Update app.py

app.py

@@ -4,11 +4,9 @@ import matplotlib.pyplot as plt
 import pandas as pd
 import joblib
 import traceback
-import numpy as np
-import textwrap
 
 # ------------------------------
-# Helper: safe load joblib with message
+# Helper: safe load joblib
 # ------------------------------
 def safe_load(path, name):
     try:
@@ -39,75 +37,47 @@ loaded_models = {
 # ------------------------------
 try:
     df_raw = pd.read_csv("job_salary_mean.csv")
-    # coba normalisasi nama kolom umum
     df_benchmark = df_raw.rename(columns={
         "Judul Pekerjaan": "judul",
         "Perusahaan": "perusahaan",
         "Lokasi": "lokasi",
-        "Gaji_Rata2": "gaji",
-        "tahun": "year",
-        "tahun_posting": "year",
-        "year": "year"
+        "Gaji_Rata2": "gaji"
     })
-    # pastikan kolom gaji numeric
-    if "gaji" in df_benchmark.columns:
-        df_benchmark["gaji"] = pd.to_numeric(df_benchmark["gaji"], errors="coerce")
-    else:
-        df_benchmark["gaji"] = np.nan
-
-    df_benchmark["judul_clean"] = df_benchmark.get("judul", "").astype(str).str.lower()
-    df_benchmark["lokasi_clean"] = df_benchmark.get("lokasi", "").astype(str).str.lower()
-    # drop missing gaji for analytics (still allow prediction fallback)
-    df_benchmark = df_benchmark.dropna(subset=["judul_clean", "lokasi_clean"])
+    df_benchmark["judul_clean"] = df_benchmark["judul"].astype(str).str.lower()
+    df_benchmark["lokasi_clean"] = df_benchmark["lokasi"].astype(str).str.lower()
+    df_benchmark = df_benchmark.dropna(subset=["judul_clean", "lokasi_clean", "gaji"])
     print(f"✅ Benchmark loaded: {len(df_benchmark)} rows")
-except Exception as e:
-    print("❌ job_salary_mean.csv not found or gagal dibaca:", e)
+except:
+    print("❌ job_salary_mean.csv not found")
     df_benchmark = pd.DataFrame(columns=["judul_clean", "lokasi_clean", "gaji"])
 
 # ------------------------------
-# LOAD WILAYAH (uploaded file path)
+# LOAD WILAYAH
 # ------------------------------
 try:
-    # path file yang kamu upload (sesuai session)
-    geo_path = "/mnt/data/dataset kabupaten indonesia.csv"
-    geo = pd.read_csv(geo_path)
-    # menyesuaikan nama kolom dari file upload: ambil kolom 'name' dan 'Unnamed: 3' seperti sebelumnya
-    if "name" in geo.columns and "Unnamed: 3" in geo.columns:
-        geo = geo[["name", "Unnamed: 3"]].rename(columns={
-            "name": "kota",
-            "Unnamed: 3": "provinsi"
-        })
-    else:
-        # fallback: coba cari kolom serupa
-        possible_kota = [c for c in geo.columns if "kota" in c.lower() or "name" in c.lower()]
-        possible_prov = [c for c in geo.columns if "provinsi" in c.lower() or "prov" in c.lower()]
-        if possible_kota and possible_prov:
-            geo = geo[[possible_kota[0], possible_prov[0]]].rename(columns={
-                possible_kota[0]: "kota",
-                possible_prov[0]: "provinsi"
-            })
-        else:
-            raise ValueError("Format dataset kabupaten tidak dikenali")
-
-    # bersihkan string
-    geo["kota_clean"] = geo["kota"].astype(str).str.lower().str.replace("kota ", "").str.replace("kabupaten ", "")
+    geo = pd.read_csv("dataset kabupaten indonesia.csv")
+    geo = geo[["name", "Unnamed: 3"]].rename(columns={
+        "name": "kota",
+        "Unnamed: 3": "provinsi"
+    })
+    geo["kota_clean"] = geo["kota"].astype(str).str.lower().str.replace("kota ", "").replace("kabupaten ", "")
     geo["provinsi"] = geo["provinsi"].astype(str).str.upper()
     MASTER_WILAYAH = pd.Series(geo.provinsi.values, index=geo.kota_clean).to_dict()
-    print(f"✅ Loaded {len(MASTER_WILAYAH)} wilayah from {geo_path}")
-except Exception as e:
-    print("⚠ dataset kabupaten indonesia.csv tidak ada atau gagal dibaca:", e)
+    print(f"✅ Loaded {len(MASTER_WILAYAH)} wilayah")
+except:
+    print("⚠ dataset kabupaten indonesia.csv tidak ada")
     MASTER_WILAYAH = {}
 
