Update app.py

app.py

@@ -10,6 +10,7 @@ import os
 import sklearn
 import kaleido
 
+
 # =================== PAGE CONFIG ===================
 st.set_page_config(
     page_title="PLN Audit Insight & Intelligence Dashboard",
@@ -325,27 +326,45 @@ with st.container():
             </div>
         """, unsafe_allow_html=True)
 
-    # RIGHT — LOGO BOX
-    with col3:
-        logo_path = "pln.png"
-        if os.path.exists(logo_path):
-            st.image(logo_path, width=200)
-        else:
-            st.error("Logo not found")
 
-    st.markdown("</div>", unsafe_allow_html=True)
 
 
-# =================== 1. Pie Charts: Temuan/Person by Company (PG & UM) - PERBAIKAN ===================
-st.markdown("<h3 class='section-title'>OBJECTIVE 1 - Company Reporting Activity: Who Reports the Most?</h3>", unsafe_allow_html=True)
+import streamlit as st
+import plotly.graph_objects as go
+import numpy as np
+import pandas as pd
+
+# =================== OBJECTIVE 1 - Company Reporting Activity (Polar Bar Chart) ===================
+st.markdown(
+    """
+    <style>
+    .section-title {
+        text-align: center;
+        font-size: 1.5rem;
+        font-weight: 600;
+        color: #2c3e50;
+        margin-bottom: 1.2rem;
+    }
+    .ai-insight {
+        background-color: #f8f9fa;
+        padding: 12px;
+        border-left: 4px solid #27ae60;
+        border-radius: 0 4px 4px 0;
+        font-size: 0.95rem;
+        line-height: 1.5;
+        margin-top: 1rem;
+    }
+    </style>
+    <h3 class='section-title'>OBJECTIVE 1 — Company Reporting Activity: Who Reports the Most?</h3>
+    """,
+    unsafe_allow_html=True
+)
 
-# Asumsikan df_filtered adalah data utama yang telah difilter
 df_local = df_filtered.copy()
 
 # Tambah kolom bulan
 df_local['created_month'] = df_local['created_at'].dt.to_period('M')
 
-# --- Langsung buat Area_Type PG / UM tanpa filter manual ---
 if 'temuan_kode_distrik' in df_local.columns:
     df_local['Area_Type'] = df_local['temuan_kode_distrik'].apply(
         lambda x: 'PG' if 'PG' in str(x).upper()
@@ -367,7 +386,6 @@ if 'temuan_kode_distrik' in df_local.columns:
         creators_by_company_month = df_area.groupby(['created_month', 'nama_perusahaan'])['creator_nid'].nunique().reset_index(name='unique_creators')
         # Gabung
         merged = findings_by_company_month.merge(creators_by_company_month, on=['created_month', 'nama_perusahaan'], how='outer')
-        # Isi NaN dengan 0 untuk kolom yang mungkin hilang dari merge
         merged = merged.fillna({'findings_count': 0, 'unique_creators': 0})
         # Filter untuk menghindari pembagian dengan nol
         merged = merged[merged['unique_creators'] > 0]
@@ -392,34 +410,102 @@ if 'temuan_kode_distrik' in df_local.columns:
     avg_ratio_pg = calculate_avg_ratio_per_company(df_pg)
     avg_ratio_um = calculate_avg_ratio_per_company(df_um)
 
