Update app.py

app.py

@@ -1122,7 +1122,7 @@ try:
     # ================================
     # 12. DISPLAY TABLE
     # ================================
-    st.subheader("Operator Risk Summary Table (8 Weeks Observed)")
+    st.subheader("Operator Hazard Summary Table (8 Weeks Observed)")
     table_display = (
         risk_matrix[[
             "Operator Name",
@@ -1546,7 +1546,7 @@ else:
                 for insight in ob_insights:
                     st.markdown(f"""
                     <div class="ai-insight-box">
-                        <div class="ai-insight-title">Risk Summary</div>
+                        <div class="ai-insight-title">Hazard Summary</div>
                         <p>{insight}</p>
                     </div>
                     """, unsafe_allow_html=True)
@@ -1573,7 +1573,7 @@ else:
                 for insight in coal_insights:
                     st.markdown(f"""
                     <div class="ai-insight-box">
-                        <div class="ai-insight-title">Risk Summary</div>
+                        <div class="ai-insight-title">Hazard Summary</div>
                         <p>{insight}</p>
                     </div>
                     """, unsafe_allow_html=True)
@@ -1661,213 +1661,219 @@ else:
 # =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
 st.subheader("OBJECTIVE 6: Instant Insights & Recommendations")
 
-# Membagi tampilan menjadi dua kolom
-col_insights, col_recs = st.columns(2)
-
-# Kolom kiri: Insights by Advanced Analytics
-with col_insights:
-    st.subheader("Insights by Advanced Analytics")
-
-    # 1. Critical Hour Analysis (2-5 AM)
-    critical_hours = [2, 3, 4, 5]
-    critical_alerts = df[df['hour'].isin(critical_hours)]
-    critical_pct = (len(critical_alerts) / len(df)) * 100 if len(df) > 0 else 0
-
-    st.markdown(f"**Critical Hour Risk (3-6 AM)**")
-    # Use conditional formatting for background color
-    bg_color = "#ffcccc" if critical_pct > 50 else "#ffebcc" if critical_pct > 25 else "#ffffcc" if critical_pct > 10 else "#e6ffe6"
-    
-    # ✅ Highlight percentage in red
-    st.markdown(
-        f'<div style="background-color: {bg_color}; padding: 10px; border-radius: 5px;">'
-        f'Critical Hour Alerts: {len(critical_alerts)} '
-        f'<span style="color:#d32f2f; font-weight:bold;">({critical_pct:.1f}% of total alerts)</span>'
-        '</div>',
-        unsafe_allow_html=True
-    )
-    
-    if critical_pct > 10:
-        st.warning(f"High risk: <span style='color:#d32f2f'>{critical_pct:.1f}%</span> of fatigue alerts occur during critical hours (3-6 AM). This is a known circadian dip period.", icon="⚠️")
-    else:
-        st.info(f"<span style='color:#d32f2f'>{critical_pct:.1f}%</span> of alerts occur during critical hours. This is within acceptable range.")
+try:
+    # Membagi tampilan menjadi dua kolom
+    col_insights, col_recs = st.columns(2)
 
-    # 2. High-Speed Fatigue Analysis
-    if col_speed and col_speed in df.columns:
-        high_speed_threshold = df[col_speed].quantile(0.75) if not df[col_speed].dropna().empty else 0
-        high_speed_fatigue = df[df[col_speed] >= high_speed_threshold] if high_speed_threshold > 0 else pd.DataFrame()
-        high_speed_pct = (len(high_speed_fatigue) / len(df)) * 100 if len(df) > 0 else 0
-        
-        st.markdown(f"**High-Speed Fatigue Risk (Speed > {high_speed_threshold:.0f} km/h)**")
+    # Kolom kiri: Insights by Advanced Analytics
+    with col_insights:
+        st.subheader("Insights by Advanced Analytics")
+
+        # 1. Critical Hour Analysis (2-5 AM)
+        critical_hours = [2, 3, 4, 5]
+        critical_alerts = df[df['hour'].isin(critical_hours)]
+        critical_pct = (len(critical_alerts) / len(df)) * 100 if len(df) > 0 else 0
+
+        st.markdown(f"**Critical Hour Risk (3-6 AM)**")
+        # Use conditional formatting for background color
+        bg_color = "#ffcccc" if critical_pct > 50 else "#ffebcc" if critical_pct > 25 else "#ffffcc" if critical_pct > 10 else "#e6ffe6"
         
