Update app.py

app.py

@@ -1,9 +1,9 @@
 # -*- coding: utf-8 -*-
 """
-IPLM 2025 — Final (Target Sampel 33.88% per Jenis) + Kinerja Relatif (Percentile)
+IPLM 2025 — Final (Target Sampel 33.88% per Jenis)
 
 ───────────────────────────────────────────────────────────────────────────────
-DOKUMENTASI / KONSEP (DIPERTAHANKAN + DIPERJELAS)
+KONSEP (DIPERTAHANKAN + DIPERJELAS)
 
 A. Skor ABSOLUT (untuk akuntabilitas)
 ------------------------------------
@@ -31,53 +31,9 @@ A. Skor ABSOLUT (untuk akuntabilitas)
      Indeks_Final_Wilayah_0_100(keseluruhan) = (final_sekolah + final_umum + final_khusus) / 3
    - Missing jenis dianggap 0 tetapi tetap dibagi 3 (sesuai requirement).
 
-B. Skor KINERJA RELATIF (untuk benchmarking, bukan pengganti skor absolut)
----------------------------------------------------------------------------
-Kolom utama: Score_Kinerja_WilayahTotal_Percentile_0_100
-Definisi: posisi relatif suatu wilayah dibanding wilayah lain secara NASIONAL.
-
-Karakteristik utama percentile:
-• Skala 0–100
-• Tidak bergantung pada asumsi distribusi normal
-• Stabil terhadap nilai ekstrem (karena berbasis peringkat)
-• Mudah diinterpretasikan sebagai posisi peringkat
-
-RUMUS / IMPLEMENTASI (yang benar dan sesuai FIX bug):
-1) Tentukan "universe" perhitungan GLOBAL sesuai mode kewenangan:
-   - Jika kewenangan = "KAB/KOTA": universe = semua kab/kota (nasional) yang KEW_NORM == "KAB/KOTA"
-   - Jika kewenangan = "PROVINSI": universe = semua provinsi (nasional) yang KEW_NORM == "PROVINSI"
-   - Jika "(Semua)": default mengikuti pilihan (atau semua yang relevan) → pada UI kita pakai nilai dropdown.
-
-2) Hitung dulu agg_total_global untuk universe tersebut (tanpa filter prov/kab):
-   - Dari df_all (nasional) → faktor_wilayah_jenis → agg_jenis_global → agg_total_global
-
-3) Hitung percentile GLOBAL dari Indeks_Final_Wilayah_0_100 pada agg_total_global:
-   - Secara konsep:
-     Percentile(w) = 100 * (rank_w / N)
-   - Implementasi pandas yang audit-friendly:
-     rank(pct=True, method="average") * 100
-
-4) Tempelkan nilai percentile global itu ke hasil filter (agg_total yang biasanya hanya 1 baris):
-   - WAJIB pakai mapping by group_key (bukan merge yang bikin kolom _x/_y)
-   - Kenapa? agar tidak terjadi:
-     • percentile jadi 100 karena dihitung dari 1 baris filter
-     • atau KPI membaca kolom yang salah akibat suffix merge
-
-C. Bug yang kamu laporkan (0.00 / 100 semua)
---------------------------------------------
-Kasus 1: "100 semua" untuk 1 wilayah yang difilter → terjadi jika percentile dihitung dari data filter.
-Solusi: percentile selalu dihitung di agg_total_global lalu ditempel.
-
-Kasus 2: KPI jadi 0.00 (padahal harus 99-an) → terjadi jika merge menghasilkan kolom
-Score_Kinerja_WilayahTotal_Percentile_0_100_x/_y sehingga kolom yang dibaca kosong/NaN.
-Solusi: mapping dengan dict (tidak ada suffix), dan pastikan KPI membaca kolom final.
-
-───────────────────────────────────────────────────────────────────────────────
-KODE DI BAWAH INI SUDAH FIX:
-✅ Score_Kinerja_WilayahTotal_Percentile_0_100 dihitung GLOBAL (nasional) sesuai kewenangan
-✅ Ditempel pakai MAP (no _x/_y)
-✅ KPI selalu baca kolom final yang benar
-✅ Tetap mempertahankan semua fitur: ringkasan, agregat, verif, detail, bell curve, export
+CATATAN:
+- Versi ini SUDAH MENGHILANGKAN seluruh fitur "Kinerja Relatif (Percentile/RobustZ)".
+- Dashboard hanya menampilkan skor absolut dan penyesuaian target 33.88% per jenis.
 """
 
 import os
@@ -100,7 +56,7 @@ except Exception:
     DOCX_AVAILABLE = False
     Document = None
 
