Update app.py

app.py

@@ -1,40 +1,45 @@
+# app.py
 import gradio as gr
 import matplotlib.pyplot as plt
 import pandas as pd
 import joblib
-# from pyspark.sql import SparkSession # No longer needed for inference
-# from pyspark.sql.functions import col, max as spark_max # No longer needed for inference
-from pyspark.sql.types import StringType, IntegerType, StructType, StructField # Still needed for schema definition if Spark is used elsewhere in the app.py, but not for this specific prediction path.
+import traceback
 
-# ==================================================
-# BAGIAN 0: INITIAL SETUP & LOAD SAVED MODELS
-# ==================================================
-print("Loading saved scikit-learn models and preprocessor...")
-
-# Load the saved preprocessor
-try:
-    preprocessor = joblib.load('preprocessor.pkl')
-    print("✅ Preprocessor loaded successfully.")
-except FileNotFoundError:
-    print("❌ Error: 'preprocessor.pkl' not found. Please ensure it's in the same directory.")
-    exit()
-
-# Load the trained scikit-learn models
-try:
-    lr_model = joblib.load('lr_model.pkl')
-    dt_model = joblib.load('dt_model.pkl')
-    rf_model = joblib.load('rf_model.pkl')
-    loaded_models = {
-        'Linear Regression': lr_model,
-        'Decision Tree': dt_model,
-        'Random Forest': rf_model
-    }
-    print("✅ Scikit-learn models loaded successfully.")
-except FileNotFoundError:
-    print("❌ Error: One or more model .pkl files not found. Please ensure they are in the same directory.")
-    exit()
+# ------------------------------
+# Helper: safe load joblib with message
+# ------------------------------
+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}")
+        raise
 
-# Load and clean job_salary_mean.csv using pandas for benchmarks
+# ==============================
+# 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')
+
+loaded_models = {
+    'Linear Regression': lr_model,
+    'Decision Tree': dt_model,
+    'Random Forest': rf_model
+}
+
+# ==============================
+# BAGIAN: LOAD BENCHMARK CSV & WILAYAH
+# ==============================
+pd_df_clean = None
 try:
     pd_df_raw = pd.read_csv('job_salary_mean.csv')
     pd_df_clean = pd_df_raw.rename(columns={
@@ -43,46 +48,29 @@ try:
         "Lokasi": "lokasi",
         "Gaji_Rata2": "gaji"
     })
-    pd_df_clean['judul_clean'] = pd_df_clean['judul'].str.lower()
-    pd_df_clean['lokasi_clean'] = pd_df_clean['lokasi'].str.lower()
-    pd_df_clean = pd_df_clean.dropna()
+    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.")
-    exit()
-
-# ==================================================
-# BAGIAN 6 (FINAL): DASHBOARD DENGAN DATABASE WILAYAH RESMI
-# ==================================================
-
-# ---------------------------------------------------------
-# A. PERSIAPAN MASTER DATA WILAYAH (Dari File CSV Baru)
-# ---------------------------------------------------------
-print("Sedang memproses Database Wilayah Indonesia...")
+    pd_df_clean = pd.DataFrame(columns=['judul_clean','lokasi_clean','gaji'])
 
-# 1. Baca Dataset Kabupaten/Kota
+# Load wilayah
+kamus_wilayah = {}
 try:
     geo_df = pd.read_csv('dataset kabupaten indonesia.csv')
-
-    # Rename kolom agar jelas: 'name' -> 'kota', 'Unnamed: 3' -> 'provinsi'
     geo_df = geo_df[['name', 'Unnamed: 3']].rename(columns={'name': 'kota', 'Unnamed: 3': 'provinsi'})
-
-    # Bersihkan Nama Kota (Hapus "KABUPATEN " dan "KOTA ") & Lowercase
-    # Contoh: "KABUPATEN ACEH BARAT" -> "aceh barat"
-    geo_df['kota_clean'] = geo_df['kota'].astype(str).str.replace('KABUPATEN ', '').str.replace('KOTA ', '').str.lower().str.strip()
+    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()
-
-    # Buat Kamus Pencarian (Dictionary)
-    # Format: {'aceh barat': 'ACEH', 'surabaya': 'JAWA TIMUR', ...}
     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("❌ ERROR: File 'dataset kabupaten indonesia.csv' tidak ditemukan. Upload dulu!")
+    print("❌ WARNING: File 'dataset kabupaten indonesia.csv' tidak ditemukan. Fitur deteksi lokasi manual masih bisa digunakan.")
     kamus_wilayah = {}
 
