Update app.py

app.py

@@ -248,13 +248,14 @@ df = load_data()
 st.markdown("""
 <div class="main-header" style="text-align:center;">
     <h1>Michelin Mining Tyre Analytics</h1>
-    <p style="font-size:14px; color:#b0b0b0; margin-top:-10px;">
-        Analysis is based on daily aggregated data
+    <p style="font-size:12px; color:#9a9a9a; margin-top:-6px;">
+        Insight daily berdasarkan 13–16 Desember 2023
     </p>
 </div>
 """, unsafe_allow_html=True)
 
 
+
 # ================= LOGO (Perbaikan: Base64 Embed - Selalu Muncul) =================
 def render_logo():
     # Logo dalam base64 (diambil dari URL Anda)
@@ -344,50 +345,6 @@ if submit:
 else:
     dff = df
 
-# ================= OBJECTIVE 1 =================
-# ================= OBJECTIVE 1 =================
-# st.markdown('<h3 class="objective-title">OBJECTIVE 1: Pressure & Temperature Trends — How Do Front and Rear Tyres Distributin?</h3>', unsafe_allow_html=True)
-
-# col1, col2 = st.columns(2)
-
-# with col1:
-#     st.markdown('<h5 style="text-align:center; margin-top: 0;">Pressure Distribution per Tyre Position</h5>', unsafe_allow_html=True)
-#     fig1 = px.box(
-#         dff,
-#         x='Position',
-#         y='Pressure (psi)',
-#         color='Position',
-#         color_discrete_map={1: '#d50000', 2: '#ff6d00', 3: '#ffcc00', 4: '#007acc'},
-#         template="plotly_white"
-#     )
-#     red_high = dff['Red High Press (psi)'].min()
-#     amber_high = dff['Amber High Press (psi)'].min()
-#     fig1.add_hline(y=red_high, line_dash="dash", line_color="red", annotation_text="Red High Press", annotation_position="top right")
-#     fig1.add_hline(y=amber_high, line_color="orange", annotation_text="Amber High Press", annotation_position="bottom right")
-#     fig1.update_layout(margin=dict(t=40))
-#     st.plotly_chart(fig1, use_container_width=True)
-
-# with col2:
-#     st.markdown('<h5 style="text-align:center; margin-top: 0;">Temperature Distribution per Tyre Position</h5>', unsafe_allow_html=True)
-#     fig2 = px.box(
-#         dff,
-#         x='Position',
-#         y='Temperature (°C)',
-#         color='Position',
-#         color_discrete_map={1: '#d50000', 2: '#ff6d00', 3: '#ffcc00', 4: '#007acc'},
-#         template="plotly_white"
-#     )
-#     red_temp = dff['Absolute Red Temp (°C)'].min()
-#     amber_temp = dff['Absolute Amber Temp (°C)'].min()
-#     fig2.add_hline(y=red_temp, line_dash="dash", line_color="red", annotation_text="Red Temp", annotation_position="top right")
-#     fig2.add_hline(y=amber_temp, line_color="orange", annotation_text="Amber Temp", annotation_position="bottom right")
-#     fig2.update_layout(margin=dict(t=40))
-#     st.plotly_chart(fig2, use_container_width=True)
-
-# Insight 1
-# Insight 1
-# ================= OBJECTIVE 1 =================
-# Ensure 'Position' is treated as ordered categorical for consistent sorting
 dff = dff.copy()
 dff['Position'] = pd.Categorical(dff['Position'], categories=[1, 2, 3, 4], ordered=True)
 
