Update app.py

app.py

@@ -2,38 +2,20 @@
 """
 IPLM 2025 — Final (Target Sampel 33.88% per Jenis)
 
-───────────────────────────────────────────────────────────────────────────────
-KONSEP (DIPERTAHANKAN + DIPERJELAS)
-
-A. Skor ABSOLUT (untuk akuntabilitas)
-------------------------------------
-1) Indeks_Dasar_0_100
-   - Dihitung pada LEVEL ENTITAS (baris perpustakaan) dari indikator:
-     Yeo-Johnson transform (per indikator) → MinMax global (0–1) → sub-indeks → dimensi → indeks.
-   - Rumus:
-     dim_kepatuhan = mean(sub_koleksi, sub_sdm)
-     dim_kinerja   = mean(sub_pelayanan, sub_pengelolaan)
-     Indeks_Dasar_0_100 = 100 * (W_KEPATUHAN*dim_kepatuhan + W_KINERJA*dim_kinerja)
-
-2) Penyesuaian kecukupan sampel berbasis TARGET 33.88% (per JENIS)
-   - TARGET_RATIO = 0.3388
-   - Untuk setiap wilayah × jenis:
-     pop_total_jenis = populasi perpustakaan jenis tsb (dari tabel POP)
-     target_total_33_88_jenis = pop_total_jenis * TARGET_RATIO
-     n_jenis = jumlah entitas (baris) terkumpul pada wilayah × jenis
-     faktor_penyesuaian_jenis = min(n_jenis / target_total_33_88_jenis, 1.0)
-   - Indeks_Final_Agregat_0_100 (wilayah×jenis):
-     Indeks_Final_Agregat_0_100 = Indeks_Dasar_Agregat_0_100 * faktor_penyesuaian_jenis
-
-3) AGREGAT WILAYAH (KESELURUHAN) = rata-rata 3 jenis (FIX)
-   - Keseluruhan wajib avg3:
-     Indeks_Dasar_Agregat_0_100(keseluruhan) = (dasar_sekolah + dasar_umum + dasar_khusus) / 3
-     Indeks_Final_Wilayah_0_100(keseluruhan) = (final_sekolah + final_umum + final_khusus) / 3
-   - Missing jenis dianggap 0 tetapi tetap dibagi 3 (sesuai requirement).
-
-CATATAN:
-- Versi ini SUDAH MENGHILANGKAN seluruh fitur "Kinerja Relatif (Percentile/RobustZ)".
-- Dashboard hanya menampilkan skor absolut dan penyesuaian target 33.88% per jenis.
+PERUBAHAN SESUAI PERMINTAAN:
+1) KPI Dashboard: HANYA 2 kartu
+   - Indeks IPLM FINAL (Disesuaikan 33.88%)
+   - Indeks Dasar (Tanpa Penyesuaian)
+   ✅ Kartu "Coverage terhadap Target 33.88% (Keseluruhan)" DIHAPUS.
+
+2) Bell Curve: DIKEMBALIKAN KE SEMULA
+   - Menampilkan distribusi **Indeks_Dasar_0_100** pada LEVEL ENTITAS (perpustakaan)
+   - Dipisah per Jenis: Sekolah / Umum / Khusus
+   - Titik entitas menampilkan label **nama perpustakaan** (hover) per jenis.
+
+Catatan:
+- Skor tetap berbasis ABSOLUT.
+- Penyesuaian target 33.88% tetap dipakai untuk indeks final agregat wilayah.
 """
 
 import os
@@ -48,7 +30,7 @@ import pandas as pd
 import plotly.graph_objects as go
 from sklearn.preprocessing import PowerTransformer
 
-# python-docx opsional (di HF Space kadang belum ter-install)
+# python-docx opsional
 DOCX_AVAILABLE = True
 try:
     from docx import Document
@@ -56,7 +38,7 @@ except Exception:
     DOCX_AVAILABLE = False
     Document = None
 
-# huggingface client opsional (LLM)
+# huggingface client opsional
 HF_AVAILABLE = True
 try:
     from huggingface_hub import InferenceClient
@@ -77,10 +59,8 @@ POP_KHUSUS  = os.getenv("POP_KHUSUS",  "Data_populasi_perp_khusus.xlsx")
 W_KEPATUHAN = float(os.getenv("W_KEPATUHAN", "0.30"))
 W_KINERJA   = float(os.getenv("W_KINERJA",   "0.70"))
 
-# ✅ target sampel 33.88% per jenis
 TARGET_RATIO = float(os.getenv("TARGET_RATIO", "0.3388"))
 
-# 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 = (
@@ -130,7 +110,6 @@ def coerce_num(val):
     t = t.replace("\u00a0", " ").replace("Rp", "").replace("%", "")
     t = re.sub(r"[^0-9,.\-]", "", t)
 
-    # smart decimal
     if t.count(".") > 1 and t.count(",") == 1:
         t = t.replace(".", "").replace(",", ".")
     elif t.count(",") > 1 and t.count(".") == 1:
@@ -152,6 +131,17 @@ def minmax_norm(s: pd.Series) -> pd.Series:
         return pd.Series(0.0, index=s.index)
     return (x - mn) / (mx - mn)
 
+def _mean_norm_cols(row, cols):
+    vals = []
+    for c in cols:
+        k = f"norm_{c}"
+        if k in row.index:
+            v = row[k]
+            if pd.isna(v):
+                v = 0.0
+            vals.append(float(v))
+    return float(np.mean(vals)) if vals else 0.0
+
 def norm_kew(v):
     if pd.isna(v):
         return None
@@ -209,16 +199,21 @@ def safe_div(num, den):
     return float(num) / float(den)
 
 def faktor_penyesuaian_total(n_total: float, target_total: float) -> float:
-    """
-    faktor = min(n / target, 1.0)
-    - Jika target <= 0 → default 1.0 (tidak menghukum)
-    """
     if target_total is None or pd.isna(target_total) or float(target_total) <= 0:
         return 1.0
     if n_total is None or pd.isna(n_total) or float(n_total) < 0:
         n_total = 0.0
     return float(min(float(n_total) / float(target_total), 1.0))
 
