show_ranking_results.py

#!/usr/bin/env python3
"""Display ranking results in readable format"""

import json

with open('test_results_option_b.json') as f:
    data = json.load(f)

print('=' * 80)
print('WHAT WAS RANKED - FULL BREAKDOWN')
print('=' * 80)
print()
print(f"Total Trials Found: {data['results']['total_found']}")
print(f"Trials Ranked by 355M: {data['benchmarking']['trials_ranked_by_355m']}")
print(f"355M Ranking Time: {data['benchmarking']['355m_ranking_time']:.1f}s ({data['benchmarking']['355m_ranking_time']/60:.1f} minutes)")
print()

print('TOP 5 TRIALS (After 355M Perplexity Ranking):')
print('-' * 80)
print()

for trial in data['trials'][:5]:
    rank_after = trial['scoring']['rank_after_355m']
    rank_before = trial['scoring']['rank_before_355m']

    print(f"Rank #{rank_after}: {trial['nct_id']}")
    print(f"  Title: {trial.get('title', 'No title')}")
    print()
    print(f"  📊 SCORES:")
    print(f"     Hybrid Score (RAG):    {trial['scoring']['hybrid_score']:.4f} ({trial['scoring']['hybrid_score']*100:.1f}%)")

    if trial['scoring']['perplexity']:
        print(f"     Perplexity (355M):     {trial['scoring']['perplexity']:.2f} (lower = better)")
        print(f"     Perplexity Score:      {trial['scoring']['perplexity_score']:.4f} ({trial['scoring']['perplexity_score']*100:.1f}%)")

    print(f"     Combined Score:        {trial['scoring']['relevance_score']:.4f} ({trial['scoring']['relevance_score']*100:.1f}%)")
    print()

    if rank_before != rank_after:
        if rank_before > rank_after:
            print(f"  📈 Rank Change: {rank_before} → {rank_after} ⬆️ IMPROVED by {rank_before - rank_after} position(s)!")
        else:
            print(f"  📉 Rank Change: {rank_before} → {rank_after} ⬇️ Dropped by {rank_after - rank_before} position(s)")
    else:
        print(f"  ➡️  Rank Change: {rank_before} → {rank_after} (No change)")

    print()
    print(f"  🔗 URL: https://clinicaltrials.gov/study/{trial['nct_id']}")
    print()
    print('-' * 80)
    print()

print()
print('📊 RANKING IMPACT SUMMARY:')
print('-' * 80)
print(f"  Average rank change: {data['benchmarking']['average_rank_change']:.1f} positions")
print(f"  Max rank improvement: {data['benchmarking']['max_rank_improvement']} position(s)")
print()
print(f"  Top 3 Perplexity Scores:")
for i, perp in enumerate(data['benchmarking']['top_3_perplexity_scores'], 1):
    print(f"    {i}. {perp:.2f} (lower = more relevant)")
print()