@@ -495,197 +452,8 @@ st.markdown(f"""
     </div>
 </div>
 """, unsafe_allow_html=True)
-# ================= OBJECTIVE 2 =================
-# ================= OBJECTIVE 2 =================
-# st.markdown('<h3 class="objective-title">OBJECTIVE 2: Hourly Alarm Trend Analysis — By Tyre Position</h3>', unsafe_allow_html=True)
-
-# # Ambil data alarm
-# alarm_data = dff[dff['is_alarm'] == 1].copy()
-
-# if alarm_data.empty:
-#     st.warning("No alarm data to display.")
-# else:
-#     # Hitung jumlah alarm per jam dan per posisi
-#     hourly_pos_counts = alarm_data.groupby(['hour', 'Position']).size().unstack(fill_value=0)
-
-#     # Pastikan semua posisi (1,2,3,4) ada di kolom
-#     for pos in [1, 2, 3, 4]:
-#         if pos not in hourly_pos_counts.columns:
-#             hourly_pos_counts[pos] = 0
-
-#     # Urutkan kolom
-#     hourly_pos_counts = hourly_pos_counts[[1, 2, 3, 4]]
-
-#     # Gunakan warna sesuai Objective 1
-#     color_map = {1: '#003DA5', 2: '#7FA6E8', 3: '#FFB300', 4: '#FFE082'}
-
-#     # Buat grafik trend
-#     fig = px.line(
-#         hourly_pos_counts,
-#         x=hourly_pos_counts.index,
-#         y=[1, 2, 3, 4],
-#         title="Hourly Alarm Count by Tyre Position",
-#         labels={'value': 'Number of Alarms', 'variable': 'Tyre Position'},
-#         template="plotly_white",
-#         line_shape='linear',
-#         color_discrete_map=color_map
-#     )
-
-#     # Ganti nama legend
-#     fig.for_each_trace(lambda t: t.update(name=f'Position {int(t.name)}'))
-
-#     fig.update_layout(
-#         xaxis=dict(
-#             title="Hour of Day",
-#             tickmode='array',
-#             tickvals=list(range(0, 24)),
-#             ticktext=[f"{h:02d}:00" for h in range(24)],
-#             tickangle=45
-#         ),
-#         yaxis=dict(title="Number of Alarms"),
-#         legend_title_text='Tyre Position',
-#         margin=dict(t=40, b=20, l=20, r=20)
-#     )
-
-#     st.plotly_chart(fig, use_container_width=True)
-
-#     # Insight singkat
-#     total_by_pos = hourly_pos_counts.sum()
-#     insight_text = f"""
-#     • Position 1: {total_by_pos[1]} alarms | Position 2: {total_by_pos[2]} alarms
-#     • Position 3: {total_by_pos[3]} alarms | Position 4: {total_by_pos[4]} alarms
-#     • Peak alarm patterns vary by position — suggesting location-specific stress factors.
-#     """
-#     st.markdown(f"""
-#     <div class="insight-box">
-#         <div class="content">
-#     {insight_text.strip()}
-#         </div>
-#     </div>
-#     """, unsafe_allow_html=True)
-# import pandas as pd
-# import plotly.express as px
-# import streamlit as st
-
-# # Judul Objective 2 — Center-aligned, elegant box-style (kanan atas kotak)
-# st.markdown('''
-# <div style="text-align: center; margin-bottom: 16px;">
-#   <div style="
-#     background-color: #2C2C2C; 
-#     color: white; 
-#     padding: 10px 16px; 
-#     display: inline-block; 
-#     border-radius: 6px;
-#     font-weight: 600;
-#     position: relative;
-#     top: 0; right: 0;
-#   ">
-#     OBJECTIVE 2: Hourly Data Capture vs Alarm Count Analysis
-#   </div>
-# </div>
-# ''', unsafe_allow_html=True)
-
-# col1, col2 = st.columns(2)
-
-# # =============== COL 1: Capture Data per Jam per Tyre ===============
-# with col1:
-#     st.markdown('<h5 style="text-align:center; margin-top: 0;">Data Capture per Hour by Tyre Position</h5>', unsafe_allow_html=True)
-
-#     # Hitung jumlah data capture per jam dan per posisi (semua data, bukan hanya alarm)
-#     capture_data = dff.copy()
-#     hourly_capture_counts = capture_data.groupby(['hour', 'Position']).size().unstack(fill_value=0)
-
-#     # Pastikan semua posisi (1,2,3,4) ada
-#     for pos in [1, 2, 3, 4]:
-#         if pos not in hourly_capture_counts.columns:
-#             hourly_capture_counts[pos] = 0
-
-#     hourly_capture_counts = hourly_capture_counts[[1, 2, 3, 4]].copy()
-
-#     # Melt data untuk plotting
-#     hourly_capture_melted = hourly_capture_counts.reset_index().melt(
-#         id_vars='hour',
-#         value_vars=[1, 2, 3, 4],
-#         var_name='Position',
-#         value_name='Capture Count'
-#     )
-#     hourly_capture_melted['Position'] = hourly_capture_melted['Position'].astype(str)
-
-#     # Warna sesuai preferensi
-#     color_map = {
-#         '1': '#003DA5',   # Dark blue
-#         '2': '#7FA6E8',   # Light blue
-#         '3': '#FFB300',   # Amber (PLN yellow)
-#         '4': '#FFE082'    # Light amber
-#     }
-
-#     fig1 = px.line(
-#         hourly_capture_melted,
-#         x='hour',
-#         y='Capture Count',
-#         color='Position',
-#         color_discrete_map=color_map,
-#         title="Data Capture per Hour by Tyre Position",
-#         labels={'Capture Count': 'Number of Records', 'Position': 'Tyre Position'},
-#         line_shape='linear',
-#         template="plotly_white"
-#     )
-
-#     fig1.update_layout(
-#         xaxis=dict(
-#             title="Hour of Day",
-#             tickmode='array',
-#             tickvals=list(range(0, 24)),
-#             ticktext=[f"{h:02d}:00" for h in range(24)],
-#             tickangle=45
-#         ),
-#         yaxis=dict(title="Number of Records"),
-#         legend_title_text='Tyre Position',
-#         margin=dict(t=40, b=40, l=40, r=20),
-#         title_x=0.5
-#     )
-
-#     st.plotly_chart(fig1, use_container_width=True)
-
-# # =============== COL 2: Count Alarm (Amber & Red Only) ===============
-# with col2:
-#     st.markdown('<h5 style="text-align:center; margin-top: 0;">Alarm Count (Amber & Red Only) per Hour by Tyre Position</h5>', unsafe_allow_html=True)
-
-#     # Filter hanya alarm Amber dan Red
-#     alarm_data = dff[dff['is_alarm'] == 1].copy()
-#     alarm_data = alarm_data[alarm_data['Alarm Status'].str.contains('Amber|Red', case=False, na=False)]
-
-#     if alarm_data.empty:
-#         st.warning("No Amber or Red alarm data to display.")
-#     else:
-#         # Hitung jumlah alarm per jam dan per posisi
-#         hourly_alarm_counts = alarm_data.groupby(['hour', 'Position']).size().unstack(fill_value=0)
-
-#         # Pastikan semua posisi (1,2,3,4) ada
-#         for pos in [1, 2, 3, 4]:
-#             if pos not in hourly_alarm_counts.columns:
-#                 hourly_alarm_counts[pos] = 0
-
-#         hourly_alarm_counts = hourly_alarm_counts[[1, 2, 3, 4]].copy()
-
-#         # Melt data untuk plotting
-#         hourly_alarm_melted = hourly_alarm_counts.reset_index().melt(
-#             id_vars='hour',
-#             value_vars=[1, 2, 3, 4],
-#             var_name='Position',
-#             value_name='Alarm Count'
-#         )
-#         hourly_alarm_melted['Position'] = hourly_alarm_melted['Position'].astype(str)
-
-#         fig2 = px.line(
-#             hourly_alarm_melted,
-#             x='hour',
-#             y='Alarm Count',
-
 st.markdown("""
-<h3 class="objective-title">OBJECTIVE 2: Alarm Frequency Analysis — Shift-Based Radial Charts</h3>
-<small>*Showing alarm types by shift: Normal (Green), Amber (Yellow), Red (Red)</small>
-""", unsafe_allow_html=True)
+<h3 class="objective-title">OBJECTIVE 2: Shift and Tyre Position - How Are Alarms Concentrated Across Shifts and Tyres?</h3>""", unsafe_allow_html=True)
 
