Update app.py

app.py

@@ -465,7 +465,7 @@ def load_default_files(force=False):
     after = len(df_raw)
 
     # =========================
-    # POP KAB (untuk TOTAL base: sekolah+umum & target_total_68)
+    # POP KAB (TOTAL base: umum+sekolah)
     # =========================
     pk = pd.read_excel(POP_KAB)
 
@@ -498,13 +498,11 @@ def load_default_files(force=False):
     if c_target_total:
         pop_kab["target_base_68"] = pd.to_numeric(pk[c_target_total], errors="coerce")
     else:
-        # fallback: target = pop * ratio
         pop_kab["target_base_68"] = pop_kab["pop_base"] * float(FALLBACK_TARGET_RATIO)
 
     pop_kab["pop_base"] = pd.to_numeric(pop_kab["pop_base"], errors="coerce")
     pop_kab["target_base_68"] = pd.to_numeric(pop_kab["target_base_68"], errors="coerce")
 
-    # fallback saling isi
     m_need_pop = pop_kab["pop_base"].isna() & pop_kab["target_base_68"].notna() & (pop_kab["target_base_68"] > 0)
     pop_kab.loc[m_need_pop, "pop_base"] = pop_kab.loc[m_need_pop, "target_base_68"] / float(FALLBACK_TARGET_RATIO)
 
@@ -519,7 +517,7 @@ def load_default_files(force=False):
     })
 
     # =========================
-    # POP PROV (untuk TOTAL base prov)
+    # POP PROV (TOTAL base prov)
     # =========================
     pp = pd.read_excel(POP_PROV)
     c_pr = pick_col(pp, ["Provinsi","PROVINSI","provinsi","Propinsi","PROPINSI","propinsi"])
@@ -534,7 +532,6 @@ def load_default_files(force=False):
     pop_prov["Provinsi_Label"] = pp[c_pr].astype(str).str.strip()
     pop_prov["prov_key"] = pop_prov["Provinsi_Label"].apply(norm_prov_label)
 
-    # base pop prov: sekolah = sma+smk+slb, umum = perpus_umum_prop (sesuai pola kamu sebelumnya)
     sma = pd.to_numeric(pp.get("sma ", pp.get("sma", 0)), errors="coerce").fillna(0.0)
     smk = pd.to_numeric(pp.get("smk", 0), errors="coerce").fillna(0.0)
     slb = pd.to_numeric(pp.get("slb", 0), errors="coerce").fillna(0.0)
@@ -618,7 +615,6 @@ def build_faktor_wilayah_total(
     if df.empty:
         return pd.DataFrame()
 
-    # tentukan level
     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()
@@ -632,10 +628,8 @@ def build_faktor_wilayah_total(
             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)
         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([]))
 
-    # semua wilayah dari data
     base_keys = df[[key_col, label_col]].drop_duplicates().rename(columns={key_col: "group_key", label_col: label_name})
 
-    # n_total (TOTAL semua jenis)
     cnt_total = (
         df.groupby([key_col, label_col], dropna=False)
           .size()
@@ -646,7 +640,6 @@ def build_faktor_wilayah_total(
     out = base_keys.merge(cnt_total, on=["group_key", label_name], how="left")
     out["n_total"] = pd.to_numeric(out["n_total"], errors="coerce").fillna(0).astype(int)
 
-    # base pop/target (KAB/PROV)
     pop_base_series = pd.Series(dtype=float)
     tgt_base_series = pd.Series(dtype=float)
 
@@ -657,7 +650,6 @@ def build_faktor_wilayah_total(
     out["pop_base"] = out["group_key"].map(pop_base_series).fillna(0.0)
     out["target_base_68"] = out["group_key"].map(tgt_base_series).fillna(0.0)
 
-    # khusus (ditambah)
     pop_khus = pd.Series(dtype=float)
     tgt_khus = pd.Series(dtype=float)
 
@@ -686,15 +678,12 @@ def build_faktor_wilayah_total(
     out["pop_khusus"] = out["group_key"].map(pop_khus).fillna(0.0)
     out["target_khusus_68"] = out["group_key"].map(tgt_khus).fillna(0.0)
 
-    # TOTAL gabungan
     out["pop_total"] = pd.to_numeric(out["pop_base"], errors="coerce").fillna(0.0) + pd.to_numeric(out["pop_khusus"], errors="coerce").fillna(0.0)
     out["target_total_68"] = pd.to_numeric(out["target_base_68"], errors="coerce").fillna(0.0) + pd.to_numeric(out["target_khusus_68"], errors="coerce").fillna(0.0)
 
-    # fallback pop dari target jika pop kosong
     m_need_pop = (out["pop_total"] <= 0) & (out["target_total_68"] > 0)
     out.loc[m_need_pop, "pop_total"] = out.loc[m_need_pop, "target_total_68"] / float(FALLBACK_TARGET_RATIO)
 
-    # faktor / coverage / gap
     out["faktor_penyesuaian_wilayah"] = [
         faktor_penyesuaian_total(n, t)
         for n, t in zip(
@@ -719,14 +708,12 @@ def build_faktor_wilayah_total(
         )
     ]
 
