test_paper_classifier.py

#!/usr/bin/env python3
"""
Test script for paper type classifier
"""




import sys
import os
sys.path.append(os.path.dirname(os.path.abspath(__file__))) 

from autoreview.paper_type_classifier import PaperTypeClassifier

os.environ['OPENAI_API_KEY'] = 'sk-Aors1iVXAbgd7sGwC9Ff781c75D14b74A71d4e63F1E46b68'
os.environ['OPENAI_BASEURL'] = 'https://api2.aigcbest.top/v1'

def test_paper_classifier():
    """Test the paper type classifier with sample content."""
    
    # Sample paper contents for testing
    test_cases = [
        {
            "content": "We propose a novel deep learning framework for natural language processing. Our approach introduces a new attention mechanism that significantly improves performance on benchmark datasets.",
            "expected": "Technical Paper"
        },
        {
            "content": "This survey provides a comprehensive overview of recent advances in computer vision. We review over 100 papers published in the last five years and present a taxonomy of current approaches.",
            "expected": "Survey Paper"
        },
        {
            "content": "We present a case study of deploying machine learning models in a real-world healthcare setting. Our application demonstrates the practical challenges and solutions for clinical decision support systems.",
            "expected": "Application Paper"
        },
        {
            "content": "We introduce a new dataset of 10,000 annotated medical images for disease classification. The dataset includes detailed annotations and is publicly available for research purposes.",
            "expected": "Dataset Paper"
        },
        {
            "content": "We release an open-source software tool for bioinformatics analysis. The tool provides a user-friendly interface and comprehensive documentation for researchers.",
            "expected": "Tool Paper"
        }
    ]
    
    classifier = PaperTypeClassifier()
    
    print("Testing Paper Type Classifier...")
    print("=" * 50)
    
    for i, test_case in enumerate(test_cases, 1):
        print(f"\nTest Case {i}:")
        print(f"Expected: {test_case['expected']}")
        
        # Test keyword-based classification
        keyword_result = classifier.classify_with_keywords(test_case['content'])
        print(f"Keyword-based: {keyword_result}")
        
        # Test LLM-based classification (if available)
        try:
            llm_result = classifier.classify_with_llm(test_case['content'])
            print(f"LLM-based: {llm_result}")
        except Exception as e:
            print(f"LLM-based: Error - {e}")
        
        print("-" * 30)

if __name__ == "__main__":
    test_paper_classifier()