-    # Fungsi untuk menentukan warna
-    def get_color_map(company_series):
-        pln_color = "#FFD700"  # Kuning untuk PLN
-        blue_colors = ["#1E90FF", "#87CEEB", "#B0E0E6", "#ADD8E6", "#E0F6FF"] 
-        color_map = {}
-        for company in company_series:
+    # Palet biru pastel konsisten (soft, harmonis)
+    pastel_blues = [
+        "#A8DADC",  # light cyan
+        "#E2ECE9",  # pale mint
+        "#CCE4E7",  # soft sky
+        "#B5D9D9",  # muted aqua
+        "#98C8D1",  # gentle teal
+        "#7FB9C1",  # calm blue
+        "#6BA9B3"   # deep pastel teal
+    ]
+    pln_color = "#FFD700"  # Kuning PLN
+
+    def assign_colors(df):
+        colors = []
+        blue_idx = 0
+        for company in df['nama_perusahaan']:
             if 'PLN' in str(company).upper():
-                color_map[company] = pln_color
+                colors.append(pln_color)
             else:
-                idx = len([c for c in color_map.values() if c != pln_color]) % len(blue_colors)
-                color_map[company] = blue_colors[idx]
-        return color_map
+                colors.append(pastel_blues[blue_idx % len(pastel_blues)])
+                blue_idx += 1
+        return colors
+
+    # Fungsi untuk membuat polar bar chart
+    def create_polar_bar_chart(df, area_name):
+        if df.empty:
+            return None
+
+        # Urutkan berdasarkan rasio untuk tampilan konsisten
+        df = df.sort_values('avg_monthly_ratio', ascending=True)
+        companies = df['nama_perusahaan'].tolist()
+        ratios = df['avg_monthly_ratio'].tolist()
+        colors = assign_colors(df)
+        
+        # Hitung total temuan untuk menghitung sudut (proporsi)
+        total_findings = df_local[df_local['Area_Type'] == area_name].groupby('nama_perusahaan').size()
+        angles = []
+        total_angle = 0
+        for comp in companies:
+            count = total_findings.get(comp, 0)
+            angle = (count / total_findings.sum()) * 360 if total_findings.sum() > 0 else 0
+            angles.append(angle)
+        
+        # Hitung sudut tengah untuk setiap bar
+        mid_angles = []
+        current_angle = 0
+        for a in angles:
+            mid_angles.append(current_angle + a / 2)
+            current_angle += a
+        
+        fig = go.Figure()
+        fig.add_trace(go.Barpolar(
+            r=ratios,
+            theta=mid_angles,
+            width=angles,
+            marker_color=colors,
+            marker_line_color="white",
+            marker_line_width=1.2,
+            opacity=0.9,
+            hovertemplate="<b>%{text}</b><br>Avg Ratio: %{r:.2f}<extra></extra>",
+            text=companies,
+        ))
+
+        fig.update_layout(
+            title=f'{area_name} Area',
+            polar=dict(
+                bgcolor="white",
+                radialaxis=dict(
+                    visible=True,
+                    tickfont=dict(size=9),
+                    gridcolor='lightgray',
+                    title=dict(text='Avg Finding/Person', font=dict(size=10))
+                ),
+                angularaxis=dict(
+                    visible=True,
+                    direction='clockwise',
+                    tickfont=dict(size=9),
+                    showline=False
+                ),
+            ),
+            showlegend=False,
+            margin=dict(t=40, b=20, l=20, r=20),
+            height=400,
+            paper_bgcolor="rgba(0,0,0,0)",
+            plot_bgcolor="rgba(0,0,0,0)"
+        )
+
+        return fig
 
     # Plot
     col1, col2 = st.columns(2)
 
     with col1:
         st.markdown("<h5>Unit Pembangkit: Avg Monthly Finding by Company</h5>", unsafe_allow_html=True)
-        if not avg_ratio_pg.empty:
-            color_discrete_map_pg = get_color_map(avg_ratio_pg['nama_perusahaan'])
-            fig_pg = px.pie(
-                avg_ratio_pg, 
-                values='avg_monthly_ratio', 
-                names='nama_perusahaan', 
-                title='PG Area',
-                color='nama_perusahaan',
-                color_discrete_map=color_discrete_map_pg
-            )
+        fig_pg = create_polar_bar_chart(avg_ratio_pg, 'PG')
+        if fig_pg:
             st.plotly_chart(fig_pg, use_container_width=True)
             
             # AI Insight untuk PG
@@ -443,16 +529,8 @@ if 'temuan_kode_distrik' in df_local.columns:
 
     with col2:
         st.markdown("<h5>Unit Maintenance: Avg Monthly Finding by Company</h5>", unsafe_allow_html=True)
-        if not avg_ratio_um.empty:
-            color_discrete_map_um = get_color_map(avg_ratio_um['nama_perusahaan'])
-            fig_um = px.pie(
-                avg_ratio_um, 
-                values='avg_monthly_ratio', 
-                names='nama_perusahaan', 
-                title='UM Area',
-                color='nama_perusahaan',
-                color_discrete_map=color_discrete_map_um
-            )
+        fig_um = create_polar_bar_chart(avg_ratio_um, 'UM')
+        if fig_um:
             st.plotly_chart(fig_um, use_container_width=True)
             
