first (part 2: other directories)

2026-04-16 15:11:25 +03:00
parent 7814e0bc6b
commit 2f0b85a0c7
203 changed files with 59989 additions and 0 deletions
@@ -0,0 +1,183 @@
+
+import pandas as pd
+import xgboost as xgb
+import pickle
+import os
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_absolute_error, r2_score
+
+# Paths
+DATA_PATH = os.path.join(os.path.dirname(__file__), "../data/training_data.csv")
+MODEL_PATH = os.path.join(os.path.dirname(__file__), "../models/xgb_score.pkl")
+
+# Import unified 56-feature array from markets trainer
+from train_xgboost_markets import FEATURES
+
+TARGETS = ["score_home", "score_away", "ht_score_home", "ht_score_away"]
+
+def train():
+    print("🚀 Training Score Prediction Model (XGBoost) - Full Time & Half Time")
+    print("=" * 60)
+
+    if not os.path.exists(DATA_PATH):
+        print(f"❌ Data file not found: {DATA_PATH}")
+        return
+
+    print(f"📦 Loading data from {DATA_PATH}...")
+    df = pd.read_csv(DATA_PATH)
+    
+    # Preprocessing
+    # Drop rows where target is missing (should verify)
+    df = df.dropna(subset=TARGETS)
+    
+    # Fill feature NaNs with median/mean or 0
+    print(f"   Original rows: {len(df)}")
+    
+    # Filter valid odds (at least ms_h > 1.0)
+    df = df[df["odds_ms_h"] > 1.0].copy()
+    print(f"   Rows with valid odds: {len(df)}")
+    
+    X = df[FEATURES]
+    y_home = df["score_home"]
+    y_away = df["score_away"]
+    y_ht_home = df["ht_score_home"]
+    y_ht_away = df["ht_score_away"]
+    
+    # Train/Test Split
+    X_train, X_test, y_h_train, y_h_test, y_a_train, y_a_test, y_ht_h_train, y_ht_h_test, y_ht_a_train, y_ht_a_test = train_test_split(
+        X, y_home, y_away, y_ht_home, y_ht_away, test_size=0.2, random_state=42
+    )
+    
+    print(f"   Training set: {len(X_train)} matches")
+    print(f"   Test set: {len(X_test)} matches")
+
+    # --- HOME GOALS MODEL ---
+    print("\n🏠 Training Home Goals Model...")
+    xgb_home = xgb.XGBRegressor(
+        objective='reg:squarederror',
+        n_estimators=1000,
+        learning_rate=0.01,
+        max_depth=5,
+        subsample=0.7,
+        colsample_bytree=0.7,
+        n_jobs=-1,
+        random_state=42,
+        early_stopping_rounds=50 # Configure here for newer XGBoost or remove if not supported in constructor (depends on version)
+    )
+    # Actually, to be safe across versions, let's remove early stopping for now or use validation set properly
+    # Using 'eval_set' without early_stopping_rounds just prints metrics
+    xgb_home = xgb.XGBRegressor(
+        objective='reg:squarederror',
+        n_estimators=1000,
+        learning_rate=0.01,
+        max_depth=5,
+        subsample=0.7,
+        colsample_bytree=0.7,
+        n_jobs=-1,
+        random_state=42
+    )
+    xgb_home.fit(X_train, y_h_train, eval_set=[(X_test, y_h_test)], verbose=False)
+    
+    home_preds = xgb_home.predict(X_test)
+    mae_home = mean_absolute_error(y_h_test, home_preds)
+    r2_home = r2_score(y_h_test, home_preds)
+    print(f"   ✅ FT Home MAE: {mae_home:.4f} goals")
+    print(f"   ✅ FT Home R2: {r2_home:.4f}")
+
+    # --- AWAY GOALS MODEL ---
+    print("\n✈️ Training FT Away Goals Model...")
