252 lines
9.3 KiB
Python
Executable File
252 lines
9.3 KiB
Python
Executable File
"""
|
||
Player Predictor Engine - V20 Ensemble Component
|
||
Analyzes squad quality, key players, and missing player impact.
|
||
|
||
Weight: 25% in ensemble
|
||
"""
|
||
|
||
import os
|
||
import sys
|
||
from typing import Dict, Optional, List
|
||
from dataclasses import dataclass
|
||
|
||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
|
||
|
||
from features.squad_analysis_engine import get_squad_analysis_engine
|
||
from features.sidelined_analyzer import get_sidelined_analyzer
|
||
|
||
|
||
@dataclass
|
||
class PlayerPrediction:
|
||
"""Player engine prediction output.
|
||
|
||
IMPORTANT: squad_quality uses the SAME composite formula as
|
||
extract_training_data.py so that inference values match the
|
||
distribution the model was trained on (~3-36 range).
|
||
"""
|
||
home_squad_quality: float = 12.0 # training-scale composite (~3-36)
|
||
away_squad_quality: float = 12.0
|
||
squad_diff: float = 0.0 # home - away (training scale)
|
||
home_key_players: int = 0
|
||
away_key_players: int = 0
|
||
home_missing_impact: float = 0.0 # 0-1, how much weaker due to missing players
|
||
away_missing_impact: float = 0.0
|
||
home_goals_form: int = 0 # Goals in last 5 matches
|
||
away_goals_form: int = 0
|
||
lineup_available: bool = False
|
||
confidence: float = 0.0
|
||
|
||
def to_dict(self) -> dict:
|
||
return {
|
||
"home_squad_quality": round(self.home_squad_quality, 1),
|
||
"away_squad_quality": round(self.away_squad_quality, 1),
|
||
"squad_diff": round(self.squad_diff, 1),
|
||
"home_key_players": self.home_key_players,
|
||
"away_key_players": self.away_key_players,
|
||
"home_missing_impact": round(self.home_missing_impact, 2),
|
||
"away_missing_impact": round(self.away_missing_impact, 2),
|
||
"home_goals_form": self.home_goals_form,
|
||
"away_goals_form": self.away_goals_form,
|
||
"lineup_available": self.lineup_available,
|
||
"confidence": round(self.confidence, 1)
|
||
}
|
||
|
||
|
||
class PlayerPredictorEngine:
|
||
"""
|
||
Player/Squad-based prediction engine.
|
||
|
||
Analyzes:
|
||
- Starting 11 quality
|
||
- Key player availability (top scorers)
|
||
- Missing player impact
|
||
- Recent goalscoring form per player
|
||
"""
|
||
|
||
def __init__(self):
|
||
self.squad_engine = get_squad_analysis_engine()
|
||
self.sidelined_analyzer = get_sidelined_analyzer()
|
||
print("✅ PlayerPredictorEngine initialized")
|
||
|
||
def predict(self,
|
||
match_id: str,
|
||
home_team_id: str,
|
||
away_team_id: str,
|
||
home_lineup: List[str] = None,
|
||
away_lineup: List[str] = None,
|
||
sidelined_data: Dict = None) -> PlayerPrediction:
|
||
"""
|
||
Generate player-based prediction.
|
||
|
||
Args:
|
||
match_id: Match ID for lineup lookup
|
||
home_team_id: Home team ID
|
||
away_team_id: Away team ID
|
||
home_lineup: Optional list of home player IDs
|
||
away_lineup: Optional list of away player IDs
|
||
|
||
Returns:
|
||
PlayerPrediction with squad analysis
|
||
"""
|
||
|
||
# Get squad features
|
||
if home_lineup and away_lineup:
|
||
# Use provided lineups (for live matches)
|
||
home_analysis = self.squad_engine.analyze_squad_from_list(
|
||
home_lineup, home_team_id
|
||
)
|
||
away_analysis = self.squad_engine.analyze_squad_from_list(
|
||
away_lineup, away_team_id
|
||
)
|
||
lineup_available = True
|
||
# Build features dict from analysis objects
|
||
features = {
|
||
"home_starting_11": home_analysis.starting_count or 11,
|
||
"home_goals_last_5": home_analysis.total_goals_last_5,
|
||
"home_assists_last_5": home_analysis.total_assists_last_5,
|
||
"home_key_players": home_analysis.key_players_count,
|
||
"home_forwards": home_analysis.forward_count or 2,
|
||
"away_starting_11": away_analysis.starting_count or 11,
|
||
"away_goals_last_5": away_analysis.total_goals_last_5,
|
||
"away_assists_last_5": away_analysis.total_assists_last_5,
|
||
"away_key_players": away_analysis.key_players_count,
|
||
"away_forwards": away_analysis.forward_count or 2,
|
||
}
|
||
elif match_id:
|
||
# Try to get from database
|
||
try:
|
||
features = self.squad_engine.get_features(
|
||
match_id, home_team_id, away_team_id
|
||
)
|
||
lineup_available = (
|
||
features.get("home_starting_11", 0) >= 11 and
|
||