+def _first_nonempty(*vals, default=""):
+    for v in vals:
+        if v is None:
+            continue
+        s = str(v).strip()
+        if s != "" and s.lower() != "nan":
+            return s
+    return default
+
 
 # ============================================================
 # 3) INDIKATOR IPLM
@@ -246,7 +241,6 @@ pengelolaan_cols = [
 ]
 all_indicators = koleksi_cols + sdm_cols + pelayanan_cols + pengelolaan_cols
 
-# alias kolom DM → nama baku indikator
 alias_map_raw = {
     "j_judul_koleksi_tercetak": "JudulTercetak",
     "j_eksemplar_koleksi_tercetak": "EksemplarTercetak",
@@ -281,32 +275,12 @@ alias_map = {_canon(k): v for k, v in alias_map_raw.items()}
 # 4) PIPELINE NASIONAL (LEVEL ENTITAS)
 # ============================================================
 
-def _mean_norm_cols(row, cols):
-    vals = []
-    for c in cols:
-        k = f"norm_{c}"
-        if k in row.index:
-            v = row[k]
-            if pd.isna(v):
-                v = 0.0
-            vals.append(float(v))
-    return float(np.mean(vals)) if vals else 0.0
-
 def prepare_global(df_src: pd.DataFrame) -> pd.DataFrame:
-    """
-    Transform + normalisasi indikator pada level entitas:
-    - rename kolom indikator (alias)
-    - coerce numeric
-    - Yeo-Johnson per indikator (standardize=False)
-    - MinMax global 0-1
-    - hitung sub_*, dim_*, Indeks_Dasar_0_100
-    """
     if df_src is None or df_src.empty:
         return df_src
 
     df = df_src.copy()
 
-    # rename indikator
     rename_map = {}
     for col in df.columns:
         c = _canon(col)
@@ -324,7 +298,6 @@ def prepare_global(df_src: pd.DataFrame) -> pd.DataFrame:
     for c in available:
         df[c] = df[c].apply(coerce_num)
 
-    # YJ per indikator + MinMax global
     for c in available:
         x = pd.to_numeric(df[c], errors="coerce").astype(float).values
         mask = ~np.isnan(x)
@@ -356,27 +329,9 @@ def prepare_global(df_src: pd.DataFrame) -> pd.DataFrame:
 # 5) CACHE LOADER (NO UPLOAD)
 # ============================================================
 
-_CACHE = {
-    "key": None,
-    "df_all": None,
-    "df_raw": None,
-    "pop_kab": None,
-    "pop_prov": None,
-    "pop_khusus": None,
-    "meta": None,
-    "info": None
-}
+_CACHE = {"key": None, "df_all": None, "df_raw": None, "pop_kab": None, "pop_prov": None, "pop_khusus": None, "meta": None, "info": None}
 
 def _parse_pop_khusus(path_xlsx: str) -> pd.DataFrame:
-    """
-    POP_KHUSUS memiliki format campuran:
-    - Baris 'PROVINSI X' → dianggap level PROV
-    - Baris berikutnya → dianggap KAB/KOTA di bawah prov tersebut
-    Output distandarkan:
-    LEVEL: PROV / KAB
-    prov_key / kab_key
-    Pop_Total_Jenis
-    """
     df = pd.read_excel(path_xlsx)
     if df is None or df.empty:
         return pd.DataFrame()
@@ -403,24 +358,12 @@ def _parse_pop_khusus(path_xlsx: str) -> pd.DataFrame:
         mm = _disp_text(m) or ""
         if mm == "":
             continue
-
         if mm.startswith("PROVINSI "):
             prov_name = mm.replace("PROVINSI", "").strip()
             current_prov = prov_name
-            rows.append({
-                "LEVEL": "PROV",
-                "Provinsi_Label": f"PROVINSI {prov_name}",
-                "Kab_Kota_Label": None,
-                "Pop_Total_Jenis": pval,
-            })
+            rows.append({"LEVEL": "PROV", "Provinsi_Label": f"PROVINSI {prov_name}", "Kab_Kota_Label": None, "Pop_Total_Jenis": pval})
             continue
-
-        rows.append({
-            "LEVEL": "KAB",
-            "Provinsi_Label": f"PROVINSI {current_prov}" if current_prov else None,
-            "Kab_Kota_Label": mm,
-            "Pop_Total_Jenis": pval,
-        })
+        rows.append({"LEVEL": "KAB", "Provinsi_Label": f"PROVINSI {current_prov}" if current_prov else None, "Kab_Kota_Label": mm, "Pop_Total_Jenis": pval})
 
     pop = pd.DataFrame(rows)
     if pop.empty:
@@ -432,19 +375,7 @@ def _parse_pop_khusus(path_xlsx: str) -> pd.DataFrame:
     return pop
 
 def load_default_files(force=False):
-    """
-    Load 4 file:
-    - DM (DATA_FILE) bisa multi-sheet → concat
-    - POP_KAB, POP_PROV, POP_KHUSUS
-    + Standarisasi kolom wilayah & jenis
-    + Dedup baris DM
-    + prepare_global() (YJ+MinMax+Indeks_Dasar)
-    """
-    key = (
-        DATA_FILE, POP_KAB, POP_PROV, POP_KHUSUS,
-        _mtime(DATA_FILE), _mtime(POP_KAB), _mtime(POP_PROV), _mtime(POP_KHUSUS)
-    )
-
+    key = (DATA_FILE, POP_KAB, POP_PROV, POP_KHUSUS, _mtime(DATA_FILE), _mtime(POP_KAB), _mtime(POP_PROV), _mtime(POP_KHUSUS))
     if (not force) and _CACHE["key"] == key and _CACHE["df_all"] is not None:
         return _CACHE["df_all"], _CACHE["df_raw"], _CACHE["pop_kab"], _CACHE["pop_prov"], _CACHE["pop_khusus"], _CACHE["meta"], _CACHE["info"]
 
