Delete test_sentiment.py

test_sentiment.py

@@ -1,152 +0,0 @@
-"""
-Test Script untuk Sentiment Analysis System
-Menguji fungsionalitas model dan evaluasi
-"""
-
-import sys
-from app import SentimentAnalyzer, SAMPLE_DATA
-
-def test_single_analysis():
-    """Test analisis single text"""
-    print("\n" + "="*60)
-    print("TEST 1: Single Text Analysis")
-    print("="*60)
-    
-    analyzer = SentimentAnalyzer()
-    
-    test_cases = [
-        "Bantuan sangat lambat, sudah 3 hari belum ada makanan!",
-        "Terima kasih banyak atas bantuan yang cepat",
-        "Kapan bantuan akan tiba di lokasi kami?",
-        "Hadeh parah banget pelayanannya gak jelas!",
-        "Mantap jiwa pelayanannya cepet banget"
-    ]
-    
-    for i, text in enumerate(test_cases, 1):
-        print(f"\n{i}. Text: {text}")
-        result = analyzer.analyze(text)
-        print(f"   Kategori: {result['kategori']}")
-        print(f"   Confidence: {result['confidence']:.2%}")
-        print(f"   Level: {result['confidence_level']}")
-        print(f"   Interpretasi: {result['interpretation']}")
-    
-    print("\n✅ Test 1 PASSED")
-
-def test_batch_analysis():
-    """Test analisis batch texts"""
-    print("\n" + "="*60)
-    print("TEST 2: Batch Analysis")
-    print("="*60)
-    
-    analyzer = SentimentAnalyzer()
-    
-    texts = [
-        "Posko pengungsian penuh sekali!",
-        "Alhamdulillah bantuan sudah sampai",
-        "Bagaimana cara mendaftar bantuan?"
-    ]
-    
-    results = analyzer.batch_analyze(texts)
-    
-    print(f"\nJumlah teks: {len(texts)}")
-    for i, (text, result) in enumerate(zip(texts, results), 1):
-        print(f"\n{i}. {text}")
-        print(f"   → {result['kategori']} ({result['confidence']:.1%})")
-    
-    print("\n✅ Test 2 PASSED")
-
-def test_evaluation():
-    """Test evaluasi model"""
-    print("\n" + "="*60)
-    print("TEST 3: Model Evaluation")
-    print("="*60)
-    
-    analyzer = SentimentAnalyzer()
-    
-    eval_results = analyzer.evaluate_model(
-        SAMPLE_DATA['texts'],
-        SAMPLE_DATA['labels']
-    )
-    
-    print(f"\nAccuracy: {eval_results['accuracy']:.2%}")
-    print(f"Total samples: {len(SAMPLE_DATA['texts'])}")
-    print(f"Classes: {', '.join(eval_results['labels'])}")
-    
-    # Per-class metrics
-    report = eval_results['classification_report']
-    print("\nPer-class Metrics:")
-    for label in eval_results['labels']:
-        if label in report:
-            print(f"\n{label}:")
-            print(f"  Precision: {report[label]['precision']:.3f}")
-            print(f"  Recall: {report[label]['recall']:.3f}")
-            print(f"  F1-Score: {report[label]['f1-score']:.3f}")
-    
-    print("\n✅ Test 3 PASSED")
-
-def test_slang_handling():
-    """Test kemampuan menangani slang Indonesia"""
-    print("\n" + "="*60)
-    print("TEST 4: Slang & Informal Language Handling")
-    print("="*60)
-    
-    analyzer = SentimentAnalyzer()
-    
-    slang_tests = [
-        ("Hadeh parah banget nih pelayanan lambat bgt!", "NEGATIVE"),
-        ("Mantap jiwa pelayanannya, keren abis!", "POSITIVE"),
-        ("Gimana sih cara daftar bantuan?", "NEUTRAL"),
-        ("Gak jelas banget nih, ribet!", "NEGATIVE"),
-        ("Josss gandos pelayanannya!", "POSITIVE")
-    ]
-    
-    correct = 0
-    for text, expected in slang_tests:
-        result = analyzer.analyze(text)
-        predicted = result['label']
-        status = "✅" if predicted == expected else "❌"
-        
-        print(f"\n{status} Text: {text}")
-        print(f"   Expected: {expected}, Got: {predicted} ({result['confidence']:.1%})")
-        
-        if predicted == expected:
-            correct += 1
-    
-    accuracy = correct / len(slang_tests)
-    print(f"\n📊 Slang Handling Accuracy: {accuracy:.1%} ({correct}/{len(slang_tests)})")
-    
-    if accuracy >= 0.6:
-        print("✅ Test 4 PASSED (Good slang handling)")
-    else:
-        print("⚠️  Test 4 WARNING (Moderate slang handling)")
-
-def run_all_tests():
-    """Jalankan semua tests"""
-    print("\n" + "="*60)
-    print("🧪 SENTIMENT ANALYSIS SYSTEM - COMPREHENSIVE TESTS")
-    print("="*60)
-    print("Model: w11wo/indonesian-roberta-base-sentiment-classifier")
-    print("="*60)
-    
-    try:
-        test_single_analysis()
-        test_batch_analysis()
-        test_evaluation()
-        test_slang_handling()
-        
-        print("\n" + "="*60)
-        print("🎉 ALL TESTS COMPLETED SUCCESSFULLY!")
-        print("="*60)
-        print("\n✅ Sistem siap digunakan untuk production")
-        print("✅ Model dapat menangani berbagai jenis teks Indonesia")
-        print("✅ Evaluasi menunjukkan performa yang baik")
-        print("\n💡 Jalankan 'python sentiment_app.py' untuk memulai aplikasi")
-        
-    except Exception as e:
-        print(f"\n❌ TEST FAILED: {str(e)}")
-        import traceback
-        traceback.print_exc()
-        sys.exit(1)
-
-if __name__ == "__main__":
-    run_all_tests()