scripts/test_basic.py

#!/usr/bin/env python3
"""
Simple test that only tests data loading and GPU monitoring without model downloads
"""

import sys
import os
sys.path.append('src')

def test_data_only():
    """Test only data loading functionality"""
    try:
        import pandas as pd
        from tevatron.utils.gpu_monitor import GPUMemoryMonitor
        
        print("Testing data loading...")
        df = pd.read_csv("data/the_vault/DOC_VAULT_train.tsv", sep='\t', nrows=5)
        print(f"Loaded {len(df)} samples")
        print(f"Columns: {list(df.columns)}")
        
        print("Testing GPU monitor...")
        monitor = GPUMemoryMonitor(memory_threshold=0.8, check_interval=10)
        stats = monitor.get_memory_stats()
        print(f"GPU monitor initialized: {stats}")
        
        print("Testing tevatron imports...")
        from tevatron.arguments import GLENP1ModelArguments, GLENP1DataArguments
        print("Arguments imported successfully")
        
        print("Basic functionality test PASSED!")
        return True
        
    except Exception as e:
        print(f"Test failed: {e}")
        import traceback
        traceback.print_exc()
        return False

if __name__ == "__main__":
    success = test_data_only()
    sys.exit(0 if success else 1)