBJECTIVE 7 — Insight and Recommendation (Final — Agentic AI, No markdown bold) ===================
-# =================== OBJECTIVE 7 — Insight and Recommendation (FINAL — 3 Cards + Phi-3-mini) ===================
-import streamlit as st
-import pandas as pd
-import re
-import os
-
-# ✅ SIMPAN df_filtered KE SESSION STATE (harus dilakukan SEBELUM Objective 7)
-# Letakkan ini tepat setelah filtering di sidebar (setelah `submit_clicked = ...`)
-st.session_state.df_filtered = df_filtered  # <-- BARIS INI WAJIB ADA!
-
-# ==============================
-# 1. IMPORT & LLM LOADING (cached)
-# ==============================
-try:
-    from transformers import pipeline
-except ImportError:
-    st.error("❌ `transformers` not installed. Run: `pip install transformers torch accelerate sentencepiece einops`")
-    pipe = None
-else:
-    @st.cache_resource
-    def load_llm():
-        try:
-            st.info("🧠 Loading Phi-3-mini-4k-instruct (optimized for safety recommendations)...")
-            pipe = pipeline(
-                "text-generation",
-                model="microsoft/Phi-3-mini-4k-instruct",
-                device_map="auto",
-                torch_dtype="auto",
-                trust_remote_code=True,
-                max_new_tokens=256
-            )
-            st.success("✅ Phi-3-mini loaded!")
-            return pipe
-        except Exception as e:
-            st.error(f"❌ Failed to load model: {e}")
-            return None
-    pipe = load_llm()
-
-# ==============================
-# 2. INSIGHT EXTRACTION (sama seperti kode Anda — diperbaiki ke 2 desimal)
-# ==============================
-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
-
-# ==============================
-# 3. LLM UTILS (aman, fallback-ready)
-# ==============================
-def generate_llm_text(insight: str, mode: str = "rec") -> str:
-    if pipe is None:
-        mode_map = {"rec": "Recommend action", "mit": "Mitigation strategy"}
-        return f"[LLM disabled] {mode_map[mode]} for: {insight[:50]}..."
-    
-    suffix = "Recommend a single high-leverage action." if mode == "rec" else "Propose one automated/systemic risk control."
-    messages = [
-        {"role": "system", "content": "You are PLN's Lead Safety AI. Output ONLY a short, professional sentence. Be directive. No markdown, no emoticons."},
-        {"role": "user", "content": f"Insight: {insight}\n\n{suffix}"}
-    ]
-    try:
-        out = pipe(
-            messages,
-            do_sample=False,
-            temperature=0.1,
-            return_full_text=False
-        )
-        text = out[0]["generated_text"].strip()
-        text = re.sub(r"^(Recommendation|Mitigation|Action|Control):\s*", "", text, flags=re.IGNORECASE)
-        text = re.sub(r"[\n\"`*]", " ", text).strip(". ")
-        return text[:250]
-    except Exception as e:
-        # Fallback aman (tetap sesuai gaya Anda)
-        fallbacks = {
-            ("1", "rec"): "Launch Agency Activation Sprint: ≥1 spot inspection/week per low-ratio location.",
-            ("1", "mit"): "Deploy QR-code checklists + automated reminders; target ratio ≥0.5 in 45 days.",
-            ("2", "rec"): "Activate Agentic Capacity Dashboard for real-time monitoring of reporter engagement and resolution efficiency.",
-            ("2", "mit"): "Auto-trigger coaching alerts if performance deviates >20% from divisional baseline.",
-            ("3", "rec"): "Enforce photo-based validation for all Unsafe Condition/Action/Near Miss submissions.",
-            ("3", "mit"): "System blocks submission if photo evidence or justification is missing.",
-            ("4", "rec"): "Assign dedicated safety crews to Quadrant I; enforce ‘One Finding, One Day’ closure for Quadrant II.",
-            ("4", "mit"): "Auto-generate VP escalation reports if division remains in risk quadrant ≥2 months.",
-            ("5", "rec"): "Form cross-functional RCA Task Force (Civil, Electrical, HSE, Contractors) for top recurring categories.",
-            ("5", "mit"): "Update tender templates: all bids must include mitigations for these historical findings.",
-        }
-        idx = str(len(insight_list) + 1) if 'insight_list' in locals() else "1"
-        return fallbacks.get((idx, mode), f"Review insight and implement targeted action for: {insight[:30]}...")
-
-# ==============================
-# 4. RUN & RENDER
-# ==============================
 st.markdown("<h3 class='section-title'>OBJECTIVE 7 — Insight and Recommendation</h3>", unsafe_allow_html=True)
 
-# Ambil df_filtered dari session state
-if 'df_filtered' not in st.session_state:
-    st.error("⚠️ `df_filtered` not found in session state. Please apply filters first.")
-    st.stop()
-
-df_filtered = st.session_state.df_filtered
+# === Ekstraksi Insight (sama seperti Anda) ===
 dev = extract_agentic_insights_v5(df_filtered)
 
-# === BUILD INSIGHT LINES ===
-insight_lines = []
+# === Buat List Insight & Rekomendasi Spesifik (perbaiki duplikasi) ===
+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_lines.append(f"1. Nine locations with the <em>lowest</em> finding-to-reporter ratio: {loc_list}.")
+    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})
 
+# 2. Capacity imbalance
 parts = []
 if dev["obj3a_lowest_div"]:
-    name, val = dev["obj3a_lowest_div"]
-    parts.append(f"division <strong>{name}</strong> (ratio: {val:.2f})")
+    parts.append(f"division <strong>{dev['obj3a_lowest_div'][0]}</strong> (ratio: {dev['obj3a_lowest_div'][1]:.2f})")
 if dev["obj3c_lowest_reporter"]:
-    name, val = dev["obj3c_lowest_reporter"]
-    parts.append(f"reporter <strong>{name}</strong> ({val:.2f} findings/month)")
+    parts.append(f"reporter <strong>{dev['obj3c_lowest_reporter'][0]}</strong> ({dev['obj3c_lowest_reporter'][1]:.2f}/month)")
 if dev["obj3d_slowest_div"]:
-    name, val = dev["obj3d_slowest_div"]
-    parts.append(f"division <strong>{name}</strong> (avg. resolution: {val:.2f} days)")
+    parts.append(f"division <strong>{dev['obj3d_slowest_div'][0]}</strong> (avg. resolution: {dev['obj3d_slowest_div'][1]:.2f} days)")
 if dev["obj3b_slowest_executor"]:
-    name, val = dev["obj3b_slowest_executor"]
-    parts.append(f"executor <strong>{name}</strong> (avg. resolution: {val:.2f} days)")
+    parts.append(f"executor <strong>{dev['obj3b_slowest_executor'][0]}</strong> (avg. resolution: {dev['obj3b_slowest_executor'][1]:.2f} days)")
 
 if parts:
-    insight_lines.append(
-        f"2. Uneven operational capacity detected: {'; '.join(parts)}. "
-        "This indicates systemic imbalance in reporting engagement and resolution efficiency."
-    )
+    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})
 
+# 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_lines.append(
-        f"3. Non-Positive finding composition: Unsafe Condition ({uc:.2f}%), Unsafe Action ({ua:.2f}%), Near Miss ({nm:.2f}%)."
-    )
+    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})
 
+# 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 "—"
-    insight_lines.append(f"4. High-risk divisions (Q1): {q1}; Hidden-risk divisions (Q2): {q2}.")
+    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})
 