features.get("away_starting_11", 0) >= 11
|
||
)
|
||
except Exception:
|
||
features = self.squad_engine.get_features_without_match(
|
||
home_team_id, away_team_id
|
||
)
|
||
lineup_available = False
|
||
else:
|
||
features = self.squad_engine.get_features_without_match(
|
||
home_team_id, away_team_id
|
||
)
|
||
lineup_available = False
|
||
|
||
# Extract features
|
||
home_goals = features.get("home_goals_last_5", 0)
|
||
away_goals = features.get("away_goals_last_5", 0)
|
||
home_key = features.get("home_key_players", 0)
|
||
away_key = features.get("away_key_players", 0)
|
||
home_assists = features.get("home_assists_last_5", 0)
|
||
away_assists = features.get("away_assists_last_5", 0)
|
||
home_starting = features.get("home_starting_11", 11)
|
||
away_starting = features.get("away_starting_11", 11)
|
||
home_fwd = features.get("home_forwards", 2)
|
||
away_fwd = features.get("away_forwards", 2)
|
||
|
||
# Calculate squad quality — MUST match extract_training_data.py formula
|
||
# Formula: starting_count * 0.3 + goals * 2.0 + assists * 1.0
|
||
# + key_players * 3.0 + fwd_count * 1.5
|
||
# Typical range: ~3 – 36 (model trained on this distribution)
|
||
home_quality = (
|
||
home_starting * 0.3 +
|
||
home_goals * 2.0 +
|
||
home_assists * 1.0 +
|
||
home_key * 3.0 +
|
||
home_fwd * 1.5
|
||
)
|
||
away_quality = (
|
||
away_starting * 0.3 +
|
||
away_goals * 2.0 +
|
||
away_assists * 1.0 +
|
||
away_key * 3.0 +
|
||
away_fwd * 1.5
|
||
)
|
||
|
||
# Squad difference
|
||
squad_diff = home_quality - away_quality
|
||
|
||
# Missing player impact
|
||
# Priority: sidelined data (position-weighted) > lineup count (basic)
|
||
if sidelined_data:
|
||
home_impact, away_impact = self.sidelined_analyzer.analyze_match(sidelined_data)
|
||
home_missing = home_impact.impact_score
|
||
away_missing = away_impact.impact_score
|
||
sidelined_available = True
|
||
else:
|
||
# Fallback: basic lineup count method
|
||
expected_xi = 11
|
||
actual_home_xi = features.get("home_starting_11", 11)
|
||
actual_away_xi = features.get("away_starting_11", 11)
|
||
home_missing = (expected_xi - actual_home_xi) / expected_xi if actual_home_xi < expected_xi else 0
|
||
away_missing = (expected_xi - actual_away_xi) / expected_xi if actual_away_xi < expected_xi else 0
|
||
sidelined_available = False
|
||
|
||
# Confidence: more data sources = higher confidence
|
||
confidence = 70.0 if lineup_available else 35.0
|
||
if home_goals + away_goals > 10:
|
||
confidence += 15
|
||
if sidelined_available:
|
||
confidence += self.sidelined_analyzer.config.get("sidelined.confidence_boost", 10)
|
||
if not lineup_available:
|
||
confidence -= 5.0
|
||
|
||
return PlayerPrediction(
|
||
home_squad_quality=home_quality,
|
||
away_squad_quality=away_quality,
|
||
squad_diff=squad_diff,
|
||
home_key_players=home_key,
|
||
away_key_players=away_key,
|
||
home_missing_impact=home_missing,
|
||
away_missing_impact=away_missing,
|
||
home_goals_form=home_goals,
|
||
away_goals_form=away_goals,
|
||
lineup_available=lineup_available,
|
||
confidence=max(5.0, confidence)
|
||
)
|
||
|
||
def get_1x2_modifier(self, prediction: PlayerPrediction) -> Dict[str, float]:
|
||
"""
|
||
Calculate 1X2 probability modifiers based on squad analysis.
|
||
|
||
Returns modifiers to apply to base probabilities.
|
||
squad_diff is in training scale (~-33 to +33), normalize to -1..+1.
|
||
"""
|
||
diff = prediction.squad_diff / 33.0 # training-scale normalisation
|
||
diff = max(-1.0, min(1.0, diff)) # clamp
|
||
|
||
return {
|
||
"home_modifier": 1.0 + (diff * 0.3), # Up to +/-30%
|
||
"away_modifier": 1.0 - (diff * 0.3),
|
||
"draw_modifier": 1.0 - abs(diff) * 0.2 # Less draw if big diff
|
||
}
|
||
|
||
|
||
# Singleton
|
||
_engine: Optional[PlayerPredictorEngine] = None
|
||
|
||
|
||
def get_player_predictor() -> PlayerPredictorEngine:
|
||
global _engine
|
||
if _engine is None:
|
||
_engine = PlayerPredictorEngine()
|
||
return _engine
|
||
|
||
|
||
if __name__ == "__main__":
|
||
engine = get_player_predictor()
|
||
|
||
print("\n🧪 Player Predictor Engine Test")
|
||
print("=" * 50)
|
||
|
||
pred = engine.predict(
|
||
match_id=None,
|
||
home_team_id="test_home",
|
||
away_team_id="test_away"
|
||
)
|
||
|
||
print(f"\n📊 Prediction:")
|
||
for k, v in pred.to_dict().items():
|
||
print(f" {k}: {v}")
|