Update app.py

app.py

@@ -1718,6 +1718,13 @@ else:
         st.error(f"Error in Top 10 Operator analysis: {str(e)}")
         st.exception(e)
 
+# =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
+        else:
+            st.info(f"No strong correlation (r = {corr:.2f}). Speed is consistent across hours.")
+    else:
+        st.info("Insufficient data for speed vs hour correlation.")
+
+# =====================================================================
 # =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
 st.subheader("OBJECTIVE 6: Instant Insights & Recommendations")
 
@@ -1760,6 +1767,7 @@ with col_insights:
 
     # ===================== 2. High-Speed Fatigue Analysis =====================
     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) > 0 else 0
@@ -1782,413 +1790,6 @@ with col_insights:
             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. Weekend vs Weekday Risk =====================
-    df['is_weekend'] = df['start'].dt.weekday >= 5
-    weekend_alerts = len(df[df['is_weekend']])
-    weekday_alerts = len(df[~df['is_weekend']])
-    weekend_pct = (weekend_alerts / len(df)) * 100 if len(df) > 0 else 0
-
-    st.markdown(f"**Weekend vs Weekday Risk Distribution**")
-    st.markdown(
-        f"""
-        <div style="display: flex; gap: 10px; justify-content: space-between;">
-            <div style="text-align: center; flex: 1;">
-                <div style="font-size: 18px; font-weight: bold;">{weekend_alerts}</div>
-                <div style="color: #555;">Weekend</div>
-                <div style="color: red; font-size: 12px;">{weekend_pct:.1f}%</div>
-            </div>
-            <div style="text-align: center; flex: 1;">
-                <div style="font-size: 18px; font-weight: bold;">{weekday_alerts}</div>
-                <div style="color: #555;">Weekday</div>
-                <div style="color: green; font-size: 12px;">{100-weekend_pct:.1f}%</div>
-            </div>
-        </div>
-        """,
-        unsafe_allow_html=True
-    )
-    if weekend_pct > 60:
-        st.warning(f"High weekend fatigue risk ({weekend_pct:.1f}%). Consider weekend rest protocols.")
-    else:
-        st.info(f"Weekend fatigue is {weekend_pct:.1f}% — balanced with weekday activity.")
-
-    # ===================== 4. Shift-Based Risk Analysis =====================
-    if col_shift and col_shift in df.columns:
-        shift_counts = df[col_shift].value_counts()
-        st.markdown(f"**Shift-Based Risk Distribution**")
-        for shift, count in shift_counts.items():
-            shift_pct = (count / len(df)) * 100
-            st.markdown(f"- **Shift {shift}**: {count} alerts ({shift_pct:.1f}%)")
-        max_shift = shift_counts.idxmax() if not shift_counts.empty else "N/A"
-        if max_shift != "N/A":
-            st.warning(f"Shift {max_shift} has the highest fatigue alert count. Investigate scheduling or rest breaks.")
-    else:
-        st.info("Shift data not available for analysis.")
-
-    # ===================== 5. Fleet Type Risk Distribution =====================
-    if col_fleet_type and col_fleet_type in df.columns:
-        fleet_counts = df[col_fleet_type].value_counts()
-        st.markdown(f"**Fleet Type Risk Distribution**")
-        for fleet, count in fleet_counts.items():
-            fleet_pct = (count / len(df)) * 100
-            st.markdown(f"- **{fleet}**: {count} alerts ({fleet_pct:.1f}%)")
-        max_fleet = fleet_counts.idxmax() if not fleet_counts.empty else "N/A"
-        if max_fleet != "N/A":
-            st.warning(f"Fleet type '{max_fleet}' has the highest fatigue alert count. Investigate vehicle-specific factors.")
-    else:
-        st.info("Fleet type data not available for analysis.")
