Update app.py

app.py

@@ -6,216 +6,172 @@ import joblib
 import traceback
 
 # ------------------------------
-# Helper: safe load joblib with message
+# Helper: safe load joblib
 # ------------------------------
 def safe_load(path, name):
     try:
         obj = joblib.load(path)
         print(f"✅ {name} loaded from {path}")
         return obj
-    except FileNotFoundError:
-        print(f"❌ Error: '{path}' not found. Please ensure it's in the same directory.")
-        raise
     except Exception as e:
-        print(f"❌ Error loading {path}: {e}")
+        print(f"❌ Error loading {name}: {e}")
         raise
 
-# ==============================
-# BAGIAN 0: LOAD PREPROCESSOR & MODELS
-# ==============================
-print("Loading saved scikit-learn models and preprocessor...")
-preprocessor = safe_load('preprocessor.pkl', 'Preprocessor')
-
-lr_model = safe_load('lr_model.pkl', 'Linear Regression model')
-dt_model = safe_load('dt_model.pkl', 'Decision Tree model')
-rf_model = safe_load('rf_model.pkl', 'Random Forest model')
+# ------------------------------
+# LOAD MODELS & PREPROCESSOR
+# ------------------------------
+print("Loading models...")
+preprocessor = safe_load("preprocessor.pkl", "Preprocessor")
+lr_model = safe_load("lr_model.pkl", "Linear Regression")
+dt_model = safe_load("dt_model.pkl", "Decision Tree")
+rf_model = safe_load("rf_model.pkl", "Random Forest")
 
 loaded_models = {
-    'Linear Regression': lr_model,
-    'Decision Tree': dt_model,
-    'Random Forest': rf_model
+    "Linear Regression": lr_model,
+    "Decision Tree": dt_model,
+    "Random Forest": rf_model
 }
 