-# huggingface client opsional
+# huggingface client opsional (LLM)
 HF_AVAILABLE = True
 try:
     from huggingface_hub import InferenceClient
@@ -124,11 +80,7 @@ W_KINERJA   = float(os.getenv("W_KINERJA",   "0.70"))
 # ✅ target sampel 33.88% per jenis
 TARGET_RATIO = float(os.getenv("TARGET_RATIO", "0.3388"))
 
-# kinerja relatif
-USE_PERCENTILE = True
-USE_ROBUST_Z   = True
-
-# LLM opsional
+# LLM opsional (tidak wajib; aman dimatikan)
 USE_LLM = True
 LLM_MODEL_NAME = os.getenv("LLM_MODEL_NAME", "meta-llama/Meta-Llama-3-8B-Instruct")
 HF_TOKEN = (
@@ -267,71 +219,6 @@ def faktor_penyesuaian_total(n_total: float, target_total: float) -> float:
         n_total = 0.0
     return float(min(float(n_total) / float(target_total), 1.0))
 
-def add_kinerja_scores(
-    df: pd.DataFrame,
-    score_col: str,
-    group_cols: list | None,
-    prefix: str = "Score_Kinerja"
-) -> pd.DataFrame:
-    """
-    Tambah kolom:
-    - {prefix}_Percentile_0_100 = rank(pct=True)*100
-    - {prefix}_RobustZ_0_100    = 50 + 10*z_robust (MAD-based), clip 0..100
-    """
-    if df is None or df.empty or score_col not in df.columns:
-        return df
-
-    out = df.copy()
-
-    # Percentile 0–100
-    if USE_PERCENTILE:
-        if group_cols:
-            out[f"{prefix}_Percentile_0_100"] = (
-                out.groupby(group_cols, dropna=False)[score_col]
-                   .rank(pct=True, method="average") * 100.0
-            )
-        else:
-            out[f"{prefix}_Percentile_0_100"] = out[score_col].rank(pct=True, method="average") * 100.0
-
-        out[f"{prefix}_Percentile_0_100"] = (
-            pd.to_numeric(out[f"{prefix}_Percentile_0_100"], errors="coerce")
-              .fillna(0.0).clip(0, 100).round(2)
-        )
-
-    # Robust Z to 0–100
-    if USE_ROBUST_Z:
-        def _robustz_to_0_100(s: pd.Series) -> pd.Series:
-            v = pd.to_numeric(s, errors="coerce").astype(float)
-            v = v.replace([np.inf, -np.inf], np.nan)
-            if v.dropna().shape[0] < 2:
-                return pd.Series(50.0, index=v.index)
-
-            med = float(np.nanmedian(v.values))
-            mad = float(np.nanmedian(np.abs(v.values - med)))
-
-            if (not np.isfinite(mad)) or mad <= 1e-12:
-                sd = float(np.nanstd(v.values, ddof=1))
-                if (not np.isfinite(sd)) or sd <= 1e-12:
-                    return pd.Series(50.0, index=v.index)
-                z = (v - med) / sd
-            else:
-                z = (v - med) / (1.4826 * mad)
-
-            score = 50.0 + 10.0 * z
-            return score.clip(0, 100).fillna(50.0)
-
-        if group_cols:
-            out[f"{prefix}_RobustZ_0_100"] = out.groupby(group_cols, dropna=False)[score_col].transform(_robustz_to_0_100)
-        else:
-            out[f"{prefix}_RobustZ_0_100"] = _robustz_to_0_100(out[score_col])
-
-        out[f"{prefix}_RobustZ_0_100"] = (
-            pd.to_numeric(out[f"{prefix}_RobustZ_0_100"], errors="coerce")
-              .fillna(50.0).clip(0, 100).round(2)
-        )
-
-    return out
-
 
 # ============================================================
 # 3) INDIKATOR IPLM
@@ -680,6 +567,24 @@ def load_default_files(force=False):
 # 6) FAKTOR WILAYAH — PER JENIS (TARGET 33.88%)
 # ============================================================
 