 # Filter semua data (termasuk alarm normal)
 alarm_data = dff.copy()
@@ -723,27 +491,36 @@ def create_radial_chart(pos_data, title, shift_hours, shift_type):
         ticktext = ["03:00", "18:00/06:00", "21:00", "00:00"]
 
     fig = go.Figure()
+
+    # Tambahkan trace untuk masing-masing kategori
     fig.add_trace(go.Barpolar(
         r=hourly_normal.values,
         theta=theta,
         name='Normal',
         marker_color='#2E7D32',  # Hijau
-        opacity=0.8
+        opacity=0.8,
+        hovertemplate='<b>Hour:</b> %{theta:.0f}<br><b>Count:</b> %{r}<br><b>Status:</b> Normal<extra></extra>',
+        customdata=shift_hours
     ))
     fig.add_trace(go.Barpolar(
         r=hourly_amber.values,
         theta=theta,
         name='Amber',
         marker_color='#FFC107',  # Kuning
-        opacity=0.8
+        opacity=0.8,
+        hovertemplate='<b>Hour:</b> %{theta:.0f}<br><b>Count:</b> %{r}<br><b>Status:</b> Amber<extra></extra>',
+        customdata=shift_hours
     ))
     fig.add_trace(go.Barpolar(
         r=hourly_red.values,
         theta=theta,
         name='Red',
         marker_color='#D32F2F',  # Merah
-        opacity=0.8
+        opacity=0.8,
+        hovertemplate='<b>Hour:</b> %{theta:.0f}<br><b>Count:</b> %{r}<br><b>Status:</b> Red<extra></extra>',
+        customdata=shift_hours
     ))
+
     fig.update_layout(
         polar=dict(
             angularaxis=dict(
@@ -773,7 +550,7 @@ with col1:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 1 (06:00–18:00)</div>', unsafe_allow_html=True)
     pos1_data = alarm_data[alarm_data['Position'] == 1].copy()
     pos1_data = pos1_data[pos1_data['hour'].between(6, 17, inclusive='both')]
-    fig1 = create_radial_chart(pos1_data, ")", list(range(6, 18)), 'pagi')
+    fig1 = create_radial_chart(pos1_data, "Position 1 (06:00–18:00)", list(range(6, 18)), 'pagi')
     if fig1 is not None:
         st.plotly_chart(fig1, use_container_width=True)
     else:
@@ -784,7 +561,7 @@ with col2:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 1 (18:00–06:00)</div>', unsafe_allow_html=True)
     pos1_data = alarm_data[alarm_data['Position'] == 1].copy()
     pos1_data = pos1_data[~pos1_data['hour'].between(6, 17, inclusive='both')]
-    fig2 = create_radial_chart(pos1_data, "", list(range(18, 24)) + list(range(0, 6)), 'sore')
+    fig2 = create_radial_chart(pos1_data, "Position 1 (18:00–06:00)", list(range(18, 24)) + list(range(0, 6)), 'sore')
     if fig2 is not None:
         st.plotly_chart(fig2, use_container_width=True)
     else:
@@ -795,7 +572,7 @@ with col3:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 2 (06:00–18:00)</div>', unsafe_allow_html=True)
     pos2_data = alarm_data[alarm_data['Position'] == 2].copy()
     pos2_data = pos2_data[pos2_data['hour'].between(6, 17, inclusive='both')]
-    fig3 = create_radial_chart(pos2_data, "", list(range(6, 18)), 'pagi')
+    fig3 = create_radial_chart(pos2_data, "Position 2 (06:00–18:00)", list(range(6, 18)), 'pagi')
     if fig3 is not None:
         st.plotly_chart(fig3, use_container_width=True)
     else:
@@ -806,7 +583,7 @@ with col4:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 2 (18:00–06:00)</div>', unsafe_allow_html=True)
     pos2_data = alarm_data[alarm_data['Position'] == 2].copy()
     pos2_data = pos2_data[~pos2_data['hour'].between(6, 17, inclusive='both')]
-    fig4 = create_radial_chart(pos2_data, "", list(range(18, 24)) + list(range(0, 6)), 'sore')
+    fig4 = create_radial_chart(pos2_data, "Position 2 (18:00–06:00)", list(range(18, 24)) + list(range(0, 6)), 'sore')
     if fig4 is not None:
         st.plotly_chart(fig4, use_container_width=True)
     else:
@@ -818,7 +595,7 @@ with col5:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 3 (06:00–18:00)</div>', unsafe_allow_html=True)
     pos3_data = alarm_data[alarm_data['Position'] == 3].copy()
     pos3_data = pos3_data[pos3_data['hour'].between(6, 17, inclusive='both')]
-    fig5 = create_radial_chart(pos3_data, "", list(range(6, 18)), 'pagi')
+    fig5 = create_radial_chart(pos3_data, "Position 3 (06:00–18:00)", list(range(6, 18)), 'pagi')
     if fig5 is not None:
         st.plotly_chart(fig5, use_container_width=True)
     else:
@@ -829,7 +606,7 @@ with col6:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 3 (18:00–06:00)</div>', unsafe_allow_html=True)
     pos3_data = alarm_data[alarm_data['Position'] == 3].copy()
     pos3_data = pos3_data[~pos3_data['hour'].between(6, 17, inclusive='both')]
-    fig6 = create_radial_chart(pos3_data, "", list(range(18, 24)) + list(range(0, 6)), 'sore')
+    fig6 = create_radial_chart(pos3_data, "Position 3 (18:00–06:00)", list(range(18, 24)) + list(range(0, 6)), 'sore')
     if fig6 is not None:
         st.plotly_chart(fig6, use_container_width=True)
     else:
@@ -840,7 +617,7 @@ with col7:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 4 (06:00–18:00)</div>', unsafe_allow_html=True)
     pos4_data = alarm_data[alarm_data['Position'] == 4].copy()
     pos4_data = pos4_data[pos4_data['hour'].between(6, 17, inclusive='both')]
-    fig7 = create_radial_chart(pos4_data, "", list(range(6, 18)), 'pagi')
+    fig7 = create_radial_chart(pos4_data, "Position 4 (06:00–18:00)", list(range(6, 18)), 'pagi')
     if fig7 is not None:
         st.plotly_chart(fig7, use_container_width=True)
     else:
@@ -851,7 +628,7 @@ with col8:
     st.markdown('<div style="text-align:center; font-weight:bold; margin-bottom: 8px;">Position 4 (18:00–06:00)</div>', unsafe_allow_html=True)
     pos4_data = alarm_data[alarm_data['Position'] == 4].copy()
     pos4_data = pos4_data[~pos4_data['hour'].between(6, 17, inclusive='both')]
-    fig8 = create_radial_chart(pos4_data, "", list(range(18, 24)) + list(range(0, 6)), 'sore')
+    fig8 = create_radial_chart(pos4_data, "Position 4 (18:00–06:00)", list(range(18, 24)) + list(range(0, 6)), 'sore')
     if fig8 is not None:
         st.plotly_chart(fig8, use_container_width=True)
     else:
@@ -886,11 +663,64 @@ else:
     red_alarms = alarm_data[alarm_data['Alarm Status'].str.contains('Red', na=False)].shape[0]
     amber_alarms = alarm_data[alarm_data['Alarm Status'].str.contains('Amber', na=False)].shape[0]
 