-# ==============================
-# BAGIAN: LOAD BENCHMARK CSV & WILAYAH
-# ==============================
-pd_df_clean = None
+# ------------------------------
+# LOAD DATASET BENCHMARK
+# ------------------------------
 try:
-    pd_df_raw = pd.read_csv('job_salary_mean.csv')
-    pd_df_clean = pd_df_raw.rename(columns={
+    df_raw = pd.read_csv("job_salary_mean.csv")
+    df_benchmark = df_raw.rename(columns={
         "Judul Pekerjaan": "judul",
         "Perusahaan": "perusahaan",
         "Lokasi": "lokasi",
         "Gaji_Rata2": "gaji"
     })
-    pd_df_clean['judul_clean'] = pd_df_clean['judul'].astype(str).str.lower()
-    pd_df_clean['lokasi_clean'] = pd_df_clean['lokasi'].astype(str).str.lower()
-    pd_df_clean = pd_df_clean.dropna(subset=['judul_clean','lokasi_clean','gaji'])
-    print(f"✅ Pandas DataFrame for benchmarks loaded and cleaned. Total rows: {len(pd_df_clean)}")
-except FileNotFoundError:
-    print("❌ Error: 'job_salary_mean.csv' not found. Please ensure it's in the same directory.")
-    pd_df_clean = pd.DataFrame(columns=['judul_clean','lokasi_clean','gaji'])
-
-# Load wilayah
-kamus_wilayah = {}
+    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:
+    print("❌ job_salary_mean.csv not found")
+    df_benchmark = pd.DataFrame(columns=["judul_clean", "lokasi_clean", "gaji"])
+
+# ------------------------------
+# LOAD WILAYAH
+# ------------------------------
 try:
-    geo_df = pd.read_csv('dataset kabupaten indonesia.csv')
-    geo_df = geo_df[['name', 'Unnamed: 3']].rename(columns={'name': 'kota', 'Unnamed: 3': 'provinsi'})
-    geo_df['kota_clean'] = geo_df['kota'].astype(str).str.replace('KABUPATEN ', '', regex=False)\
-                                                   .str.replace('KOTA ', '', regex=False)\
-                                                   .str.lower().str.strip()
-    geo_df['provinsi'] = geo_df['provinsi'].astype(str).str.upper().str.strip()
-    kamus_wilayah = pd.Series(geo_df.provinsi.values, index=geo_df.kota_clean).to_dict()
-    print(f"✅ Berhasil memuat {len(kamus_wilayah)} wilayah administrasi Indonesia.")
-except FileNotFoundError:
-    print("❌ WARNING: File 'dataset kabupaten indonesia.csv' tidak ditemukan. Fitur deteksi lokasi manual masih bisa digunakan.")
-    kamus_wilayah = {}
-
-def get_pulau_from_provinsi(provinsi):
-    p = provinsi.upper()
-    if any(x in p for x in ['JAWA', 'DKI', 'BANTEN', 'YOGYAKARTA']): return "PULAU JAWA"
-    if any(x in p for x in ['SUMATERA', 'ACEH', 'RIAU', 'JAMBI', 'BENGKULU', 'LAMPUNG', 'BANGKA']): return "PULAU SUMATERA"
-    if any(x in p for x in ['KALIMANTAN']): return "PULAU KALIMANTAN"
-    if any(x in p for x in ['SULAWESI', 'GORONTALO']): return "PULAU SULAWESI"
-    if any(x in p for x in ['BALI', 'NUSA TENGGARA']): return "BALI & NUSA TENGGARA"
-    if any(x in p for x in ['PAPUA', 'MALUKU']): return "PAPUA & MALUKU"
-    return "INDONESIA (LAINNYA)"
-
-def deteksi_info_lokasi(input_user):
-    text = str(input_user).lower().strip()
-    provinsi_terdeteksi = "INDONESIA"
-    for kota_db, prov_db in kamus_wilayah.items():
-        if kota_db in text:
-            provinsi_terdeteksi = prov_db
-            break
-    pulau_terdeteksi = get_pulau_from_provinsi(provinsi_terdeteksi)
-    return provinsi_terdeteksi, pulau_terdeteksi
-
-# ==============================
-# FUNGSI UTAMA: analisis_gaji_final
-# ==============================
-def analisis_gaji_final(judul_input, lokasi_input, model_choice):
+    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")
+except:
+    print("⚠ dataset kabupaten indonesia.csv tidak ada")
+    MASTER_WILAYAH = {}
+
+# ------------------------------
+# WILAYAH FUNCTIONS
+# ------------------------------
+def get_pulau_from_provinsi(p):
+    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"]): 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"]): return "BALI & NUSA TENGGARA"
+    if any(x in p for x in ["PAPUA", "MALUKU"]): return "PAPUA & MALUKU"
+    return "INDONESIA"
+
+def deteksi_wilayah(text):
+    txt = str(text).lower()
+    for kota, prov in MASTER_WILAYAH.items():
+        if kota in txt:
+            return prov, get_pulau_from_provinsi(prov)
+    return "INDONESIA", "INDONESIA"
+
+# ------------------------------
+# PREDIKSI + BENCHMARK
+# ------------------------------
+def analisis_gaji_final(judul, lokasi, model_choice):
     try:
-        # Safety for empty inputs
-        if not judul_input or not lokasi_input:
-            return ("<div style='color:#9a1f1f; padding:12px;'><b>Masukkan posisi dan lokasi terlebih dahulu.</b></div>", None)
-
-        model_pipeline = loaded_models.get(model_choice)
-        if model_pipeline is None:
-            return (f"<div style='color:#9a1f1f; padding:12px;'><b>Model '{model_choice}' tidak tersedia.</b></div>", None)
-
-        input_df = pd.DataFrame({
-            'judul_clean': [str(judul_input).lower()],
-            'lokasi_clean': [str(lokasi_input).lower()],
-            'perusahaan': ['unknown_company_for_prediction']
+        if not judul or not lokasi:
+            return "<b style='color:red;'>Mohon masukkan posisi dan lokasi.</b>", None
+
+        model = loaded_models.get(model_choice)
+
+        df_input = pd.DataFrame({
+            "judul_clean": [judul.lower()],
+            "lokasi_clean": [lokasi.lower()],
+            "perusahaan": ["unknown"]
         })
 