+def _get_series_from_cols(base_pop: pd.DataFrame, col_candidates: list, index_name: str):
+    """
+    Ambil series dari base_pop berdasarkan kandidat nama kolom.
+    Return series float dengan index base_pop.index.
+    """
+    for c in col_candidates:
+        if c in base_pop.columns:
+            return pd.to_numeric(base_pop[c], errors="coerce").fillna(0.0)
+    # fallback: coba versi canon
+    can_map = {_canon(c): c for c in base_pop.columns}
+    for c in col_candidates:
+        k = _canon(c)
+        if k in can_map:
+            cc = can_map[k]
+            return pd.to_numeric(base_pop[cc], errors="coerce").fillna(0.0)
+    # jika tidak ada, return zeros
+    return pd.Series(0.0, index=base_pop.index, name=f"{index_name}_zeros")
+
 def build_faktor_wilayah_jenis(
     df_filtered: pd.DataFrame,
     pop_kab: pd.DataFrame,
@@ -709,16 +614,22 @@ def build_faktor_wilayah_jenis(
         key_col, label_col, label_name, mode = "prov_key", "PROV_DISP", "Provinsi", "PROV"
         base_pop = pop_prov.copy() if (pop_prov is not None and not pop_prov.empty) else pd.DataFrame()
         if not base_pop.empty and "prov_key" not in base_pop.columns:
-            base_pop["prov_key"] = base_pop["Provinsi_Label"].apply(norm_prov_label) if "Provinsi_Label" in base_pop.columns else base_pop.iloc[:, 0].apply(norm_prov_label)
+            if "Provinsi_Label" in base_pop.columns:
+                base_pop["prov_key"] = base_pop["Provinsi_Label"].apply(norm_prov_label)
+            else:
+                base_pop["prov_key"] = base_pop.iloc[:, 0].apply(norm_prov_label)
         base_pop = base_pop.set_index("prov_key") if (not base_pop.empty and "prov_key" in base_pop.columns) else pd.DataFrame().set_index(pd.Index([]))
     else:
         key_col, label_col, label_name, mode = "kab_key", "KAB_DISP", "Kab/Kota", "KAB"
         base_pop = pop_kab.copy() if (pop_kab is not None and not pop_kab.empty) else pd.DataFrame()
         if not base_pop.empty and "kab_key" not in base_pop.columns:
-            base_pop["kab_key"] = base_pop["Kab_Kota_Label"].apply(norm_kab_label) if "Kab_Kota_Label" in base_pop.columns else base_pop.iloc[:, 0].apply(norm_kab_label)
+            if "Kab_Kota_Label" in base_pop.columns:
+                base_pop["kab_key"] = base_pop["Kab_Kota_Label"].apply(norm_kab_label)
+            else:
+                base_pop["kab_key"] = base_pop.iloc[:, 0].apply(norm_kab_label)
         base_pop = base_pop.set_index("kab_key") if (not base_pop.empty and "kab_key" in base_pop.columns) else pd.DataFrame().set_index(pd.Index([]))
 
-    # GRID: semua wilayah × 3 jenis
+    # GRID: semua wilayah × 3 jenis (yang muncul di data hasil filter)
     base_keys = df[[key_col, label_col]].drop_duplicates().rename(columns={key_col: "group_key", label_col: label_name})
     full = base_keys.assign(_tmp=1).merge(
         pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}),
@@ -741,24 +652,34 @@ def build_faktor_wilayah_jenis(
     base_n["pop_total_jenis"] = 0.0
 
     # SEKOLAH + UMUM dari POP_KAB/POP_PROV
+    pop_sekolah = None
+    pop_umum = None
+    tgt_sekolah = None
+    tgt_umum = None
+
     if not base_pop.empty:
         if mode == "KAB":
-            pop_sekolah = pd.to_numeric(base_pop.get("jumlah_populasi_sekolah", 0), errors="coerce").fillna(0.0)
-            pop_umum    = pd.to_numeric(base_pop.get("jumlah_populasi_umum", 0), errors="coerce").fillna(0.0)
-
+            pop_sekolah = _get_series_from_cols(
+                base_pop,
+                ["jumlah_populasi_sekolah", "pop_sekolah", "sekolah"],
+                "pop_sekolah"
+            )
+            pop_umum = _get_series_from_cols(
+                base_pop,
+                ["jumlah_populasi_umum", "pop_umum", "umum"],
+                "pop_umum"
+            )
             tgt_sekolah = pop_sekolah * float(TARGET_RATIO)
             tgt_umum    = pop_umum * float(TARGET_RATIO)
         else:
-            sma = pd.to_numeric(base_pop.get("sma ", base_pop.get("sma", 0)), errors="coerce").fillna(0.0)
-            smk = pd.to_numeric(base_pop.get("smk", 0)), 
-            slb = pd.to_numeric(base_pop.get("slb", 0)), 
-            smk = pd.to_numeric(base_pop.get("smk", 0), errors="coerce").fillna(0.0)
-            slb = pd.to_numeric(base_pop.get("slb", 0), errors="coerce").fillna(0.0)
-
-            pop_sekolah = sma + smk + slb
+            # prov: sekolah = sma + smk + slb (nama kolom bisa bervariasi)
+            sma = _get_series_from_cols(base_pop, ["sma", "SMA", "sma "], "sma")
+            smk = _get_series_from_cols(base_pop, ["smk", "SMK"], "smk")
+            slb = _get_series_from_cols(base_pop, ["slb", "SLB"], "slb")
+            pop_sekolah = (sma + smk + slb)
             tgt_sekolah = pop_sekolah * float(TARGET_RATIO)
 
