scripts/compare_tennessee_plays.py

#!/usr/bin/env python3
"""Compare Tennessee benchmark vs current FFmpeg output to identify missing plays."""

import json
import logging
from pathlib import Path

logging.basicConfig(level=logging.INFO, format="%(message)s")
logger = logging.getLogger(__name__)


def load_json(path: str) -> dict:
    """Load a JSON file."""
    with open(path, "r") as f:
        return json.load(f)


def find_matching_play(play: dict, play_list: list, tolerance: float = 2.0) -> dict | None:
    """Find a matching play in the list based on start_time proximity."""
    for p in play_list:
        if abs(p["start_time"] - play["start_time"]) <= tolerance:
            return p
    return None


def main():
    # Load both outputs
    benchmark_path = Path("output/benchmarks/v6_baseline.json")
    current_path = Path("output/OSU_vs_Tenn_12_21_24_plays.json")

    benchmark = load_json(benchmark_path)
    current = load_json(current_path)

    benchmark_plays = benchmark["plays"]
    current_plays = current["plays"]

    logger.info("=" * 80)
    logger.info("TENNESSEE PLAY COMPARISON: Benchmark vs FFmpeg")
    logger.info("=" * 80)
    logger.info(f"\nBenchmark plays: {len(benchmark_plays)}")
    logger.info(f"Current plays:   {len(current_plays)}")
    logger.info(f"Difference:      {len(benchmark_plays) - len(current_plays)}")

    # Compare play type distributions
    logger.info("\n" + "-" * 40)
    logger.info("PLAY TYPE COMPARISON")
    logger.info("-" * 40)

    benchmark_types = benchmark["stats"]["play_types"]
    current_types = current["stats"]["play_types"]

    logger.info(f"{'Type':<15} {'Benchmark':<12} {'Current':<12} {'Diff':<10}")
    for ptype in set(list(benchmark_types.keys()) + list(current_types.keys())):
        b_count = benchmark_types.get(ptype, 0)
        c_count = current_types.get(ptype, 0)
        diff = b_count - c_count
        logger.info(f"{ptype:<15} {b_count:<12} {c_count:<12} {diff:+d}")

    # Find plays in benchmark that are missing from current
    logger.info("\n" + "-" * 40)
    logger.info("PLAYS IN BENCHMARK BUT MISSING FROM CURRENT")
    logger.info("-" * 40)

    missing_plays = []
    for bp in benchmark_plays:
        match = find_matching_play(bp, current_plays, tolerance=3.0)
        if match is None:
            missing_plays.append(bp)

    logger.info(f"\nFound {len(missing_plays)} missing plays:\n")
    for p in missing_plays:
        logger.info(f"  Play #{p['play_number']:3d}: {p['start_time']:7.1f}s - {p['end_time']:7.1f}s")
        logger.info(f"            Type: {p['play_type']}, Method: {p['start_method']}")
        logger.info(f"            Duration: {p['duration']:.1f}s, Clock: {p.get('start_clock_value')} -> {p.get('end_clock_value')}")
        logger.info("")

    # Group missing plays by type
    logger.info("-" * 40)
    logger.info("MISSING PLAYS BY TYPE")
    logger.info("-" * 40)
    missing_by_type = {}
    for p in missing_plays:
        ptype = p["play_type"]
        if ptype not in missing_by_type:
            missing_by_type[ptype] = []
        missing_by_type[ptype].append(p)

    for ptype, plays in sorted(missing_by_type.items()):
        logger.info(f"\n{ptype.upper()} plays missing: {len(plays)}")
        for p in plays:
            logger.info(f"  - #{p['play_number']}: {p['start_time']:.1f}s (method: {p['start_method']})")

    # Find plays in current that don't exist in benchmark (extra plays)
    logger.info("\n" + "-" * 40)
    logger.info("PLAYS IN CURRENT BUT NOT IN BENCHMARK (extras)")
    logger.info("-" * 40)

    extra_plays = []
    for cp in current_plays:
        match = find_matching_play(cp, benchmark_plays, tolerance=3.0)
        if match is None:
            extra_plays.append(cp)

    if extra_plays:
        logger.info(f"\nFound {len(extra_plays)} extra plays:\n")
        for p in extra_plays:
            logger.info(f"  Play #{p['play_number']:3d}: {p['start_time']:7.1f}s - {p['end_time']:7.1f}s")
            logger.info(f"            Type: {p['play_type']}, Method: {p['start_method']}")
    else:
        logger.info("\nNo extra plays found (current is a subset of benchmark)")

    # Check first play difference - benchmark starts at ~121s, current starts at ~180s
    logger.info("\n" + "-" * 40)
    logger.info("FIRST FEW PLAYS COMPARISON")
    logger.info("-" * 40)
    logger.info("\nBenchmark first 5 plays:")
    for p in benchmark_plays[:5]:
        logger.info(f"  #{p['play_number']}: {p['start_time']:.1f}s - {p['play_type']} ({p['start_method']})")

    logger.info("\nCurrent first 5 plays:")
    for p in current_plays[:5]:
        logger.info(f"  #{p['play_number']}: {p['start_time']:.1f}s - {p['play_type']} ({p['start_method']})")


if __name__ == "__main__":
    main()