+    # Insight Spesifik Per Position dan Shift
     insight_lines = [
         f"• {dominant_band} is the dominant period ({dominant_pct:.1f}% of all data).",
         f"• {second_dominant_band} is the second-highest period ({second_pct:.1f}% of data).",
         f"• Total: Normal={normal_alarms}, Amber={amber_alarms}, Red={red_alarms}"
     ]
+
+    # Position 1 (Shift Pagi)
+    pos1_pagi = alarm_data[(alarm_data['Position'] == 1) & (alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos1_pagi.empty:
+        pos1_pagi_total = pos1_pagi.groupby('hour').size()
+        if not pos1_pagi_total.empty:
+            dominant_hour_p1_pagi = pos1_pagi_total.idxmax()
+            dominant_count_p1_pagi = pos1_pagi_total.max()
+            insight_lines.append(f"• Position 1 (06:00–18:00): Dominant alarm at {dominant_hour_p1_pagi:02d}:00 with {dominant_count_p1_pagi} alarms.")
+
+    # Position 1 (Shift Sore)
+    pos1_sore = alarm_data[(alarm_data['Position'] == 1) & (~alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos1_sore.empty:
+        pos1_sore_red = pos1_sore[pos1_sore['Alarm Status'].str.contains('Red', na=False)]
+        if not pos1_sore_red.empty:
+            red_percentage_p1_sore = (len(pos1_sore_red) / len(pos1_sore)) * 100
+            insight_lines.append(f"• Position 1 (18:00–06:00): Red alarms account for {red_percentage_p1_sore:.1f}% of total alarms.")
+
+    # Position 3 (Shift Pagi)
+    pos3_pagi = alarm_data[(alarm_data['Position'] == 3) & (alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos3_pagi.empty:
+        pos3_pagi_total = pos3_pagi.groupby('hour').size()
+        if not pos3_pagi_total.empty:
+            dominant_hour_p3_pagi = pos3_pagi_total.idxmax()
+            dominant_count_p3_pagi = pos3_pagi_total.max()
+            insight_lines.append(f"• Position 3 (06:00–18:00): Dominant alarm at {dominant_hour_p3_pagi:02d}:00 with {dominant_count_p3_pagi} alarms.")
+
+    # Position 3 (Shift Sore)
+    pos3_sore = alarm_data[(alarm_data['Position'] == 3) & (~alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos3_sore.empty:
+        pos3_sore_amber = pos3_sore[pos3_sore['Alarm Status'].str.contains('Amber', na=False)]
+        if not pos3_sore_amber.empty:
+            amber_percentage_p3_sore = (len(pos3_sore_amber) / len(pos3_sore)) * 100
+            insight_lines.append(f"• Position 3 (18:00–06:00): Amber alarms account for {amber_percentage_p3_sore:.1f}% of total alarms.")
+
+    # Position 4 (Shift Pagi)
+    pos4_pagi = alarm_data[(alarm_data['Position'] == 4) & (alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos4_pagi.empty:
+        pos4_pagi_total = pos4_pagi.groupby('hour').size()
+        if not pos4_pagi_total.empty:
+            dominant_hour_p4_pagi = pos4_pagi_total.idxmax()
+            dominant_count_p4_pagi = pos4_pagi_total.max()
+            insight_lines.append(f"• Position 4 (06:00–18:00): Dominant alarm at {dominant_hour_p4_pagi:02d}:00 with {dominant_count_p4_pagi} alarms.")
+
+    # Position 4 (Shift Sore)
+    pos4_sore = alarm_data[(alarm_data['Position'] == 4) & (~alarm_data['hour'].between(6, 17, inclusive='both'))]
+    if not pos4_sore.empty:
+        pos4_sore_amber = pos4_sore[pos4_sore['Alarm Status'].str.contains('Amber', na=False)]
+        if not pos4_sore_amber.empty:
+            amber_percentage_p4_sore = (len(pos4_sore_amber) / len(pos4_sore)) * 100
+            insight_lines.append(f"• Position 4 (18:00–06:00): Amber alarms account for {amber_percentage_p4_sore:.1f}% of total alarms.")
+
     insight_text = "\n".join(insight_lines)
 
