Update app.py

app.py

@@ -696,110 +696,148 @@ def build_faktor_wilayah(df_filtered: pd.DataFrame, pop_kab: pd.DataFrame, pop_p
 # 7) AGREGAT WILAYAH × JENIS (Final pakai faktor wilayah)
 # ============================================================
 
-def build_agg_wilayah_jenis(df_filtered: pd.DataFrame, faktor_wilayah: pd.DataFrame, pop_khusus: pd.DataFrame, kew_value: str):
-    if df_filtered is None or df_filtered.empty:
+def build_agg_wilayah_total_from_jenis(
+    agg_jenis: pd.DataFrame,
+    faktor_wilayah: pd.DataFrame,
+    pop_khusus: pd.DataFrame,          # <-- PATCH: tambah
+    kew_value: str
+):
+    if agg_jenis is None or agg_jenis.empty:
         return pd.DataFrame()
 
     kew_norm = str(kew_value or "").upper()
-    df = df_filtered.copy()
+    label_name = "Kab/Kota" if ("KAB" in kew_norm or "KOTA" in kew_norm) else ("Provinsi" if "PROV" in kew_norm else "Kab/Kota")
 
-    if "KAB" in kew_norm or "KOTA" in kew_norm:
-        key_col = "kab_key"
-        label_col = "KAB_DISP"
-        label_name = "Kab/Kota"
-    elif "PROV" in kew_norm:
-        key_col = "prov_key"
-        label_col = "PROV_DISP"
-        label_name = "Provinsi"
-    else:
-        key_col = "kab_key"
-        label_col = "KAB_DISP"
-        label_name = "Kab/Kota"
+    jenis_list = ["sekolah", "umum", "khusus"]
 
-    df = df[df["_dataset"].isin(["sekolah", "umum", "khusus"])].copy()
-    if df.empty:
-        return pd.DataFrame()
+    a = agg_jenis.copy()
+    a["Jenis"] = a["Jenis"].astype(str).str.lower().str.strip()
 
-    agg = df.groupby([key_col, label_col, "_dataset"], dropna=False).agg(
-        Jumlah=("Indeks_Dasar_0_100", "size"),
-        Rata2_sub_koleksi=("sub_koleksi", "mean"),
-        Rata2_sub_sdm=("sub_sdm", "mean"),
-        Rata2_sub_pelayanan=("sub_pelayanan", "mean"),
-        Rata2_sub_pengelolaan=("sub_pengelolaan", "mean"),
-        Rata2_dim_kepatuhan=("dim_kepatuhan", "mean"),
-        Rata2_dim_kinerja=("dim_kinerja", "mean"),
-        Indeks_Dasar_Agregat_0_100=("Indeks_Dasar_0_100", "mean"),
-    ).reset_index()
+    base_keys = a[["group_key", label_name]].drop_duplicates()
 
-    agg = agg.rename(columns={key_col: "group_key", label_col: label_name, "_dataset": "Jenis"})
+    full = base_keys.assign(_tmp=1).merge(
+        pd.DataFrame({"Jenis": jenis_list, "_tmp": 1}),
+        on="_tmp"
+    ).drop(columns="_tmp")
 