-    # display format (REQUEST)
     out["target_total_68"] = pd.to_numeric(out["target_total_68"], errors="coerce").fillna(0).round(0).astype(int)
     out["pop_total"] = pd.to_numeric(out["pop_total"], errors="coerce").fillna(0).round(0).astype(int)
     out["coverage_total_%"] = pd.to_numeric(out["coverage_total_%"], errors="coerce").fillna(0.0).round(2)
     out["faktor_penyesuaian_wilayah"] = pd.to_numeric(out["faktor_penyesuaian_wilayah"], errors="coerce").fillna(1.0).round(3)
     out["gap_target68_total"] = pd.to_numeric(out["gap_target68_total"], errors="coerce").fillna(0).round(0).astype(int)
 
-    # rapikan kolom
     keep = [
         "group_key", label_name,
         "n_total",
@@ -734,7 +721,6 @@ def build_faktor_wilayah_total(
         "coverage_total_%",
         "faktor_penyesuaian_wilayah",
         "gap_target68_total",
-        # opsional debug:
         "pop_base","pop_khusus","target_base_68","target_khusus_68",
     ]
     keep = [c for c in keep if c in out.columns]
@@ -742,7 +728,7 @@ def build_faktor_wilayah_total(
 
 
 # ============================================================
-# 7) AGREGAT WILAYAH × JENIS (faktor wilayah total, sama untuk semua jenis)
+# 7) AGREGAT WILAYAH × JENIS
 # ============================================================
 
 def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_total: pd.DataFrame, kew_value: str):
@@ -763,7 +749,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_total: pd.
 
     jenis_list = ["sekolah", "umum", "khusus"]
 
-    # grid 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}),
@@ -790,7 +775,6 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_total: pd.
 
     agg["Jumlah"] = agg["Jumlah"].round(0).astype(int)
 
-    # merge faktor wilayah total (sama untuk semua jenis)
     if faktor_wilayah_total is None or faktor_wilayah_total.empty:
         agg["faktor_penyesuaian_wilayah"] = 1.0
     else:
@@ -819,7 +803,8 @@ def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah_total: pd.
 
 
 # ============================================================
-# 8) AGREGAT WILAYAH (KESELURUHAN) — avg3 dari 3 jenis + tempel faktor_wilayah_total
+# 8) AGREGAT WILAYAH (KESELURUHAN) — avg3 dari 3 jenis
+#     ✅ FIX DI SINI: JANGAN MERGE fw kolom n_total (hindari bentrok)
 # ============================================================
 
 def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_total: pd.DataFrame, kew_value: str):
@@ -866,19 +851,19 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_t
         Indeks_Final_Wilayah_0_100=("Indeks_Final_Agregat_0_100", "mean"),
     )
 
-    # tempel Pop/Target/Coverage/Faktor TOTAL
+    # ✅ tempel Pop/Target/Coverage/Faktor TOTAL
+    # ❌ JANGAN tempel n_total dari fw (biar tidak bentrok)
     if faktor_wilayah_total is not None and not faktor_wilayah_total.empty:
         fw = faktor_wilayah_total.copy()
         cols = [c for c in [
             "group_key", label_name,
             "pop_total","target_total_68","coverage_total_%",
-            "faktor_penyesuaian_wilayah","gap_target68_total","n_total"
+            "faktor_penyesuaian_wilayah","gap_target68_total"
         ] if c in fw.columns]
         fw = fw[cols].copy()
         out = out.merge(fw, on=["group_key", label_name], how="left")
 
-        # format display
-        for c in ["pop_total","target_total_68","gap_target68_total","n_total"]:
+        for c in ["pop_total","target_total_68","gap_target68_total"]:
             if c in out.columns:
                 out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0).round(0).astype(int)
         if "coverage_total_%" in out.columns:
@@ -897,14 +882,13 @@ def build_agg_wilayah_total_from_jenis(agg_jenis: pd.DataFrame, faktor_wilayah_t
         if c in out.columns:
             out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(2)
 
+    # ✅ sekarang aman, n_total tetap ada (tidak bentrok)
     out["n_total"] = pd.to_numeric(out["n_total"], errors="coerce").fillna(0).round(0).astype(int)
     return out
 
 
 # ============================================================
 # 9) SUMMARY (PER JENIS) + KESELURUHAN
-#    Pop/Target/Coverage per jenis TIDAK dipakai (karena total-only),
-#    tapi tetap ditampilkan agar 4 baris konsisten.
 # ============================================================
 
 def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame, faktor_wilayah_total: pd.DataFrame = None):
@@ -967,7 +951,6 @@ def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame, fa
                  + rows_by_jenis["umum"]["Indeks_Final_Disesuaikan_0_100"]
                  + rows_by_jenis["khusus"]["Indeks_Final_Disesuaikan_0_100"]) / 3.0
 
-    # TOTAL pop/target/coverage ditarik dari faktor_wilayah_total (nasional/filtered)
     pop_all = 0
     target_all = 0
     terkumpul_all = int(rows_by_jenis["sekolah"]["Terkumpul_Jenis"]
@@ -1013,7 +996,7 @@ def build_summary_per_jenis(agg_jenis: pd.DataFrame, agg_total: pd.DataFrame, fa
 