-
-    # ===================== 6. Top 5 Operators by Alert Count =====================
-    if col_operator and col_operator in df.columns:
-        top5_operators = df[col_operator].value_counts().head(5)
-        st.markdown(f"**Top 5 Operators by Fatigue Alerts**")
-        for op, count in top5_operators.items():
-            op_pct = (count / len(df)) * 100
-            st.markdown(f"- **{op}**: {count} alerts ({op_pct:.1f}%)")
-        if not top5_operators.empty:
-            top_op = top5_operators.index[0]
-            st.warning(f"Operator {top_op} has the highest alert count. Prioritize fatigue intervention.")
-    else:
-        st.info("Operator data not available for analysis.")
-
-    # ===================== 7. Fatigue Alert Trend Over Time (Weekly) =====================
-    df_weekly = df.set_index('start').resample('W').size().reset_index(name='count')
-    if len(df_weekly) > 0:
-        trend_slope = np.polyfit(range(len(df_weekly)), df_weekly['count'], 1)[0]
-        st.markdown(f"**Fatigue Alert Trend (Weekly)**")
-        if trend_slope > 0.5:
-            st.warning(f"Trend is increasing (slope: {trend_slope:.2f}). Fatigue risk is rising.")
-        elif trend_slope < -0.5:
-            st.info(f"Trend is decreasing (slope: {trend_slope:.2f}). Fatigue risk is improving.")
-        else:
-            st.info(f"Trend is stable (slope: {trend_slope:.2f}).")
-    else:
-        st.info("Insufficient data for weekly trend analysis.")
-
-    # ===================== 8. Geographic Risk Hotspots =====================
-    if 'location' in df.columns or ('lat' in df.columns and 'lon' in df.columns):
-        st.markdown(f"**Geographic Risk Hotspots**")
-        if 'location' in df.columns:
-            loc_counts = df['location'].value_counts().head(3)
-            for loc, count in loc_counts.items():
-                loc_pct = (count / len(df)) * 100
-                st.markdown(f"- **{loc}**: {count} alerts ({loc_pct:.1f}%)")
-        else:
-            st.info("Geographic data not available for hotspot analysis.")
-    else:
-        st.info("Geographic data not available for hotspot analysis.")
-
-    # ===================== 9. Correlation: Speed vs Hour =====================
-    if col_speed and col_speed in df.columns and 'hour' in df.columns:
-        corr = df[col_speed].corr(df['hour'])
-        st.markdown(f"**Correlation: Speed vs Hour**")
-        if abs(corr) > 0.3:
-            st.warning(f"Moderate correlation detected (r = {corr:.2f}). Speed patterns may vary by hour.")
-        else:
-            st.info(f"No strong correlation (r = {corr:.2f}). Speed is consistent across hours.")
-    else:
-        st.info("Insufficient data for speed vs hour correlation.")
-
-# =====================================================================
-# 🔹 KOLOM KANAN — AI RECOMMENDATIONS
-# =====================================================================
-with col_recs:
-    st.subheader("AI Recommendations")
-
-    # Generate 9 recommendations based on the 9 insights above
-    recs = []
-
-    # 1. Critical Hour
-    if critical_pct > 10:
-        recs.append("Implement mandatory 15-min break protocol during 3-6 AM shifts.")
-    else:
-        recs.append("Maintain current scheduling for early shifts — risk is low.")
-
-    # 2. High-Speed Fatigue
-    if 'col_speed' in locals() and col_speed in df.columns:
-        if high_speed_pct > 20:
-            recs.append("Install speed monitoring systems to alert drivers during high-speed fatigue alerts.")
-        else:
-            recs.append("Continue monitoring speed-related fatigue — current levels are acceptable.")
-    else:
-        recs.append("Enable speed data collection to assess high-speed fatigue risk.")
-
-    # 3. Weekend Risk
-    if weekend_pct > 60:
-        recs.append("Schedule mandatory rest periods after weekend shifts to reduce fatigue accumulation.")
-    else:
-        recs.append("Maintain current weekend scheduling protocols — risk is balanced.")