 # =============== DISPLAY INSIGHT ===============
@@ -901,6 +731,7 @@ st.markdown(f"""
     </div>
 </div>
 """, unsafe_allow_html=True)
+
 # ================= OBJECTIVE 3 =================
 st.markdown('<h3 class="objective-title">OBJECTIVE 3: Correlation — How Does Heat Influence Pressure and Which Tyres Trigger Red Alarms?</h3>', unsafe_allow_html=True)
 
@@ -1227,12 +1058,23 @@ def safe_corr(a, b):
     return np.corrcoef(a[mask], b[mask])[0, 1]
 
 corr_p_t_front = safe_corr(front_df['Temperature (°C)'], front_df['Pressure (psi)'])
-corr_t_s_front = safe_corr(front_df['Temperature (°C)'], front_df['Speed (km/h)'])
 corr_p_t_rear = safe_corr(rear_df['Temperature (°C)'], rear_df['Pressure (psi)'])
-corr_t_s_rear = safe_corr(rear_df['Temperature (°C)'], rear_df['Speed (km/h)'])
 
-insight_text = f"""
-Front tyres show stronger temperature-driven pressure response (r = {corr_p_t_front:.2f}) vs rear (r = {corr_p_t_rear:.2f}), confirming heat has greater impact on front tyre inflation. Temperature speed correlation is low on both front (r = {corr_t_s_front:.2f}) and rear (r = {corr_t_s_rear:.2f}), indicating speed alone is not the primary heat source — likely dominated by load and friction. Red and amber alarms cluster in specific pressure-temperature zones, indicating critical failure thresholds.
+# Hitung jumlah alarm red saat suhu >= 52°C di front tyre
+high_temp_front = front_df[front_df['Temperature (°C)'] >= 52]
+red_high_pressure_count = high_temp_front[high_temp_front['Alarm Status'] == 'Red High Pressure'].shape[0]
+
+# Hitung korelasi Pressure vs T/V (Temperature / Speed)
+if not front_df.empty and (front_df['Speed (km/h)'] > 0).any():
+    front_df_filtered = front_df[front_df['Speed (km/h)'] > 0].copy()
+    front_df_filtered['Temp_Speed_Ratio'] = front_df_filtered['Temperature (°C)'] / front_df_filtered['Speed (km/h)']
+    corr_p_tv_front = safe_corr(front_df_filtered['Pressure (psi)'], front_df_filtered['Temp_Speed_Ratio'])
+else:
+    corr_p_tv_front = 0.0
+# Strong correlation between temperature and pressure in front tyres (r = {corr_p_t_front:.2f}) vs rear (r = {corr_p_t_rear:.2f}).
+# •
+insight_text = f""" At temperatures ≥52°C, front tyres trigger {red_high_pressure_count} Red High Pressure alarms, indicating critical heat thresholds.
+• Pressure vs (T/v) shows weak correlation (r = {corr_p_tv_front:.2f}), suggesting speed alone is not primary heat factor.
 """
 
 st.markdown(f"""
@@ -1243,8 +1085,8 @@ st.markdown(f"""
 </div>
 """, unsafe_allow_html=True)
 
-# ================= OBJECTIVE 5 =================
-st.markdown('<h3 class="objective-title">OBJECTIVE 5: Spatial Risk Mapping — Where Do Red Pressure Alarms Occur Most Frequently?</h3>', unsafe_allow_html=True)
+# ================= OBJECTIVE 4 =================
+st.markdown('<h3 class="objective-title">OBJECTIVE 4: Spatial Risk Mapping — Where Do Red Pressure Alarms Occur Most Frequently?</h3>', unsafe_allow_html=True)
 
 st.markdown('<h5 style="text-align:center; margin-top: 0;">Tyre Alarms Distribution by Location</h5>', unsafe_allow_html=True)
 
