File size: 7,655 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
"""Quick optimizer — re-score cached races with new weights."""
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, result_lookup: dict) -> dict:
    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
    
    return stats


def evaluate_all(dates: list[str], weights: dict) -> dict:
    agg = {"total": 0, "top1": 0, "exact": 0, "box": 0}
    for date in dates:
        result_lookup = load_results(date)
        stats = evaluate_date(date, weights, result_lookup)
        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"]
    
    # 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,
    }
    
    print("Base weights:", evaluate_all(dates, base))
    
    # Try different combinations
    best_pct = 0
    best_weights = None
    
    # Systematic search over key parameters
    for form in [0.15, 0.20, 0.25, 0.30]:
        for class_w in [0.10, 0.15, 0.20]:
            for dist in [0.06, 0.10, 0.14]:
                for td in [0.06, 0.10, 0.14]:
                    for barrier in [0.06, 0.10, 0.14]:
                        for fitness in [0.04, 0.08, 0.12]:
                            weights = {
                                "form": form, "class": class_w, "distance": dist,
                                "track": dist, "track_distance": td,
                                "condition": 0.05, "jockey": 0.06,
                                "fitness": fitness, "barrier": barrier,
                                "weight": fitness, "pace": 0.03,
                            }
                            total_w = sum(weights.values())
                            weights = {k: v / total_w for k, v in weights.items()}
                            
                            stats = evaluate_all(dates, weights)
                            if stats["top1_pct"] > best_pct:
                                best_pct = stats["top1_pct"]
                                best_weights = weights
                                print(f"New best: {best_pct:.1f}%")
    
    print(f"\nBest: {best_pct:.1f}%")
    print(f"Weights: {best_weights}")
    
    # Per-date breakdown
    for date in dates:
        result_lookup = load_results(date)
        stats = evaluate_date(date, best_weights, result_lookup)
        if stats['total'] > 0:
            print(f"  {date}: {stats['top1']}/{stats['total']} ({stats['top1']/stats['total']*100:.0f}%)")
    
    return best_weights


if __name__ == "__main__":
    main()