Update app.py

app.py

@@ -772,368 +772,286 @@ st.markdown(f"""
 </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)
+st.markdown("""
+<h3 class="objective-title">OBJECTIVE 2: Shift and Tyre Position - How Are Alarms Concentrated Across Shifts and Tyres?</h3>
+""", unsafe_allow_html=True)
 
-# Prepare data
-front_df = dff[dff['Position'].isin([1, 2])].copy()
-rear_df = dff[dff['Position'].isin([3, 4])].copy()
+# Filter semua data (termasuk alarm normal)
+alarm_data = dff.copy()
 
-col1, col2 = st.columns(2)
+# Buat 2 baris × 4 kolom
+col1, col2, col3, col4 = st.columns(4)
+col5, col6, col7, col8 = st.columns(4)
 
-# =============== COL 1: Front — Temperature → Pressure (Scatter + Regression Area) ===============
-with col1:
-    st.markdown('<h5 style="text-align:center; margin-top: 0;">Front Tyres: Temperature → Pressure</h5>', unsafe_allow_html=True)
-    
-    if not front_df.empty:
-        # Tambahkan kategori alarm status
-        front_df['Category'] = front_df.apply(
-            lambda row: f"Normal Front Tyre" if row['Alarm Status'] == 'No Alarm'
-            else f"Amber Pressure Front Tyre" if 'Amber' in row['Alarm Status']
-            else f"Red Pressure Front Tyre", axis=1
-        )
-        categories = ["Normal Front Tyre", "Amber Pressure Front Tyre", "Red Pressure Front Tyre"]
-        front_df['Category'] = pd.Categorical(front_df['Category'], categories=categories, ordered=True)
-
-        # Filter valid data
-        valid_data = front_df.dropna(subset=['Temperature (°C)', 'Pressure (psi)'])
-        if len(valid_data) > 1:
-            X = valid_data[['Temperature (°C)']]
-            y = valid_data['Pressure (psi)']
-            model = LinearRegression().fit(X, y)
-            x_line = np.linspace(X.min(), X.max(), 100).reshape(-1, 1)
-            y_line = model.predict(x_line)
-            corr = np.corrcoef(valid_data['Temperature (°C)'], valid_data['Pressure (psi)'])[0, 1]
-
-            fig1 = px.scatter(
-                valid_data,
-                x='Temperature (°C)',
-                y='Pressure (psi)',
-                color='Category',
-                color_discrete_map={
-                    "Normal Front Tyre": "#2E7D32",         # Hijau
-                    "Amber Pressure Front Tyre": "#FFC107", # Kuning
-                    "Red Pressure Front Tyre": "#D32F2F"    # Merah
-                },
-                category_orders={'Category': categories},
-                template="plotly_white",
-                labels={'Temperature (°C)': 'Temperature (°C)', 'Pressure (psi)': 'Pressure (psi)'}
-            )
+# Fungsi helper untuk membuat radial chart per posisi dan shift
+def create_radial_chart(pos_data, title, shift_hours, shift_type):
+    if pos_data.empty:
+        return None
 
-            fig1.update_traces(
-                hovertemplate="<b>%{marker.color}</b><br>Temp: %{x:.1f}°C<br>Pressure: %{y:.1f} psi<extra></extra>",
-                marker=dict(size=6)
-            )
+    # Kelompokkan jam dan status
+    hourly_status_counts = pos_data.groupby(['hour', 'Alarm Status']).size().unstack(fill_value=0)
 