@@ -1261,7 +1103,65 @@ else:
         width='100%',
         height='520px'
     )
-    
+
+    # === Tambahkan Polygon untuk Location 1 & 2 (Contoh koordinat — ganti sesuai data Anda)
+    # Jika Anda punya kolom 'Zone' atau 'Location', gunakan itu untuk grouping
+    # Di sini saya asumsikan:
+    # - Location 1: Zona dengan nama 'Parking 1'
+    # - Location 2: Zona dengan nama 'Parking 2'
+
+    # Contoh koordinat polygon (ganti dengan nilai nyata dari data Anda jika ada)
+    # Jika tidak ada, Anda bisa definisikan manual berdasarkan range latitude/longitude
+
+    # Untuk demo, saya buat polygon manual
+    # Location 1: Parking 1
+    location1_coords = [
+        [center_lat - 0.0008, center_lon - 0.001],   # kiri bawah
+        [center_lat - 0.0008, center_lon + 0.001],   # kiri atas
+        [center_lat + 0.0008, center_lon + 0.001],   # kanan atas
+        [center_lat + 0.0008, center_lon - 0.001],   # kanan bawah
+        [center_lat - 0.0008, center_lon - 0.001]    # kembali ke awal
+    ]
+    folium.Polygon(
+        locations=location1_coords,
+        color='#1976D2',
+        fill_color='#1976D2',
+        fill_opacity=0.1,
+        weight=2,
+        popup="Location 1"
+    ).add_to(m)
+
+    # Location 2: Parking 2
+    location2_coords = [
+        [center_lat + 0.001, center_lon - 0.0015],
+        [center_lat + 0.001, center_lon + 0.0015],
+        [center_lat + 0.002, center_lon + 0.0015],
+        [center_lat + 0.002, center_lon - 0.0015],
+        [center_lat + 0.001, center_lon - 0.0015]
+    ]
+    folium.Polygon(
+        locations=location2_coords,
+        color='#FF9800',
+        fill_color='#FF9800',
+        fill_opacity=0.1,
+        weight=2,
+        popup="Location 2"
+    ).add_to(m)
+
+    # Tambahkan teks label di tengah polygon
+    folium.Marker(
+        location=[center_lat - 0.0004, center_lon],
+        icon=folium.DivIcon(html=f'<div style="font-weight:bold; font-size:14px; color:#1976D2; text-shadow: 1px 1px 2px white;">Location 1</div>'),
+        tooltip="Location 1"
+    ).add_to(m)
+
+    folium.Marker(
+        location=[center_lat + 0.0015, center_lon],
+        icon=folium.DivIcon(html=f'<div style="font-weight:bold; font-size:14px; color:#FF9800; text-shadow: 1px 1px 2px white;">Location 2</div>'),
+        tooltip="Location 2"
+    ).add_to(m)
+
+    # === Plot marker per tyre
     for _, r in valid_gps.iterrows():
         color = '#D32F2F' if r['Alarm Status'] == 'Red High Pressure' else '#2E7D32'
         radius = 6 + (r['Temperature (°C)'] - valid_gps['Temperature (°C)'].min()) / (valid_gps['Temperature (°C)'].max() - valid_gps['Temperature (°C)'].min() + 1e-5) * 12
@@ -1285,7 +1185,7 @@ else:
             weight=1,
             popup=folium.Popup(popup_html, max_width=250)
         ).add_to(m)
-    
+
     # Legend
     legend_html = '''
     <div style="
@@ -1303,17 +1203,14 @@ else:
         <b>Legend</b><br>
         <span style="color:#2E7D32">●</span> Normal (No Alarm)<br>
         <span style="color:#D32F2F">●</span> Red Pressure<br>
-        <span style="color:#1976D2">▲</span> Front Tyre<br>
-        <span style="color:#1976D2">★</span> Rear Tyre<br>
         <i>Size ∝ Temperature</i>
     </div>
     '''
     m.get_root().html.add_child(folium.Element(legend_html))
-    
+
     st_folium(m, width='100%', height=520, returned_objects=[])
 
-# Insight 4
-# Analisis data untuk menentukan pola spasial
+# =============== INSIGHT 4 ===============
 if not valid_gps.empty:
     # Hitung jumlah alarm per zona
     zone_counts = valid_gps[valid_gps['is_alarm'] == 1]['Zone'].value_counts()
@@ -1335,15 +1232,13 @@ if not valid_gps.empty:
     else:
         front_percentage = 0
 
-    insight_text = f"""
-    Alarm concentration is highest in {top_zone}, with {top_zone_count} alarms representing {percentage:.1f}% of total alarms.
-Front tyres account for {front_percentage:.1f}% of all alarms, indicating a higher alarm occurrence compared to rear tyres.
-GNSS data confirms alarm clustering within specific operational zones. Alarm events are concentrated by location and tyre position based on observed data distribution.
-"""
+    insight_text = f"""Alarm concentration is highest in {top_zone}, with {top_zone_count} alarms representing {percentage:.1f}% of total alarms. Front tyres account for {front_percentage:.1f}% of all alarms, indicating a higher alarm occurrence compared to rear tyres. GNSS data confirms alarm clustering within specific operational zones. Alarm events are concentrated by location and tyre position based on observed data distribution.
+    """
+
 else:
     insight_text = """
-No valid GNSS data available for analysis.
-"""
+    No valid GNSS data available for analysis.
+    """
 
 st.markdown(f"""
 <div class="insight-box">
@@ -1352,19 +1247,17 @@ st.markdown(f"""
     </div>
 </div>
 """, unsafe_allow_html=True)
+
 # ================= OBJECTIVE 5 =================
-# ================= OBJECTIVE 6 =================
-st.markdown('<h3 class="objective-title">OBJECTIVE 6: Insights & Mitigation — How Can Red Pressure Alarms Be Reduced?</h3>', unsafe_allow_html=True)
+st.markdown('<h3 class="objective-title">OBJECTIVE 5: Insights & Mitigation — How Can Red Pressure Alarms Be Reduced?</h3>', unsafe_allow_html=True)
 
 # --- DATA PREP ---
 front_pressure_avg = dff[dff['Position'].isin([1, 2])]['Pressure (psi)'].mean()
 front_temp_avg = dff[dff['Position'].isin([1, 2])]['Temperature (°C)'].mean()
-
 hourly_counts = dff[dff['is_alarm'] == 1]['hour'].value_counts().reindex(range(24), fill_value=0)
 dominant_hour = hourly_counts.idxmax() if len(hourly_counts) > 0 else "N/A"
 total_alarms = hourly_counts.sum()
 dominant_percentage = (hourly_counts[dominant_hour] / total_alarms) * 100 if total_alarms > 0 else 0
-
 zone_counts = dff[dff['is_alarm'] == 1]['Zone'].value_counts()
 top_zone = zone_counts.index[0] if not zone_counts.empty else "N/A"
 top_zone_percentage = (zone_counts.iloc[0] / total_alarms) * 100 if total_alarms > 0 else 0
@@ -1383,90 +1276,141 @@ if not rear_df.empty and len(rear_df[['Speed (km/h)']].dropna()) > 1 and len(rea
 else:
     corr_rear = 0
 