-        # ✅ st.metric doesn't support HTML, so replace with markdown
+        # ✅ Highlight percentage in red using markdown
         st.markdown(
-            f"<div style='font-size:1.1em; margin:8px 0;'>"
-            f"High-Speed Fatigue Events: <b>{len(high_speed_fatigue)}</b> "
-            f"<span style='color:#d32f2f; font-weight:bold;'>({high_speed_pct:.1f}% of total alerts)</span>"
-            "</div>",
+            f'<div style="background-color: {bg_color}; padding: 10px; border-radius: 5px;">'
+            f'Critical Hour Alerts: {len(critical_alerts)} '
+            f'<span style="color:#d32f2f; font-weight:bold;">({critical_pct:.1f}% of total alerts)</span>'
+            '</div>',
             unsafe_allow_html=True
         )
         
-        if high_speed_pct > 20:
-            st.warning(f"High risk: <span style='color:#d32f2f'>{high_speed_pct:.1f}%</span> of fatigue alerts occur at high speeds. This increases accident severity potential.")
+        # ✅ Gunakan st.markdown untuk menampilkan peringatan/info dengan HTML
+        if critical_pct > 10:
+            st.markdown(f"⚠️ <span style='color:#d32f2f; font-weight:bold;'>High risk: {critical_pct:.1f}%</span> of fatigue alerts occur during critical hours (3-6 AM). This is a known circadian dip period.", unsafe_allow_html=True)
         else:
-            st.info(f"<span style='color:#d32f2f'>{high_speed_pct:.1f}%</span> of alerts occur at high speeds. This is within acceptable range.")
+            st.markdown(f"<span style='color:#d32f2f; font-weight:bold;'>{critical_pct:.1f}%</span> of alerts occur during critical hours. This is within acceptable range.", unsafe_allow_html=True)
 
-    # 3. Shift Pattern Analysis
-    if col_shift and col_shift in df.columns:
-        shift_counts = df[col_shift].value_counts()
-        st.markdown(f"**Shift Pattern Risk**")
-        
-        for shift_val in shift_counts.index:
-            shift_pct = (shift_counts[shift_val] / len(df)) * 100
-            # ✅ Replace st.metric with red-percentage version
-            st.markdown(
-                f"**Shift {shift_val} Alerts**<br>"
-                f"{shift_counts[shift_val]} "
-                f'<span style="color:#d32f2f; font-weight:bold;">({shift_pct:.1f}% of total alerts)</span>',
-                unsafe_allow_html=True
-            )
+        # 2. High-Speed Fatigue Analysis
+        if col_speed and col_speed in df.columns:
+            high_speed_threshold = df[col_speed].quantile(0.75) if not df[col_speed].dropna().empty else 0
+            high_speed_fatigue = df[df[col_speed] >= high_speed_threshold] if high_speed_threshold > 0 else pd.DataFrame()
+            high_speed_pct = (len(high_speed_fatigue) / len(df)) * 100 if len(df) > 0 else 0
             