-        # If your preprocessor expects different feature names, ensure alignment here.
         try:
-            prediksi_user = model_pipeline.predict(input_df)[0]
-            prediksi_user = max(0, float(prediksi_user))
+            pred = float(model.predict(df_input)[0])
+            pred = max(0, pred)
         except Exception as e:
-            tb = traceback.format_exc()
-            print("Prediction error:", tb)
-            return (f"<div style='color:#9a1f1f; padding:12px;'><b>Gagal memprediksi:</b> {str(e)}</div>", None)
-
-        # Benchmark logic
-        judul_lower = str(judul_input).lower()
-        filtered_jobs = pd_df_clean[pd_df_clean['judul_clean'].str.contains(judul_lower, na=False)]
-        if not filtered_jobs.empty:
-            max_gaji_job = float(filtered_jobs['gaji'].max())
-        else:
-            max_gaji_job = prediksi_user * 1.2
-
-        provinsi_found, pulau_found = deteksi_info_lokasi(lokasi_input)
-        keyword_pencarian = pulau_found.replace("PULAU ", "").lower()
-        filtered_locations = pd_df_clean[pd_df_clean['lokasi_clean'].str.contains(keyword_pencarian, na=False)]
-        if not filtered_locations.empty:
-            max_gaji_region = float(filtered_locations['gaji'].max())
-        else:
-            max_gaji_region = prediksi_user * 1.5
-
-        # Visualisasi (matplotlib)
-        fig, ax = plt.subplots(figsize=(9,4.6))
-        labels = [f"Estimasi Anda\n({lokasi_input})", f"Max Posisi\n(Nasional)", f"Max Regional\n({pulau_found})"]
-        values = [prediksi_user, max_gaji_job, max_gaji_region]
-        # subtle colors
-        colors = ['#60a5fa', '#94a3b8', '#fbbf24']
-
-        bars = ax.bar(labels, values, color=colors, edgecolor='none', alpha=0.95)
-        ax.axhline(y=prediksi_user, color='#2563eb', linestyle='--', linewidth=1)
-        ax.set_ylabel("Gaji (Rupiah)")
-        ax.set_title(f"Analisis Gaji: {judul_input} — {provinsi_found}  | Model: {model_choice}", fontsize=12)
-        ax.grid(axis='y', linestyle='--', alpha=0.4)
-        for bar in bars:
-            height = bar.get_height()
-            ax.text(bar.get_x() + bar.get_width()/2., height + (max(values)*0.015),
-                    f'Rp {int(height):,}', ha='center', va='bottom', fontsize=9)
-
-        # HTML card hasil
-        html_output = f"""
-        <div style="font-family: Inter, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial; 
-                    padding:18px; border-radius:12px; background: linear-gradient(180deg, #ffffff 0%, #fbfbfc 100%); 
-                    box-shadow: 0px 6px 20px rgba(16,24,40,0.04); color:#0f172a;">
-            <h2 style="margin:0 0 6px 0; font-size:18px; color:#0f172a;">💰 Estimasi Gaji: <span style="color:#0b6fb7;">Rp {int(prediksi_user):,}</span></h2>
-            <div style="font-size:13px; color:#475569; margin-bottom:10px;">
-                📍 <b>{provinsi_found}</b> / {pulau_found} &nbsp; • &nbsp; Model: <b>{model_choice}</b>
-            </div>
-            <div style="padding:10px; border-radius:8px; background:#f8fafc; color:#0f172a; font-size:13px;">
-                Berdasarkan data historis, batas atas untuk posisi <b>{judul_input}</b> (nasional) mencapai <b>Rp {int(max_gaji_job):,}</b>.
-                Untuk regional ({pulau_found}) tertinggi tercatat Rp <b>{int(max_gaji_region):,}</b>.
-            </div>
+            return f"<b>Gagal memprediksi:</b> {e}", None
+
+        # Benchmark job
+        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)
+        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: 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>
         """
-        plt.tight_layout()
-        return html_output, fig
+
+        return html, fig
 