-            # Tambahkan garis regresi
-            fig1.add_trace(go.Scatter(
-                x=x_line.flatten(), y=y_line,
-                mode='lines', name='Trend Line',
-                line=dict(color='#1976D2', dash='dot', width=2)
-            ))
-
-            # Tambahkan area confidence interval (soft background)
-            y_pred = model.predict(X)
-            residuals = y - y_pred
-            mse = np.mean(residuals**2)
-            std_error = np.sqrt(mse)
-            y_upper = y_line + 1.96 * std_error
-            y_lower = y_line - 1.96 * std_error
-
-            fig1.add_trace(go.Scatter(
-                x=np.concatenate([x_line.flatten(), x_line.flatten()[::-1]]),
-                y=np.concatenate([y_upper, y_lower[::-1]]),
-                fill='toself',
-                fillcolor='rgba(211, 47, 47, 0.1)',  # Merah transparan
-                line=dict(color='rgba(255,255,255,0)'),
-                showlegend=False,
-                name='Confidence Interval'
-            ))
-
-            fig1.update_layout(
-                margin=dict(t=40),
-                annotations=[
-                    dict(
-                        x=0.95, y=0.95,
-                        xref="paper", yref="paper",
-                        text=f"r = {corr:.2f}",
-                        showarrow=False,
-                        bgcolor="white",
-                        bordercolor="black",
-                        borderwidth=1,
-                        font=dict(color="black")
-                    )
-                ],
-                legend=dict(
-                    title_text='Tyre Status',
-                    bgcolor="white",
-                    bordercolor="lightgray",
-                    borderwidth=1,
-                    itemclick=False,
-                    itemdoubleclick=False
-                ),
-                showlegend=True
-            )
-            st.plotly_chart(fig1, use_container_width=True)
-        else:
-            st.warning("Insufficient data for front tyres.")
-    else:
-        st.warning("No front tyre data.")
+    # Klasifikasi berdasarkan kata kunci
+    hourly_normal = hourly_status_counts.get('No Alarm', pd.Series(0, index=shift_hours)).reindex(shift_hours, fill_value=0)
+    hourly_amber = hourly_status_counts.filter(regex='Amber').sum(axis=1).reindex(shift_hours, fill_value=0)  # Semua yang mengandung "Amber"
+    hourly_red = hourly_status_counts.filter(regex='Red').sum(axis=1).reindex(shift_hours, fill_value=0)      # Semua yang mengandung "Red"
 
-# =============== COL 2: Front — Temperature / Speed (Boxplot) ===============
-with col2:
-    st.markdown('<h5 style="text-align:center; margin-top: 0;">Front Tyres: Pressure vs (Temperature / Speed)</h5>', unsafe_allow_html=True)
-    
-    if not front_df.empty:
-        # Filter kecepatan > 0 untuk hindari pembagian dengan nol
-        front_df = front_df[front_df['Speed (km/h)'] > 10]
-        front_df['Temp_Speed_Ratio'] = front_df['Temperature (°C)'] / front_df['Speed (km/h)']
-
-        # Tambahkan kategori alarm status
-        front_df['Category'] = front_df.apply(
-            lambda row: f"Normal Front Tyre" if row['Alarm Status'] == 'No Alarm'
-            else f"Amber Pressure Front Tyre" if 'Amber' in row['Alarm Status']
-            else f"Red Pressure Front Tyre", axis=1
-        )
-        categories = ["Normal Front Tyre", "Amber Pressure Front Tyre", "Red Pressure Front Tyre"]
-        front_df['Category'] = pd.Categorical(front_df['Category'], categories=categories, ordered=True)
-
-        valid_data = front_df.dropna(subset=['Temp_Speed_Ratio', 'Pressure (psi)'])
-        if not valid_data.empty:
-            fig2 = px.scatter(
-                valid_data,
-                x='Temp_Speed_Ratio',
-                y='Pressure (psi)',
-                color='Category',
-                color_discrete_map={
-                    "Normal Front Tyre": "#2E7D32",         # Hijau
-                    "Amber Pressure Front Tyre": "#FFC107", # Kuning
-                    "Red Pressure Front Tyre": "#D32F2F"    # Merah
-                },
-                category_orders={'Category': categories},
-                template="plotly_white",
-                labels={'Temp_Speed_Ratio': 'Temperature / Speed', 'Pressure (psi)': 'Pressure (psi)'}
-            )
+    # Total per jam
+    total_per_hour = hourly_normal + hourly_amber + hourly_red
 