-            pop_umum = pd.to_numeric(base_pop.get("perpus_umum_prop", 0), errors="coerce").fillna(0.0)
+            pop_umum = _get_series_from_cols(base_pop, ["perpus_umum_prop", "perpus_umum", "umum"], "pop_umum")
             tgt_umum = pop_umum * float(TARGET_RATIO)
 
         m = base_n["Jenis"].eq("sekolah")
@@ -837,14 +758,11 @@ def build_faktor_wilayah_jenis(
 
 def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.DataFrame, kew_value: str):
     """
-    Agregasi:
-    wilayah × jenis:
+    Agregasi wilayah × jenis:
       - Jumlah (n entitas)
       - rata-rata sub/dim
       - Indeks_Dasar_Agregat_0_100 = mean(Indeks_Dasar_0_100)
       - Indeks_Final_Agregat_0_100 = Indeks_Dasar_Agregat_0_100 * faktor_penyesuaian_jenis
-    + score kinerja relatif per jenis:
-      Score_Kinerja_WilayahJenis_Percentile_0_100
     """
     if df_filtered is None or df_filtered.empty:
         return pd.DataFrame()
@@ -924,14 +842,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
         * pd.to_numeric(agg["faktor_penyesuaian_jenis"], errors="coerce").fillna(1.0)
     )
 
-    # Kinerja relatif per jenis
-    agg = add_kinerja_scores(
-        agg,
-        score_col="Indeks_Final_Agregat_0_100",
-        group_cols=["Jenis"],
-        prefix="Score_Kinerja_WilayahJenis"
-    )
-
     # rounding
     for c in [
         "Rata2_sub_koleksi","Rata2_sub_sdm","Rata2_sub_pelayanan","Rata2_sub_pengelolaan",
@@ -1053,8 +963,6 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_j
         )
         out["coverage_target33_88_all_%"] = pd.to_numeric(out["coverage_target33_88_all_%"], errors="coerce").fillna(0.0).round(2)
 
-    # NOTE: percentile global untuk wilayah keseluruhan tidak dihitung di sini.
-    #       Ia dihitung oleh fungsi global (compute_global_wilayah_scores) lalu ditempel.
     for c in [
         "Rata2_sub_koleksi","Rata2_sub_sdm","Rata2_sub_pelayanan","Rata2_sub_pengelolaan",
         "Rata2_dim_kepatuhan","Rata2_dim_kinerja"
@@ -1070,79 +978,6 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_j
     return out
 
