disco/pipeline/utils/combine_keywords.py

"""
Compare and combine keyword identification methods.
"""

import json

def combine_keywords(semantic_results, llm_results):
    """Combine keywords from both methods"""
    combined = {}
    for criterion_num_str in semantic_results["criteria"].keys():
        criterion_num = int(criterion_num_str)
        semantic_kws = set(kw["word"] for kw in semantic_results["criteria"][criterion_num_str]["keywords"])
        llm_kws = set(llm_results["criteria"][criterion_num_str]["keywords"])
        combined[criterion_num] = sorted(list(semantic_kws | llm_kws))
    return combined

def analyze_overlap(semantic_results, llm_results):
    """Analyze overlap between methods"""
    print("\nKEYWORD METHOD COMPARISON")
    for criterion_num_str in semantic_results["criteria"].keys():
        criterion_num = int(criterion_num_str)
        semantic_kws = set(kw["word"] for kw in semantic_results["criteria"][criterion_num_str]["keywords"])
        llm_kws = set(llm_results["criteria"][criterion_num_str]["keywords"])
        overlap = semantic_kws & llm_kws
        print(f"Criterion {criterion_num}: {len(overlap)} overlap, {len(semantic_kws | llm_kws)} total")