     except Exception as e:
-        tb = traceback.format_exc()
-        print("Unhandled error in analisis_gaji_final:", tb)
-        return (f"<div style='color:#9a1f1f; padding:12px;'><b>Terjadi kesalahan:</b> {str(e)}</div>", None)
-
-# ==============================
-# GRADIO UI - with custom CSS for subtle/elegant look
-# ==============================
-custom_css = """
-:root{
-  --primary:#0b6fb7;
-  --muted:#94a3b8;
-  --card-bg: #ffffff;
-  --accent: #f8fafc;
-}
-body { font-family: Inter, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial; }
-.gradio-container { max-width: 1100px; margin: 18px auto; }
-.header { display:flex; align-items:center; gap:12px; margin-bottom:8px; }
-.small-brand { font-weight:700; color:var(--primary); font-size:20px; }
-.description { color:var(--muted); margin-bottom:14px; }
-.input-box .gr-textbox { border-radius:10px; }
-.gr-button { border-radius:10px; padding:10px 14px; font-weight:600; }
-.result-card { border-radius:12px; padding:6px; }
+        return f"<b>Error:</b> {e}", None
+
+# ------------------------------
+# CLEAN UI (NEW GRADIO FORMAT)
+# ------------------------------
+
+css = """
+.gradio-container {max-width: 1000px !important; margin:auto;}
 """
 
-with gr.Blocks(title="Salary AI — Elegant", css=custom_css) as demo:
-    with gr.Column():
-        with gr.Row(elem_id="top-row"):
-            with gr.Column(scale=2):
-                gr.Markdown("<div class='header'><div class='small-brand'>🇮🇩 Salary AI</div></div>")
-                gr.Markdown("<div class='description'>Prediksi gaji berbasis machine learning + data benchmark wilayah Indonesia. Masukkan posisi pekerjaan dan kabupaten/kota untuk analisis.</div>")
-                with gr.Row():
-                    t1 = gr.Textbox(label="Posisi Pekerjaan", placeholder="Contoh: Guru, Driver, Manager", elem_id="t1")
-                    t2 = gr.Textbox(label="Kabupaten / Kota", placeholder="Contoh: Simeulue, Surakarta, Malang", elem_id="t2")
-                model_selector = gr.Dropdown(label="Pilih Model Prediksi",
-                                            choices=list(loaded_models.keys()),
-                                            value='Random Forest',
-                                            interactive=True)
-                btn = gr.Button("🔍 Analisis Sekarang", variant="primary")
-            with gr.Column(scale=1):
-                gr.Markdown("### Hasil")
-                out_html = gr.HTML()
-                out_plot = gr.Plot()
-    # Connect
-    btn.click(analisis_gaji_final, inputs=[t1, t2, model_selector], outputs=[out_html, out_plot])
+with gr.Blocks(title="Salary AI", css=css) as demo:
+
+    gr.Markdown("<h1 style='text-align:center;'>💼 Salary AI</h1>")
+    gr.Markdown("<p style='text-align:center; color:gray;'>Prediksi gaji dengan Machine Learning + Benchmark Indonesia.</p>")
+
+    with gr.Row():
+        with gr.Column():
+            t1 = gr.Textbox(label="Posisi Pekerjaan")
+            t2 = gr.Textbox(label="Kabupaten/Kota")
+            model = gr.Dropdown(
+                choices=list(loaded_models.keys()),
+                value="Random Forest",
+                label="Model Prediksi"
+            )
+            btn = gr.Button("🔍 Analisis", variant="primary")
+
+        with gr.Column():
+            out_html = gr.HTML()
+            out_plot = gr.Plot()
+
+    btn.click(analisis_gaji_final, inputs=[t1, t2, model], outputs=[out_html, out_plot])
 
 if __name__ == "__main__":
-    print("Menjalankan Aplikasi Final...")
+    print("App running...")
     demo.launch(share=True, debug=True)