"""Fast optimization using random search.""" import json import random from pathlib import Path import sys sys.path.insert(0, '/home/brettanthonysjoberg179/trifecta-bro-hf-space') from trifecta_bro.data.models import RaceModel, RunnerModel from trifecta_bro.model.scoring import score_runner from trifecta_bro.model.pace_analysis import classify_pace from trifecta_bro.model.distance_profiles import classify_distance DATA_DIR = Path('/home/brettanthonysjoberg179/trifecta-bro-hf-space/data') CACHE_DIR = DATA_DIR / 'cache' RESULTS_DIR = DATA_DIR / 'results' random.seed(42) def load_cached_races(date: str) -> list[dict]: races = [] for f in CACHE_DIR.glob('*.json'): try: with open(f) as fp: data = json.load(fp) if data.get('date') == date: races.append(data) except: continue return races def load_results(date: str) -> dict: result_lookup = {} result_path = RESULTS_DIR / f"{date}-ra.json" if not result_path.exists(): result_path = RESULTS_DIR / f"{date}.json" if not result_path.exists(): return result_lookup with open(result_path) as f: rdata = json.load(f) if isinstance(rdata, dict): if 'tracks' in rdata: for track, races in rdata['tracks'].items(): if isinstance(races, dict): for rn, r in races.items(): runners = r.get('runners', []) winners = [] for runner in runners: pos = runner.get('position') if pos and pos <= 3: winners.append((pos, runner['number'])) winners.sort() actual = [w[1] for w in winners] if actual: result_lookup[(track, int(rn))] = actual elif isinstance(races, list): for r in races: if 'trifecta' in r: result_lookup[(track, r.get('race', 0))] = [int(str(x).replace('e','')) for x in r['trifecta']] else: for track, races in rdata.items(): if isinstance(races, list): for r in races: if 'trifecta' in r: result_lookup[(track, r['race'])] = [int(str(x).replace('e','')) for x in r['trifecta']] return result_lookup def score_race(race_data: dict, weights: dict) -> list[int] | None: try: runners = [] for r in race_data.get('runners', []): if r.get('scratched'): continue runner = RunnerModel( number=r['number'], name=r.get('name', ''), jockey=r.get('jockey'), trainer=r.get('trainer'), weight=r.get('weight'), barrier=r.get('barrier'), age=r.get('age'), sex=r.get('sex'), form=r.get('form', ''), last20_starts=r.get('last20Starts', ''), stats=r.get('stats', {}), ) runners.append(runner) if len(runners) < 3: return None race = RaceModel( date=race_data.get('date', ''), track=race_data.get('track', ''), track_slug=race_data.get('slug', race_data.get('track', '').lower()), race_number=race_data.get('raceNumber', 0), race_name=race_data.get('raceName', ''), distance=race_data.get('distance'), condition=race_data.get('condition'), race_class=race_data.get('raceClass'), abandoned=race_data.get('abandoned', False), start_time=race_data.get('startTime'), prize_money=str(race_data.get('prizeMoney', '')), number_of_runners=race_data.get('numberOfRunners', len(runners)), runners=runners, ) pace = classify_pace(race, runners) scored = [] for r in runners: sc = score_runner(r, race, pace, weights) scored.append((r.number, sc['score'])) scored.sort(key=lambda x: x[1], reverse=True) return [s[0] for s in scored[:3]] except: return None def evaluate_date(date: str, weights: dict) -> dict: result_lookup = load_results(date) races = load_cached_races(date) stats = {"total": 0, "top1": 0, "exact": 0, "box": 0} for race_data in races: track = race_data.get('track', '') race_num = race_data.get('raceNumber', 0) actual = result_lookup.get((track, race_num)) if not actual: continue pred = score_race(race_data, weights) if not pred: continue stats["total"] += 1 if pred == actual: stats["exact"] += 1 if set(pred) == set(actual): stats["box"] += 1 if pred[0] == actual[0]: stats["top1"] += 1 if stats["total"] > 0: stats["top1_pct"] = stats["top1"] / stats["total"] * 100 return stats def evaluate_all(dates: list[str], weights: dict) -> dict: agg = {"total": 0, "top1": 0, "exact": 0, "box": 0} for date in dates: stats = evaluate_date(date, weights) agg["total"] += stats["total"] agg["top1"] += stats["top1"] agg["exact"] += stats["exact"] agg["box"] += stats["box"] agg["top1_pct"] = agg["top1"] / agg["total"] * 100 if agg["total"] > 0 else 0 return agg def random_weights() -> dict: """Generate random weights that sum to ~1.0.""" keys = ["form", "class", "distance", "track", "track_distance", "condition", "jockey", "fitness", "barrier", "weight", "pace"] vals = [random.random() for _ in keys] total = sum(vals) return {k: v / total for k, v in zip(keys, vals)} def main(): dates = ["2026-08-07", "2026-08-08", "2026-08-09", "2026-08-14"] print("=" * 60) print("FAST OPTIMIZATION (Random Search)") print("=" * 60) # Base weights base = { "form": 0.18, "class": 0.14, "distance": 0.10, "track": 0.10, "track_distance": 0.10, "condition": 0.05, "jockey": 0.06, "fitness": 0.08, "barrier": 0.08, "weight": 0.08, "pace": 0.03, } base_stats = evaluate_all(dates, base) print(f"Base: {base_stats['top1_pct']:.1f}% ({base_stats['top1']}/{base_stats['total']})") # Random search - 100 iterations best_pct = base_stats['top1_pct'] best_weights = base for i in range(100): weights = random_weights() stats = evaluate_all(dates, weights) if stats['top1_pct'] > best_pct: best_pct = stats['top1_pct'] best_weights = weights print(f" New best at iter {i+1}: {best_pct:.1f}%") print(f"\nBest: {best_pct:.1f}%") w = best_weights print(f"form={w['form']:.2f}, class={w['class']:.2f}, dist={w['distance']:.2f}, " f"track={w['track']:.2f}, td={w['track_distance']:.2f}, " f"cond={w['condition']:.2f}, jockey={w['jockey']:.2f}, " f"fitness={w['fitness']:.2f}, barrier={w['barrier']:.2f}, " f"weight={w['weight']:.2f}, pace={w['pace']:.2f}") # Per-date breakdown print("\nPer-date breakdown:") for date in dates: stats = evaluate_date(date, best_weights) if stats['total'] > 0: print(f" {date}: {stats['top1']}/{stats['total']} ({stats['top1_pct']:.1f}%)") # Per-distance breakdown print("\nPer-distance breakdown:") for dist_class in ["sprint", "middle", "staying"]: dist_stats = {"total": 0, "top1": 0} for date in dates: result_lookup = load_results(date) races = load_cached_races(date) for race_data in races: if classify_distance(race_data.get('distance', '1200m')) == dist_class: track = race_data.get('track', '') race_num = race_data.get('raceNumber', 0) actual = result_lookup.get((track, race_num)) if not actual: continue pred = score_race(race_data, best_weights) if not pred: continue dist_stats["total"] += 1 if pred[0] == actual[0]: dist_stats["top1"] += 1 if dist_stats["total"] > 0: print(f" {dist_class}: {dist_stats['top1']}/{dist_stats['total']} ({dist_stats['top1']/dist_stats['total']*100:.1f}%)") return best_weights if __name__ == "__main__": main()