code/benchmarks/calculate_rankings.py

import pandas as pd
import numpy as np

TASKS = ['domain', 'kingdom', 'phylum', 'class', 'order', 'family', 'genus', 'species', 'immunogenicity', 'link']

for dataset in ['strict', 'strict_3']:
    print(f"\n{'='*80}")
    print(f"DATASET: {dataset.upper()}")
    print(f"{'='*80}")
    
    df = pd.read_csv(f'benchmark_comparison_{dataset}.csv', index_col=0)
    
    # Calculate ranks per task (higher accuracy = rank 1)
    ranks = df.rank(ascending=False, method='min')
    
    # Calculate mean rank
    mean_ranks = ranks.mean(axis=1).sort_values()
    
    # Display sorted by accuracy per task
    print("\n📊 ACCURACY BY TASK (sorted by mean rank):")
    print("-"*100)
    
    # Sort by mean rank
    df['Mean_Rank'] = mean_ranks
    df_sorted = df.sort_values('Mean_Rank')
    
    # Format nicely
    for col in df_sorted.columns:
        if col != 'Mean_Rank':
            df_sorted[col] = df_sorted[col].apply(lambda x: f"{x*100:.1f}%" if pd.notnull(x) else "-")
        else:
            df_sorted[col] = df_sorted[col].apply(lambda x: f"{x:.2f}")
    
    print(df_sorted.to_string())
    
    print("\n\n🏆 RANKINGS BY TASK:")
    print("-"*100)
    for task in TASKS:
        if task in df.columns:
            task_ranks = df[task].sort_values(ascending=False)
            print(f"\n{task.upper():15} | ", end="")
            for i, (model, acc) in enumerate(task_ranks.items(), 1):
                if isinstance(acc, str):
                    acc_val = float(acc.replace('%', ''))/100
                else:
                    acc_val = acc
                print(f"#{i}: {model}({acc_val*100:.1f}%) ", end="")
    
    print("\n\n\n📈 MEAN RANK SUMMARY:")
    print("-"*50)
    for model, rank in mean_ranks.items():
        print(f"  {model:20} : {rank:.2f}")
        
    # Determine winner
    winner = mean_ranks.idxmin()
    print(f"\n🥇 BEST MODEL (lowest mean rank): {winner} ({mean_ranks[winner]:.2f})")