import csv

def check_nodes(filename, label):
    nodes_list = []
    durations = []
    with open(filename, 'r') as f:
        reader = csv.reader(f)
        next(reader)
        for row in reader:
            if not row or row[0].startswith('#'):
                continue
            try:
                nodes_list.append(int(row[3]))
                durations.append(int(row[1]))
            except:
                pass
    
    print(f"\n=== {label} NODES EXPANDED ===")
    print(f"Total paths: {len(nodes_list)}")
    
    # Group by node count
    node_buckets = [(0, 0), (1, 64), (65, 200), (201, 500), (501, 1000), (1001, 10000)]
    for lo, hi in node_buckets:
        count = sum(1 for n in nodes_list if lo <= n <= hi)
        pct = 100*count/len(nodes_list) if nodes_list else 0
        print(f"  {lo}-{hi if hi < 10000 else 'inf'} nodes: {count} ({pct:.1f}%)")
    
    # Show duration correlation with nodes
    print("\nDuration by node count:")
    for lo, hi in [(1, 64), (65, 200), (201, 500), (501, 1000), (1001, 10000)]:
        subset_durations = [d for n, d in zip(nodes_list, durations) if lo <= n <= hi]
        if subset_durations:
            avg = sum(subset_durations) / len(subset_durations)
            print(f"  {lo}-{hi if hi < 10000 else 'inf'} nodes: avg {avg:.0f}µs, count {len(subset_durations)}")

check_nodes("pathfinding_benchmark_current.csv", "CURRENT")