-            fig2.update_traces(
-                hovertemplate="<b>%{marker.color}</b><br>T/S: %{x:.2f}<br>Pressure: %{y:.1f} psi<extra></extra>",
-                marker=dict(size=6)
-            )
+    # Sudut: sesuaikan agar jam 12 di bawah (180°), jam 6 di kanan (90°), jam 3 di atas (0°), jam 9 di kiri (270°)
+    if shift_type == 'pagi':
+        # Shift Pagi (06:00–18:00) → 0° = 03:00, 90° = 06:00, 180° = 12:00, 270° = 18:00
+        theta = [(h - 3) * 30 for h in shift_hours]  # 12 jam * 30° = 360°
+        tickvals = [0, 90, 180, 270]
+        ticktext = ["03:00", "06:00", "12:00", "18:00"]
+    else:  # Shift Sore (18:00–06:00)
+        # Shift Sore (18:00–06:00) → 0° = 18:00, 90° = 21:00, 180° = 00:00, 270° = 03:00
+        theta = [(h - 18) * 30 if h >= 18 else (h + 6) * 30 for h in shift_hours]  # 12 jam * 30° = 360°
+        tickvals = [0, 90, 180, 270]
+        ticktext = ["18:00", "21:00", "00:00", "03:00"]
+
+    fig = go.Figure()
+
+    # Tambahkan trace untuk masing-masing kategori dengan hovertemplate custom
+    fig.add_trace(go.Barpolar(
+        r=hourly_normal.values,
+        theta=theta,
+        name='Normal',
+        marker_color='#2E7D32',  # Hijau
+        opacity=0.8,
+        hovertemplate='<b>Hour:</b> %{customdata}:00<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,
+        hovertemplate='<b>Hour:</b> %{customdata}:00<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,
+        hovertemplate='<b>Hour:</b> %{customdata}:00<br><b>Count:</b> %{r}<br><b>Status:</b> Red<extra></extra>',
+        customdata=shift_hours
+    ))
 
-            fig2.update_layout(
-                margin=dict(t=40),
-                legend=dict(
-                    title_text='Tyre Status',
-                    bgcolor="white",
-                    bordercolor="lightgray",
-                    borderwidth=1,
-                    itemclick=False,
-                    itemdoubleclick=False
-                )
+    fig.update_layout(
+        polar=dict(
+            angularaxis=dict(
+                direction="clockwise",
+                period=len(shift_hours),
+                rotation=0,
+                tickvals=tickvals,
+                ticktext=ticktext,
+                tickfont=dict(size=12)
+            ),
+            radialaxis=dict(
+                visible=True,
+                range=[0, max(total_per_hour.max() * 1.1, 1)]
             )
-            st.plotly_chart(fig2, use_container_width=True)
-        else:
-            st.warning("Insufficient data for front tyres.")
+        ),
+        showlegend=False,
+        margin=dict(t=30, b=20, l=20, r=20),
+        height=250,
+        title_text=title,
+        title_x=0.5
+    )
+    return fig
+
+# =============== ROW 1: Position 1 & 2 (Pagi & Sore) ===============
+with col1:
+    # Position 1 Pagi (06:00–18:00)
+    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, "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:
-        st.warning("No front tyre data.")
+        st.warning("No data for Position 1 (06:00–18:00)")
 
-# =============== COL 3: Rear — Temperature → Pressure (Scatter + Regression Area) ===============
-col3, col4 = st.columns(2)
+with col2:
+    # Position 1 Sore (18:00–06:00)
+    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, "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:
+        st.warning("No data for Position 1 (18:00–06:00)")
 
 with col3:
-    st.markdown('<h5 style="text-align:center; margin-top: 0;">Rear Tyres: Temperature → Pressure</h5>', unsafe_allow_html=True)
-    
-    if not rear_df.empty:
-        rear_df['Category'] = rear_df.apply(
-            lambda row: f"Normal Rear Tyre" if row['Alarm Status'] == 'No Alarm'
-            else f"Amber Pressure Rear Tyre" if 'Amber' in row['Alarm Status']
-            else f"Red Pressure Rear Tyre", axis=1
-        )
-        categories = ["Normal Rear Tyre", "Amber Pressure Rear Tyre", "Red Pressure Rear Tyre"]
-        rear_df['Category'] = pd.Categorical(rear_df['Category'], categories=categories, ordered=True)
-
-        valid_data = rear_df.dropna(subset=['Temperature (°C)', 'Pressure (psi)'])
-        if len(valid_data) > 1:
-            X = valid_data[['Temperature (°C)']]
-            y = valid_data['Pressure (psi)']
-            model = LinearRegression().fit(X, y)
-            x_line = np.linspace(X.min(), X.max(), 100).reshape(-1, 1)
-            y_line = model.predict(x_line)
-            corr = np.corrcoef(valid_data['Temperature (°C)'], valid_data['Pressure (psi)'])[0, 1]
-
-            fig3 = px.scatter(
-                valid_data,
-                x='Temperature (°C)',
-                y='Pressure (psi)',
-                color='Category',
-                color_discrete_map={
-                    "Normal Rear Tyre": "#2E7D32",
-                    "Amber Pressure Rear Tyre": "#FFC107",
-                    "Red Pressure Rear Tyre": "#D32F2F"
-                },
-                category_orders={'Category': categories},
-                template="plotly_white"
-            )
+    # Position 2 Pagi (06:00–18:00)
+    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, "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:
+        st.warning("No data for Position 2 (06:00–18:00)")
 