@@ -460,7 +391,7 @@ def load_default_files(force=False):
     df_raw = pd.concat(frames, ignore_index=True, sort=False)
 
     prov_col  = pick_col(df_raw, ["provinsi", "Provinsi", "PROVINSI"])
-    kab_col   = pick_col(df_raw, ["kab_kota", "Kab/Kota", "Kab_Kota", "KAB/KOTA", "kabupaten_kota", "Kabupaten/Kota", "kabupaten kota", "kota"])
+    kab_col   = pick_col(df_raw, ["kab/kota", "kab_kota", "Kab/Kota", "Kab_Kota", "KAB/KOTA", "kabupaten_kota", "Kabupaten/Kota", "kabupaten kota", "kota"])
     kew_col   = pick_col(df_raw, ["kewenangan", "jenis_kewenangan", "Kewenangan", "KEWENANGAN"])
     jenis_col = pick_col(df_raw, ["jenis_perpustakaan", "Jenis Perpustakaan", "JENIS_PERPUSTAKAAN"])
     nama_col  = pick_col(df_raw, ["nm_perpustakaan","nama_perpustakaan","Nama Perpustakaan","nm_instansi_lembaga","nm_perpus"])
@@ -475,7 +406,6 @@ def load_default_files(force=False):
         _CACHE.update({"key": key, "df_all": None, "df_raw": None, "pop_kab": None, "pop_prov": None, "pop_khusus": None, "meta": {}, "info": info})
         return None, None, None, None, None, {}, info
 
-    # mapping jenis → baku (sekolah/umum/khusus)
     val_map_jenis = {
         "PERPUSTAKAAN SEKOLAH": "sekolah", "SEKOLAH": "sekolah",
         "PERPUSTAKAAN UMUM": "umum", "UMUM": "umum", "PERPUSTAKAAN DAERAH": "umum",
@@ -489,7 +419,7 @@ def load_default_files(force=False):
     df_raw["prov_key"]  = df_raw["PROV_DISP"].apply(norm_prov_label)
     df_raw["kab_key"]   = df_raw["KAB_DISP"].apply(norm_kab_label)
 
-    # Dedup aman berdasarkan (prov,kab,kew,jenis,nama_perpus)
+    # Dedup berdasarkan (prov,kab,kew,jenis,nama)
     if nama_col and nama_col in df_raw.columns:
         kcols = [prov_col, kab_col, kew_col, jenis_col, nama_col]
     else:
@@ -550,16 +480,7 @@ def load_default_files(force=False):
         f"🕒 mtime: DM={time.ctime(_mtime(DATA_FILE))} | Kab={time.ctime(_mtime(POP_KAB))} | Prov={time.ctime(_mtime(POP_PROV))} | Khusus={time.ctime(_mtime(POP_KHUSUS))}"
     )
 
-    _CACHE.update({
-        "key": key,
-        "df_all": df_all,
-        "df_raw": df_raw,
-        "pop_kab": pop_kab,
-        "pop_prov": pop_prov,
-        "pop_khusus": pop_khusus,
-        "meta": meta,
-        "info": info
-    })
+    _CACHE.update({"key": key, "df_all": df_all, "df_raw": df_raw, "pop_kab": pop_kab, "pop_prov": pop_prov, "pop_khusus": pop_khusus, "meta": meta, "info": info})
     return df_all, df_raw, pop_kab, pop_prov, pop_khusus, meta, info
 
 
@@ -568,36 +489,18 @@ def load_default_files(force=False):
 # ============================================================
 
 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,
-    pop_prov: pd.DataFrame,
-    pop_khusus: pd.DataFrame,
-    kew_value: str
-):
-    """
-    Output tabel:
-    group_key + (Kab/Kota atau Provinsi) + Jenis
-    n_jenis, pop_total_jenis, target_total_33_88_jenis,
-    coverage_jenis_%, faktor_penyesuaian_jenis, gap_target33_88_jenis
-    """
+def build_faktor_wilayah_jenis(df_filtered: pd.DataFrame, pop_kab: pd.DataFrame, pop_prov: pd.DataFrame, pop_khusus: pd.DataFrame, kew_value: str):
     if df_filtered is None or df_filtered.empty:
         return pd.DataFrame()
 
@@ -609,7 +512,6 @@ def build_faktor_wilayah_jenis(
 
     jenis_list = ["sekolah", "umum", "khusus"]
 
-    # tentukan level berdasarkan kewenangan
     if "PROV" in kew_norm:
         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()
@@ -629,18 +531,12 @@ def build_faktor_wilayah_jenis(
                 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 (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}),
-        on="_tmp"
-    ).drop(columns="_tmp")
+    full = base_keys.assign(_tmp=1).merge(pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}), on="_tmp").drop(columns="_tmp")
 
-    # count entitas per wilayah×jenis
     cnt = (
         df.groupby([key_col, label_col, "_dataset"], dropna=False)
-          .size()
-          .reset_index(name="n_jenis")
+          .size().reset_index(name="n_jenis")
           .rename(columns={key_col: "group_key", label_col: label_name, "_dataset": "Jenis"})
     )
     cnt["Jenis"] = cnt["Jenis"].astype(str).str.lower().str.strip()
@@ -651,36 +547,21 @@ def build_faktor_wilayah_jenis(
     base_n["target_total_33_88_jenis"] = 0.0
     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
-
+    # sekolah + umum dari POP_KAB/POP_PROV
     if not base_pop.empty:
         if mode == "KAB":
-            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"
-            )
+            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:
-            # prov: sekolah = sma + smk + slb (nama kolom bisa bervariasi)
-            sma = _get_series_from_cols(base_pop, ["sma", "SMA", "sma "], "sma")
+            sma = _get_series_from_cols(base_pop, ["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 = _get_series_from_cols(base_pop, ["perpus_umum_prop", "perpus_umum", "umum"], "pop_umum")
-            tgt_umum = pop_umum * float(TARGET_RATIO)
+            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")
         base_n.loc[m, "pop_total_jenis"] = base_n.loc[m, "group_key"].map(pop_sekolah).fillna(0.0).values
@@ -690,7 +571,7 @@ def build_faktor_wilayah_jenis(
         base_n.loc[m, "pop_total_jenis"] = base_n.loc[m, "group_key"].map(pop_umum).fillna(0.0).values
         base_n.loc[m, "target_total_33_88_jenis"] = base_n.loc[m, "group_key"].map(tgt_umum).fillna(0.0).values
 