+    xgb_away = xgb.XGBRegressor(
+        objective='reg:squarederror',
+        n_estimators=1000,
+        learning_rate=0.01,
+        max_depth=5,
+        subsample=0.7,
+        colsample_bytree=0.7,
+        n_jobs=-1,
+        random_state=42
+    )
+    xgb_away.fit(X_train, y_a_train, eval_set=[(X_test, y_a_test)], verbose=False)
+    
+    away_preds = xgb_away.predict(X_test)
+    mae_away = mean_absolute_error(y_a_test, away_preds)
+    r2_away = r2_score(y_a_test, away_preds)
+    print(f"   ✅ FT Away MAE: {mae_away:.4f} goals")
+    print(f"   ✅ FT Away R2: {r2_away:.4f}")
+    
+    # --- HT HOME GOALS MODEL ---
+    print("\n🏠 Training HT Home Goals Model...")
+    xgb_ht_home = xgb.XGBRegressor(
+        objective='reg:squarederror',
+        n_estimators=1000,
+        learning_rate=0.01,
+        max_depth=5,
+        subsample=0.7,
+        colsample_bytree=0.7,
+        n_jobs=-1,
+        random_state=42
+    )
+    xgb_ht_home.fit(X_train, y_ht_h_train, eval_set=[(X_test, y_ht_h_test)], verbose=False)
+    
+    ht_home_preds = xgb_ht_home.predict(X_test)
+    mae_ht_home = mean_absolute_error(y_ht_h_test, ht_home_preds)
+    print(f"   ✅ HT Home MAE: {mae_ht_home:.4f} goals")
+
+    # --- HT AWAY GOALS MODEL ---
+    print("\n✈️ Training HT Away Goals Model...")
+    xgb_ht_away = xgb.XGBRegressor(
+        objective='reg:squarederror',
+        n_estimators=1000,
+        learning_rate=0.01,
+        max_depth=5,
+        subsample=0.7,
+        colsample_bytree=0.7,
+        n_jobs=-1,
+        random_state=42
+    )
+    xgb_ht_away.fit(X_train, y_ht_a_train, eval_set=[(X_test, y_ht_a_test)], verbose=False)
+    
+    ht_away_preds = xgb_ht_away.predict(X_test)
+    mae_ht_away = mean_absolute_error(y_ht_a_test, ht_away_preds)
+    print(f"   ✅ HT Away MAE: {mae_ht_away:.4f} goals")
+    
+    # --- EVALUATE EXACT SCORE ACCURACY (ROUNDED) ---
+    print("\n🎯 Exact FT Score Accuracy (Test Set):")
+    correct = 0
+    close = 0 # Within 1 goal diff for both
+    
+    for h_true, a_true, h_pred, a_pred in zip(y_h_test, y_a_test, home_preds, away_preds):
+        h_p = round(h_pred)
+        a_p = round(a_pred)
+        if h_p == h_true and a_p == a_true:
+            correct += 1
+        if abs(h_p - h_true) <= 1 and abs(a_p - a_true) <= 1:
+            close += 1
+            
+    acc = correct / len(X_test) * 100
+    close_acc = close / len(X_test) * 100
+    print(f"   Exact Match: {acc:.2f}%")
+    print(f"   Close Match (+/- 1 goal): {close_acc:.2f}%")
+
+    # Save
+    print(f"\n💾 Saving models to {MODEL_PATH}...")
+    model_data = {
+        "home_model": xgb_home,
+        "away_model": xgb_away,
+        "ht_home_model": xgb_ht_home,
+        "ht_away_model": xgb_ht_away,
+        "features": FEATURES,
+        "meta": {
+            "mae_home": mae_home,
+            "mae_away": mae_away,
+            "mae_ht_home": mae_ht_home,
+            "mae_ht_away": mae_ht_away,
+            "acc": acc
+        }
+    }
+    with open(MODEL_PATH, "wb") as f:
+        pickle.dump(model_data, f)
+    
+    print("✅ Done.")
+
+if __name__ == "__main__":
+    train()