test_local.py

"""
Test application locally before deploying
"""

import os
import sys

print("="*70)
print("LOCAL TEST - Speech Emotion Recognition")
print("="*70)

# ============================================================================
# 1. CHECK FILES
# ============================================================================
print("\n1️⃣ Checking required files...")

required_files = [
    'app.py',
    'requirements.txt',
    'README.md',
    'src/__init__.py',
    'src/feature_extraction.py',
    'src/ensemble_model.py',
    'src/utils.py',
    'weights/xgboost_model.pkl',
    'weights/lightgbm_model.pkl',
    'weights/gradientboost_model.pkl',
    'weights/adaboost_model.pkl',
    'weights/scaler.pkl',
    'weights/label_encoder.pkl',
    'weights/config.json'
]

missing_files = []
for file in required_files:
    if os.path.exists(file):
        print(f"   ✓ {file}")
    else:
        print(f"   ✗ {file} - MISSING")
        missing_files.append(file)

if missing_files:
    print(f"\n❌ Missing {len(missing_files)} files. Please create them first.")
    sys.exit(1)

# ============================================================================
# 2. TEST IMPORTS
# ============================================================================
print("\n2️⃣ Testing imports...")

try:
    import numpy
    print("   ✓ numpy")
except:
    print("   ✗ numpy - Install: pip install numpy")

try:
    import pandas
    print("   ✓ pandas")
except:
    print("   ✗ pandas - Install: pip install pandas")

try:
    import sklearn
    print("   ✓ scikit-learn")
except:
    print("   ✗ scikit-learn - Install: pip install scikit-learn")

try:
    import xgboost
    print("   ✓ xgboost")
except:
    print("   ✗ xgboost - Install: pip install xgboost")

try:
    import lightgbm
    print("   ✓ lightgbm")
except:
    print("   ✗ lightgbm - Install: pip install lightgbm")

try:
    import librosa
    print("   ✓ librosa")
except:
    print("   ✗ librosa - Install: pip install librosa")

try:
    import gradio
    print("   ✓ gradio")
except:
    print("   ✗ gradio - Install: pip install gradio")

# ============================================================================
# 3. TEST MODEL LOADING
# ============================================================================
print("\n3️⃣ Testing model loading...")

try:
    from src.ensemble_model import EnsembleEmotionRecognizer
    
    model = EnsembleEmotionRecognizer(weights_dir='weights')
    print("   ✓ Model loaded successfully")
    
    # Get model info
    info = model.get_model_info()
    print(f"   ✓ Models: {', '.join(info['models'])}")
    print(f"   ✓ Features: {info['n_features_selected']}/{info['n_features_total']}")
    print(f"   ✓ Emotions: {', '.join(info['emotions'])}")
    
except Exception as e:
    print(f"   ✗ Error loading model: {e}")
    sys.exit(1)

# ============================================================================
# 4. TEST FEATURE EXTRACTION
# ============================================================================
print("\n4️⃣ Testing feature extraction...")

try:
    from src.feature_extraction import extract_features
    import numpy as np
    
    # Create dummy audio
    import librosa
    y = np.random.randn(22050 * 3)  # 3 seconds of random audio
    
    # Save to temp file
    import soundfile as sf
    sf.write('temp_test.wav', y, 22050)
    
    # Extract features
    features, _, _ = extract_features('temp_test.wav')
    print(f"   ✓ Features extracted: shape {features.shape}")
    
    # Test prediction
    prediction = model.predict(features)
    print(f"   ✓ Prediction works: {model.decode_emotion(prediction[0])}")
    
    # Cleanup
    os.remove('temp_test.wav')
    
except Exception as e:
    print(f"   ✗ Error in feature extraction: {e}")
    sys.exit(1)

# ============================================================================
# 5. FILE SIZES
# ============================================================================
print("\n5️⃣ Checking file sizes...")

total_size = 0
for file in required_files:
    if os.path.exists(file):
        size = os.path.getsize(file) / 1024 / 1024  # MB
        total_size += size
        if size > 10: