Update app.py

app.py

@@ -1982,6 +1982,7 @@ 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) ===================
 
 
 def extract_critical_deviations(df: pd.DataFrame):
@@ -2010,7 +2011,6 @@ def extract_critical_deviations(df: pd.DataFrame):
         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()
-        # Ambil yang 0.95 ≤ ratio ≤ 1.05
         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()
 
@@ -2066,14 +2066,12 @@ def extract_critical_deviations(df: pd.DataFrame):
             if cat in cat_counts.index:
                 dev["obj4_unsafe_share"][cat] = round(cat_counts[cat], 1)
 
-    # === OBJ 5: Risk Matrix kuadran ===
-    # Gunakan logika yang sama seperti Objective 5 (X_LIMIT=20, Y_LIMIT=3)
+    # === OBJ 5: Risk Matrix kuadran (X_LIMIT=20, Y_LIMIT=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))
-        # Avg bulanan per divisi
         monthly_counts = df_risk.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')
@@ -2089,36 +2087,33 @@ def extract_critical_deviations(df: pd.DataFrame):
             elif cnt < X_LIMIT and lt >= Y_LIMIT:
                 dev["obj5_quadrant_II"].append(div)
 
-    # === OBJ 6: Whiteboard — 2 bubble terbesar (Avg/Month tertinggi) ===
+    # === 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']
+        df_nonpos = df[df['temuan_kategori'] != 'Positive'].copy()
         if not df_nonpos.empty:
-            start_month = df['created_at'].min().to_period('M')
-            end_month = df['created_at'].max().to_period('M')
-            n_months = len(pd.period_range(start=start_month, end=end_month, freq='M'))
-            cat_avg = (
-                df_nonpos.groupby('kategori').size() / n_months
-            ).sort_values(ascending=False).head(2)
-            dev["obj6_top2_bubbles"] = [(cat, round(val, 2)) for cat, val in cat_avg.items()]
+            start = df['created_at'].min().to_period('M')
+            end = df['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()]
 
     return dev
 
-# Jalankan ekstraksi
+# Jalankan ekstraksi deviasi
 deviations = extract_critical_deviations(df_filtered)
 
-# Bangun insight berbasis temuan nyata
+# Bangun Insight Summary
 insight_parts = []
-rec_parts = []
 
-# Objective 2
+# Obj 2: 9 lokasi ratio ~1.0
 if deviations["obj2_locations_ratio_1"]:
-    locs = ", ".join(deviations["obj2_locations_ratio_1"][:5])  # Tampilkan 5 saja di teks
+    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."
     )
 
-# Objective 3
+# 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.")
@@ -2132,13 +2127,13 @@ 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.")
 
-# Objective 4
+# 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.")
 
-# Objective 5
+# 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}.")
@@ -2146,7 +2141,7 @@ 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.")
 
-# Objective 6
+# Obj 6: Top 2 bubble
 if deviations["obj6_top2_bubbles"]:
     bub1, bub2 = deviations["obj6_top2_bubbles"]
     insight_parts.append(
@@ -2154,19 +2149,14 @@ if deviations["obj6_top2_bubbles"]:
         f"and {bub2[0]} ({bub2[1]}/month), indicating systemic root causes."
     )
 
-# Combine insight
 insight_text = " ".join(insight_parts) if insight_parts else "No significant deviations detected based on current filters."
 
-# Rekomendasi & Risk Mitigation
-rec_parts.append(
-    "Prioritize capacity assessment and coaching for divisions and individuals with lowest activity or longest resolution times."
-)
-rec_parts.append(
-    "Initiate root-cause analysis on top two high-frequency unsafe categories to prevent recurrence."
-)
-rec_parts.append(
+# 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."
-)
+]
 
 mitigation_parts = [
     "Establish SLA thresholds: max 7 days lead time, min 0.5 findings/reporter/month for active status.",
@@ -2177,7 +2167,7 @@ mitigation_parts = [
 recommendation_text = " ".join(rec_parts)
 mitigation_text = " ".join(mitigation_parts)
 
-# Tampilkan — SATU CARD INSIGHT, SATU CARD REKOMENDASI + MITIGASI
+# Tampilkan — dua card terpisah
 st.markdown(
     f"""
     <div class="card" style="