 
-# ============================================================
-# 8B) GLOBAL SCORE TABLE (FIX: percentile harus dihitung nasional)
-# ============================================================
-
-_GLOBAL_SCORE_CACHE = {}
-
-def compute_global_wilayah_scores(df_all, pop_kab, pop_prov, pop_khusus, kew_value: str):
-    """
-    FIX UTAMA:
-    - Hitung agg_total GLOBAL (nasional) sesuai mode kewenangan (KAB/KOTA vs PROVINSI)
-    - Lalu hitung Score_Kinerja_WilayahTotal_Percentile_0_100 pada agg_total_global
-    - Return mapping dict: group_key -> percentile (dan robustZ jika dipakai)
-
-    Kenapa mapping dict?
-    - Menghindari merge suffix _x/_y
-    - Mencegah KPI membaca kolom yang salah (0.00)
-    """
-    kew_norm = str(kew_value or "").upper()
-    cache_key = (
-        kew_norm,
-        _mtime(DATA_FILE), _mtime(POP_KAB), _mtime(POP_PROV), _mtime(POP_KHUSUS),
-        float(TARGET_RATIO), float(W_KEPATUHAN), float(W_KINERJA),
-        bool(USE_PERCENTILE), bool(USE_ROBUST_Z)
-    )
-    if cache_key in _GLOBAL_SCORE_CACHE:
-        return _GLOBAL_SCORE_CACHE[cache_key]
-
-    if df_all is None or df_all.empty:
-        _GLOBAL_SCORE_CACHE[cache_key] = ({}, {})
-        return {}, {}
-
-    # Universe global sesuai kewenangan
-    if kew_norm in {"KAB/KOTA", "PROVINSI"}:
-        df_univ = df_all[df_all["KEW_NORM"] == kew_norm].copy()
-    else:
-        # fallback: pakai semua (tapi tetap nanti label mengikuti agg_total yang dipakai)
-        df_univ = df_all.copy()
-
-    faktor = build_faktor_wilayah_jenis(df_univ, pop_kab, pop_prov, pop_khusus, kew_norm)
-    agg_jenis = build_agg_wilayah_jenis(df_univ, faktor, kew_norm)
-    agg_total = build_agg_wilayah_total_from_jenis(agg_jenis, faktor, kew_norm)
-
-    # Hitung score relatif global pada agg_total_global
-    agg_total = add_kinerja_scores(
-        agg_total,
-        score_col="Indeks_Final_Wilayah_0_100",
-        group_cols=None,
-        prefix="Score_Kinerja_WilayahTotal"
-    )
-
-    pctl_map = {}
-    rz_map = {}
-
-    if "group_key" in agg_total.columns and "Score_Kinerja_WilayahTotal_Percentile_0_100" in agg_total.columns:
-        pctl_map = (
-            agg_total[["group_key", "Score_Kinerja_WilayahTotal_Percentile_0_100"]]
-            .dropna(subset=["group_key"])
-            .set_index("group_key")["Score_Kinerja_WilayahTotal_Percentile_0_100"]
-            .to_dict()
-        )
-
-    if "group_key" in agg_total.columns and "Score_Kinerja_WilayahTotal_RobustZ_0_100" in agg_total.columns:
-        rz_map = (
-            agg_total[["group_key", "Score_Kinerja_WilayahTotal_RobustZ_0_100"]]
-            .dropna(subset=["group_key"])
-            .set_index("group_key")["Score_Kinerja_WilayahTotal_RobustZ_0_100"]
-            .to_dict()
-        )
-
-    _GLOBAL_SCORE_CACHE[cache_key] = (pctl_map, rz_map)
-    return pctl_map, rz_map
-
-
 # ============================================================
 # 9) SUMMARY (PER JENIS) + KESELURUHAN
 # ============================================================
@@ -1259,7 +1094,6 @@ def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame):
 
 # ============================================================
 # 10) DETAIL ENTITAS: Final menempel dari agg_total (wilayah)
-#     + skor kinerja relatif per jenis (entitas-level)
 # ============================================================
 
 def attach_final_to_detail(df_filtered: pd.DataFrame, agg_total: pd.DataFrame, meta: dict, kew_value: str):
@@ -1300,14 +1134,6 @@ def attach_final_to_detail(df_filtered: pd.DataFrame, agg_total: pd.DataFrame, m
     out = df[keep].copy()
     out = out.rename(columns={label_cols[0]:"Provinsi", label_cols[1]:"Kab/Kota", "_dataset":"Jenis"})
 
-    # skor kinerja relatif per entitas (dibandingkan sesama jenis)
-    out = add_kinerja_scores(
-        out,
-        score_col="Indeks_Dasar_0_100",
-        group_cols=["Jenis"],
-        prefix="Score_Kinerja_Entitas"
-    )
-
     for c in ["sub_koleksi","sub_sdm","sub_pelayanan","sub_pengelolaan","dim_kepatuhan","dim_kinerja"]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(3)
@@ -1352,10 +1178,10 @@ def build_verif_jenis(faktor_wilayah_jenis: pd.DataFrame, kew_value: str):
 
 
 # ============================================================
-# 12) BELL CURVE (sama seperti versi kamu, disederhanakan aman)
+# 12) BELL CURVE (menampilkan distribusi skor ABSOLUT)
 # ============================================================
 
-def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, label_col: str | None = None, hover_cols: list | None = None, min_points: int = 2):
+def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, min_points: int = 2):
     fig = go.Figure()
     fig.update_layout(
         title=title,
@@ -1411,7 +1237,7 @@ def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, label_col: str |
 
