Update app.py

app.py

@@ -1260,15 +1260,6 @@ except Exception as e:
     st.error(f"⚠️ Error Risk Matrix: {e}")
     # st.exception(e) # Uncomment for debugging
 
-# =================== 7. PREDICTIVE INSIGHTS (FINAL — PLN BLUE EDITION v2) ===================
-# ✅ Panel 1: ONLY Coverage < 90% AND Slope < 0
-# ✅ Panel 3: ONLY Coverage = 100% AND Slope > 0 → Avg/Month
-# ✅ Estetik: Sortable, Hover, Zebra, PLN Blue, No Emoticons
-import streamlit as st
-import plotly.graph_objects as go
-import numpy as np
-import pandas as pd
-
 import streamlit as st
 import plotly.graph_objects as go
 import numpy as np
@@ -1413,7 +1404,9 @@ function makeSortable(tableId) {
 }
 setTimeout(() => {
     makeSortable('tbl-creators');
-    makeSortable('tbl-issues');
+    makeSortable('tbl-locations');
+    makeSortable('tbl-divisions');
+    makeSortable('tbl-categories');
 }, 800);
 </script>
 """, unsafe_allow_html=True)
@@ -1435,11 +1428,9 @@ def ascii_sparkline_pln(data):
     except:
         return "<span class='spark' style='color:#999;'>▁▁▁</span>"
 
-# ——————— 1. Creators: ONLY Coverage < 90% AND Slope < 0 (Non-Positive Only) ———————
+# ——————— 1. Creators: ONLY Coverage < 90% AND Slope < 0 ———————
 def predict_creators(df):
-    # 🔥 Filter: Hanya yang bukan 'Positive'
-    df = df[df['temuan_kategori'] != 'Positive'].copy()  # ✅ Filter non-Positive
-    
+    # ❌ Tidak ada filter Non-Positive
     if 'creator_name' not in df.columns or df.empty:
         return pd.DataFrame()
     
@@ -1485,13 +1476,109 @@ def predict_creators(df):
     # ✅ Ambil 10 creator dengan slope paling negatif (paling turun)
     return df_res.sort_values('Trend Slope', ascending=True).head(10) if not df_res.empty else df_res
 
-# ——————— 3. Issues: ONLY Coverage=100% & Trend Slope > 0 → Avg/Month ———————
-def predict_issues(df):
-    if 'kategori' not in df.columns or df.empty:
+# ——————— 2. Locations: ONLY Coverage < 90% AND Slope < 0 ———————
+def predict_locations(df):
+    # ❌ Tidak ada filter Non-Positive
+    if 'nama_lokasi_full' not in df.columns or df.empty:
         return pd.DataFrame()
     