-# Insight
-insight_text = f"""1. Front tyres (Pos 1 & 2) show average pressure of {front_pressure_avg:.1f} psi and temperature of {front_temp_avg:.1f}°C, indicating potential over-inflation or insufficient load distribution.
-<br>
-2. Peak alarms occur at {dominant_hour}:00–{(dominant_hour+1)%24}:00, accounting for {dominant_percentage:.1f}% of total alarms, primarily in {top_zone}.
-<br>
-3. Front tyres exhibit a pressure–temperature correlation of r = {corr_front:.2f}, while rear tyres show r = {corr_rear:.2f}, indicating higher operational stress on front tyres.
-<br>
-4. {top_zone} contains {top_zone_percentage:.1f}% of all alarms, confirmed as a high-risk hotspot through GNSS data."""
+# Insight dari Objective 1-4
+# Insight 1: Fisika & Mekanikal
+front_pressure_avg_obj1 = dff[dff['Position'].isin([1, 2])]['Pressure (psi)'].mean()
+rear_pressure_avg_obj1 = dff[dff['Position'].isin([3, 4])]['Pressure (psi)'].mean()
+front_temp_avg_obj1 = dff[dff['Position'].isin([1, 2])]['Temperature (°C)'].mean()
+rear_temp_avg_obj1 = dff[dff['Position'].isin([3, 4])]['Temperature (°C)'].mean()
+
+# Insight 2: Shift & Alarm Distribution
+pos1_pagi = dff[(dff['Position'] == 1) & (dff['hour'].between(6, 17, inclusive='both'))]
+pos1_sore = dff[(dff['Position'] == 1) & (~dff['hour'].between(6, 17, inclusive='both'))]
+pos3_pagi = dff[(dff['Position'] == 3) & (dff['hour'].between(6, 17, inclusive='both'))]
+pos3_sore = dff[(dff['Position'] == 3) & (~dff['hour'].between(6, 17, inclusive='both'))]
+
+# Insight 3: Korelasi
+corr_p_t_front = safe_corr(front_df['Temperature (°C)'], front_df['Pressure (psi)'])
+corr_p_t_rear = safe_corr(rear_df['Temperature (°C)'], rear_df['Pressure (psi)'])
+
+high_temp_front = front_df[front_df['Temperature (°C)'] >= 52]
+red_high_pressure_count = high_temp_front[high_temp_front['Alarm Status'] == 'Red High Pressure'].shape[0]
+
+if not front_df.empty and (front_df['Speed (km/h)'] > 0).any():
+    front_df_filtered = front_df[front_df['Speed (km/h)'] > 0].copy()
+    front_df_filtered['Temp_Speed_Ratio'] = front_df_filtered['Temperature (°C)'] / front_df_filtered['Speed (km/h)']
+    corr_p_tv_front = safe_corr(front_df_filtered['Pressure (psi)'], front_df_filtered['Temp_Speed_Ratio'])
+else:
+    corr_p_tv_front = 0.0
+
+# Insight 4: Spatial
+if not valid_gps.empty:
+    zone_counts_obj4 = valid_gps[valid_gps['is_alarm'] == 1]['Zone'].value_counts()
+    top_zone_obj4 = zone_counts_obj4.index[0] if not zone_counts_obj4.empty else "N/A"
+    top_zone_count_obj4 = zone_counts_obj4.iloc[0] if not zone_counts_obj4.empty else 0
+    total_alarms_obj4 = valid_gps[valid_gps['is_alarm'] == 1].shape[0]
+    percentage_obj4 = (top_zone_count_obj4 / total_alarms_obj4) * 100 if total_alarms_obj4 > 0 else 0
+    front_alarms_obj4 = valid_gps[(valid_gps['is_alarm'] == 1) & (valid_gps['Position'].isin([1, 2]))].shape[0]
+    rear_alarms_obj4 = valid_gps[(valid_gps['is_alarm'] == 1) & (valid_gps['Position'].isin([3, 4]))].shape[0]
+    total_alarms_obj4_total = front_alarms_obj4 + rear_alarms_obj4
+    if total_alarms_obj4_total > 0:
+        front_percentage_obj4 = (front_alarms_obj4 / total_alarms_obj4_total) * 100
+    else:
+        front_percentage_obj4 = 0
+else:
+    top_zone_obj4 = "N/A"
+    percentage_obj4 = 0
+    front_percentage_obj4 = 0
 
+# Gabungkan semua insight dari Objective 1-4
+insight_text = f"""
+1. **Pressure & Temperature Distribution (Objective 1):**
+   • Front tyres (Pos 1 & 2) show lower pressure ({front_pressure_avg_obj1:.1f} psi) and higher temperature ({front_temp_avg_obj1:.1f}°C) due to higher stress from braking/steering.
+   • Rear tyres (Pos 3 & 4) show higher pressure ({rear_pressure_avg_obj1:.1f} psi) and lower temperature ({rear_temp_avg_obj1:.1f}°C), indicating stable operation.
+
+2. **Alarm Distribution by Shift (Objective 2):**
+   • Position 1 (06:00–18:00): Dominant alarm at {dominant_hour}:00 with {hourly_counts[dominant_hour]} alarms.
+   • Position 1 (18:00–06:00): Red alarms account for {(len(pos1_sore[pos1_sore['Alarm Status'].str.contains('Red', na=False)]) / len(pos1_sore)) * 100:.1f}% of total alarms.
+   • Position 3 (06:00–18:00): Dominant alarm at {dominant_hour}:00 with {hourly_counts[dominant_hour]} alarms.
+   • Position 3 (18:00–06:00): Amber alarms account for {(len(pos3_sore[pos3_sore['Alarm Status'].str.contains('Amber', na=False)]) / len(pos3_sore)) * 100:.1f}% of total alarms.
+
+3. **Correlation Analysis (Objective 3):**
+   • Strong correlation between temperature and pressure in front tyres (r = {corr_p_t_front:.2f}) vs rear (r = {corr_p_t_rear:.2f}).
+   • At temperatures ≥52°C, front tyres trigger {red_high_pressure_count} Red High Pressure alarms.
+   • Pressure vs (T/v) shows weak correlation (r = {corr_p_tv_front:.2f}), suggesting speed alone is not primary heat factor.
+
+4. **Spatial Risk Mapping (Objective 4):**
+   • Alarm concentration is highest in {top_zone_obj4}, with {top_zone_count_obj4} alarms representing {percentage_obj4:.1f}% of total alarms.
+   • Front tyres account for {front_percentage_obj4:.1f}% of all alarms, indicating higher alarm occurrence compared to rear tyres.
+"""
 