-            fig3.update_traces(
-                hovertemplate="<b>%{marker.color}</b><br>Temp: %{x:.1f}°C<br>Pressure: %{y:.1f} psi<extra></extra>",
-                marker=dict(size=6)
-            )
+with col4:
+    # Position 2 Sore (18:00–06:00)
+    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, "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:
+        st.warning("No data for Position 2 (18:00–06:00)")
 
-            fig3.add_trace(go.Scatter(
-                x=x_line.flatten(), y=y_line,
-                mode='lines', name='Trend Line',
-                line=dict(color='#1976D2', dash='dot', width=2)
-            ))
-
-            # Tambahkan area confidence interval (soft background)
-            y_pred = model.predict(X)
-            residuals = y - y_pred
-            mse = np.mean(residuals**2)
-            std_error = np.sqrt(mse)
-            y_upper = y_line + 1.96 * std_error
-            y_lower = y_line - 1.96 * std_error
-
-            fig3.add_trace(go.Scatter(
-                x=np.concatenate([x_line.flatten(), x_line.flatten()[::-1]]),
-                y=np.concatenate([y_upper, y_lower[::-1]]),
-                fill='toself',
-                fillcolor='rgba(211, 47, 47, 0.1)',  # Merah transparan
-                line=dict(color='rgba(255,255,255,0)'),
-                showlegend=False,
-                name='Confidence Interval'
-            ))
-
-            fig3.update_layout(
-                margin=dict(t=40),
-                annotations=[
-                    dict(
-                        x=0.95, y=0.95,
-                        xref="paper", yref="paper",
-                        text=f"r = {corr:.2f}",
-                        showarrow=False,
-                        bgcolor="white",
-                        bordercolor="black",
-                        borderwidth=1,
-                        font=dict(color="black")
-                    )
-                ],
-                legend=dict(
-                    title_text='Tyre Status',
-                    bgcolor="white",
-                    bordercolor="lightgray",
-                    borderwidth=1,
-                    itemclick=False,
-                    itemdoubleclick=False
-                ),
-                showlegend=True
-            )
-            st.plotly_chart(fig3, use_container_width=True)
-        else:
-            st.warning("Insufficient data for rear tyres.")
+# =============== ROW 2: Position 3 & 4 (Pagi & Sore) ===============
+with col5:
+    # Position 3 Pagi (06:00–18:00)
+    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, "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:
-        st.warning("No rear tyre data.")
+        st.warning("No data for Position 3 (06:00–18:00)")
 
-# =============== COL 4: Rear — Pressure vs (Temperature / Speed) ===============
-with col4:
-    st.markdown('<h5 style="text-align:center; margin-top: 0;">Rear Tyres: Pressure vs (Temperature / Speed)</h5>', unsafe_allow_html=True)
-    
-    if not rear_df.empty:
-        # Filter kecepatan > 0 untuk hindari pembagian dengan nol
-        rear_df = rear_df[rear_df['Speed (km/h)'] > 10]
-        rear_df['Temp_Speed_Ratio'] = rear_df['Temperature (°C)'] / rear_df['Speed (km/h)']
-
-        # Tambahkan kategori alarm status
-        rear_df['Category'] = rear_df.apply(
-            lambda row: f"Normal Rear Tyre" if row['Alarm Status'] == 'No Alarm'
-            else f"Amber Pressure Rear Tyre" if 'Amber' in row['Alarm Status']
-            else f"Red Pressure Rear Tyre", axis=1
-        )
-        categories = ["Normal Rear Tyre", "Amber Pressure Rear Tyre", "Red Pressure Rear Tyre"]
-        rear_df['Category'] = pd.Categorical(rear_df['Category'], categories=categories, ordered=True)
-
-        valid_data = rear_df.dropna(subset=['Temp_Speed_Ratio', 'Pressure (psi)'])
-        if not valid_data.empty:
-            fig4 = px.scatter(
-                valid_data,
-                x='Temp_Speed_Ratio',
-                y='Pressure (psi)',
-                color='Category',
-                color_discrete_map={
-                    "Normal Rear Tyre": "#2E7D32",
-                    "Amber Pressure Rear Tyre": "#FFC107",
-                    "Red Pressure Rear Tyre": "#D32F2F"
-                },
-                category_orders={'Category': categories},
-                template="plotly_white"
-            )
+with col6:
+    # Position 3 Sore (18:00–06:00)
+    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, "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:
+        st.warning("No data for Position 3 (18:00–06:00)")
 