+    start_month = df['created_at'].min().to_period('M')
+    end_month = df['created_at'].max().to_period('M')
+    all_months = pd.period_range(start=start_month, end=end_month, freq='M')
+    
+    df_monthly = (
+        df.groupby(['nama_lokasi_full', df['created_at'].dt.to_period('M')])
+        .size()
+        .unstack(fill_value=0)
+        .reindex(columns=all_months, fill_value=0)
+        .stack()
+        .reset_index(name='count')
+    )
+    df_monthly.columns = ['Location', 'Month', 'Count']
+    
+    results = []
+    for lokasi, group in df_monthly.groupby('Location'):
+        ts = group.set_index('Month')['Count']
+        total = len(all_months)
+        active = (ts > 0).sum()
+        coverage = active / total if total > 0 else 0
+        avg_rate = ts.mean()
+        
+        if len(ts) >= 2:
+            try:
+                slope = np.polyfit(np.arange(len(ts)), ts.values, 1)[0]
+                # ✅ FILTER: Coverage < 90% AND Slope < 0
+                if slope < 0 and coverage < 0.9:
+                    reason = f"Slope = {slope:.3f}, Coverage = {coverage*100:.1f}%. Avg: {avg_rate:.2f}/mo."
+                    results.append({
+                        'Location': lokasi,
+                        'Avg Reports/Month': round(avg_rate, 2),
+                        'Coverage (%)': round(coverage * 100, 1),
+                        'Trend Slope': round(slope, 3),
+                        'Trend': ascii_sparkline_pln(ts.values.tolist()),
+                        'Reason': reason
+                    })
+            except:
+                continue
+    df_res = pd.DataFrame(results)
+    # ✅ Ambil 10 lokasi dengan slope paling negatif (paling turun)
+    return df_res.sort_values('Trend Slope', ascending=True).head(10) if not df_res.empty else df_res
+
+# ——————— 3. Divisions: ONLY Coverage < 90% AND Slope < 0 ———————
+def predict_divisions(df):
+    # ❌ Tidak ada filter Non-Positive
+    if 'nama' not in df.columns or df.empty:
+        return pd.DataFrame()
+    
+    start_month = df['created_at'].min().to_period('M')
+    end_month = df['created_at'].max().to_period('M')
+    all_months = pd.period_range(start=start_month, end=end_month, freq='M')
+    
+    df_monthly = (
+        df.groupby(['nama', df['created_at'].dt.to_period('M')])
+        .size()
+        .unstack(fill_value=0)
+        .reindex(columns=all_months, fill_value=0)
+        .stack()
+        .reset_index(name='count')
+    )
+    df_monthly.columns = ['Division', 'Month', 'Count']
+    
+    results = []
+    for div, group in df_monthly.groupby('Division'):
+        ts = group.set_index('Month')['Count']
+        total = len(all_months)
+        active = (ts > 0).sum()
+        coverage = active / total if total > 0 else 0
+        avg_rate = ts.mean()
+        
+        if len(ts) >= 2:
+            try:
+                slope = np.polyfit(np.arange(len(ts)), ts.values, 1)[0]
+                # ✅ FILTER: Coverage < 90% AND Slope < 0
+                if slope < 0 and coverage < 0.9:
+                    reason = f"Slope = {slope:.3f}, Coverage = {coverage*100:.1f}%. Avg: {avg_rate:.2f}/mo."
+                    results.append({
+                        'Division': div,
+                        'Avg Reports/Month': round(avg_rate, 2),
+                        'Coverage (%)': round(coverage * 100, 1),
+                        'Trend Slope': round(slope, 3),
+                        'Trend': ascii_sparkline_pln(ts.values.tolist()),
+                        'Reason': reason
+                    })
+            except:
+                continue
+    df_res = pd.DataFrame(results)
+    # ✅ Ambil 10 divisi dengan slope paling negatif (paling turun)
+    return df_res.sort_values('Trend Slope', ascending=True).head(10) if not df_res.empty else df_res
+
+# ——————— 4. Categories: ONLY Non-Positive + Coverage=100% & Trend Slope > 0 ———————
+def predict_categories(df):
     # 🔥 Filter: Hanya yang bukan 'Positive'
-    df = df[df['kategori'] != 'Positive'].copy()  # ✅ Filter non-Positive
+    df = df[df['temuan_kategori'] != 'Positive'].copy()  # ✅ Filter non-Positive
+    
+    if 'temuan_kategori' not in df.columns or df.empty:
+        return pd.DataFrame()
     
     start_month = df['created_at'].min().to_period('M')
     end_month = df['created_at'].max().to_period('M')
@@ -1499,7 +1586,7 @@ def predict_issues(df):
     n_months = len(all_months)
     
     results = []
-    for cat, group in df.groupby('kategori'):
+    for cat, group in df.groupby('temuan_kategori'):
         ts_data = (
             group.groupby(group['created_at'].dt.to_period('M'))
             .size()
@@ -1540,13 +1627,15 @@ def predict_issues(df):
         )
         df_res = df_res.sort_values('Trend Slope', ascending=False)
     
-    return df_res.reset_index(drop=True)
+    return df_res.reset_index(drop=True).head(10) if not df_res.empty else df_res
 
 # ——————— RUN ———————
 df_creator = predict_creators(df_filtered)
-df_issue = predict_issues(df_filtered)
+df_location = predict_locations(df_filtered)
+df_division = predict_divisions(df_filtered)
+df_category = predict_categories(df_filtered)
 
-# 🎯 PANEL 1: Creators (FILTERED: Coverage < 90% & Slope < 0) — Non-Positive Only
+# 🎯 PANEL 1: Creators (FILTERED: Coverage < 90% & Slope < 0)
 st.markdown("<div class='predictive-panel'>", unsafe_allow_html=True)
 st.markdown("<div class='predictive-header'>1. Which Reporters Are Predicted to Have No Future Inspections? (Top 10 Most Declining)</div>", unsafe_allow_html=True)
 if not df_creator.empty:
@@ -1582,11 +1671,83 @@ if not df_creator.empty:
     # )
 st.markdown("</div>", unsafe_allow_html=True)
 