-# 2. Mapping Provinsi ke Pulau (Logic Tambahan)
 def get_pulau_from_provinsi(provinsi):
     p = provinsi.upper()
     if any(x in p for x in ['JAWA', 'DKI', 'BANTEN', 'YOGYAKARTA']): return "PULAU JAWA"
@@ -93,135 +81,141 @@ def get_pulau_from_provinsi(provinsi):
     if any(x in p for x in ['PAPUA', 'MALUKU']): return "PAPUA & MALUKU"
     return "INDONESIA (LAINNYA)"
 
-# ---------------------------------------------------------
-# B. FUNGSI CERDAS: DETEKSI LOKASI USER
-# ---------------------------------------------------------
 def deteksi_info_lokasi(input_user):
-    text = input_user.lower().strip()
-
-    # Cek apakah input user mengandung nama kota yang ada di database
-    provinsi_terdeteksi = "INDONESIA" # Default
-
+    text = str(input_user).lower().strip()
+    provinsi_terdeteksi = "INDONESIA"
     for kota_db, prov_db in kamus_wilayah.items():
-        # Jika user ngetik "Simeulue" dan di db ada "simeulue", maka ketemu!
         if kota_db in text:
             provinsi_terdeteksi = prov_db
             break
-
     pulau_terdeteksi = get_pulau_from_provinsi(provinsi_terdeteksi)
     return provinsi_terdeteksi, pulau_terdeteksi
 