-
-    # 4. Shift Risk
-    if col_shift and col_shift in df.columns:
-        max_shift = df[col_shift].value_counts().idxmax() if not df[col_shift].value_counts().empty else "N/A"
-        if max_shift != "N/A":
-            recs.append(f"Review shift {max_shift} scheduling and rest-break frequency for operators.")
-        else:
-            recs.append("No dominant shift risk — continue monitoring all shifts equally.")
-    else:
-        recs.append("Enable shift data collection to assess shift-based fatigue risk.")
-
-    # 5. Fleet Risk
-    if col_fleet_type and col_fleet_type in df.columns:
-        max_fleet = df[col_fleet_type].value_counts().idxmax() if not df[col_fleet_type].value_counts().empty else "N/A"
-        if max_fleet != "N/A":
-            recs.append(f"Investigate fatigue factors specific to fleet type '{max_fleet}' (e.g., ergonomics, route, etc.).")
-        else:
-            recs.append("No dominant fleet risk — continue monitoring all fleet types equally.")
-    else:
-        recs.append("Enable fleet type data collection to assess vehicle-specific fatigue risk.")
-
-    # 6. Top Operator Risk
-    if col_operator and col_operator in df.columns:
-        if not df[col_operator].value_counts().empty:
-            top_op = df[col_operator].value_counts().index[0]
-            recs.append(f"Scheduled one-on-one fatigue risk assessment for operator {top_op}.")
-        else:
-            recs.append("No top operator identified — continue general monitoring.")
-    else:
-        recs.append("Enable operator data collection to identify high-risk drivers.")
-
-    # 7. Trend Risk
-    if len(df_weekly) > 0:
-        trend_slope = np.polyfit(range(len(df_weekly)), df_weekly['count'], 1)[0]
-        if trend_slope > 0.5:
-            recs.append("Initiate immediate fatigue risk review across all shifts and operators.")
-        elif trend_slope < -0.5:
-            recs.append("Recognize current safety protocols — continue to monitor trend reversal.")
-        else:
-            recs.append("Maintain current protocols — fatigue trend is stable.")
-    else:
-        recs.append("Insufficient data to assess fatigue trend.")
-
-    # 8. Geographic Risk
-    if 'location' in df.columns or ('lat' in df.columns and 'lon' in df.columns):
-        if 'location' in df.columns:
-            top_loc = df['location'].value_counts().index[0] if not df['location'].value_counts().empty else "N/A"
-            if top_loc != "N/A":
-                recs.append(f"Review route planning and rest stops for high-risk location: {top_loc}.")
-            else:
-                recs.append("No geographic hotspots identified.")
-        else:
-            recs.append("Enable geographic data collection for hotspot analysis.")
-    else:
-        recs.append("Enable geographic data collection for hotspot analysis.")
-
-    # 9. Correlation Risk
-    if col_speed and col_speed in df.columns and 'hour' in df.columns:
-        corr = df[col_speed].corr(df['hour'])
-        if abs(corr) > 0.3:
-            recs.append("Implement time-of-day speed limits to reduce hour-speed correlation risk.")
-        else:
-            recs.append("Speed patterns are consistent — no immediate action required.")
-    else:
-        recs.append("Enable speed and hour data for correlation analysis.")
-
-    # Display all 9 recommendations in one box with 9 list items
-    st.markdown(f"""
-    <div class="ai-insight-box">
-        <div class="ai-insight-title">AI Action Plan</div>
-        <ul style="padding-left: 20px; margin: 8px 0; line-height: 1.5;">
-    """, unsafe_allow_html=True)
-
-    for i, rec in enumerate(recs, 1):
-        st.markdown(f"<li>{rec}</li>", unsafe_allow_html=True)
-
-    st.markdown("</ul></div>", 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
-
-            st.markdown(
-                f"""
-                <div style="font-size: 24px; font-weight: bold;">{shift_counts[shift_val]}</div>
-                <div style="color: red; font-size: 14px; margin-top: -5px;">↑ {shift_pct:.1f}% of total alerts</div>
-                """,
-                unsafe_allow_html=True
-            )
-
-            if shift_pct > 50:
-                st.warning(
-                    f"Shift {shift_val} has disproportionately high alerts ({shift_pct:.1f}%). "
-                    f"Review shift scheduling and workload."