 # ------------------------------
 # WILAYAH FUNCTIONS
 # ------------------------------
 def get_pulau_from_provinsi(p):
-    p = str(p).upper()
+    p = p.upper()
     if any(x in p for x in ["JAWA", "DKI", "BANTEN"]): return "PULAU JAWA"
-    if any(x in p for x in ["SUMATERA", "ACEH", "RIAU", "LAMPUNG", "BENGKULU", "KEPULAUAN RIAU", "SUMATERA UTARA", "SUMATERA SELATAN", "SUMATERA BARAT"]): return "PULAU SUMATERA"
+    if any(x in p for x in ["SUMATERA", "ACEH", "RIAU"]): return "PULAU SUMATERA"
     if "KALIMANTAN" in p: return "PULAU KALIMANTAN"
     if "SULAWESI" in p: return "PULAU SULAWESI"
-    if any(x in p for x in ["BALI", "NUSA", "NTB", "NTT"]): return "BALI & NUSA TENGGARA"
+    if any(x in p for x in ["BALI", "NUSA"]): return "BALI & NUSA TENGGARA"
     if any(x in p for x in ["PAPUA", "MALUKU"]): return "PAPUA & MALUKU"
     return "INDONESIA"
 
@@ -119,159 +89,61 @@ def deteksi_wilayah(text):
     return "INDONESIA", "INDONESIA"
 
 # ------------------------------
-# PLOTTING HELPERS
-# ------------------------------
-def plot_trend_nasional(df):
-    fig, ax = plt.subplots(figsize=(8,3.5))
-    # jika ada kolom year gunakan line chart median per year
-    if "year" in df.columns:
-        try:
-            trend = df.dropna(subset=["year", "gaji"]).groupby("year")["gaji"].median().sort_index()
-            if len(trend) > 1:
-                ax.plot(trend.index.astype(str), trend.values, marker="o")
-                ax.set_title("Tren Gaji Nasional (median per tahun)")
-                ax.set_xlabel("Tahun")
-                ax.set_ylabel("Rp (median)")
-                ax.grid(alpha=0.25)
-            else:
-                # fallback: histogram
-                ax.hist(df["gaji"].dropna(), bins=40)
-                ax.set_title("Distribusi Gaji Nasional (tahun tidak cukup)")
-                ax.set_xlabel("Rp")
-        except Exception:
-            ax.hist(df["gaji"].dropna(), bins=40)
-            ax.set_title("Distribusi Gaji Nasional")
-            ax.set_xlabel("Rp")
-    else:
-        # jika tidak ada kolom year, tampilkan histogram distribusi gaji
-        ax.hist(df["gaji"].dropna(), bins=40)
-        ax.set_title("Distribusi Gaji Nasional (tidak ada data tahun)")
-        ax.set_xlabel("Rp")
-    plt.tight_layout()
-    return fig
-
-def plot_boxplot_per_pulau(df):
-    fig, ax = plt.subplots(figsize=(8,3.5))
-    # gabungkan provinsi via MASTER_WILAYAH mapping
-    df_local = df.copy()
-    def map_prov_from_lokasi(x):
-        prov, pulau = deteksi_wilayah(x)
-        return pulau
-    df_local["pulau"] = df_local["lokasi_clean"].apply(map_prov_from_lokasi)
-    # only keep entries with numeric gaji
-    df_local = df_local.dropna(subset=["gaji"])
-    groups = df_local.groupby("pulau")["gaji"].apply(list)
-    # siapkan data dan label
-    data = []
-    labels = []
-    for pulau, arr in groups.items():
-        data.append(arr)
-        labels.append(pulau)
-    if len(data) == 0:
-        ax.text(0.5, 0.5, "Tidak ada data gaji untuk boxplot", ha="center")
-    else:
-        ax.boxplot(data, labels=labels, vert=False, patch_artist=True)
-        ax.set_title("Boxplot Gaji per Pulau")
-        ax.set_xlabel("Rp")
-    plt.tight_layout()
-    return fig
-
-def plot_heatmap_provinsi(df):
-    # rata-rata gaji per provinsi
-    fig, ax = plt.subplots(figsize=(6,8))
-    df_local = df.copy()
-    # coba mapping provinsi dari lokasi
-    def map_prov(x):
-        prov, pulau = deteksi_wilayah(x)
-        return prov
-    df_local["provinsi_mapped"] = df_local["lokasi_clean"].apply(map_prov)
-    agg = df_local.dropna(subset=["gaji"]).groupby("provinsi_mapped")["gaji"].mean().sort_values(ascending=False)
-    if agg.empty:
-        ax.text(0.5, 0.5, "Tidak ada data untuk heatmap provinsi", ha="center")
-        ax.axis("off")
-        return fig
-    # untuk tampilkan heatmap simpel: gunakan bar horizontal dengan colormap, disusun ke 2 kolom agar mirip heatmap
-    provs = agg.index.tolist()
-    values = agg.values
-    # normalisasi untuk colormap
-    norm = plt.Normalize(vmin=min(values), vmax=max(values))
-    cmap = plt.cm.viridis
-    colors = cmap(norm(values))
-    y = np.arange(len(provs))
-    ax.barh(y, values, color=colors)
-    ax.set_yticks(y)
-    ax.set_yticklabels(provs, fontsize=8)
-    ax.invert_yaxis()
-    ax.set_title("Rata-rata Gaji per Provinsi (Rp)")
-    plt.tight_layout()
-    return fig
-
-# ------------------------------
-# PREDIKSI + BENCHMARK + GRAFIK
+# PREDIKSI + BENCHMARK
 # ------------------------------
 def analisis_gaji_final(judul, lokasi, model_choice):
     try:
         if not judul or not lokasi:
-            return "<b style='color:red;'>Mohon masukkan posisi dan lokasi.</b>", None, None, None
+            return "<b style='color:red;'>Mohon masukkan posisi dan lokasi.</b>", None
 