 
 # ============================================================
-# 13) KPI DASHBOARD (skor absolut + percentile GLOBAL)
+# 13) KPI DASHBOARD (skor absolut saja)
 # ============================================================
 
 def _safe_first(df, col, default=0.0, where=None):
@@ -1424,22 +1250,17 @@ def _safe_first(df, col, default=0.0, where=None):
         return default
     return float(pd.to_numeric(sub[col], errors="coerce").fillna(default).iloc[0])
 
-def compute_dashboard_kpis(summary_jenis: pd.DataFrame, agg_total: pd.DataFrame):
+def compute_dashboard_kpis(summary_jenis: pd.DataFrame):
     final_all = _safe_first(summary_jenis, "Indeks_Final_Disesuaikan_0_100", 0.0, where=summary_jenis["Jenis"].astype(str).str.lower().eq("keseluruhan"))
     dasar_all = _safe_first(summary_jenis, "Indeks_Dasar_0_100", 0.0, where=summary_jenis["Jenis"].astype(str).str.lower().eq("keseluruhan"))
+    cov_all = _safe_first(summary_jenis, "Coverage_Target33_88_Jenis_%", 0.0, where=summary_jenis["Jenis"].astype(str).str.lower().eq("keseluruhan"))
+    return {"final_all": final_all, "dasar_all": dasar_all, "cov_all": cov_all}
 
-    # KPI percentile wilayah terpilih: di agg_total (sudah ditempel global)
-    pctl_sel = 0.0
-    if agg_total is not None and not agg_total.empty and "Score_Kinerja_WilayahTotal_Percentile_0_100" in agg_total.columns:
-        pctl_sel = float(pd.to_numeric(agg_total["Score_Kinerja_WilayahTotal_Percentile_0_100"], errors="coerce").fillna(0.0).iloc[0])
-
-    return {"final_all": final_all, "dasar_all": dasar_all, "pctl_sel": pctl_sel}
-
-def build_kpi_markdown(summary_jenis: pd.DataFrame, agg_total: pd.DataFrame) -> str:
+def build_kpi_markdown(summary_jenis: pd.DataFrame) -> str:
     if summary_jenis is None or summary_jenis.empty:
         return ""
 
-    k = compute_dashboard_kpis(summary_jenis, agg_total)
+    k = compute_dashboard_kpis(summary_jenis)
 
     def fmt(x, nd=2):
         return "NA" if pd.isna(x) else f"{x:.{nd}f}"
@@ -1459,9 +1280,9 @@ def build_kpi_markdown(summary_jenis: pd.DataFrame, agg_total: pd.DataFrame) ->
   </div>
 
   <div style="border:1px solid #333; border-radius:10px; padding:10px 12px; min-width:260px;">
-    <div style="opacity:0.8;">Nilai Kinerja (Percentile Wilayah)</div>
-    <div style="font-size:26px; font-weight:700;">{fmt(k["pctl_sel"],2)}</div>
-    <div style="opacity:0.7;">Percentile GLOBAL (nasional), bukan hasil filter</div>
+    <div style="opacity:0.8;">Coverage terhadap Target 33.88% (Keseluruhan)</div>
+    <div style="font-size:26px; font-weight:700;">{fmt(k["cov_all"],2)}%</div>
+    <div style="opacity:0.7;">(Terkumpul ÷ Target33.88) × 100</div>
   </div>
 </div>
 """.strip()
@@ -1497,9 +1318,9 @@ def generate_llm_analysis(summary_jenis, agg_total, verif_total, wilayah, kew):
             model=LLM_MODEL_NAME,
             messages=[
                 {"role":"system","content":"Anda adalah analis kebijakan perpustakaan di Indonesia. Tulis analisis ringkas berbasis data."},
-                {"role":"user","content":f"{ctx}\nBuat analisis 3 paragraf: skor absolut, kinerja relatif percentile, rekomendasi singkat."}
+                {"role":"user","content":f"{ctx}\nBuat analisis 3 paragraf: (1) skor dasar vs final, (2) kecukupan sampel 33.88% per jenis, (3) rekomendasi singkat."}
             ],
-            max_tokens=500,
+            max_tokens=520,
             temperature=0.25,
             top_p=0.9,
         )
@@ -1514,7 +1335,6 @@ def generate_word_report(wilayah, summary_jenis, analysis_text):
     doc = Document()
     doc.add_heading(f"Laporan IPLM — {wilayah}", level=1)
     doc.add_paragraph(f"Target sampel per jenis: {TARGET_RATIO*100:.2f}%")
-    doc.add_paragraph("Catatan: Percentile kinerja wilayah yang ditampilkan adalah percentile GLOBAL (nasional), bukan dari hasil filter.")
     doc.add_heading("Ringkasan (Jenis + Keseluruhan)", level=2)
     if summary_jenis is not None and not summary_jenis.empty:
         show = summary_jenis.copy()
@@ -1585,29 +1405,14 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         agg_total = build_agg_wilayah_total_from_jenis(agg_jenis_full, faktor_wilayah_jenis, kew_norm)
 
