Update app.py

app.py

@@ -1661,222 +1661,224 @@ else:
 
 
 # =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
-st.subheader("OBJECTIVE 6: Instant Insights & Recommendations")
-
-try:
-    # Membagi tampilan menjadi dua kolom
-    col_insights, col_recs = st.columns(2)
+st.markdown('<div style="text-align: center; font-size: 1.5em; font-weight: bold; margin-bottom: 20px;">OBJECTIVE 6: Instant Insights & Recommendations</div>', unsafe_allow_html=True)
+
+# Membagi tampilan menjadi dua kolom
+col_insights, col_recs = st.columns(2)
+
+# Helper function for red % formatting
+def format_red_pct(value):
+    return f'<span style="color: #d32f2f; font-weight: bold;">{value:.1f}%</span>'
+
+# Kolom kiri: Insights by Advanced Analytics
+with col_insights:
+    st.markdown('<div style="text-align: center; font-size: 1.3em; font-weight: bold; margin-bottom: 15px;">Insights by Advanced Analytics</div>', unsafe_allow_html=True)
+
+    # 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)**", unsafe_allow_html=True)
+    # 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.markdown(
+        f'<div style="background-color: {bg_color}; padding: 10px; border-radius: 5px; margin-bottom: 10px;">'
+        f'Critical Hour Alerts: <b>{len(critical_alerts)}</b> ({format_red_pct(critical_pct)} of total alerts)'
+        f'</div>', 
+        unsafe_allow_html=True
+    )
+    if critical_pct > 10:
+        st.warning(f"High risk: {format_red_pct(critical_pct)} of fatigue alerts occur during critical hours (3-6 AM). This is a known circadian dip period.")
+    else:
+        st.info(f"{format_red_pct(critical_pct)} of alerts occur during critical hours. This is within acceptable range.")
 
-    # Kolom kiri: Insights by Advanced Analytics
-    with col_insights:
-        st.subheader("Insights by Advanced Analytics")
+    # 2. High-Speed Fatigue Analysis (Environmental Risk)
+    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
 