         model = loaded_models.get(model_choice)
 
         df_input = pd.DataFrame({
-            "judul_clean": [str(judul).lower()],
-            "lokasi_clean": [str(lokasi).lower()],
+            "judul_clean": [judul.lower()],
+            "lokasi_clean": [lokasi.lower()],
             "perusahaan": ["unknown"]
         })
 
         try:
-            # jika model membutuhkan preprocessor, apply jika tersedia
-            try:
-                X_in = preprocessor.transform(df_input)
-            except Exception:
-                X_in = df_input
-            pred = float(model.predict(df_input if X_in is None else df_input)[0])
+            pred = float(model.predict(df_input)[0])
             pred = max(0, pred)
         except Exception as e:
-            # fallback: jika model gagal, beri pesan
-            return f"<b>Gagal memprediksi:</b> {e}", None, None, None
+            return f"<b>Gagal memprediksi:</b> {e}", None
 
         # Benchmark job
-        job_match = df_benchmark[df_benchmark["judul_clean"].str.contains(str(judul).lower(), na=False)]
-        max_job = float(job_match["gaji"].max()) if not job_match.empty and job_match["gaji"].notna().any() else pred * 1.3
+        job_match = df_benchmark[df_benchmark["judul_clean"].str.contains(judul.lower(), na=False)]
+        max_job = float(job_match["gaji"].max()) if not job_match.empty else pred * 1.3
 
         # Benchmark location
         provinsi, pulau = deteksi_wilayah(lokasi)
-        # cari regional dengan mencocokkan nama provinsi atau nama pulau (simple contains)
-        region_match = df_benchmark[df_benchmark["lokasi_clean"].str.contains(provinsi.lower(), na=False)]
-        if region_match.empty:
-            # coba cari berdasarkan pulau (ambil kata terakhir dari string pulau => mis. 'PULAU JAWA' -> 'JAWA')
-            region_term = pulau.split()[-1].lower() if pulau != "INDONESIA" else ""
-            if region_term:
-                region_match = df_benchmark[df_benchmark["lokasi_clean"].str.contains(region_term, na=False)]
-        max_reg = float(region_match["gaji"].max()) if not region_match.empty and region_match["gaji"].notna().any() else pred * 1.6
-
-        # Build HTML result
+        region_match = df_benchmark[df_benchmark["lokasi_clean"].str.contains(pulau.split()[-1].lower(), na=False)]
+        max_reg = float(region_match["gaji"].max()) if not region_match.empty else pred * 1.6
+
+        # Graph
+        fig, ax = plt.subplots(figsize=(8,4))
+        labels = ["Prediksi Anda", "Max Nasional", "Max Regional"]
+        values = [pred, max_job, max_reg]
+        ax.bar(labels, values)
+        ax.set_title(f"Analisis Gaji: {judul} ({provinsi})")
+        ax.set_ylabel("Rp")
+
+        # HTML clean
         html = f"""
         <div style='padding:14px; border-radius:10px; background:#f8fafc'>
-            <h3>💰 Estimasi Gaji: <b>Rp {pred:,.0f}</b></h3>
+            <h3>💰 Estimasi Gaji: Rp {pred:,.0f}</h3>
             <p>📍 Lokasi terdeteksi: <b>{provinsi}</b> — {pulau}</p>
             <p>Max Nasional posisi ini: <b>Rp {max_job:,.0f}</b></p>
             <p>Max Regional: <b>Rp {max_reg:,.0f}</b></p>
         </div>
         """
 