-# 🎯 PANEL 3: Issues (FILTERED: Coverage=100% & Rising) — Hanya Non-Positive
+# 🎯 PANEL 2: Locations (FILTERED: Coverage < 90% & Slope < 0)
+st.markdown("<div class='predictive-panel'>", unsafe_allow_html=True)
+st.markdown("<div class='predictive-header'>2. Which Locations Are Predicted to Have No Future Inspections? (Top 10 Most Declining)</div>", unsafe_allow_html=True)
+if not df_location.empty:
+    cols = ['Location', 'Avg Reports/Month', 'Coverage (%)', 'Trend Slope', 'Trend', 'Reason']
+
+    # 🔥 Rename hanya untuk DISPLAY, bukan data asli
+    df_display = df_location[cols].rename(columns={
+        "Reason": "Reason Forecast"
+    })
+
+    html = df_display.to_html(escape=False, index=False, table_id="tbl-locations")
+    st.markdown(f"<div class='predictive-table-wrapper'>{html}</div>", unsafe_allow_html=True)
+
+    # st.markdown(
+    #     "<div class='predictive-note'>"
+    #     "<strong>Criteria:</strong> Coverage < 90% AND negative slope. "
+    #     "High-risk: steep negative slope + low baseline activity."
+    #     "</div>",
+    #     unsafe_allow_html=True
+    # )
+
+# else:
+#     st.markdown(
+#         "<div class='predictive-table-wrapper'>"
+#         "<p style='text-align:center; color:#666; padding:24px; font-style:italic;'>"
+#         "No locations meet criteria: Coverage < 90% and negative trend."
+#         "</p>"
+#         "<div class='warning-box'>"
+#         "💡 Note: Locations with Coverage ≥ 90% are excluded — they are considered stable reporting zones."
+#         "</div>"
+#         "</div>",
+#         unsafe_allow_html=True
+    # )
+st.markdown("</div>", unsafe_allow_html=True)
+
+# 🎯 PANEL 3: Divisions (FILTERED: Coverage < 90% & Slope < 0)
+st.markdown("<div class='predictive-panel'>", unsafe_allow_html=True)
+st.markdown("<div class='predictive-header'>3. Which Divisions Are Predicted to Have No Future Inspections? (Top 10 Most Declining)</div>", unsafe_allow_html=True)
+if not df_division.empty:
+    cols = ['Division', 'Avg Reports/Month', 'Coverage (%)', 'Trend Slope', 'Trend', 'Reason']
+
+    # 🔥 Rename hanya untuk DISPLAY, bukan data asli
+    df_display = df_division[cols].rename(columns={
+        "Reason": "Reason Forecast"
+    })
+
+    html = df_display.to_html(escape=False, index=False, table_id="tbl-divisions")
+    st.markdown(f"<div class='predictive-table-wrapper'>{html}</div>", unsafe_allow_html=True)
+
+    # st.markdown(
+    #     "<div class='predictive-note'>"
+    #     "<strong>Criteria:</strong> Coverage < 90% AND negative slope. "
+    #     "High-risk: steep negative slope + low baseline activity."
+    #     "</div>",
+    #     unsafe_allow_html=True
+    # )
+
+# else:
+#     st.markdown(
+#         "<div class='predictive-table-wrapper'>"
+#         "<p style='text-align:center; color:#666; padding:24px; font-style:italic;'>"
+#         "No divisions meet criteria: Coverage < 90% and negative trend."
+#         "</p>"
+#         "<div class='warning-box'>"
+#         "💡 Note: Divisions with Coverage ≥ 90% are excluded — they are considered stable reporting zones."
+#         "</div>"
+#         "</div>",
+#         unsafe_allow_html=True
+    # )
+st.markdown("</div>", unsafe_allow_html=True)
+
+# 🎯 PANEL 4: Categories (FILTERED: Non-Positive + Coverage=100% & Rising)
 st.markdown("<div class='predictive-panel'>", unsafe_allow_html=True)
 st.markdown(
     "<div class='predictive-header'>"
-    "2. Which Issue Categories Are Likely to Appear in the Next 3 Months (Non Positive Only)"
+    "4. Which Issue Categories Are Likely to Appear in the Next 3 Months (Non-Positive Only)"
     "<span style='font-size:0.75em; font-weight:400; color:#003DA5;'>"
     " &nbsp;&nbsp;(* Categorization uses NLP — Natural Language Processing from random text)"
     "</span>"
@@ -1594,48 +1755,48 @@ st.markdown(
     unsafe_allow_html=True
 )
 