 
 # ============================================================
-# 10) DETAIL ENTITAS: Final menempel dari agg_total (wilayah)
+# 10) DETAIL ENTITAS: Final menempel dari agg_total
 # ============================================================
 
 def attach_final_to_detail(df_filtered: pd.DataFrame, agg_total: pd.DataFrame, meta: dict, kew_value: str):
@@ -1068,7 +1051,7 @@ def attach_final_to_detail(df_filtered: pd.DataFrame, agg_total: pd.DataFrame, m
 
 
 # ============================================================
-# 11) VERIFIKASI TOTAL (tanpa koma untuk integer, coverage 2 desimal)
+# 11) VERIFIKASI TOTAL
 # ============================================================
 
 def build_verif_total(faktor_wilayah_total: pd.DataFrame, kew_value: str):
@@ -1211,7 +1194,7 @@ def _make_bell_curve(dfp: pd.DataFrame, xcol: str, title: str, label_col: str |
 
 
 # ============================================================
-# 13) KPI DASHBOARD (FINAL: hanya Final & Dasar)
+# 13) KPI DASHBOARD
 # ============================================================
 
 def compute_dashboard_kpis(summary_jenis: pd.DataFrame):
@@ -1385,7 +1368,6 @@ 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.")
 
-        # FILTER (df_all)
         df = df_all.copy()
         if prov_value and prov_value != "(Semua)":
             df = df[df["PROV_DISP"] == prov_value]
@@ -1397,23 +1379,17 @@ 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.")
 
-        # === TOTAL-only faktor wilayah
         faktor_wilayah_total = build_faktor_wilayah_total(df, pop_kab, pop_prov, pop_khusus, kew_value or "(Semua)")
 
-        # agregat jenis + total
         agg_jenis_full = build_agg_wilayah_jenis(df, faktor_wilayah_total, kew_value or "(Semua)")
         agg_total = build_agg_wilayah_total_from_jenis(agg_jenis_full, faktor_wilayah_total, kew_value or "(Semua)")
 
-        # summary (4 baris)
         summary_jenis = build_summary_per_jenis(agg_jenis_full, agg_total, faktor_wilayah_total=faktor_wilayah_total)
 
-        # verifikasi total
         verif_total = build_verif_total(faktor_wilayah_total, kew_value or "(Semua)")
 
-        # detail entitas
         detail_view = attach_final_to_detail(df, agg_total, meta, kew_value or "(Semua)")
 
-        # view agg_jenis (UI cuma sampai indeks dasar)
         if agg_jenis_full is None or agg_jenis_full.empty:
             agg_jenis_view = agg_jenis_full
         else:
@@ -1431,7 +1407,6 @@ 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()
 
-        # FILTER RAW DOWNLOAD (df_raw)
         raw = df_raw.copy()
         if prov_value and prov_value != "(Semua)":
             raw = raw[raw["PROV_DISP"] == prov_value]
@@ -1440,7 +1415,6 @@ 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]
 
-        # bell curve per jenis (entitas)
         if detail_view is None or detail_view.empty:
             fig_sekolah = _make_bell_curve(pd.DataFrame(), "Indeks_Dasar_0_100", "Bell Curve — Jenis: Sekolah", min_points=2)
             fig_umum = _make_bell_curve(pd.DataFrame(), "Indeks_Dasar_0_100", "Bell Curve — Jenis: Umum", min_points=2)
@@ -1458,7 +1432,6 @@ def run_calc(prov_value, kab_value, kew_value, df_all, df_raw, pop_kab, pop_prov
             fig_umum = _fig_jenis_ent("umum", "Bell Curve — Jenis: Umum (Indeks per Entitas)")
             fig_khusus = _fig_jenis_ent("khusus", "Bell Curve — Jenis: Khusus (Indeks per Entitas)")
 
-        # KPI
         kpi_md = build_kpi_markdown(summary_jenis)
 
         tmpdir = tempfile.mkdtemp()
@@ -1543,13 +1516,14 @@ def on_prov_change(prov_value):
 with gr.Blocks() as demo:
     gr.Markdown(f"""
 # IPLM 2025 — Final (TOTAL-only Pop/Target68: gabungan sekolah+umum+khusus)
-**Mode NO UPLOAD (cache aktif).** File dibaca dari repo/server:
+
+Mode NO UPLOAD (cache aktif). File dibaca dari repo/server:
 - `DATA_FILE`   = **{DATA_FILE}**
 - `POP_KAB`     = **{POP_KAB}**
 - `POP_PROV`    = **{POP_PROV}**
 - `POP_KHUSUS`  = **{POP_KHUSUS}**
 
-**UPDATE UTAMA:**
+UPDATE UTAMA:
 - Penyesuaian sampel berbasis TOTAL wilayah: n_total vs target_total_68 (gabungan base + khusus)
 - Pop/Target = (base KAB/PROV) + (KHUSUS)
 - Faktor wilayah dipakai sama untuk semua jenis