-    # KHUSUS dari POP_KHUSUS
+    # khusus dari POP_KHUSUS
     if pop_khusus is not None and not pop_khusus.empty:
         pk = pop_khusus.copy()
         pk["Pop_Total_Jenis"] = pd.to_numeric(pk.get("Pop_Total_Jenis", 0), errors="coerce").fillna(0.0)
@@ -713,11 +594,9 @@ def build_faktor_wilayah_jenis(
     base_n["target_total_33_88_jenis"] = pd.to_numeric(base_n["target_total_33_88_jenis"], errors="coerce").fillna(0.0)
     base_n["pop_total_jenis"] = pd.to_numeric(base_n["pop_total_jenis"], errors="coerce").fillna(0.0)
 
-    # fallback pop jika 0 tapi target ada
     m_need_pop = (base_n["pop_total_jenis"] <= 0) & (base_n["target_total_33_88_jenis"] > 0)
     base_n.loc[m_need_pop, "pop_total_jenis"] = base_n.loc[m_need_pop, "target_total_33_88_jenis"] / float(TARGET_RATIO)
 
-    # faktor penyesuaian
     base_n["faktor_penyesuaian_jenis"] = [
         faktor_penyesuaian_total(n, t)
         for n, t in zip(
@@ -742,7 +621,6 @@ def build_faktor_wilayah_jenis(
         )
     ]
 
-    # display formatting
     base_n["target_total_33_88_jenis"] = pd.to_numeric(base_n["target_total_33_88_jenis"], errors="coerce").fillna(0).round(0).astype(int)
     base_n["pop_total_jenis"]          = pd.to_numeric(base_n["pop_total_jenis"], errors="coerce").fillna(0).round(0).astype(int)
     base_n["coverage_jenis_%"]         = pd.to_numeric(base_n["coverage_jenis_%"], errors="coerce").fillna(0.0).round(2)
@@ -757,13 +635,6 @@ 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:
-      - 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
-    """
     if df_filtered is None or df_filtered.empty:
         return pd.DataFrame()
 
@@ -781,14 +652,9 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
 
     jenis_list = ["sekolah", "umum", "khusus"]
 
-    # GRID semua wilayah × 3 jenis
     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}),
-        on="_tmp"
-    ).drop(columns="_tmp")
+    full = base_keys.assign(_tmp=1).merge(pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}), on="_tmp").drop(columns="_tmp")
 
-    # agregat real
     agg_real = df.groupby([key_col, label_col, "_dataset"], dropna=False).agg(
         Jumlah=("Indeks_Dasar_0_100", "size"),
         Rata2_sub_koleksi=("sub_koleksi", "mean"),
@@ -810,7 +676,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
 
     agg["Jumlah"] = agg["Jumlah"].round(0).astype(int)
 
-    # merge faktor jenis
     if faktor_wilayah_jenis is None or faktor_wilayah_jenis.empty:
         agg["faktor_penyesuaian_jenis"] = 1.0
         agg["target_total_33_88_jenis"] = 0
@@ -820,7 +685,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
     else:
         fw = faktor_wilayah_jenis.copy()
         fw["Jenis"] = fw["Jenis"].astype(str).str.lower().str.strip()
-
         keep = ["group_key", label_name, "Jenis",
                 "faktor_penyesuaian_jenis", "target_total_33_88_jenis", "pop_total_jenis",
                 "coverage_jenis_%", "gap_target33_88_jenis", "n_jenis"]
@@ -832,28 +696,23 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
         for c in ["target_total_33_88_jenis","pop_total_jenis","gap_target33_88_jenis","n_jenis"]:
             if c in agg.columns:
                 agg[c] = pd.to_numeric(agg[c], errors="coerce").fillna(0).round(0).astype(int)
-
         if "coverage_jenis_%" in agg.columns:
             agg["coverage_jenis_%"] = pd.to_numeric(agg["coverage_jenis_%"], errors="coerce").fillna(0.0).round(2)
 
-    # Indeks FINAL per jenis
     agg["Indeks_Final_Agregat_0_100"] = (
         pd.to_numeric(agg["Indeks_Dasar_Agregat_0_100"], errors="coerce").fillna(0.0)
         * pd.to_numeric(agg["faktor_penyesuaian_jenis"], errors="coerce").fillna(1.0)
     )
 
-    # rounding
     for c in [
         "Rata2_sub_koleksi","Rata2_sub_sdm","Rata2_sub_pelayanan","Rata2_sub_pengelolaan",
         "Rata2_dim_kepatuhan","Rata2_dim_kinerja"
     ]:
         if c in agg.columns:
             agg[c] = pd.to_numeric(agg[c], errors="coerce").fillna(0.0).round(3)
-
     for c in ["Indeks_Dasar_Agregat_0_100","Indeks_Final_Agregat_0_100"]:
         if c in agg.columns:
             agg[c] = pd.to_numeric(agg[c], errors="coerce").fillna(0.0).round(2)
-
     agg["faktor_penyesuaian_jenis"] = pd.to_numeric(agg["faktor_penyesuaian_jenis"], errors="coerce").fillna(1.0).round(3)
     return agg
 
@@ -863,11 +722,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_jenis: pd.
 # ============================================================
 
 def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_jenis: pd.DataFrame, kew_value: str):
-    """
-    Membentuk tabel wilayah keseluruhan dari agg_jenis, dengan FIX avg3:
-      Indeks_Dasar_Agregat_0_100 (keseluruhan) = mean(dasar_3jenis)  [missing=0, tetap /3]
-      Indeks_Final_Wilayah_0_100 (keseluruhan) = mean(final_3jenis)  [missing=0, tetap /3]
-    """
     if agg_jenis is None or agg_jenis.empty:
         return pd.DataFrame()
 