-            if shift_pct > 50:
-                st.warning(f"Shift {shift_val} has disproportionately high alerts (<span style='color:#d32f2f'>{shift_pct:.1f}%</span>). Review shift scheduling and workload.")
-            else:
-                st.info(f"Shift {shift_val} alert distribution is acceptable (<span style='color:#d32f2f'>{shift_pct:.1f}%</span>).")
-
-    # 4. Operator Risk Profiling
-    if col_operator and col_operator in df.columns:
-        operator_alerts = df[col_operator].value_counts()
-        top_risk_operators = operator_alerts.head(5)
-        st.markdown(f"**High-Risk Operator Identification**")
-        
-        for op_name, count in top_risk_operators.items():
-            op_pct = (count / len(df)) * 100
+            st.markdown(f"**High-Speed Fatigue Risk (Speed > {high_speed_threshold:.0f} km/h)**")
+            
+            # ✅ st.metric doesn't support HTML, so replace with markdown
             st.markdown(
-                f"**Operator: {op_name}**<br>"
-                f"{count} alerts "
-                f'<span style="color:#d32f2f; font-weight:bold;">({op_pct:.1f}% of total alerts)</span>',
+                f"<div style='font-size:1.1em; margin:8px 0;'>"
+                f"High-Speed Fatigue Events: <b>{len(high_speed_fatigue)}</b> "
+                f"<span style='color:#d32f2f; font-weight:bold;'>({high_speed_pct:.1f}% of total alerts)</span>"
+                "</div>",
                 unsafe_allow_html=True
             )
             
-            if op_pct > 5:
-                st.warning(f"Operator {op_name} has high fatigue risk (<span style='color:#d32f2f'>{op_pct:.1f}%</span> of alerts). Consider coaching or rest plan.")
+            if high_speed_pct > 20:
+                st.markdown(f"High risk: <span style='color:#d32f2f; font-weight:bold;'>{high_speed_pct:.1f}%</span> of fatigue alerts occur at high speeds. This increases accident severity potential.", unsafe_allow_html=True)
             else:
-                st.info(f"Operator {op_name} fatigue risk is within acceptable range (<span style='color:#d32f2f'>{op_pct:.1f}%</span>).")
+                st.markdown(f"<span style='color:#d32f2f; font-weight:bold;'>{high_speed_pct:.1f}%</span> of alerts occur at high speeds. This is within acceptable range.", unsafe_allow_html=True)
 
-    else:
-        st.info("Operator data not available for Operator Risk Profiling.")
+        # 3. Shift Pattern Analysis
+        if col_shift and col_shift in df.columns:
+            shift_counts = df[col_shift].value_counts()
+            st.markdown(f"**Shift Pattern Risk**")
+            
+            for shift_val in shift_counts.index:
+                shift_pct = (shift_counts[shift_val] / len(df)) * 100
+                # ✅ Replace st.metric with red-percentage version
+                st.markdown(
+                    f"**Shift {shift_val} Alerts**<br>"
+                    f"{shift_counts[shift_val]} "
+                    f'<span style="color:#d32f2f; font-weight:bold;">({shift_pct:.1f}% of total alerts)</span>',
+                    unsafe_allow_html=True
+                )
+                
+                if shift_pct > 50:
+                    st.markdown(f"Shift {shift_val} has disproportionately high alerts (<span style='color:#d32f2f; font-weight:bold;'>{shift_pct:.1f}%</span>). Review shift scheduling and workload.", unsafe_allow_html=True)
+                else:
+                    st.markdown(f"Shift {shift_val} alert distribution is acceptable (<span style='color:#d32f2f; font-weight:bold;'>{shift_pct:.1f}%</span>).", unsafe_allow_html=True)
 
-# Kolom kanan: AI Recommendations
-with col_recs:
-    st.subheader("Recommendations")
-    ai_recs = []
-    insights_found = []
+        # 4. Operator Risk Profiling
+        if col_operator and col_operator in df.columns:
+            operator_alerts = df[col_operator].value_counts()
+            top_risk_operators = operator_alerts.head(5)
+            st.markdown(f"**High-Risk Operator Identification**")
+            
+            for op_name, count in top_risk_operators.items():
+                op_pct = (count / len(df)) * 100
+                st.markdown(
+                    f"**Operator: {op_name}**<br>"
+                    f"{count} alerts "
+                    f'<span style="color:#d32f2f; font-weight:bold;">({op_pct:.1f}% of total alerts)</span>',
+                    unsafe_allow_html=True
+                )
+                
+                if op_pct > 5:
+                    st.markdown(f"Operator {op_name} has high fatigue risk (<span style='color:#d32f2f; font-weight:bold;'>{op_pct:.1f}%</span> of alerts). Consider coaching or rest plan.", unsafe_allow_html=True)
+                else:
+                    st.markdown(f"Operator {op_name} fatigue risk is within acceptable range (<span style='color:#d32f2f; font-weight:bold;'>{op_pct:.1f}%</span>).", unsafe_allow_html=True)
 