             # AI Insight untuk UM
@@ -702,7 +780,7 @@ st.markdown(
         margin-top: 1rem;
     }
     </style>
-    <h3 class='section-title'>OBJECTIVE 3 — Frequency & Response Time: Who Reports Well? Who Executes Well?</h3>
+    <h3 class='section-title'>OBJECTIVE 4 — Frequency & Response Time: Who Reports Well? Who Executes Well?</h3>
     """,
     unsafe_allow_html=True
 )
@@ -791,11 +869,11 @@ avg_leadtime_per_executor = compute_executor_leadtime_by_pic(df_local)
 col_3a, col_3c = st.columns(2)
 
 with col_3a:
-    st.markdown("<h5>3a. Average Finding by Division (Reporter)</h5>", unsafe_allow_html=True)
+    st.markdown("<h5>4a. Average Finding by Division (Reporter)</h5>", unsafe_allow_html=True)
     if avg_ratio_per_nama.empty:
         st.warning("No data for reporter analysis by division.")
     else:
-        sort_option_3a = st.selectbox("Show 3a:", ["Top 10", "Bottom 10"], key='sort_3a')
+        sort_option_3a = st.selectbox("Show 4a:", ["Top 10", "Bottom 10"], key='sort_3a')
         
         # Urutkan data dari tertinggi ke terendah
         sorted_data_all = avg_ratio_per_nama.sort_values('avg_monthly_ratio', ascending=False)
@@ -854,11 +932,11 @@ with col_3a:
         st.markdown(insight_text, unsafe_allow_html=True)
 
 with col_3c:
-    st.markdown("<h5>3c. Average Finding Rate per Reporter (Name)</h5>", unsafe_allow_html=True)
+    st.markdown("<h5>4b. Average Finding Rate per Reporter (Name)</h5>", unsafe_allow_html=True)
     if avg_rate_per_creator.empty:
         st.warning("No data for reporter analysis by creator_name.")
     else:
-        sort_option_3c = st.selectbox("Show 3c:", ["Top 10", "Bottom 10"], key='sort_3c')
+        sort_option_3c = st.selectbox("Show 4b:", ["Top 10", "Bottom 10"], key='sort_3c')
         
         # Urutkan data dari tertinggi ke terendah
         sorted_data_all = avg_rate_per_creator.sort_values('avg_monthly_rate', ascending=False)
@@ -921,11 +999,11 @@ with col_3c:
 col_3b, col_3d = st.columns(2)
 
 with col_3b:
-    st.markdown("<h5>3b. Average Lead Time by Division (Executor)</h5>", unsafe_allow_html=True)
+    st.markdown("<h5>4c. Average Lead Time by Division (Executor)</h5>", unsafe_allow_html=True)
     if avg_leadtime_nama.empty:
         st.warning("No data for executor analysis by division.")
     else:
-        sort_option_3b = st.selectbox("Show 3b:", ["Top 10", "Bottom 10"], key='sort_3b')
+        sort_option_3b = st.selectbox("Show 4c:", ["Top 10", "Bottom 10"], key='sort_3b')
         
         # Urutkan data dari tertinggi ke terendah
         sorted_data_all = avg_leadtime_nama.sort_values('avg_monthly_leadtime', ascending=False)
@@ -982,11 +1060,11 @@ with col_3b:
         st.markdown(insight_text, unsafe_allow_html=True)
 
 with col_3d:
-    st.markdown("<h5>3d. Average Lead Time by Executor (Name)</h5>", unsafe_allow_html=True)
+    st.markdown("<h5>4d. Average Lead Time by Executor (Name)</h5>", unsafe_allow_html=True)
     if avg_leadtime_per_executor.empty:
         st.warning("No data for executor analysis by nama_pic.")
     else:
-        sort_option_3d = st.selectbox("Show 3d:", ["Top 10", "Bottom 10"], key='sort_3d')
+        sort_option_3d = st.selectbox("Show 4d:", ["Top 10", "Bottom 10"], key='sort_3d')
         
         # Urutkan data dari tertinggi ke terendah
         sorted_data_all = avg_leadtime_per_executor.sort_values('avg_monthly_leadtime', ascending=False)
@@ -1043,6 +1121,7 @@ with col_3d:
         st.markdown(insight_text, unsafe_allow_html=True)
 
 
+
 ####OBJECTIVE 4
 try:
     from wordcloud import WordCloud