-    # faktor wilayah (sama untuk semua jenis)
-    if faktor_wilayah is None or faktor_wilayah.empty:
-        agg["faktor_penyesuaian_wilayah"] = 1.0
-        agg["target_total_68"] = np.nan
-        agg["pop_total"] = np.nan
-        agg["coverage_total_%"] = np.nan
-    else:
-        fw = faktor_wilayah.copy()
-        keep = ["group_key", label_name, "faktor_penyesuaian", "target_total_68", "pop_total", "coverage_total_%"]
-        keep = [c for c in keep if c in fw.columns]
-        fw = fw[keep].rename(columns={"faktor_penyesuaian": "faktor_penyesuaian_wilayah"})
-        agg = agg.merge(fw, on=["group_key", label_name], how="left")
-        agg["faktor_penyesuaian_wilayah"] = pd.to_numeric(agg["faktor_penyesuaian_wilayah"], errors="coerce").fillna(1.0)
-
-    agg["faktor_penyesuaian"] = agg["faktor_penyesuaian_wilayah"]
-    agg["Indeks_Final_Agregat_0_100"] = pd.to_numeric(agg["Indeks_Dasar_Agregat_0_100"], errors="coerce").fillna(0.0) * agg["faktor_penyesuaian"]
-
-    # target/pop/coverage per jenis (hanya khusus, dari POP_KHUSUS) — supaya tidak tampil null -> isi 0
-    agg["target_total_68_jenis"] = 0.0
-    agg["pop_total_jenis"] = 0.0
-    agg["coverage_jenis"] = 0.0
-
-    if (pop_khusus is not None) and (not pop_khusus.empty) and ("KAB" in kew_norm or "KOTA" in kew_norm or kew_norm in {"(SEMUA)", "(SEMUA)".upper()}):
-        pk = pop_khusus.set_index("kab_key")
-        for i, r in agg.iterrows():
-            if str(r.get("Jenis", "")).lower() != "khusus":
-                continue
-            gk = r.get("group_key", None)
-            if gk in pk.index:
-                t = pk.loc[gk, "Target68_Total_Jenis"] if "Target68_Total_Jenis" in pk.columns else np.nan
-                p = pk.loc[gk, "Pop_Total_Jenis"] if "Pop_Total_Jenis" in pk.columns else np.nan
-                if pd.notna(t):
-                    agg.at[i, "target_total_68_jenis"] = float(t)
-                if pd.notna(p):
-                    agg.at[i, "pop_total_jenis"] = float(p)
+    cols_need = [
+        "Jumlah",
+        "Rata2_sub_koleksi","Rata2_sub_sdm","Rata2_sub_pelayanan","Rata2_sub_pengelolaan",
+        "Rata2_dim_kepatuhan","Rata2_dim_kinerja",
+        "Indeks_Dasar_Agregat_0_100",
+        "Indeks_Final_Agregat_0_100",
+    ]
+    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"
+    )
+
+    # missing=0 (kunci avg3 tetap ÷3)
+    for c in cols_present:
+        full[c] = pd.to_numeric(full[c], errors="coerce").fillna(0.0)
+
+    # keseluruhan wilayah = avg3 dari 3 jenis
+    out = full.groupby(["group_key", label_name], as_index=False).agg(
+        n_total=("Jumlah", "sum"),
+        Rata2_sub_koleksi=("Rata2_sub_koleksi", "mean"),
+        Rata2_sub_sdm=("Rata2_sub_sdm", "mean"),
+        Rata2_sub_pelayanan=("Rata2_sub_pelayanan", "mean"),
+        Rata2_sub_pengelolaan=("Rata2_sub_pengelolaan", "mean"),
+        Rata2_dim_kepatuhan=("Rata2_dim_kepatuhan", "mean"),
+        Rata2_dim_kinerja=("Rata2_dim_kinerja", "mean"),
+        Indeks_Dasar_Agregat_0_100=("Indeks_Dasar_Agregat_0_100", "mean"),
+        Indeks_Final_Wilayah_0_100=("Indeks_Final_Agregat_0_100", "mean"),
+    )
 
-    agg["target_total_68_jenis"] = pd.to_numeric(agg["target_total_68_jenis"], errors="coerce").fillna(0.0)
-    agg["pop_total_jenis"] = pd.to_numeric(agg["pop_total_jenis"], errors="coerce").fillna(0.0)
+    # tempel faktor/target/pop/coverage (informasi verifikasi)
+    if faktor_wilayah is not None and not faktor_wilayah.empty:
+        fw = faktor_wilayah.copy()
+        keep_fw = ["group_key", label_name, "target_total_68", "pop_total", "faktor_penyesuaian", "coverage_total_%"]
+        keep_fw = [c for c in keep_fw if c in fw.columns]
+        out = out.merge(fw[keep_fw], on=["group_key", label_name], how="left")
 