-    # Peak hour
-    if "hour" in df.columns and not df.empty:
-        peak_hour = df["hour"].value_counts().idxmax()
-        critical_hours = [2, 3, 4, 5]
-        if peak_hour in critical_hours:
-            insights_found.append(f"Most fatigue risk occurs at **{peak_hour}:00** — during critical circadian low period (3-6 AM). Consider enhanced monitoring.")
         else:
-            insights_found.append(f"Most fatigue risk occurs at **{peak_hour}:00** — likely due to circadian drop.")
-
-    # Risk shift
-    if col_shift and not df.empty:
-        worst_shift = df[col_shift].value_counts().idxmax()
-        insights_found.append(f"Highest fatigue recorded in **Shift {worst_shift}** — review scheduling & workload.")
-
-    # Worst operator
-    if col_operator and not df.empty:
-        worst_operator = df[col_operator].value_counts().idxmax()
-        insights_found.append(f"Operator at highest risk: **{worst_operator}** — suggested coaching or rest plan.")
-
-    # Duration risk
-    if "duration_sec" in df.columns and not df.empty:
-        avg_duration = df["duration_sec"].mean()
-        if not pd.isna(avg_duration) and avg_duration > 10:
-            insights_found.append("Long fatigue event duration suggests slow response — improve alerting training.")
-
-    # Recommendations based on insights
-    if insights_found:
-        if any("circadian low" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Deploy enhanced fatigue monitoring systems (e.g., EOR) specifically during 3-6 AM shifts.",
-                "data_point": f"Critical Hour Alerts: {len(critical_alerts)} "
-                              f"<span style='color:#d32f2f;'>({critical_pct:.1f}% of total alerts)</span>",
-                "reason": "High percentage of alerts during circadian low period (3–6 AM) indicates elevated risk."
-            })
-        if any("shift" in i.lower() for i in insights_found):
-            pct = (df[col_shift].value_counts()[worst_shift] / len(df)) * 100
-            ai_recs.append({
-                "recommendation": "Review shift rotation schedules to minimize consecutive high-risk shifts.",
-                "data_point": f"Shift {worst_shift} Alerts: {df[col_shift].value_counts()[worst_shift]} "
-                              f"<span style='color:#d32f2f;'>({pct:.1f}% of total alerts)</span>",
-                "reason": f"Shift {worst_shift} accounts for a disproportionate share of fatigue events."
-            })
-        if any("operator" in i.lower() for i in insights_found):
-            pct = (df[col_operator].value_counts()[worst_operator] / len(df)) * 100
-            ai_recs.append({
-                "recommendation": "Initiate individual coaching or mandatory rest periods for high-risk operators.",
-                "data_point": f"Operator {worst_operator} Alerts: {df[col_operator].value_counts()[worst_operator]} "
-                              f"<span style='color:#d32f2f;'>({pct:.1f}% of total alerts)</span>",
-                "reason": f"Individual intervention needed to mitigate recurrence risk."
-            })
-        if any("duration" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Review and improve alert response protocols and training.",
-                "data_point": f"Average Fatigue Event Duration: {avg_duration:.2f} seconds",
-                "reason": "Long duration suggests delayed response — requires procedural review."
-            })
-        if any("high-speed" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Implement speed management strategies in conjunction with fatigue monitoring.",
-                "data_point": f"High-Speed Fatigue Events: {len(high_speed_fatigue)} "
-                              f"<span style='color:#d32f2f;'>({high_speed_pct:.1f}% of total alerts)</span>",
-                "reason": "High-speed fatigue greatly increases collision severity risk."
-            })
-        if not ai_recs:
-            ai_recs.append({
-                "recommendation": "Data quality is sufficient. Focus on implementing recommendations from Objectives 1–5.",
-                "data_point": "General Data Quality Check",
-                "reason": "No critical anomalies detected in aggregate metrics."
-            })
+            st.info("Operator data not available for Operator Risk Profiling.")
+
+    # Kolom kanan: AI Recommendations
+    with col_recs:
+        st.subheader("Recommendations")
+        ai_recs = []
+        insights_found = []
+
+        # Peak hour
+        if "hour" in df.columns and not df.empty:
+            peak_hour = df["hour"].value_counts().idxmax()
+            critical_hours = [2, 3, 4, 5]
+            if peak_hour in critical_hours:
+                insights_found.append(f"Most fatigue risk occurs at **{peak_hour}:00** — during critical circadian low period (3-6 AM). Consider enhanced monitoring.")
+            else:
+                insights_found.append(f"Most fatigue risk occurs at **{peak_hour}:00** — likely due to circadian drop.")
+
+        # Risk shift
+        if col_shift and not df.empty:
+            worst_shift = df[col_shift].value_counts().idxmax()
+            insights_found.append(f"Highest fatigue recorded in **Shift {worst_shift}** — review scheduling & workload.")
+
+        # Worst operator
+        if col_operator and not df.empty:
+            worst_operator = df[col_operator].value_counts().idxmax()
+            insights_found.append(f"Operator at highest risk: **{worst_operator}** — suggested coaching or rest plan.")
+
+        # Duration risk
+        if "duration_sec" in df.columns and not df.empty:
+            avg_duration = df["duration_sec"].mean()
+            if not pd.isna(avg_duration) and avg_duration > 10:
+                insights_found.append("Long fatigue event duration suggests slow response — improve alerting training.")
+
+        # Recommendations based on insights
+        if insights_found:
+            if any("circadian low" in i.lower() for i in insights_found):
+                ai_recs.append({
+                    "recommendation": "Deploy enhanced fatigue monitoring systems (e.g., EOR) specifically during 3-6 AM shifts.",
+                    "data_point": f"Critical Hour Alerts: {len(critical_alerts)} "
+                                  f"<span style='color:#d32f2f;'>({critical_pct:.1f}% of total alerts)</span>",
+                    "reason": "High percentage of alerts during circadian low period (3–6 AM) indicates elevated risk."
+                })
+            if any("shift" in i.lower() for i in insights_found):
+                pct = (df[col_shift].value_counts()[worst_shift] / len(df)) * 100
+                ai_recs.append({
+                    "recommendation": "Review shift rotation schedules to minimize consecutive high-risk shifts.",
+                    "data_point": f"Shift {worst_shift} Alerts: {df[col_shift].value_counts()[worst_shift]} "
+                                  f"<span style='color:#d32f2f;'>({pct:.1f}% of total alerts)</span>",
+                    "reason": f"Shift {worst_shift} accounts for a disproportionate share of fatigue events."
+                })
+            if any("operator" in i.lower() for i in insights_found):
+                pct = (df[col_operator].value_counts()[worst_operator] / len(df)) * 100
+                ai_recs.append({
+                    "recommendation": "Initiate individual coaching or mandatory rest periods for high-risk operators.",
+                    "data_point": f"Operator {worst_operator} Alerts: {df[col_operator].value_counts()[worst_operator]} "
+                                  f"<span style='color:#d32f2f;'>({pct:.1f}% of total alerts)</span>",
+                    "reason": f"Individual intervention needed to mitigate recurrence risk."
+                })
+            if any("duration" in i.lower() for i in insights_found):
+                ai_recs.append({
+                    "recommendation": "Review and improve alert response protocols and training.",
+                    "data_point": f"Average Fatigue Event Duration: {avg_duration:.2f} seconds",
+                    "reason": "Long duration suggests delayed response — requires procedural review."
+                })
+            if any("high-speed" in i.lower() for i in insights_found):
+                ai_recs.append({
+                    "recommendation": "Implement speed management strategies in conjunction with fatigue monitoring.",
+                    "data_point": f"High-Speed Fatigue Events: {len(high_speed_fatigue)} "
+                                  f"<span style='color:#d32f2f;'>({high_speed_pct:.1f}% of total alerts)</span>",
+                    "reason": "High-speed fatigue greatly increases collision severity risk."
+                })
+            if not ai_recs:
+                ai_recs.append({
+                    "recommendation": "Data quality is sufficient. Focus on implementing recommendations from Objectives 1–5.",
+                    "data_point": "General Data Quality Check",
+                    "reason": "No critical anomalies detected in aggregate metrics."
+                })
 