-                )
-            else:
-                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()):
-            op_pct = (count / len(df)) * 100
-            color = colors[idx] if idx < len(colors) else colors[-1]
-
-            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
-            )
-
-            if op_pct > 5:
-                st.warning(
-                    f"Operator {op_name} has high fatigue risk ({op_pct:.1f}%). "
-                    f"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.")
-
-
-# =====================================================================
-# 🔹 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)."
-            )
-        else:
-            insights_found.append(
-                f"Most fatigue risk occurs at **{peak_hour}:00** — likely due to circadian drop."
-            )
-
-    # Risk Shift
-    if col_shift and col_shift in df.columns 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 col_operator in df.columns 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 avg_duration > 10:
-            insights_found.append(
-                "Long fatigue event duration suggests slow response — improve alerting training."
-            )
-
-    # ===================== AI DECISION ENGINE =====================
-    if insights_found:
-
-        if any("circadian" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Deploy enhanced fatigue monitoring systems during 3-6 AM.",
-                "data_point": f"Critical Hour Alerts: {len(critical_alerts)} ({critical_pct:.1f}%)",
-                "reason": "High percentage of alerts during circadian low period."
-            })
-
-        if any("shift" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Review shift rotation schedules.",
-                "data_point": f"Shift {worst_shift}: {df[col_shift].value_counts()[worst_shift]} alerts",
-                "reason": "This shift shows highest fatigue alerts."
-            })
-
-        if any("operator" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Coaching or mandatory rest for the identified high-risk operator.",
-                "data_point": f"Operator {worst_operator}: {df[col_operator].value_counts()[worst_operator]} alerts",
-                "reason": "Operator has highest fatigue alerts."
-            })
-
-        if any("duration" in i.lower() for i in insights_found):
-            ai_recs.append({
-                "recommendation": "Improve fatigue alert response training.",
-                "data_point": f"Avg Duration: {avg_duration:.1f} sec",
-                "reason": "Long fatigue event duration indicates slow response."
-            })
-
-        # Render all recommendations
-        import re
-
-        for rec in ai_recs:
-
-            data_point_colored = re.sub(
-                r'(\d+\.?\d*%)',
-                r'<span style="color: red;">\1</span>',
-                rec['data_point']
-            )
-
-            reason_colored = re.sub(
-                r'(\d+\.?\d*%)',
-                r'<span style="color: red;">\1</span>',
-                rec['reason']
-            )
-
-            st.markdown(
-                f"""
-                <div style="
-                    background: #f8f9fa;
-                    border: 1px solid #dee2e6;
-                    border-radius: 8px;
-                    padding: 15px;
-                    margin: 10px 0;
-                ">
-                    <div style="font-weight: bold; background: #e9ecef; padding: 8px; border-radius: 5px;">
-                        AI Recommendation
-                    </div>
-                    <div style="padding-top: 8px;"><strong>Action:</strong> {rec['recommendation']}</div>
-                    <div style="padding: 8px; background: #e9ecef; border-radius: 5px;">
-                        <strong>Data Point:</strong> {data_point_colored}
-                    </div>
-                    <div style="padding: 8px; background: #f1f1f1; border-radius: 5px;">
-                        <strong>AI Reasoning:</strong> {reason_colored}
-                    </div>
-                </div>
-                """,
-                unsafe_allow_html=True
-            )
 
     else:
-        st.info(
-            "No specific data points available for AI recommendations. "
-            "Ensure relevant columns are present (hour, shift, operator, duration, speed)."
-        )
-
-# ================= 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.info("Speed data not available for High-Speed Fatigue Analysis.")