-        # 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 using markdown
+        st.markdown(f"**High-Speed Fatigue Risk (Speed > {high_speed_threshold:.0f} km/h)**", unsafe_allow_html=True)
         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>',
+            f'<div style="background-color: #f8f9fa; padding: 10px; border-radius: 5px; border: 1px solid #dee2e6; margin-bottom: 10px;">'
+            f'<b>High-Speed Fatigue Events:</b> <span style="color: #1a73e8; font-weight: bold;">{len(high_speed_fatigue)}</span>'
+            f' ({format_red_pct(high_speed_pct)} of total alerts)'
+            f'</div>',
             unsafe_allow_html=True
         )
-        
-        # ✅ 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)
+        if high_speed_pct > 20:
+            st.warning(f"High risk: {format_red_pct(high_speed_pct)} of fatigue alerts occur at high speeds. This increases accident severity potential.")
         else:
-            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)
-
-        # 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)**")
-            
-            # ✅ st.metric doesn't support HTML, so replace with markdown
+            st.info(f"{format_red_pct(high_speed_pct)} of alerts occur at high speeds. This is within acceptable range.")
+    else:
+        st.info("Speed data not available for High-Speed Fatigue Analysis.")
+
+    # 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**", unsafe_allow_html=True)
+        for shift_val in shift_counts.index:
+            count = shift_counts[shift_val]
+            shift_pct = (count / len(df)) * 100
             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: #f8f9fa; padding: 8px; border-radius: 5px; border: 1px solid #e9ecef; margin: 5px 0;">'
+                f'<b>Shift {shift_val} Alerts:</b> <span style="color: #1a73e8; font-weight: bold;">{count}</span>'
+                f' ({format_red_pct(shift_pct)} of total alerts)'
+                f'</div>',
                 unsafe_allow_html=True
             )
-            
-            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)
+            if shift_pct > 50:
+                st.warning(f"Shift {shift_val} has disproportionately high alerts ({format_red_pct(shift_pct)}). Review shift scheduling and workload.")
             else:
-                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)
-
-        # 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)
-
-        # 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)
+                st.info(f"Shift {shift_val} alert distribution is acceptable ({format_red_pct(shift_pct)}).")
+    else:
+        st.info("Shift data not available for Shift Pattern Analysis.")
+
+    # 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**", unsafe_allow_html=True)
+        for op_name, count in top_risk_operators.items():
+            op_pct = (count / len(df)) * 100
+            # Anonymize name: first part only
+            display_name = op_name.split()[0] if isinstance(op_name, str) else str(op_name)
+            st.markdown(
+                f'<div style="background-color: #f8f9fa; padding: 8px; border-radius: 5px; border: 1px solid #e9ecef; margin: 5px 0;">'
+                f'<b>Operator: {display_name}</b> — <span style="color: #1a73e8; font-weight: bold;">{count}</span> alerts'
+                f' ({format_red_pct(op_pct)} of total alerts)'
+                f'</div>',
+                unsafe_allow_html=True
+            )
+            if op_pct > 5:
+                st.warning(f"Operator {display_name} has high fatigue risk ({format_red_pct(op_pct)} of alerts). Consider coaching or rest plan.")
+            else:
+                st.info(f"Operator {display_name} fatigue risk is within acceptable range ({format_red_pct(op_pct)}).")
+    else:
+        st.info("Operator data not available for Operator Risk Profiling.")
+
+
+# Kolom kanan: AI Recommendations
+with col_recs:
+    st.markdown('<div style="text-align: center; font-size: 1.3em; font-weight: bold; margin-bottom: 15px;">Recommendations</div>', unsafe_allow_html=True)
+    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:
-            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."
-                })
+            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()
+        display_name = worst_operator.split()[0] if isinstance(worst_operator, str) else str(worst_operator)
+        insights_found.append(f"Operator at highest risk: **{display_name}** — 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.")
+
+    # High-speed insight (add conditionally)
+    if col_speed and col_speed in df.columns and high_speed_pct > 20:
+        insights_found.append("High-speed fatigue events exceed threshold — integrate with speed management.")
+
+    # Generate recommendations based on found 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)} ({format_red_pct(critical_pct)} of total alerts)",
+                "reason": "High percentage of alerts occurring during the known circadian low period (3-6 AM) indicates increased risk during these hours."
+            })
+        if any("shift" in i.lower() for i in insights_found):
+            shift_pct_val = (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]} ({format_red_pct(shift_pct_val)} of total alerts)",
+                "reason": f"The identified high-risk shift ({worst_shift}) has the highest number of fatigue alerts, suggesting scheduling or workload issues."
+            })
+        if any("operator" in i.lower() for i in insights_found):
+            op_pct_val = (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 {display_name} Alerts: {df[col_operator].value_counts()[worst_operator]} ({format_red_pct(op_pct_val)} of total alerts)",
+                "reason": f"The identified high-risk operator ({display_name}) has the highest number of fatigue alerts, indicating a need for targeted intervention."
+            })
+        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 average duration suggests potential delays in response time or alert acknowledgment, requiring protocol 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)} ({format_red_pct(high_speed_pct)} of total alerts)",
+                "reason": "A significant percentage of alerts occur at high speeds, increasing accident severity risk. Speed control is crucial."
+            })
+        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 specific high-impact insights were automatically identified from the aggregated data in this section."
+            })
 
-            # Render recommendations
-            for rec in ai_recs:
-                st.markdown(f"""
+        # Display recommendations with consistent styling
+        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);
+            ">
                 <div style="
-                    background: #f8f9fa;
-                    border: 1px solid #dee2e6;
-                    border-radius: 8px;
-                    padding: 15px;
-                    margin: 10px 0;
+                    font-weight: bold;
                     color: #2c3e50;
-                    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>
+                    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>
-                """, 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
+                <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>
+            """, 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.")
 
 # ================= FOOTER ===========================
 st.markdown("---")
-st.markdown('<div class="footer">FatigueAnalyzer - Transforming Mining Safety with Intelligent Analytics | Contact: info@bukittechnology.com</div>', unsafe_allow_html=True)
+st.markdown(
+    '<div style="text-align: center; color: #6c757d; font-size: 0.9em; margin-top: 20px;">'
+    'FatigueAnalyzer - Transforming Mining Safety with Intelligent Analytics | Contact: info@bukittechnology.com'
+    '</div>',
+    unsafe_allow_html=True
+)