Update app.py

app.py

@@ -1663,106 +1663,122 @@ else:
 # =================== OBJECTIVE 6: Automated Insights & AI Recommendations =====================
 st.subheader("OBJECTIVE 6: Instant Insights & Recommendations")
 
-# Membagi tampilan menjadi dua kolom
+# Membagi menjadi 2 kolom
 col_insights, col_recs = st.columns(2)
 
-# Kolom kiri: Insights by Advanced Analytics
+# ============================
+# KIRI — INSIGHTS
+# ============================
 with col_insights:
     st.subheader("Insights by Advanced Analytics")
 
-    # 1. Critical Hour Analysis (2-5 AM)
+    # 1. Critical Hour Analysis
     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.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.")
+    st.markdown("**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;">'
+        f'Critical Hour Alerts: {len(critical_alerts)} ({critical_pct:.1f}% of total alerts)'
+        f'</div>',
+        unsafe_allow_html=True
+    )
+
+    if critical_pct > 10:
+        st.warning(f"High risk: {critical_pct:.1f}% of fatigue alerts occur during critical hours.")
     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. Within acceptable range.")
 
-    # 2. High-Speed Fatigue Analysis (Environmental Risk)
+    # 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  # 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
-        
+        high_speed_threshold = df[col_speed].quantile(0.75)
+        high_speed_fatigue = df[df[col_speed] >= high_speed_threshold]
+        high_speed_pct = (len(high_speed_fatigue) / len(df)) * 100
+
         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.")
+
+        if high_speed_pct > 20:
+            st.warning(f"High risk: {high_speed_pct:.1f}% of alerts occur at high speeds.")
         else:
-            st.info(f"{high_speed_pct:.1f}% of alerts occur at high speeds. This is within acceptable range.")
+            st.info(f"{high_speed_pct:.1f}% occur at high speeds. Acceptable.")
     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_color = "#d32f2f"  # merah gelap
-
-    for shift_val in shift_counts.index:
-        shift_pct = (shift_counts[shift_val] / len(df)) * 100
-
-        st.markdown(
-            f"""
-            <div style="padding:12px 16px; border-radius:10px; background-color:#fff; border:1px solid #eee; margin-bottom:10px;">
-                <div style="font-size:16px; font-weight:600; color:inherit;">Shift {shift_val} Alerts</div>
-                <div style="font-size:28px; font-weight:700; color:inherit;">{shift_counts[shift_val]}</div>
-                <div style="font-size:14px; font-weight:700;">
-                    <span style="color:{shift_color};">{shift_pct:.1f}% of total alerts</span>
-                </div>
-            </div>
-            """,
-            unsafe_allow_html=True
-        )
 
-        if shift_pct > 50:
-            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}%).")
-else:
-    st.info("Shift data not available for Shift Pattern Analysis.")
+# ============================
+# KANAN — RECOMMENDATIONS
+# ============================
+with col_recs:
+    st.subheader("AI-Driven Recommendations")
 
+    # 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_color = "#d32f2f"
+
+        for shift_val in shift_counts.index:
+            shift_pct = (shift_counts[shift_val] / len(df)) * 100
+
+            st.markdown(
+                f"""
+                <div style="padding:12px 16px; border-radius:10px; background-color:#fff; 
+                    border:1px solid #eee; margin-bottom:10px;">
+                    <div style="font-size:16px; font-weight:600;">Shift {shift_val} Alerts</div>
+                    <div style="font-size:28px; font-weight:700;">{shift_counts[shift_val]}</div>
+                    <div style="font-size:14px; font-weight:700;">
+                        <span style="color:{shift_color};">{shift_pct:.1f}% of total alerts</span>
+                    </div>
+                </div>
+                """,
+                unsafe_allow_html=True
+            )
 
+            if shift_pct > 50:
+                st.warning(f"Shift {shift_val} has disproportionately high alerts ({shift_pct:.1f}%).")
+            else:
+                st.info(f"Shift {shift_val} 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)  # Top 5 operators by alerts
+    # 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**")
+        st.markdown("**High-Risk Operator Identification**")
 
-    # Warna berdasarkan ranking 1–5
-    colors = ["#d32f2f", "#e57373", "#ef9a9a", "#ffcdd2", "#ffe1e4"]
+        # Warna ranking
+        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]
+        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]
 
-        # Teks normal untuk nama dan jumlah alert
-        st.markdown(f"**Operator:** {op_name}  \n**Alerts:** {count}")
+            # Nama & jumlah
+            st.markdown(f"**Operator:** {op_name}  \n**Alerts:** {count}")
 
-        # Hanya 'Share' yang berwarna sesuai ranking
-        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
-        )
+            # Share berwarna
+            st.markdown(
+                f"<b>Share:</b> <span style='color:{color}; font-weight:700'>{op_pct:.1f}% of total alerts</span>",
+                unsafe_allow_html=True
+            )
 
-        # Risk message (tetap gunakan component Streamlit agar konsisten)
-        if op_pct > 5:
-            st.warning(f"Operator {op_name} has high fatigue risk ({op_pct:.1f}%). Consider coaching or rest plan.")
-        else:
-            st.info(f"Operator {op_name} fatigue risk is within acceptable range ({op_pct:.1f}%).")
+            if op_pct > 5:
+                st.warning(f"Operator {op_name} shows high fatigue tendency ({op_pct:.1f}%).")
+            else:
+                st.info(f"Operator {op_name} is within the expected alert range ({op_pct:.1f}%).")
+    else:
+        st.info("Operator data not available for Operator Risk Profiling.")
 
-else:
-    st.info("Operator data not available for Operator Risk Profiling.")
 
 
 # Kolom kanan: AI Recommendations