@@ -879,10 +733,7 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_j
     a["Jenis"] = a["Jenis"].astype(str).str.lower().str.strip()
 
     base_keys = a[["group_key", label_name]].drop_duplicates()
-    full = base_keys.assign(_tmp=1).merge(
-        pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}),
-        on="_tmp"
-    ).drop(columns="_tmp")
+    full = base_keys.assign(_tmp=1).merge(pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}), on="_tmp").drop(columns="_tmp")
 
     cols_need = [
         "Jumlah",
@@ -893,12 +744,7 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_j
     ]
     cols_present = [c for c in cols_need if c in a.columns]
 
-    full = full.merge(
-        a[["group_key", label_name, "Jenis"] + cols_present],
-        on=["group_key", label_name, "Jenis"],
-        how="left"
-    )
-
+    full = full.merge(a[["group_key", label_name, "Jenis"] + cols_present], on=["group_key", label_name, "Jenis"], how="left")
     for c in cols_present:
         full[c] = pd.to_numeric(full[c], errors="coerce").fillna(0.0)
 
@@ -914,62 +760,12 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_j
         Indeks_Final_Wilayah_0_100=("Indeks_Final_Agregat_0_100", "mean"),
     )
 
-    # Tempel info Pop/Target/N per jenis + total (opsional)
-    if faktor_wilayah_jenis is not None and not faktor_wilayah_jenis.empty:
-        fw = faktor_wilayah_jenis.copy()
-        fw["Jenis"] = fw["Jenis"].astype(str).str.lower().str.strip()
-
-        piv = fw.pivot_table(
-            index=["group_key", label_name],
-            columns="Jenis",
-            values=["pop_total_jenis", "target_total_33_88_jenis", "n_jenis", "gap_target33_88_jenis", "faktor_penyesuaian_jenis"],
-            aggfunc="first"
-        )
-        piv.columns = [f"{v}_{k}" for v, k in piv.columns]
-        piv = piv.reset_index()
-        out = out.merge(piv, on=["group_key", label_name], how="left")
-
-        for j in ["sekolah", "umum", "khusus"]:
-            for basecol in ["pop_total_jenis", "target_total_33_88_jenis", "n_jenis", "gap_target33_88_jenis"]:
-                c = f"{basecol}_{j}"
-                if c in out.columns:
-                    out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0).round(0).astype(int)
-            cfac = f"faktor_penyesuaian_jenis_{j}"
-            if cfac in out.columns:
-                out[cfac] = pd.to_numeric(out[cfac], errors="coerce").fillna(1.0).round(3)
-
-        out["pop_total_all"] = (
-            out.get("pop_total_jenis_sekolah", 0)
-            + out.get("pop_total_jenis_umum", 0)
-            + out.get("pop_total_jenis_khusus", 0)
-        ).astype(int)
-
-        out["target_total_33_88_all"] = (
-            out.get("target_total_33_88_jenis_sekolah", 0)
-            + out.get("target_total_33_88_jenis_umum", 0)
-            + out.get("target_total_33_88_jenis_khusus", 0)
-        ).astype(int)
-
-        out["terkumpul_all"] = (
-            out.get("n_jenis_sekolah", 0)
-            + out.get("n_jenis_umum", 0)
-            + out.get("n_jenis_khusus", 0)
-        ).astype(int)
-
-        out["coverage_target33_88_all_%"] = np.where(
-            pd.to_numeric(out["target_total_33_88_all"], errors="coerce").fillna(0).values > 0,
-            (pd.to_numeric(out["terkumpul_all"], errors="coerce").fillna(0).values / pd.to_numeric(out["target_total_33_88_all"], errors="coerce").fillna(0).values) * 100.0,
-            0.0
-        )
-        out["coverage_target33_88_all_%"] = pd.to_numeric(out["coverage_target33_88_all_%"], errors="coerce").fillna(0.0).round(2)
-
     for c in [
         "Rata2_sub_koleksi","Rata2_sub_sdm","Rata2_sub_pelayanan","Rata2_sub_pengelolaan",
         "Rata2_dim_kepatuhan","Rata2_dim_kinerja"
     ]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(3)
-
     for c in ["Indeks_Dasar_Agregat_0_100","Indeks_Final_Wilayah_0_100"]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(2)
@@ -993,7 +789,7 @@ def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame):
             "Pop_Total_Jenis": 0,
             "Target33_88_Total_Jenis": 0,
             "Terkumpul_Jenis": 0,
-            "Coverage_Target33_88_Jenis_%": 0.0,
+            "Coverage_Target33_88_Jenis_%": 0.0,  # tetap ada di tabel ringkasan (kalau Anda mau hapus juga, bilang)
             "Indeks_Dasar_0_100": 0.0,
             "Indeks_Final_Disesuaikan_0_100": 0.0,
             "Penyesuaian_Poin": 0.0,
@@ -1084,62 +880,42 @@ def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame):
     for c in ["Jumlah_Wilayah","Total_Perpus","Pop_Total_Jenis","Target33_88_Total_Jenis","Terkumpul_Jenis"]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0).round(0).astype(int)
-
     for c in ["Coverage_Target33_88_Jenis_%","Indeks_Dasar_0_100","Indeks_Final_Disesuaikan_0_100","Penyesuaian_Poin"]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(2)
-
     return out
 
 
 # ============================================================
-# 10) DETAIL ENTITAS: Final menempel dari agg_total (wilayah)
+# 10) DETAIL ENTITAS (untuk tabel + bell curve)
 # ============================================================
 
-def attach_final_to_detail(df_filtered: pd.DataFrame, agg_total: pd.DataFrame, meta: dict, kew_value: str):
+def build_detail_entitas(df_filtered: pd.DataFrame, meta: dict):
     if df_filtered is None or df_filtered.empty:
         return pd.DataFrame()
 
