Update app.py

app.py

@@ -1659,141 +1659,192 @@ else:
         st.exception(e)  # optionally show full traceback during dev
 
 
+
 # =================== 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)
 
-# =========================================
-#        LEFT COLUMN — INSIGHTS
-# =========================================
+# Kolom kiri: Insights by Advanced Analytics
 with col_insights:
-
     st.subheader("Insights by Advanced Analytics")
 
-    # 1. Critical Hour Analysis (3–6 AM)
+    # 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)**")
-
-    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;">
-            Critical Hour Alerts: {len(critical_alerts)} ({critical_pct:.1f}% of total alerts)
-        </div>
-        """,
-        unsafe_allow_html=True
-    )
-
-    if critical_pct > 10:
-        st.warning(
-            f"High risk: {critical_pct:.1f}% of fatigue alerts occur during critical hours (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.markdown(f'<div style="background-color: {bg_color}; padding: 10px; border-radius: 5px;">Critical Hour Alerts: {len(critical_alerts)} ({critical_pct:.1f}% of total alerts)</div>', unsafe_allow_html=True)
+    if critical_pct > 10:  # If more than 10% of alerts happen in critical hours
+        st.warning(f"High risk: {critical_pct:.1f}% of fatigue alerts occur during critical hours (3-6 AM). This is a known circadian dip period.")
     else:
-        st.info(
-            f"{critical_pct:.1f}% of alerts occur during critical hours. This is within acceptable range."
-        )
+        st.info(f"{critical_pct:.1f}% of alerts occur during critical hours. This is within acceptable range.")
 
-    # 2. High-Speed Fatigue Analysis
+    # 2. High-Speed Fatigue Analysis (Environmental Risk)
     if col_speed and col_speed in df.columns:
-
-        high_speed_threshold = 20
-        high_speed_fatigue = df[df[col_speed] > high_speed_threshold]
-        high_speed_pct = (len(high_speed_fatigue) / len(df)) * 100 if len(df) else 0
-
-        # Title
-        st.markdown("**High-Speed Fatigue Risk (Speed > 20 km/h)**")
-
-        # Red text (no box)
-        st.markdown(
-            f"""
-            <p style="color:#d32f2f; font-size:20px; font-weight:700; margin-bottom:4px;">
-                High-Speed Fatigue Events: {len(high_speed_fatigue)}
-            </p>
-            <p style="color:#d32f2f; font-size:15px; font-weight:500; margin-top:-6px;">
-                {high_speed_pct:.1f}% of total alerts (Speed > {high_speed_threshold} km/h)
-            </p>
-            """,
-            unsafe_allow_html=True
-        )
-
-        if high_speed_pct > 20:
-            st.warning(
-                f"High risk: {high_speed_pct:.1f}% fatigue alerts occur at high speeds."
-            )
+        high_speed_threshold = df[col_speed].quantile(0.75) if not df[col_speed].dropna().empty else 0  # Handle empty series
+        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("High-Speed Fatigue Events", f"{len(high_speed_fatigue)}", f"{high_speed_pct:.1f}% of total alerts")
+        if high_speed_pct > 20:  # If more than 20% of alerts happen at high speed
+            st.warning(f"High risk: {high_speed_pct:.1f}% of fatigue alerts occur at high speeds. This increases accident severity potential.")
         else:
-            st.info(
-                f"{high_speed_pct:.1f}% of alerts occur at high speeds. Within acceptable limits."
-            )
+            st.info(f"{high_speed_pct:.1f}% 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("**Shift Pattern Risk**")
-
+        # shift_alerts_by_hour = df.groupby([col_shift, 'hour']).size().reset_index(name='alerts') # Tidak digunakan dalam tampilan ini
+        
+        st.markdown(f"**Shift Pattern Risk**")
         for shift_val in shift_counts.index:
             shift_pct = (shift_counts[shift_val] / len(df)) * 100
-
-            st.metric(
-                f"Shift {shift_val} Alerts",
-                f"{shift_counts[shift_val]}",
-                f"{shift_pct:.1f}% of total alerts"
-            )
-
-            if shift_pct > 50:
-                st.warning(
-                    f"Shift {shift_val} has disproportionately high alerts ({shift_pct:.1f}%)."
-                )
+            st.metric(f"Shift {shift_val} Alerts", f"{shift_counts[shift_val]}", f"{shift_pct:.1f}% of total alerts")
+            if shift_pct > 50:  # If one shift has more than 50% of alerts
+                st.warning(f"Shift {shift_val} has disproportionately high alerts ({shift_pct:.1f}%). Review shift scheduling and workload.")
             else:
-                st.info(
-                    f"Shift {shift_val} alert distribution is acceptable ({shift_pct:.1f}%)."
-                )
+                st.info(f"Shift {shift_val} alert distribution is acceptable ({shift_pct:.1f}%).")
     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("**High-Risk Operator Identification**")
-
-        colors = ["#d32f2f", "#e57373", "#ef9a9a", "#ffcdd2", "#ffe1e4"]
-
-        for idx, (op_name, count) in enumerate(top_risk_operators.items()):
+        top_risk_operators = operator_alerts.head(5)  # Top 5 operators by alerts
+        
+        st.markdown(f"**High-Risk Operator Identification**")
+        for op_name, count in top_risk_operators.items():
             op_pct = (count / len(df)) * 100
-            color = colors[idx] if idx < len(colors) else colors[-1]
+            st.metric(f"Operator: {op_name}", f"{count} alerts", f"{op_pct:.1f}% of total alerts")
+            if op_pct > 5:  # If an operator has more than 5% of all alerts
+                st.warning(f"Operator {op_name} has high fatigue risk ({op_pct:.1f}% of alerts). Consider coaching or rest plan.")
+            else:
+                st.info(f"Operator {op_name} fatigue risk is within acceptable range ({op_pct:.1f}%).")
+    else:
+        st.info("Operator data not available for Operator Risk Profiling.")
 
