hakmem/analyze_final.py

#!/usr/bin/env python3
"""
analyze_final.py - Final analysis with jemalloc/mimalloc
"""

import csv
import sys
from collections import defaultdict
import statistics

def load_results(filename):
    """Load CSV results"""
    data = defaultdict(lambda: defaultdict(list))
    
    with open(filename, 'r') as f:
        reader = csv.DictReader(f)
        for row in reader:
            allocator = row['allocator']
            scenario = row['scenario']
            avg_ns = int(row['avg_ns'])
            soft_pf = int(row['soft_pf'])
            
            data[scenario][allocator].append({
                'avg_ns': avg_ns,
                'soft_pf': soft_pf,
            })
    
    return data

def analyze(data):
    """Analyze with 5 allocators"""
    print("=" * 100)
    print("🔥 FINAL BATTLE: hakmem vs system vs jemalloc vs mimalloc (50 runs)")
    print("=" * 100)
    print()
    
    for scenario in ['json', 'mir', 'vm', 'mixed']:
        print(f"## {scenario.upper()} Scenario")
        print("-" * 100)
        
        allocators = ['hakmem-baseline', 'hakmem-evolving', 'system', 'jemalloc', 'mimalloc']
        
        # Header
        print(f"{'Allocator':<20} {'Median (ns)':<15} {'P95 (ns)':<15} {'P99 (ns)':<15} {'vs Best':<15}")
        print("-" * 100)
        
        results = {}
        for allocator in allocators:
            if allocator not in data[scenario]:
                continue
                
            latencies = [r['avg_ns'] for r in data[scenario][allocator]]
            
            if not latencies:
                continue
                
            median_ns = statistics.median(latencies)
            p95_ns = statistics.quantiles(latencies, n=20)[18] if len(latencies) >= 20 else max(latencies)
            p99_ns = statistics.quantiles(latencies, n=100)[98] if len(latencies) >= 100 else max(latencies)
            
            results[allocator] = median_ns
        
        # Find winner
        if results:
            best_allocator = min(results, key=results.get)
            best_time = results[best_allocator]
            
            for allocator in allocators:
                if allocator not in results:
                    continue
                    
                median_ns = results[allocator]
                latencies = [r['avg_ns'] for r in data[scenario][allocator]]
                p95_ns = statistics.quantiles(latencies, n=20)[18] if len(latencies) >= 20 else max(latencies)
                p99_ns = statistics.quantiles(latencies, n=100)[98] if len(latencies) >= 100 else max(latencies)
                
                if allocator == best_allocator:
                    vs_best = "🥇 WINNER"
                else:
                    slowdown_pct = ((median_ns - best_time) / best_time) * 100
                    vs_best = f"+{slowdown_pct:.1f}%"
                
                print(f"{allocator:<20} {median_ns:<15.1f} {p95_ns:<15.1f} {p99_ns:<15.1f} {vs_best:<15}")
        
        print()
    
    # Overall summary
    print("=" * 100)
    print("📊 OVERALL SUMMARY")
    print("=" * 100)
    
    overall_scores = defaultdict(int)
    
    for scenario in ['json', 'mir', 'vm', 'mixed']:
        allocators = ['hakmem-baseline', 'hakmem-evolving', 'system', 'jemalloc', 'mimalloc']
        results = {}
        
        for allocator in allocators:
            if allocator in data[scenario] and data[scenario][allocator]:
                latencies = [r['avg_ns'] for r in data[scenario][allocator]]
                results[allocator] = statistics.median(latencies)
        
        if results:
            sorted_allocators = sorted(results.items(), key=lambda x: x[1])
            
            for rank, (allocator, _) in enumerate(sorted_allocators):
                points = len(sorted_allocators) - rank
                overall_scores[allocator] += points
    
    print("\nPoints System (5 points for 1st, 4 for 2nd, etc.):\n")
    sorted_scores = sorted(overall_scores.items(), key=lambda x: x[1], reverse=True)
    
    for rank, (allocator, points) in enumerate(sorted_scores, 1):
        medal = "🥇" if rank == 1 else "🥈" if rank == 2 else "🥉" if rank == 3 else "  "
        print(f"{medal} #{rank}: {allocator:<20} {points} points")
    
    print()

if __name__ == '__main__':
    if len(sys.argv) != 2:
        print(f"Usage: {sys.argv[0]} <results.csv>")
        sys.exit(1)
    
    data = load_results(sys.argv[1])
    analyze(data)