-    kew_norm = str(kew_value or "").upper()
     df = df_filtered.copy()
-
-    if "PROV" in kew_norm:
-        key_col = "prov_key"
-        label_cols = ("PROV_DISP", "KAB_DISP")
-    else:
-        key_col = "kab_key"
-        label_cols = ("PROV_DISP", "KAB_DISP")
-
-    if agg_total is None or agg_total.empty:
-        df["Indeks_Final_0_100"] = df["Indeks_Dasar_0_100"]
-    else:
-        m = agg_total[["group_key", "Indeks_Final_Wilayah_0_100"]].copy()
-        df = df.merge(m, left_on=key_col, right_on="group_key", how="left")
-        df["Indeks_Final_0_100"] = df["Indeks_Final_Wilayah_0_100"].fillna(df["Indeks_Dasar_0_100"])
-        df = df.drop(columns=[c for c in ["group_key","Indeks_Final_Wilayah_0_100"] if c in df.columns])
-
-    base_cols = [label_cols[0], label_cols[1], "KEW_NORM", "_dataset"]
     if meta.get("nama_col") and meta["nama_col"] in df.columns:
         df["nm_perpustakaan"] = df[meta["nama_col"]].astype(str)
-        base_cols.insert(2, "nm_perpustakaan")
+    else:
+        df["nm_perpustakaan"] = ""
 
-    keep = base_cols + [
+    keep = [
+        "nm_perpustakaan", "PROV_DISP", "KAB_DISP", "KEW_NORM", "_dataset",
         "sub_koleksi","sub_sdm","sub_pelayanan","sub_pengelolaan",
         "dim_kepatuhan","dim_kinerja",
         "Indeks_Dasar_0_100",
-        "Indeks_Final_0_100",
     ]
     keep = [c for c in keep if c in df.columns]
 
     out = df[keep].copy()
-    out = out.rename(columns={label_cols[0]:"Provinsi", label_cols[1]:"Kab/Kota", "_dataset":"Jenis"})
+    out = out.rename(columns={"PROV_DISP":"Provinsi", "KAB_DISP":"Kab/Kota", "_dataset":"Jenis"})
 
     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)
-    for c in ["Indeks_Dasar_0_100","Indeks_Final_0_100"]:
-        if c in out.columns:
-            out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(2)
+    if "Indeks_Dasar_0_100" in out.columns:
+        out["Indeks_Dasar_0_100"] = pd.to_numeric(out["Indeks_Dasar_0_100"], errors="coerce").fillna(0.0).round(2)
 
     return out
 
@@ -1167,10 +943,8 @@ def build_verif_jenis(faktor_wilayah_jenis: pd.DataFrame, kew_value: str):
     for c in ["pop_total_jenis", "target_total_33_88_jenis", "n_jenis", "gap_target33_88_jenis"]:
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0).round(0).astype(int)
-
     if "coverage_jenis_%" in out.columns:
         out["coverage_jenis_%"] = pd.to_numeric(out["coverage_jenis_%"], errors="coerce").fillna(0.0).round(2)
-
     if "faktor_penyesuaian_jenis" in out.columns:
         out["faktor_penyesuaian_jenis"] = pd.to_numeric(out["faktor_penyesuaian_jenis"], errors="coerce").fillna(1.0).round(3)
 
@@ -1178,43 +952,42 @@ def build_verif_jenis(faktor_wilayah_jenis: pd.DataFrame, kew_value: str):
 
 
 # ============================================================
-# 12) BELL CURVE (menampilkan distribusi skor ABSOLUT)
+# 12) BELL CURVE — Indeks Dasar per Entitas + label nama perpus
 # ============================================================
 
-def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, min_points: int = 2):
+def _make_bell_curve_entitas(detail_df: pd.DataFrame, jenis: str, title: str):
     fig = go.Figure()
     fig.update_layout(
         title=title,
-        xaxis_title="Skor (0–100)",
+        xaxis_title="Indeks Dasar (0–100)",
         yaxis_title="Kepadatan",
-        hovermode="x unified",
+        hovermode="closest",
         margin=dict(l=40, r=20, t=60, b=40),
         legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="left", x=0),
     )
 
-    if dfp is None or dfp.empty or xcol not in dfp.columns:
+    fig.update_xaxes(range=[0, 100])
+    fig.update_yaxes(rangemode="tozero")
+
+    if detail_df is None or detail_df.empty:
         fig.add_annotation(text="Tidak ada data untuk ditampilkan.", x=0.5, y=0.5, xref="paper", yref="paper", showarrow=False)
-        fig.update_xaxes(range=[0, 100])
-        fig.update_yaxes(rangemode="tozero")
         return fig
 
-    d = dfp.dropna(subset=[xcol]).copy()
-    if len(d) < 1:
+    d = detail_df.copy()
+    d["Jenis"] = d["Jenis"].astype(str).str.lower().str.strip()
+    d = d[d["Jenis"] == jenis].copy()
+    if d.empty or "Indeks_Dasar_0_100" not in d.columns:
         fig.add_annotation(text="Tidak ada data untuk ditampilkan.", x=0.5, y=0.5, xref="paper", yref="paper", showarrow=False)
-        fig.update_xaxes(range=[0, 100])
-        fig.update_yaxes(rangemode="tozero")
         return fig
 
-    if len(d) < min_points:
-        x_single = float(pd.to_numeric(d[xcol], errors="coerce").iloc[0])
-        fig.add_trace(go.Scatter(x=[x_single], y=[0], mode="markers", showlegend=False))
-        fig.add_vline(x=x_single, line_width=1, line_dash="dash", annotation_text=f"Nilai: {x_single:.1f}", annotation_position="top")
-        fig.update_xaxes(range=[0, 100])
-        fig.update_yaxes(rangemode="tozero")
+    x = pd.to_numeric(d["Indeks_Dasar_0_100"], errors="coerce").astype(float).values
+    mask = np.isfinite(x)
+    d = d.loc[mask].copy()
+    x = x[mask]
+    if len(x) == 0:
+        fig.add_annotation(text="Tidak ada data untuk ditampilkan.", x=0.5, y=0.5, xref="paper", yref="paper", showarrow=False)
         return fig
 
