#!/usr/bin/env python3
"""Reproduce the headline calculations from the published CSV ledger."""
from pathlib import Path
import csv

csv_path = Path(__file__).resolve().parents[1] / "data" / "testosterone-long-duration-rct-ledger-2026.csv"
with csv_path.open(newline="", encoding="utf-8") as f:
    rows = list(csv.DictReader(f))

n = {row["trial"]: int(row["randomized_n"]) for row in rows}
total = sum(n.values())
traverse = n["TRAVERSE"]
other = total - traverse
top_three = sum(sorted(n.values(), reverse=True)[:3])

assert len(rows) == 11
assert total == 9249
assert traverse == 5246
assert other == 4003
assert traverse - other == 1243
assert top_three == 7043
assert round(traverse / total * 100, 1) == 56.7
assert round(top_three / total * 100, 1) == 76.1

print(f"Trials: {len(rows)}")
print(f"Randomized men: {total:,}")
print(f"TRAVERSE: {traverse:,} ({traverse / total * 100:.1f}%)")
print(f"Other 10 trials: {other:,}")
print(f"TRAVERSE minus other 10: {traverse - other:,}")
print(f"Three largest trials: {top_three:,} ({top_three / total * 100:.1f}%)")