-        # Build charts (gunakan seluruh df_benchmark untuk analytics)
-        fig_trend = plot_trend_nasional(df_benchmark)
-        fig_box = plot_boxplot_per_pulau(df_benchmark)
-        fig_heat = plot_heatmap_provinsi(df_benchmark)
-
-        return html, fig_trend, fig_box, fig_heat
+        return html, fig
 
     except Exception as e:
-        tb = traceback.format_exc()
-        return f"<b>Error:</b> {e}<pre>{tb}</pre>", None, None, None
+        return f"<b>Error:</b> {e}", None
 
 # ------------------------------
-# CLEAN UI (DASHBOARD STYLE) - FIXED + ANALYTICS
+# CLEAN UI (DASHBOARD STYLE) - FIXED
 # ------------------------------
 
 custom_css = """
@@ -282,25 +154,27 @@ custom_css = """
     border-radius: 12px;
     box-shadow: 0 2px 10px rgba(0,0,0,0.06);
 }
-.gradio-container {max-width: 1200px !important; margin:auto;}
-.small-muted {color: #6b7280; font-size: 0.95rem;}
-.card-title {font-weight:600; margin-bottom:8px;}
+.gradio-container {max-width: 1100px !important; margin:auto;}
 </style>
 """
 
-with gr.Blocks(title="Salary AI Dashboard") as demo:
+with gr.Blocks(title="Salary AI") as demo:
 
     # Inject CSS
     gr.HTML(custom_css)
 
-    gr.Markdown("<h1 style='text-align:center;'>💼 Salary AI Dashboard</h1>")
-    gr.Markdown("<p style='text-align:center; color:gray;'>Prediksi gaji + Benchmark Nasional & Regional Indonesia.</p>")
+    gr.Markdown("""
+    <h1 style='text-align:center;'>💼 Salary AI Dashboard</h1>
+    <p style='text-align:center; color:gray;'>
+        Prediksi gaji + Benchmark Nasional & Regional Indonesia.
+    </p>
+    """)
 
     with gr.Row():
+
         # LEFT PANEL — INPUT FORM
         with gr.Column(scale=1):
-            gr.HTML("<div class='dashboard-box'>")
-            gr.Markdown("### 📥 Input Data")
+            gr.HTML("<div class='dashboard-box'><h3>📥 Input Data</h3>")
             t1 = gr.Textbox(label="Posisi Pekerjaan", placeholder="cth: Data Analyst")
             t2 = gr.Textbox(label="Kabupaten/Kota", placeholder="cth: Bandung")
             model = gr.Dropdown(
@@ -311,32 +185,19 @@ with gr.Blocks(title="Salary AI Dashboard") as demo:
             btn = gr.Button("🔍 Analisis Gaji", variant="primary")
             gr.HTML("</div>")
 
-            # quick info card
-            with gr.Row():
-                with gr.Column():
-                    gr.HTML("<div class='dashboard-box'>")
-                    gr.Markdown("#### ℹ️ Info Dataset")
-                    gr.Markdown(f"- Rows benchmark: **{len(df_benchmark)}**")
-                    gr.Markdown(f"- Wilayah terdaftar: **{len(MASTER_WILAYAH)}**")
-                    gr.HTML("</div>")
-
-        # RIGHT PANEL — OUTPUT & ANALYTICS
+        # RIGHT PANEL — OUTPUT
         with gr.Column(scale=2):
-            gr.HTML("<div class='dashboard-box'>")
-            gr.Markdown("### 📊 Hasil Analisis")
+            gr.HTML("<div class='dashboard-box'><h3>📊 Hasil Analisis</h3>")
             out_html = gr.HTML()
-            gr.Markdown("#### Grafik Analitik")
-            out_trend = gr.Plot()
-            out_box = gr.Plot()
-            out_heat = gr.Plot()
+            out_plot = gr.Plot()
             gr.HTML("</div>")
 
     btn.click(
         analisis_gaji_final,
         inputs=[t1, t2, model],
-        outputs=[out_html, out_trend, out_box, out_heat]
+        outputs=[out_html, out_plot]
     )
 
 if __name__ == "__main__":
     print("App running...")
-    demo.launch(share=True, debug=True)
+    demo.launch(share=True, debug=True)