-    x = pd.to_numeric(d[xcol], errors="coerce").astype(float).values
-    x = x[np.isfinite(x)]
     mu = float(np.mean(x))
     sigma = float(np.std(x, ddof=1)) if len(x) > 1 else 1.0
     sigma = max(sigma, 1e-3)
@@ -1224,28 +997,44 @@ def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, min_points: int =
     xs = np.linspace(xmin, xmax, 250)
     pdf = (1.0 / (sigma * np.sqrt(2 * np.pi))) * np.exp(-0.5 * ((xs - mu) / sigma) ** 2)
 
+    # kurva normal fit
     fig.add_trace(go.Scatter(x=xs, y=pdf, mode="lines", name="Kurva Normal (fit)"))
-    fig.add_trace(go.Scatter(x=x, y=np.zeros_like(x), mode="markers", showlegend=False))
 
+    # titik entitas (y=0) dengan hover label nama perpus
+    hover_text = []
+    for _, r in d.iterrows():
+        nm = _first_nonempty(r.get("nm_perpustakaan"), default="-")
+        pv = _first_nonempty(r.get("Provinsi"), default="-")
+        kb = _first_nonempty(r.get("Kab/Kota"), default="-")
+        sc = r.get("Indeks_Dasar_0_100")
+        hover_text.append(f"<b>{nm}</b><br>{pv}<br>{kb}<br>Indeks Dasar: {float(sc):.2f}")
+
+    fig.add_trace(go.Scatter(
+        x=x,
+        y=np.zeros_like(x),
+        mode="markers",
+        name="Entitas",
+        hovertext=hover_text,
+        hoverinfo="text",
+        showlegend=False
+    ))
+
+    # garis Q1/Q2/Q3/Mean
     q1, q2, q3 = np.percentile(x, [25, 50, 75])
     for xv, lab in [(q1, "Q1"), (q2, "Q2 (Median)"), (q3, "Q3"), (mu, "Mean")]:
         fig.add_vline(x=float(xv), line_width=1, line_dash="dash", annotation_text=f"{lab}: {xv:.1f}", annotation_position="top")
 
-    fig.update_xaxes(range=[0, 100])
-    fig.update_yaxes(rangemode="tozero")
     return fig
 
 
 # ============================================================
-# 13) KPI DASHBOARD (skor absolut saja)
+# 13) KPI DASHBOARD — HANYA 2 KARTU
 # ============================================================
 
 def _safe_first(df, col, default=0.0, where=None):
     if df is None or df.empty or col not in df.columns:
         return default
-    sub = df
-    if where is not None:
-        sub = df.loc[where]
+    sub = df if where is None else df.loc[where]
     if sub is None or sub.empty:
         return default
     return float(pd.to_numeric(sub[col], errors="coerce").fillna(default).iloc[0])
@@ -1253,8 +1042,7 @@ def _safe_first(df, col, default=0.0, where=None):
 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}
+    return {"final_all": final_all, "dasar_all": dasar_all}
 
 def build_kpi_markdown(summary_jenis: pd.DataFrame) -> str:
     if summary_jenis is None or summary_jenis.empty:
@@ -1265,10 +1053,11 @@ def build_kpi_markdown(summary_jenis: pd.DataFrame) -> str:
     def fmt(x, nd=2):
         return "NA" if pd.isna(x) else f"{x:.{nd}f}"
 
+    # ✅ HANYA 2 KARTU
     return f"""
 <div style="display:flex; gap:12px; flex-wrap:wrap;">
   <div style="border:1px solid #333; border-radius:10px; padding:10px 12px; min-width:260px;">
-    <div style="opacity:0.8;">Indeks IPLM FINAL (Disesuaikan 33.88%)</div>
+    <div style="opacity:0.8;">Indeks IPLM FINAL (Disesuaikan {TARGET_RATIO*100:.2f}%)</div>
     <div style="font-size:26px; font-weight:700;">{fmt(k["final_all"],2)}</div>
     <div style="opacity:0.7;">Skor absolut (untuk akuntabilitas)</div>
   </div>
@@ -1278,12 +1067,6 @@ def build_kpi_markdown(summary_jenis: pd.DataFrame) -> str:
     <div style="font-size:26px; font-weight:700;">{fmt(k["dasar_all"],2)}</div>
     <div style="opacity:0.7;">Sebelum faktor kecukupan sampel</div>
   </div>
-
-  <div style="border:1px solid #333; border-radius:10px; padding:10px 12px; min-width:260px;">
-    <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()
 
@@ -1308,7 +1091,7 @@ def get_llm_client():
         _HF_CLIENT = None
         return None
 
-def generate_llm_analysis(summary_jenis, agg_total, verif_total, wilayah, kew):
+def generate_llm_analysis(summary_jenis, wilayah, kew):
     client = get_llm_client()
     if client is None or (not USE_LLM):
         return "Analisis otomatis (LLM) tidak digunakan / tidak tersedia."
@@ -1318,7 +1101,7 @@ 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: (1) skor dasar vs final, (2) kecukupan sampel 33.88% per jenis, (3) rekomendasi singkat."}
+                {"role":"user","content":f"{ctx}\nBuat analisis 3 paragraf: (1) skor dasar vs final, (2) penyesuaian 33.88% per jenis, (3) rekomendasi singkat."}
             ],
             max_tokens=520,
             temperature=0.25,
@@ -1335,6 +1118,7 @@ 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_heading("Ringkasan (Jenis + Keseluruhan)", level=2)
     if summary_jenis is not None and not summary_jenis.empty:
         show = summary_jenis.copy()
@@ -1353,10 +1137,12 @@ def generate_word_report(wilayah, summary_jenis, analysis_text):
                     cells[i].text = str(int(v))
                 else:
                     cells[i].text = str(v)
+
     doc.add_heading("Analisis (opsional)", level=2)
     for p in (analysis_text or "").split("\n"):
         if p.strip():
             doc.add_paragraph(p.strip())
+
     outpath = tempfile.mktemp(suffix=".docx")
     doc.save(outpath)
     return outpath
@@ -1382,9 +1168,6 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         if df_all is None or df_all.empty or df_raw is None or df_raw.empty:
             return _empty_outputs("⚠�� Data belum ter-load. Pastikan file tersedia di repo/server.")
 