+# 5. Top categories
 if dev["obj6_top2_categories"]:
     c1, c2 = dev["obj6_top2_categories"]
-    insight_lines.append(
-        f"5. Top two recurring non-Positive categories: <strong>{c1[0]}</strong> ({c1[1]:.2f}/month) and <strong>{c2[0]}</strong> ({c2[1]:.2f}/month)."
-    )
-
-insight_text = "<br>".join(insight_lines)
-
-# === RENDER 3 CARDS ===
-# Card 1: Insight
-st.markdown(
-    f"""
+    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})
+
+# === RENDER TABEL TERPADU ===
+if entries:
+    rows = []
+    for e in entries:
+        rows.append(f"""
+        <tr>
+            <td style="padding:12px; font-weight:bold; vertical-align:top; background-color:#f8f9fa;">{e['Risk Category']}</td>
+            <td style="padding:12px; vertical-align:top; line-height:1.5;">{e['Insight']}</td>
+            <td style="padding:12px; vertical-align:top; line-height:1.5; color:#2E7D32;"><strong>▶</strong> {e['Recommendation']}</td>
+            <td style="padding:12px; vertical-align:top; line-height:1.5; color:#1976D2;"><strong>✓</strong> {e['Mitigation']}</td>
+        </tr>
+        """)
+
+    table_html = f"""
     <div class="card" style="
-        background-color: #f8f9fa;
+        background-color: white;
         border-left: 5px solid #003DA5;
         padding: 20px;
         margin-bottom: 24px;
         border-radius: 6px;
-        box-shadow: 0 3px 6px rgba(0,0,0,0.06);
+        box-shadow: 0 3px 8px rgba(0,0,0,0.08);
     ">
-        <h4 style="margin-top: 0; color: #003DA5; text-align: center;">🔍 Insight Summary</h4>
-        <p style="margin-bottom: 0; line-height: 1.6; font-size: 0.98em;">{insight_text}</p>
+        <h4 style="margin-top: 0; color: #003DA5; text-align: center;">🔍 Objective 7 — Risk-Based Insight, Recommendation & Mitigation</h4>
+        <table style="width:100%; border-collapse:collapse; font-size:0.95em; margin-top:16px;">
+            <thead>
+                <tr style="background-color:#e3f2fd;">
+                    <th style="padding:12px; text-align:center; border:1px solid #ccc; font-weight:600; color:#0D47A1;">Risk Category</th>
+                    <th style="padding:12px; text-align:left;   border:1px solid #ccc; font-weight:600; color:#0D47A1;">Insight</th>
+                    <th style="padding:12px; text-align:left;   border:1px solid #ccc; font-weight:600; color:#2E7D32;">Recommendation</th>
+                    <th style="padding:12px; text-align:left;   border:1px solid #ccc; font-weight:600; color:#0D47A1;">Risk Mitigation Strategy</th>
+                </tr>
+            </thead>
+            <tbody>
+                {"".join(rows)}
+            </tbody>
+        </table>
     </div>
-    """,
-    unsafe_allow_html=True
-)
-
-# Card 2 & 3: Recommendation + Mitigation (only if insights exist)
-if insight_lines:
-    rec_list, mit_list = [], []
-    with st.spinner("🧠 Generating Recommendation & Risk Mitigation with Phi-3-mini..."):
-        for i, ins in enumerate(insight_lines, 1):
-            clean_ins = re.sub(r"<[^>]+>", "", ins)
-            # Hapus nomor urut depan (misal "1. ", "2. ")
-            for prefix in ["1. ", "2. ", "3. ", "4. ", "5. "]:
-                if clean_ins.startswith(prefix):
-                    clean_ins = clean_ins[len(prefix):]
-                    break
-            clean_ins = clean_ins.strip()
-            rec = generate_llm_text(clean_ins, "rec")
-            mit = generate_llm_text(clean_ins, "mit")
-            rec_list.append(f"{i}. {rec}")
-            mit_list.append(f"{i}. {mit}")
-
-    rec_text = "<br>".join(rec_list)
-    mit_text = "<br>".join(mit_list)
-
-    # Card 2: Recommendation
-    st.markdown(
-        f"""
-        <div class="card" style="
-            background-color: #e8f5e9;
-            border-left: 5px solid #4CAF50;
-            padding: 20px;
-            margin-bottom: 24px;
-            border-radius: 6px;
-            box-shadow: 0 3px 6px rgba(0,0,0,0.06);
-        ">
-            <h4 style="margin-top: 0; color: #2E7D32; text-align: center;">✅ Recommendation</h4>
-            <p style="margin-bottom: 0; line-height: 1.6; font-size: 0.98em;">{rec_text}</p>
-        </div>
-        """,
-        unsafe_allow_html=True
-    )
-
-    # Card 3: Risk Mitigation
-    st.markdown(
-        f"""
-        <div class="card" style="
-            background-color: #e3f2fd;
-            border-left: 5px solid #1976D2;
-            padding: 20px;
-            margin-bottom: 24px;
-            border-radius: 6px;
-            box-shadow: 0 3px 6px rgba(0,0,0,0.06);
-        ">
-            <h4 style="margin-top: 0; color: #0D47A1; text-align: center;">🛡️ Risk Mitigation Strategy</h4>
-            <p style="margin-bottom: 0; line-height: 1.6; font-size: 0.98em;">{mit_text}</p>
-        </div>
-        """,
-        unsafe_allow_html=True
-    )
+    """
+    st.markdown(table_html, unsafe_allow_html=True)
 else:
-    st.info("ℹ️ No insights generated. Ensure required columns are present in the dataset.")
+    st.info("ℹ️ No actionable insights generated. Ensure required columns exist.")