 try:
     import requests
     import json
-
-    API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta    "
-
+    API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
     prompt = f"""
 Role: Fleet Operations Risk Analyst
-
 Insights:
-- High-risk zone: {top_zone} ({top_zone_percentage:.1f}% of alarms)
-- Front tyres: 62% of total alarms
+- High-risk zone: {top_zone_obj4} ({percentage_obj4:.1f}% of alarms)
+- Front tyres: {front_percentage_obj4:.1f}% of total alarms
 - Peak alarm hour: {dominant_hour}:00 ({dominant_percentage:.1f}%)
-- Front tyre pressure–temperature correlation r = {corr_front:.2f}
-
+- Front tyre pressure–temperature correlation r = {corr_p_t_front:.2f}
+- At temperatures ≥52°C, {red_high_pressure_count} Red High Pressure alarms
+- Strong correlation between temperature and pressure in front tyres (r = {corr_p_t_front:.2f})
 Task:
 Generate:
 1. Business Recommendations
 2. Risk Mitigation Actions
-
 Rules:
 - Use only provided insights
 - No root-cause speculation
 - Business-ready language
 """
-
     payload = {
         "inputs": prompt,
         "parameters": {
-            "max_new_tokens": 25000,
+            "max_new_tokens": 250,
             "temperature": 0.8,
             "top_p": 0.9
         }
     }
-
     response = requests.post(API_URL, json=payload)
     generated_text = response.json()[0]["generated_text"]
-
     recommendation_text = generated_text
     risk_mitigation_text = generated_text
-
     # Jika response kosong, gunakan versi manual
     if recommendation_text == "":
         recommendation_text = f"""1. Calibrate front tyre pressure regularly to maintain optimal {front_pressure_avg:.1f} psi and prevent over-inflation.
 <br>
-2. Implement operational restrictions during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) in {top_zone} to reduce alarm frequency.
+2. Implement operational restrictions during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) in {top_zone_obj4} to reduce alarm frequency.
 <br>
-3. Monitor pressure and temperature correlation in front tyres (r = {corr_front:.2f}) to prevent overheating and premature wear.
+3. Monitor pressure and temperature correlation in front tyres (r = {corr_p_t_front:.2f}) to prevent overheating and premature wear.
 <br>
-4. Restrict vehicle access to {top_zone} until pavement maintenance is completed, as it contributes to {top_zone_percentage:.1f}% of alarms."""
+4. Restrict vehicle access to {top_zone_obj4} until pavement maintenance is completed, as it contributes to {percentage_obj4:.1f}% of alarms."""
     if risk_mitigation_text == "":
         risk_mitigation_text = f"""1. Adjust front tyre load distribution to reduce {front_temp_avg:.1f}°C temperature and prevent overheating.
 <br>
 2. Schedule additional inspections during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) when {dominant_percentage:.1f}% of alarms occur.
 <br>
-3. Introduce predictive maintenance for front tyres with correlation r = {corr_front:.2f} to prevent unplanned downtime.
+3. Introduce predictive maintenance for front tyres with correlation r = {corr_p_t_front:.2f} to prevent unplanned downtime.
 <br>
-4. Implement real-time monitoring in {top_zone} where {top_zone_percentage:.1f}% of alarms are concentrated."""
+4. Implement real-time monitoring in {top_zone_obj4} where {percentage_obj4:.1f}% of alarms are concentrated."""
 except:
     # Jika response dari model kosong atau gagal, gunakan versi manual
     recommendation_text = f"""1. Calibrate front tyre pressure regularly to maintain optimal {front_pressure_avg:.1f} psi and prevent over-inflation.
 <br>
-2. Implement operational restrictions during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) in {top_zone} to reduce alarm frequency.
+2. Implement operational restrictions during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) in {top_zone_obj4} to reduce alarm frequency.
 <br>
-3. Monitor pressure and temperature correlation in front tyres (r = {corr_front:.2f}) to prevent overheating and premature wear.
+3. Monitor pressure and temperature correlation in front tyres (r = {corr_p_t_front:.2f}) to prevent overheating and premature wear.
 <br>
-4. Restrict vehicle access to {top_zone} until pavement maintenance is completed, as it contributes to {top_zone_percentage:.1f}% of alarms."""
+4. Restrict vehicle access to {top_zone_obj4} until pavement maintenance is completed, as it contributes to {percentage_obj4:.1f}% of alarms."""
     # Risk Mitigation
     risk_mitigation_text = f"""1. Adjust front tyre load distribution to reduce {front_temp_avg:.1f}°C temperature and prevent overheating.
 <br>
 2. Schedule additional inspections during peak hours ({dominant_hour}:00–{(dominant_hour+1)%24}:00) when {dominant_percentage:.1f}% of alarms occur.
 <br>
-3. Introduce predictive maintenance for front tyres with correlation r = {corr_front:.2f} to prevent unplanned downtime.
-4. Implement real-time monitoring in {top_zone} where {top_zone_percentage:.1f}% of alarms are concentrated."""
+3. Introduce predictive maintenance for front tyres with correlation r = {corr_p_t_front:.2f} to prevent unplanned downtime.
+4. Implement real-time monitoring in {top_zone_obj4} where {percentage_obj4:.1f}% of alarms are concentrated."""
 
 # ============== SUBHEADER + BOX 1: INSIGHT ==============
 st.markdown('<h4 style="text-align:center; margin:10px 0 5px 0; font-weight:bold;">INSIGHT</h4>', unsafe_allow_html=True)