-            fig4.update_traces(
-                hovertemplate="<b>%{marker.color}</b><br>T/S: %{x:.2f}<br>Pressure: %{y:.1f} psi<extra></extra>",
-                marker=dict(size=6)
-            )
+with col7:
+    # Position 4 Pagi (06:00–18:00)
+    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, "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:
+        st.warning("No data for Position 4 (06:00–18:00)")
 
-            fig4.update_layout(
-                margin=dict(t=40),
-                legend=dict(
-                    title_text='Tyre Status',
-                    bgcolor="white",
-                    bordercolor="lightgray",
-                    borderwidth=1,
-                    itemclick=False,
-                    itemdoubleclick=False
-                )
-            )
-            st.plotly_chart(fig4, use_container_width=True)
-        else:
-            st.warning("Insufficient data for rear tyres.")
+with col8:
+    # Position 4 Sore (18:00–06:00)
+    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, "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:
-        st.warning("No rear tyre data.")
+        st.warning("No data for Position 4 (18:00–06:00)")
 
-# =============== INSIGHT 4 ===============
-def safe_corr(a, b):
-    mask = ~(np.isnan(a) | np.isnan(b))
-    if mask.sum() < 2:
-        return 0.0
-    return np.corrcoef(a[mask], b[mask])[0, 1]
+# =============== INSIGHT 3 ===============
+if alarm_data.empty:
+    insight_text = "• No data available for analysis."
+else:
+    # Insight tetap sama
+    alarm_hours = alarm_data['hour']
 
-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)'])
+    def hour_to_band(h):
+        if 0 <= h < 6:   return "00:00–06:00 (Night)"
+        if 6 <= h < 12:  return "06:00–12:00 (Morning)"
+        if 12 <= h < 18: return "12:00–18:00 (Afternoon)"
+        return "18:00–00:00 (Evening)"
 
-# 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]
+    alarm_hours_df = pd.DataFrame({'hour': alarm_hours})
+    alarm_hours_df['band'] = alarm_hours_df['hour'].apply(hour_to_band)
+    band_counts = alarm_hours_df['band'].value_counts().sort_index()
 
-# Hitung korelasi Pressure vs T/V (Temperature / Speed) untuk front
-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
+    top_bands = band_counts.nlargest(2)
+    dominant_band = top_bands.index[0] if len(top_bands) > 0 else "N/A"
+    second_dominant_band = top_bands.index[1] if len(top_bands) > 1 else "N/A"
 
-# Hitung korelasi Pressure vs T/V (Temperature / Speed) untuk rear
-if not rear_df.empty and (rear_df['Speed (km/h)'] > 0).any():
-    rear_df_filtered = rear_df[rear_df['Speed (km/h)'] > 0].copy()
-    rear_df_filtered['Temp_Speed_Ratio'] = rear_df_filtered['Temperature (°C)'] / rear_df_filtered['Speed (km/h)']
-    corr_p_tv_rear = safe_corr(rear_df_filtered['Pressure (psi)'], rear_df_filtered['Temp_Speed_Ratio'])
-else:
-    corr_p_tv_rear = 0.0
+    dominant_pct = (top_bands.iloc[0] / band_counts.sum() * 100) if len(top_bands) > 0 else 0
+    second_pct = (top_bands.iloc[1] / band_counts.sum() * 100) if len(top_bands) > 1 else 0
 
-# Insight
-insight_text = f"""
-• 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, indicating critical heat thresholds.
-• Pressure vs (T/v) shows weak correlation in front (r = {corr_p_tv_front:.2f}) and rear (r = {corr_p_tv_rear:.2f}), suggesting speed alone is not primary heat factor.
-"""
+    # Hitung jumlah masing-masing jenis alarm
+    normal_alarms = alarm_data[alarm_data['Alarm Status'] == 'No Alarm'].shape[0]
+    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 ===============
 st.markdown(f"""
 <div class="insight-box">
     <div class="content">
-{insight_text.strip()}
+{insight_text}
     </div>
 </div>
 """, 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)
 