-# ---------------------------------------------------------
-# C. FUNGSI ANALISIS UTAMA
-# ---------------------------------------------------------
+# ==============================
+# FUNGSI UTAMA: analisis_gaji_final
+# ==============================
 def analisis_gaji_final(judul_input, lokasi_input, model_choice):
-    # 1. Prediksi ML (Menggunakan Scikit-learn model)
-    model_pipeline = loaded_models[model_choice]
-
-    # Prepare input for scikit-learn pipeline (pandas DataFrame)
-    input_df = pd.DataFrame({
-        'judul_clean': [judul_input.lower()],
-        'lokasi_clean': [lokasi_input.lower()],
-        'perusahaan': ['unknown_company_for_prediction'] # Placeholder for 'perusahaan'
-    })
-
     try:
-        prediksi_user = model_pipeline.predict(input_df)[0]
-        # Ensure prediction is non-negative
-        prediksi_user = max(0, prediksi_user)
-    except Exception as e:
-        return f"<h1>⚠️ Error during prediction: {e}</h1>", None
-
-    # 2. Deteksi Wilayah Cerdas
-    provinsi_found, pulau_found = deteksi_info_lokasi(lokasi_input)
-
-    # 3. Logika Benchmark (Pembanding) - Menggunakan pd_df_clean
-    judul_lower = judul_input.lower()
-
-    # A. Max Gaji Pekerjaan (Nasional)
-    # Filter jobs where judul_clean contains the input judul_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 = filtered_jobs['gaji'].max()
-    else:
-        max_gaji_job = prediksi_user * 1.2 # Fallback if no matching jobs found
-
-    # B. Max Gaji Regional (Berdasarkan Pulau yang ditemukan)
-    keyword_pencarian = pulau_found.replace("PULAU ", "").lower() # Misal "jawa", "sumatera"
-    # Filter locations where lokasi_clean contains the keyword_pencarian
-    filtered_locations = pd_df_clean[pd_df_clean['lokasi_clean'].str.contains(keyword_pencarian, na=False)]
-    if not filtered_locations.empty:
-        max_gaji_region = filtered_locations['gaji'].max()
-    else:
-        max_gaji_region = prediksi_user * 1.5 # Fallback if no matching locations found
-
-    # 4. Visualisasi Matplotlib
-    plt.style.use('seaborn-v0_8-whitegrid')
-    fig, ax = plt.subplots(figsize=(10, 5.5))
-
-    labels = [f"Estimasi Anda\n({lokasi_input})", f"Max Posisi '{judul_input}'\n(Nasional)", f"Max Regional\n({pulau_found})"]
-    values = [prediksi_user, max_gaji_job, max_gaji_region]
-    colors = ['#0ea5e9', '#94a3b8', '#f59e0b'] # Biru Langit, Abu, Oranye
-
-    bars = ax.bar(labels, values, color=colors, edgecolor='black', alpha=0.9)
-
-    # Garis referensi gaji user
-    ax.axhline(y=prediksi_user, color='#0ea5e9', linestyle='--', linewidth=2, label="Posisi Anda")
-
-    for bar in bars:
-        height = bar.get_height()
-        ax.text(bar.get_x() + bar.get_width()/2., height + (height*0.015),
-                 f'Rp {height/1000000:.1f} Jt',
-                 ha='center', va='bottom', fontweight='bold', fontsize=11)
-
-    ax.set_title(f"Analisis Gaji: {judul_input} @ {provinsi_found} (Model: {model_choice}) ", fontsize=14, fontweight='bold', pad=15)
-    ax.set_ylabel("Gaji (Rupiah)")
-    ax.grid(axis='y', linestyle='--', alpha=0.5)
-
-    # 5. Generate Output HTML
-    html_output = f"""
-    <div style="font-family: sans-serif; padding: 20px; border: 1px solid #e2e8f0; border-radius: 12px; background: linear-gradient(to right, #f8fafc, #ffffff);">
-        <h2 style="color: #0f172a; margin-bottom: 5px;">💰 Estimasi: Rp {int(prediksi_user):,.0f}</h2>
-        <span style="background-color: #e0f2fe; color: #0369a1; padding: 4px 10px; border-radius: 20px; font-size: 0.85em; font-weight: bold;">
-            📍 {provinsi_found} / {pulau_found}
-        </span>
-        <p style="margin-top: 15px; color: #475569; line-height: 1.5;">
-            Sistem mendeteksi lokasi Anda berada di provinsi <b>{provinsi_found}</b>.
-            Berdasarkan data historis, standar gaji pasar untuk <b>{judul_input}</b> di wilayah ini adalah seperti di atas.
-        </p>
-        <div style="margin-top: 15px; padding: 10px; background-color: #fff7ed; border-left: 4px solid #f97316; color: #9a3412; font-size: 0.9em;">
-            💡 <b>Insight Regional:</b> Batas atas gaji tertinggi (semua sektor) di {pulau_found} tercatat mencapai <b>Rp {int(max_gaji_region):,.0f}</b>.
+        # 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 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))
+        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>
         </div>
-    </div>
-    """
-
-    return html_output, fig
-
-# ---------------------------------------------------------
-# D. INTERFACE GRADIO
-# ---------------------------------------------------------
-theme = gr.themes.Soft(primary_hue="cyan", secondary_hue="slate")
-
-with gr.Blocks(theme=theme, title="Salary AI") as demo:
-    gr.Markdown("# 🇮🇩 AI Salary Predictor & Geo-Intelligence")
-    gr.Markdown("Prediksi gaji menggunakan Scikit-learn Models + Database Wilayah BPS Indonesia.")
-
-    with gr.Row():
-        with gr.Column():
-            t1 = gr.Textbox(label="Posisi Pekerjaan", placeholder="Contoh: Guru, Driver, Manager")
-            t2 = gr.Textbox(label="Kabupaten / Kota", placeholder="Contoh: Simeulue, Surakarta, Malang")
-            model_selector = gr.Dropdown(
-                label="Pilih Model Prediksi",
-                choices=list(loaded_models.keys()),
-                value='Decision Tree' # Default selected model
-            )
-            btn = gr.Button("🔍 Analisis Sekarang", variant="primary")
-        with gr.Column():
-            out_html = gr.HTML(label="Hasil Analisis")
-
-    out_plot = gr.Plot(label="Grafik Komparasi")
+        """
+        plt.tight_layout()
+        return html_output, 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; }
+"""
+
+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])
 
-print("Menjalankan Aplikasi Final...")
-demo.launch(share=True, debug=True)
+if __name__ == "__main__":
+    print("Menjalankan Aplikasi Final...")
+    demo.launch(share=True, debug=True)