-        # Render recommendations
-        for rec in ai_recs:
-            st.markdown(f"""
-            <div style="
-                background: #f8f9fa;
-                border: 1px solid #dee2e6;
-                border-radius: 8px;
-                padding: 15px;
-                margin: 10px 0;
-                color: #2c3e50;
-                font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
-                box-shadow: 0 2px 8px rgba(0,0,0,0.05);
-            ">
+            # Render recommendations
+            for rec in ai_recs:
+                st.markdown(f"""
                 <div style="
-                    font-weight: bold;
+                    background: #f8f9fa;
+                    border: 1px solid #dee2e6;
+                    border-radius: 8px;
+                    padding: 15px;
+                    margin: 10px 0;
                     color: #2c3e50;
-                    margin-bottom: 8px;
-                    font-size: 14px;
-                    background: #e9ecef;
-                    padding: 8px;
-                    border-radius: 5px;
-                    border-left: 4px solid #495057;
-                ">AI Recommendation</div>
-                <div style="padding-top: 8px; font-size: 14px; margin-bottom: 10px;">
-                    <strong>Action:</strong> {rec['recommendation']}
-                </div>
-                <div style="font-size: 12px; padding: 8px; background: #e9ecef; border-radius: 5px; margin-top: 5px;">
-                    <strong>Data Point:</strong> {rec['data_point']}
-                </div>
-                <div style="font-size: 12px; padding: 8px; background: #f1f1f1; border-radius: 5px; margin-top: 5px;">
-                    <strong>AI Reasoning:</strong> {rec['reason']}
+                    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+                    box-shadow: 0 2px 8px rgba(0,0,0,0.05);
+                ">
+                    <div style="
+                        font-weight: bold;
+                        color: #2c3e50;
+                        margin-bottom: 8px;
+                        font-size: 14px;
+                        background: #e9ecef;
+                        padding: 8px;
+                        border-radius: 5px;
+                        border-left: 4px solid #495057;
+                    ">AI Recommendation</div>
+                    <div style="padding-top: 8px; font-size: 14px; margin-bottom: 10px;">
+                        <strong>Action:</strong> {rec['recommendation']}
+                    </div>
+                    <div style="font-size: 12px; padding: 8px; background: #e9ecef; border-radius: 5px; margin-top: 5px;">
+                        <strong>Data Point:</strong> {rec['data_point']}
+                    </div>
+                    <div style="font-size: 12px; padding: 8px; background: #f1f1f1; border-radius: 5px; margin-top: 5px;">
+                        <strong>AI Reasoning:</strong> {rec['reason']}
+                    </div>
                 </div>
-            </div>
-            """, unsafe_allow_html=True)
-    else:
-        st.info("No specific data points available for AI recommendations. Ensure relevant columns (hour, shift, operator, duration, speed) are present and populated.")
+                """, unsafe_allow_html=True)
+        else:
+            st.info("No specific data points available for AI recommendations. Ensure relevant columns (hour, shift, operator, duration, speed) are present and populated.")
+
+except Exception as e:
+    st.error(f"Error in Objective 6: {e}")
+    st.exception(e) # Untuk debugging lebih lanjut
 
 # ================= FOOTER ===========================
 st.markdown("---")