-            st.markdown(f"**Operator:** {op_name}  \n**Alerts:** {count}")
 
-            st.markdown(
-                f"<span style='font-weight:600'>Share:</span> "
-                f"<span style='color:{color}; font-weight:700'>{op_pct:.1f}% of total alerts</span>",
-                unsafe_allow_html=True
-            )
+# Kolom kanan: AI Recommendations
+with col_recs:
+    st.subheader("Recommendations")
+    ai_recs = []
+    insights_found = [] # Untuk menyimpan insight yang ditemukan
 
-            if op_pct > 5:
-                st.warning(
-                    f"Operator {op_name} has high fatigue risk ({op_pct:.1f}%)."
-                )
-            else:
-                st.info(
-                    f"Operator {op_name} risk is acceptable ({op_pct:.1f}%)."
-                )
+    # 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.")
+
+    # Generate recommendations based on found insights
+    if insights_found:
+        # Contoh rekomendasi berdasarkan insight
+        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)} ({critical_pct:.1f}% 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):
+            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]} ({(df[col_shift].value_counts()[worst_shift] / len(df)) * 100:.1f}% 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):
+            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]} ({(df[col_operator].value_counts()[worst_operator] / len(df)) * 100:.1f}% of total alerts)",
+                "reason": f"The identified high-risk operator ({worst_operator}) 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)} ({high_speed_pct:.1f}% 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."
+            })
+
+        # Menampilkan rekomendasi dalam format kotak yang sesuai dengan permintaan
+        for rec in ai_recs:
+            # Gunakan div dengan class khusus untuk membuat kotak rekomendasi di kolom kanan
+            # Gaya diambil dari .insight-box untuk konsistensi dan menghindari warna ungu
+            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);
+                display: flex;
+                flex-direction: column;
+                justify-content: space-between;
+            ">
+                <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>
+            """, unsafe_allow_html=True)
     else:
-        st.info("Operator data not available for Operator Risk Profiling.")
+        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)