@@ -1243,6 +1161,7 @@ st.markdown(f"""
 """, unsafe_allow_html=True)
 # ================= OBJECTIVE 5 =================
 # ================= OBJECTIVE 5 =================
+# ================= OBJECTIVE 5 =================
 st.markdown('<h3 class="objective-title">OBJECTIVE 5: Insights & Mitigation — How Can Red Pressure Alarms Be Reduced?</h3>', unsafe_allow_html=True)
 
 # --- DATA PREP ---
@@ -1270,6 +1189,57 @@ if not rear_df.empty and len(rear_df[['Speed (km/h)']].dropna()) > 1 and len(rea
 else:
     corr_rear = 0
 
+# === DATA UNTUK OBJECTIVE 2 (Insight Spesifik Per Position dan Shift) ===
+# Position 1 (Shift Pagi)
+pos1_pagi = dff[(dff['Position'] == 1) & (dff['hour'].between(6, 17, inclusive='both'))]
+# Position 1 (Shift Sore)
+pos1_sore = dff[(dff['Position'] == 1) & (~dff['hour'].between(6, 17, inclusive='both'))]
+# Position 3 (Shift Pagi)
+pos3_pagi = dff[(dff['Position'] == 3) & (dff['hour'].between(6, 17, inclusive='both'))]
+# Position 3 (Shift Sore)
+pos3_sore = dff[(dff['Position'] == 3) & (~dff['hour'].between(6, 17, inclusive='both'))]
+
+# === DATA UNTUK OBJECTIVE 3 (Correlation Analysis) ===
+# 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) untuk front
+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)']
+    def safe_corr(a, b):
+        mask = ~(np.isnan(a) | np.isnan(b))
+        if mask.sum() < 2:
+            return 0.0
+        return np.corrcoef(a[mask], b[mask])[0, 1]
+    corr_p_tv_front = safe_corr(front_df_filtered['Pressure (psi)'], front_df_filtered['Temp_Speed_Ratio'])
+else:
+    corr_p_tv_front = 0.0
+
+# === DATA UNTUK OBJECTIVE 4 (Spatial Risk Mapping) ===
+valid_gps = dff.dropna(subset=['Latitude_y', 'Longitude_y'])
+if not valid_gps.empty:
+    # Hitung jumlah alarm per zona
+    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
+    # Hitung jumlah alarm per posisi (front vs rear)
+    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"
+    top_zone_count_obj4 = 0
+    percentage_obj4 = 0
+    front_percentage_obj4 = 0
+
 # 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:.1f} psi) and higher temperature ({front_temp_avg:.1f}°C) due to higher stress from braking/steering.
@@ -1298,10 +1268,12 @@ try:
     prompt = f"""
 Role: Fleet Operations Risk Analyst
 Insights:
-- High-risk zone: {top_zone} ({percentage_obj4:.1f}% of 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_p_t_front:.2f}
+- Front tyre pressure–temperature correlation r = {corr_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_front:.2f})
 Task:
 Generate:
 1. Business Recommendations
@@ -1327,36 +1299,34 @@ Rules:
     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_p_t_front:.2f}) to prevent overheating and premature wear.
+3. Monitor pressure and temperature correlation in front tyres (r = {corr_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 {percentage_obj4:.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_p_t_front:.2f} to prevent unplanned downtime.
-<br>
-4. Implement real-time monitoring in {top_zone} where {percentage_obj4:.1f}% of alarms are concentrated."""
+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_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_p_t_front:.2f}) to prevent overheating and premature wear.
+3. Monitor pressure and temperature correlation in front tyres (r = {corr_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 {percentage_obj4:.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_p_t_front:.2f} to prevent unplanned downtime.
-<br>
-4. Implement real-time monitoring in {top_zone} where {percentage_obj4:.1f}% of alarms are concentrated."""
+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_obj4} where {percentage_obj4:.1f}% of alarms are concentrated."""
 
 # ============== SUBHEADER + BOX 1: INSIGHT ==============
 st.markdown('<h4 style="text-align:left; margin:10px 0 5px 0; font-weight:bold;">INSIGHT</h4>', unsafe_allow_html=True)
@@ -1387,7 +1357,6 @@ st.markdown(f"""
     </div>
 </div>
 """, unsafe_allow_html=True)
-
 # ================= FOOTER =================
 st.markdown("""
 <div class="footer">