Spaces:
Configuration error
Configuration error
File size: 10,240 Bytes
e23172f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 | """Final optimization — full grid search and per-date analysis."""
import json
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
DATA_DIR = Path('/home/brettanthonysjoberg179/trifecta-bro-hf-space/data')
CACHE_DIR = DATA_DIR / 'cache'
RESULTS_DIR = DATA_DIR / 'results'
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 main():
dates = ["2026-08-07", "2026-08-08", "2026-08-09", "2026-08-14"]
# Best weights from first pass
best = {
"form": 0.20, "class": 0.13, "distance": 0.08, "track": 0.08,
"track_distance": 0.08, "condition": 0.07, "jockey": 0.08,
"fitness": 0.05, "barrier": 0.13, "weight": 0.05, "pace": 0.04,
}
print("=" * 60)
print("OPTIMIZED WEIGHTS — PER DATE BREAKDOWN")
print("=" * 60)
total_races = 0
total_top1 = 0
for date in dates:
stats = evaluate_date(date, best)
if stats['total'] > 0:
total_races += stats['total']
total_top1 += stats['top1']
print(f"\n{date}: {stats['total']} races, {stats['top1']} top1 ({stats['top1']/stats['total']*100:.1f}%)")
# Show individual races
result_lookup = load_results(date)
races = load_cached_races(date)
for race_data in sorted(races, key=lambda x: (x.get('track', ''), x.get('raceNumber', 0))):
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)
if not pred:
continue
status = "EXACT!" if pred == actual else ("TOP1!" if pred[0] == actual[0] else "")
if status:
print(f" {track} R{race_num}: Pred {'→'.join(str(x) for x in pred)} | Actual {'→'.join(str(x) for x in actual)} {status}")
print(f"\n{'='*60}")
print(f"TOTAL: {total_top1}/{total_races} ({total_top1/total_races*100:.1f}%)")
print(f"{'='*60}")
# Now try to optimize for Aug 14 specifically to understand what's different
print("\n" + "=" * 60)
print("AUG 14 DEEP DIVE")
print("=" * 60)
# Load Aug 14 results
result_lookup = load_results("2026-08-14")
races = load_cached_races("2026-08-14")
# For each race, show what the model missed
for race_data in sorted(races, key=lambda x: (x.get('track', ''), x.get('raceNumber', 0))):
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)
if not pred:
continue
# Show top 3 picks vs actual
print(f"\n{track} R{race_num}:")
print(f" Actual: {'→'.join(str(x) for x in actual)}")
print(f" Predicted: {'→'.join(str(x) for x in pred)}")
# Show ranked runners
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)
race = RaceModel(
date='2026-08-14', track=track,
track_slug=track.lower(),
race_number=race_num,
race_name=race_data.get('raceName', ''),
distance=race_data.get('distance'),
condition=race_data.get('condition'),
race_class=race_data.get('raceClass'),
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, best)
scored.append({
'no': r.number, 'name': r.name, 'score': sc['score'],
'barrier': r.barrier, 'weight': r.weight, 'form': r.form,
'win_pct': r.win_percent, 'place_pct': r.place_percent,
})
scored.sort(key=lambda x: x['score'], reverse=True)
print(f" Ranked:")
for i, s in enumerate(scored[:6]):
marker = " <-- WINNER" if s['no'] == actual[0] else ""
print(f" {i+1}. #{s['no']} {s['name'][:20]:<20} score={s['score']:.1f} b={s['barrier']} w={s['weight']} form={s['form']} win={s['win_pct']*100:.0f}%{marker}")
if __name__ == "__main__":
main()
|