-# if not df_issue.empty:
-#     cols = ['Category', 'Avg/Month', 'Coverage (%)', 'Trend Slope', 'Status', 'Trend']
-
-#     # 🔵 Rename ONLY for display
-#     df_display = df_issue[cols].rename(columns={
-#         "Status": "Status Issue for Next Month"
-#     })
-
-#     html = df_display.to_html(escape=False, index=False, table_id="tbl-issues")
-#     st.markdown(f"<div class='predictive-table-wrapper'>{html}</div>", unsafe_allow_html=True)
-
-# #     st.markdown(
-# #         "<div class='predictive-note'>"
-# #         "<strong>Filtered:</strong> Reported every month (100% coverage) with increasing trend. "
-# #         "<strong>Avg/Month</strong> = total ÷ months. "
-# #         "<span class='trend-rising'>High-Risk Rising</span> = slope > 0.2."
-# #         "</div>",
-# #         unsafe_allow_html=True
-# #     )
-
-# # else:
-# #     st.markdown(
-# #         "<div class='predictive-table-wrapper'>"
-# #         "<p style='text-align:center; color:#c62828; padding:24px; font-weight:500;'>"
-# #         "⚠️ No rising categories with 100% monthly coverage."
-# #         "</p>"
-# #         "<p style='text-align:center; color:#666; font-size:0.9em;'>"
-# #         "Consider relaxing coverage filter if data is sparse."
-# #         "</p></div>",
-# #         unsafe_allow_html=True
-# #     )
-
-# st.markdown("</div>", unsafe_allow_html=True)
-
-
-# # =================== WHITEBOARD STYLE CHART FOR PANEL 3 ===================
-# st.markdown("<h4 style='text-align: center; color: #2c3e50;'>Whiteboard Insight: Trend vs Frequency</h4>", unsafe_allow_html=True)
-
-# # Buat chart scatter dengan gaya whiteboard
-if not df_issue.empty:
+if not df_category.empty:
+    cols = ['Category', 'Avg/Month', 'Coverage (%)', 'Trend Slope', 'Status', 'Trend']
+
+    # 🔵 Rename ONLY for display
+    df_display = df_category[cols].rename(columns={
+        "Status": "Status Issue for Next Month"
+    })
+
+    html = df_display.to_html(escape=False, index=False, table_id="tbl-categories")
+    st.markdown(f"<div class='predictive-table-wrapper'>{html}</div>", unsafe_allow_html=True)
+
+#     st.markdown(
+#         "<div class='predictive-note'>"
+#         "<strong>Filtered:</strong> Reported every month (100% coverage) with increasing trend. "
+#         "<strong>Avg/Month</strong> = total ÷ months. "
+#         "<span class='trend-rising'>High-Risk Rising</span> = slope > 0.2."
+#         "</div>",
+#         unsafe_allow_html=True
+#     )
+
+# else:
+#     st.markdown(
+#         "<div class='predictive-table-wrapper'>"
+#         "<p style='text-align:center; color:#c62828; padding:24px; font-weight:500;'>"
+#         "⚠️ No rising categories with 100% monthly coverage."
+#         "</p>"
+#         "<p style='text-align:center; color:#666; font-size:0.9em;'>"
+#         "Consider relaxing coverage filter if data is sparse."
+#         "</p></div>",
+#         unsafe_allow_html=True
+#     )
+
+st.markdown("</div>", unsafe_allow_html=True)
+
+
+# =================== WHITEBOARD STYLE CHART FOR PANEL 4 ===================
+st.markdown("<h4 style='text-align: center; color: #2c3e50;'>Whiteboard Insight: Trend vs Frequency</h4>", unsafe_allow_html=True)
+
+# Buat chart scatter dengan gaya whiteboard
+if not df_category.empty:
     # Ambil data untuk scatter
-    df_plot = df_issue.copy()
+    df_plot = df_category.copy()
     df_plot['Size'] = df_plot['Avg/Month']  # Ukuran lingkaran = frekuensi (Avg/Month)
     df_plot['Y'] = df_plot['Trend Slope']   # Y = Trend Slope
 
@@ -1661,7 +1822,7 @@ if not df_issue.empty:
 
     # Layout
     fig.update_layout(
-        title=dict(text="<b>Issue Trend vs Frequency (Non-Positive)</b>", x=0.5, y=0.95),
+        title=dict(text="<b>Issue Category Trend vs Frequency (Non-Positive)</b>", x=0.5, y=0.95),
         xaxis=dict(
             title="Category",
             tickangle=45,
@@ -1733,8 +1894,7 @@ if not df_issue.empty:
     )
     st.markdown(insight_text, unsafe_allow_html=True)
 else:
-    st.info("No data available for non-positive issues with 100% coverage and positive trend.")
-# =================== 6. ✅ AI INSIGHT ENGINE (BARU - BERDASARKAN DATA & RATIO) ===================
+    st.info("No data available for non-positive issue categories with 100% coverage and positive trend.")
 
 st.markdown("<h3 class='section-title'>OBJECTIVE 7 - Insight and Recommendation</h3>", unsafe_allow_html=True)