-    m_need_pop = (agg["pop_total_jenis"] <= 0) & (agg["target_total_68_jenis"] > 0)
-    agg.loc[m_need_pop, "pop_total_jenis"] = agg.loc[m_need_pop, "target_total_68_jenis"] / float(FALLBACK_TARGET_RATIO)
+    # =========================================================
+    # PATCH UTAMA:
+    # Tambahkan target_total_68 & pop_total dari POP_KHUSUS
+    # (tanpa kolom khusus tambahan)
+    # =========================================================
+    if (pop_khusus is not None) and (not pop_khusus.empty):
+        pk = pop_khusus.copy()
+
+        # pastikan numerik
+        for c in ["Target68_Total_Jenis", "Pop_Total_Jenis"]:
+            if c in pk.columns:
+                pk[c] = pd.to_numeric(pk[c], errors="coerce").fillna(0.0)
+
+        add_df = None
+
+        # KAB/KOTA: join langsung by kab_key == group_key
+        if ("KAB" in kew_norm or "KOTA" in kew_norm):
+            if "kab_key" in pk.columns:
+                add_df = pk.groupby("kab_key", as_index=False).agg(
+                    add_target=("Target68_Total_Jenis", "sum"),
+                    add_pop=("Pop_Total_Jenis", "sum"),
+                ).rename(columns={"kab_key": "group_key"})
+
+        # PROVINSI: agregasi by prov_key == group_key
+        elif ("PROV" in kew_norm):
+            if "prov_key" in pk.columns:
+                add_df = pk.groupby("prov_key", as_index=False).agg(
+                    add_target=("Target68_Total_Jenis", "sum"),
+                    add_pop=("Pop_Total_Jenis", "sum"),
+                ).rename(columns={"prov_key": "group_key"})
+
+        if add_df is not None and not add_df.empty:
+            out = out.merge(add_df, on="group_key", how="left")
+            out["add_target"] = pd.to_numeric(out.get("add_target", 0), errors="coerce").fillna(0.0)
+            out["add_pop"]    = pd.to_numeric(out.get("add_pop", 0), errors="coerce").fillna(0.0)
+
+            # tambah ke total existing (kalau belum ada kolomnya -> dianggap 0)
+            out["target_total_68"] = pd.to_numeric(out.get("target_total_68", 0), errors="coerce").fillna(0.0) + out["add_target"]
+            out["pop_total"]       = pd.to_numeric(out.get("pop_total", 0), errors="coerce").fillna(0.0) + out["add_pop"]
+
+            # opsional tapi konsisten: update coverage & faktor berdasarkan total baru (DI TABEL INI SAJA)
+            out["coverage_total_%"] = [
+                (safe_div(n, p) * 100) if (p is not None and not pd.isna(p) and float(p) > 0) else 0.0
+                for n, p in zip(
+                    pd.to_numeric(out.get("n_total", 0), errors="coerce").fillna(0).astype(float).tolist(),
+                    pd.to_numeric(out.get("pop_total", 0), errors="coerce").fillna(0).astype(float).tolist()
+                )
+            ]
+            out["faktor_penyesuaian"] = [
+                faktor_penyesuaian_total(n, t)
+                for n, t in zip(
+                    pd.to_numeric(out.get("n_total", 0), errors="coerce").fillna(0).astype(float).tolist(),
+                    pd.to_numeric(out.get("target_total_68", 0), errors="coerce").fillna(0).astype(float).tolist()
+                )
+            ]
 
-    m2 = agg["pop_total_jenis"] > 0
-    agg.loc[m2, "coverage_jenis"] = (pd.to_numeric(agg.loc[m2, "Jumlah"], errors="coerce").fillna(0.0) / agg.loc[m2, "pop_total_jenis"]) * 100.0
+            # bersihkan kolom helper
+            out = out.drop(columns=[c for c in ["add_target", "add_pop"] if c in out.columns])
 
-    # rounding (tampilan konsisten)
+    # rounding (yang sudah ada sebelumnya)
     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)
+        if c in out.columns:
+            out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0).round(3)
 
-    for c in ["faktor_penyesuaian_wilayah","faktor_penyesuaian"]:
-        if c in agg.columns:
-            agg[c] = pd.to_numeric(agg[c], errors="coerce").fillna(1.0).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)
 
-    for c in ["target_total_68","pop_total","coverage_total_%","target_total_68_jenis","pop_total_jenis","coverage_jenis"]:
-        if c in agg.columns:
-            agg[c] = pd.to_numeric(agg[c], errors="coerce").fillna(0.0)
+    if "faktor_penyesuaian" in out.columns:
+        out["faktor_penyesuaian"] = pd.to_numeric(out["faktor_penyesuaian"], errors="coerce").fillna(1.0).round(3)
 
-    return agg
+    for c in ["target_total_68","pop_total","coverage_total_%"]:
+        if c in out.columns:
+            out[c] = pd.to_numeric(out[c], errors="coerce").fillna(0.0)
 
+    return out
 
 # ============================================================
 # 8) AGREGAT WILAYAH (KESELURUHAN) — RUMUS BARU: AVG3 dari 3 jenis