-        # =========================================================
-        # 1) FILTER df_all (entitas) sesuai dropdown
-        # =========================================================
         df = df_all.copy()
         if prov_value and prov_value != "(Semua)":
             df = df[df["PROV_DISP"] == prov_value]
@@ -1396,24 +1179,19 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         if df.empty:
             return _empty_outputs("Tidak ada data untuk filter ini.")
 
-        # =========================================================
-        # 2) PIPELINE FILTER → faktor → agg_jenis → agg_total
-        # =========================================================
         kew_norm = kew_value if (kew_value and kew_value != "(Semua)") else "(Semua)"
+
         faktor_wilayah_jenis = build_faktor_wilayah_jenis(df, pop_kab, pop_prov, pop_khusus, kew_norm)
         agg_jenis_full = build_agg_wilayah_jenis(df, faktor_wilayah_jenis, kew_norm)
         agg_total = build_agg_wilayah_total_from_jenis(agg_jenis_full, faktor_wilayah_jenis, kew_norm)
 
-        # =========================================================
-        # 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)
 
-        # =========================================================
-        # 4) agg_jenis view (UI hanya sampai indeks dasar)
-        # =========================================================
+        # ✅ detail entitas khusus untuk bell curve + tabel detail (indeks dasar)
+        detail_view = build_detail_entitas(df, meta)
+
+        # UI: agg_jenis hanya sampai indeks dasar
         if agg_jenis_full is None or agg_jenis_full.empty:
             agg_jenis_view = agg_jenis_full
         else:
@@ -1431,9 +1209,7 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
             cols_upto = [c for c in cols_upto if c in agg_jenis_full.columns]
             agg_jenis_view = agg_jenis_full[cols_upto].copy()
 
-        # =========================================================
-        # 5) FILTER RAW DOWNLOAD (harus raw hasil filter)
-        # =========================================================
+        # RAW download (hasil filter)
         raw = df_raw.copy()
         if prov_value and prov_value != "(Semua)":
             raw = raw[raw["PROV_DISP"] == prov_value]
@@ -1442,31 +1218,15 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         if kew_value and kew_value != "(Semua)":
             raw = raw[raw["KEW_NORM"] == kew_value]
 
-        # =========================================================
-        # 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(), "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 = "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)
-            fig_sekolah = _fig("sekolah")
-            fig_umum = _fig("umum")
-            fig_khusus = _fig("khusus")
-
-        # =========================================================
-        # 7) KPI (skor absolut)
-        # =========================================================
+        # ✅ Bell curve: Indeks Dasar per entitas + hover nama perpus
+        fig_sekolah = _make_bell_curve_entitas(detail_view, "sekolah", "Bell Curve — Jenis: Sekolah (Indeks Dasar per Entitas)")
+        fig_umum    = _make_bell_curve_entitas(detail_view, "umum",    "Bell Curve — Jenis: Umum (Indeks Dasar per Entitas)")
+        fig_khusus  = _make_bell_curve_entitas(detail_view, "khusus",  "Bell Curve — Jenis: Khusus (Indeks Dasar per Entitas)")
+
+        # ✅ KPI hanya 2 kartu
         kpi_md = build_kpi_markdown(summary_jenis)
 
-        # =========================================================
-        # 8) Export (xlsx + opsional docx)
-        # =========================================================
+        # Export
         tmpdir = tempfile.mkdtemp()
         prov_slug = (_canon(prov_value or "SEMUA").upper() or "SEMUA")
         kab_slug = (_canon(kab_value or "SEMUA").upper() or "SEMUA")
@@ -1475,7 +1235,7 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         p_summary = str(Path(tmpdir) / f"IPLM_RingkasanJenisKeseluruhan_33_88_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
         p_total   = str(Path(tmpdir) / f"IPLM_AgregatWilayah_Keseluruhan_33_88_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
         p_raw     = str(Path(tmpdir) / f"IPLM_RAW_DATA_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
-        p_detail  = str(Path(tmpdir) / f"IPLM_DetailEntitas_FinalMenempelWilayah_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
+        p_detail  = str(Path(tmpdir) / f"IPLM_DetailEntitas_IndeksDasar_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
         p_verif   = str(Path(tmpdir) / f"IPLM_KecukupanSampel_33_88_{prov_slug}_{kab_slug}_{kew_slug}.xlsx")
 
         summary_jenis.to_excel(p_summary, index=False)
@@ -1485,7 +1245,7 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
         verif_total.to_excel(p_verif, index=False)
 
         wilayah_txt = kab_value if (kab_value and kab_value != "(Semua)") else (prov_value if (prov_value and prov_value != "(Semua)") else "Nasional/All")
-        analysis_text = generate_llm_analysis(summary_jenis, agg_total, verif_total, wilayah_txt, kew_value or "(Semua)")
+        analysis_text = generate_llm_analysis(summary_jenis, wilayah_txt, kew_value or "(Semua)")
         word_path = generate_word_report(wilayah_txt, summary_jenis, analysis_text)
 
         msg = (
@@ -1558,10 +1318,8 @@ with gr.Blocks() as demo:
 
 **TARGET RATIO (per jenis): {TARGET_RATIO*100:.2f}%**
 
-✅ 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)
+✅ Dashboard KPI: **HANYA Indeks Dasar & Indeks Final** (Coverage card dihapus).
+✅ Bell curve: **Indeks Dasar per entitas** + hover **nama perpustakaan** per jenis.
 """)
 
     state_df = gr.State(None)
@@ -1594,13 +1352,13 @@ with gr.Blocks() as demo:
     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)")
+    gr.Markdown("## Detail Entitas (Indeks Dasar per Perpustakaan)")
     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 (Skor Absolut Entitas)")
+    gr.Markdown("## Bell Curve — per Jenis (Indeks Dasar per Entitas + nama perpustakaan)")
     gr.Markdown("### Perpustakaan Umum")
     bell_umum = gr.Plot(scale=1)
 
@@ -1638,4 +1396,4 @@ 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()