         # =========================================================
-        # 3) FIX PERCENTILE: hitung GLOBAL dulu, lalu TEMPEL via MAP
-        #    (NO MERGE → no _x/_y, KPI tidak akan 0.00)
-        # =========================================================
-        pctl_map, rz_map = compute_global_wilayah_scores(df_all, pop_kab, pop_prov, pop_khusus, kew_norm)
-
-        if agg_total is not None and not agg_total.empty and "group_key" in agg_total.columns:
-            agg_total["Score_Kinerja_WilayahTotal_Percentile_0_100"] = (
-                agg_total["group_key"].map(pctl_map).fillna(0.0).astype(float).round(2)
-            )
-            if USE_ROBUST_Z:
-                agg_total["Score_Kinerja_WilayahTotal_RobustZ_0_100"] = (
-                    agg_total["group_key"].map(rz_map).fillna(50.0).astype(float).round(2)
-                )
-
-        # =========================================================
-        # 4) OUTPUT TABLES
+        # 3) OUTPUT TABLES
         # =========================================================
         summary_jenis = build_summary_per_jenis(agg_jenis_full, agg_total)
         verif_total = build_verif_jenis(faktor_wilayah_jenis, kew_norm)
         detail_view = attach_final_to_detail(df, agg_total, meta, kew_norm)
 
         # =========================================================
-        # 5) agg_jenis view (UI hanya sampai indeks dasar)
+        # 4) agg_jenis view (UI hanya sampai indeks dasar)
         # =========================================================
         if agg_jenis_full is None or agg_jenis_full.empty:
             agg_jenis_view = agg_jenis_full
@@ -1627,7 +1432,7 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
             agg_jenis_view = agg_jenis_full[cols_upto].copy()
 
         # =========================================================
-        # 6) FILTER RAW DOWNLOAD (harus raw hasil filter)
+        # 5) FILTER RAW DOWNLOAD (harus raw hasil filter)
         # =========================================================
         raw = df_raw.copy()
         if prov_value and prov_value != "(Semua)":
@@ -1638,14 +1443,15 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
             raw = raw[raw["KEW_NORM"] == kew_value]
 
         # =========================================================
-        # 7) Bell curve per jenis (entitas)
+        # 6) Bell curve per jenis (ENTITAS) — skor ABSOLUT
+        #    default pakai Indeks_Final_0_100 (lebih “nyambung” dg penyesuaian)
         # =========================================================
         if detail_view is None or detail_view.empty:
-            fig_umum = _make_bell_curve(pd.DataFrame(), "Score_Kinerja_Entitas_Percentile_0_100", "Bell Curve — Jenis: Umum", min_points=2)
-            fig_sekolah = _make_bell_curve(pd.DataFrame(), "Score_Kinerja_Entitas_Percentile_0_100", "Bell Curve — Jenis: Sekolah", min_points=2)
-            fig_khusus = _make_bell_curve(pd.DataFrame(), "Score_Kinerja_Entitas_Percentile_0_100", "Bell Curve — Jenis: Khusus", min_points=2)
+            fig_umum = _make_bell_curve(pd.DataFrame(), "Indeks_Final_0_100", "Bell Curve — Jenis: Umum", min_points=2)
+            fig_sekolah = _make_bell_curve(pd.DataFrame(), "Indeks_Final_0_100", "Bell Curve — Jenis: Sekolah", min_points=2)
+            fig_khusus = _make_bell_curve(pd.DataFrame(), "Indeks_Final_0_100", "Bell Curve — Jenis: Khusus", min_points=2)
         else:
-            xcol_ent = "Score_Kinerja_Entitas_Percentile_0_100" if "Score_Kinerja_Entitas_Percentile_0_100" in detail_view.columns else "Indeks_Dasar_0_100"
+            xcol_ent = "Indeks_Final_0_100" if "Indeks_Final_0_100" in detail_view.columns else "Indeks_Dasar_0_100"
             def _fig(j):
                 d = detail_view[detail_view["Jenis"].astype(str).str.lower() == j].copy()
                 return _make_bell_curve(d, xcol_ent, f"Bell Curve — Jenis: {j.title()} (Skor: {xcol_ent})", min_points=2)
@@ -1654,12 +1460,12 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
             fig_khusus = _fig("khusus")
 
         # =========================================================
-        # 8) KPI (percentile sudah GLOBAL)
+        # 7) KPI (skor absolut)
         # =========================================================
-        kpi_md = build_kpi_markdown(summary_jenis, agg_total)
+        kpi_md = build_kpi_markdown(summary_jenis)
 
         # =========================================================
-        # 9) Export (xlsx + opsional docx)
+        # 8) Export (xlsx + opsional docx)
         # =========================================================
         tmpdir = tempfile.mkdtemp()
         prov_slug = (_canon(prov_value or "SEMUA").upper() or "SEMUA")
@@ -1743,7 +1549,7 @@ def on_prov_change(prov_value):
 
 with gr.Blocks() as demo:
     gr.Markdown(f"""
-# IPLM 2025 — Final (Target Sampel **33.88%** per Jenis) + Kinerja Relatif (Percentile GLOBAL)
+# IPLM 2025 — Final (Target Sampel **33.88%** per Jenis)
 **Mode NO UPLOAD (cache aktif).** File dibaca dari repo/server:
 - `DATA_FILE`   = **{DATA_FILE}**
 - `POP_KAB`     = **{POP_KAB}**
@@ -1752,15 +1558,10 @@ with gr.Blocks() as demo:
 
 **TARGET RATIO (per jenis): {TARGET_RATIO*100:.2f}%**
 
-✅ Dashboard KPI menampilkan juga:
-- `Score_Kinerja_WilayahTotal_Percentile_0_100` (**GLOBAL nasional**; bukan hasil filter)
-
-**Skor Absolut (untuk akuntabilitas):**
-- `Indeks_Final_*` (sudah disesuaikan target 33.88%)
-
-**Skor Kinerja Relatif (untuk benchmarking):**
-- `Score_Kinerja_*_Percentile_0_100` (utama, stabil tanpa asumsi normal)
-- `Score_Kinerja_*_RobustZ_0_100` (opsional, tahan outlier)
+✅ Output fokus pada **Skor Absolut**:
+- `Indeks_Dasar_0_100` (entitas)
+- `Indeks_Final_*` (agregat) = skor dasar × faktor kecukupan sampel 33.88% (per jenis)
+- `Keseluruhan` wajib **avg3** (missing=0 tapi tetap dibagi 3)
 """)
 
     state_df = gr.State(None)
@@ -1787,19 +1588,19 @@ with gr.Blocks() as demo:
     gr.Markdown("## Ringkasan (Jenis + Keseluruhan) — Pop/Target33.88/Terkumpul/Coverage + Penyesuaian")
     out_summary = gr.DataFrame(interactive=False)
 
-    gr.Markdown("## Agregat Wilayah (Keseluruhan) — FIX avg3 + Score Kinerja Relatif (GLOBAL)")
+    gr.Markdown("## Agregat Wilayah (Keseluruhan) — FIX avg3 (Skor Absolut)")
     out_agg_total = gr.DataFrame(interactive=False)
 
     gr.Markdown("## Agregat Wilayah × Jenis — (ditampilkan sampai Indeks_Dasar_Agregat_0_100)")
     out_agg_jenis = gr.DataFrame(interactive=False)
 
-    gr.Markdown("## Detail Entitas (Final menempel dari wilayah + Skor Kinerja Relatif per Jenis)")
+    gr.Markdown("## Detail Entitas (Final menempel dari wilayah)")
     out_detail = gr.DataFrame(interactive=False)
 
     gr.Markdown("## Kecukupan Sampel 33.88% (tanpa angka koma untuk integer)")
     out_verif = gr.DataFrame(interactive=False)
 
-    gr.Markdown("## Bell Curve — per Jenis")
+    gr.Markdown("## Bell Curve — per Jenis (Skor Absolut Entitas)")
     gr.Markdown("### Perpustakaan Umum")
     bell_umum = gr.Plot(scale=1)
 
@@ -1837,4 +1638,4 @@ with gr.Blocks() as demo:
         outputs=[state_df, state_raw, state_pop_kab, state_pop_prov, state_pop_khusus, state_meta, info_box, dd_prov, dd_kab, dd_kew]
     )
 
-demo.launch()
+demo.launch()