132 lines
4.1 KiB
Python
132 lines
4.1 KiB
Python
|
import os
|
|||
|
|
import pandas as pd
|
|||
|
|
import numpy as np
|
|||
|
|
from catboost import CatBoostClassifier, Pool
|
|||
|
|
from sklearn.model_selection import train_test_split
|
|||
|
|
from sklearn.metrics import roc_auc_score
|
|||
|
|
|
|||
|
|
print("Загрузка датасета...")
|
|||
|
|
|
|||
|
|
df = pd.read_parquet("data/dataset_from_db.parquet")
|
|||
|
|
|
|||
|
|
print(f"Всего записей (матчей): {len(df)}")
|
|||
|
|
print(f"Radiant wins: {df['y'].sum()} ({df['y'].mean()*100:.1f}%)")
|
|||
|
|
print(f"Dire wins: {len(df) - df['y'].sum()} ({(1-df['y'].mean())*100:.1f}%)")
|
|||
|
|
|
|||
|
|
# --- Создаём признаки на уровне матча ---
|
|||
|
|
print("\nСоздание признаков...")
|
|||
|
|
|
|||
|
|
hero_cols_r = [f"r_h{i}" for i in range(1, 6)]
|
|||
|
|
hero_cols_d = [f"d_h{i}" for i in range(1, 6)]
|
|||
|
|
pos_cols_r = [f"rp_h{i}" for i in range(1, 6)]
|
|||
|
|
pos_cols_d = [f"dp_h{i}" for i in range(1, 6)]
|
|||
|
|
|
|||
|
|
# Создаём признаки: каждый герой на каждой позиции для каждой команды
|
|||
|
|
# Формат: radiant_{hero_id}_pos_{position}, dire_{hero_id}_pos_{position}
|
|||
|
|
|
|||
|
|
rows = []
|
|||
|
|
|
|||
|
|
for idx, row in df.iterrows():
|
|||
|
|
features = {}
|
|||
|
|
|
|||
|
|
# Radiant heroes с позициями
|
|||
|
|
for i in range(5):
|
|||
|
|
hero_id = int(row[hero_cols_r[i]])
|
|||
|
|
position = int(row[pos_cols_r[i]])
|
|||
|
|
|
|||
|
|
if hero_id >= 0 and position >= 0:
|
|||
|
|
features[f"radiant_h{hero_id}_p{position}"] = 1
|
|||
|
|
|
|||
|
|
# Dire heroes с позициями
|
|||
|
|
for i in range(5):
|
|||
|
|
hero_id = int(row[hero_cols_d[i]])
|
|||
|
|
position = int(row[pos_cols_d[i]])
|
|||
|
|
|
|||
|
|
if hero_id >= 0 and position >= 0:
|
|||
|
|
features[f"dire_h{hero_id}_p{position}"] = 1
|
|||
|
|
|
|||
|
|
features['y'] = int(row['y'])
|
|||
|
|
rows.append(features)
|
|||
|
|
|
|||
|
|
df_features = pd.DataFrame(rows).fillna(0)
|
|||
|
|
|
|||
|
|
print(f"Создано признаков: {len(df_features.columns) - 1}")
|
|||
|
|
|
|||
|
|
# Целевая
|
|||
|
|
y = df_features['y'].astype(int)
|
|||
|
|
X = df_features.drop('y', axis=1)
|
|||
|
|
|
|||
|
|
# Разбиение
|
|||
|
|
X_train, X_test, y_train, y_test = train_test_split(
|
|||
|
|
X, y,
|
|||
|
|
test_size=0.2,
|
|||
|
|
random_state=42,
|
|||
|
|
stratify=y
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print(f"\nTrain: {len(X_train)} матчей")
|
|||
|
|
print(f"Test: {len(X_test)} матчей")
|
|||
|
|
|
|||
|
|
# Обучение
|
|||
|
|
train_pool = Pool(X_train, y_train)
|
|||
|
|
test_pool = Pool(X_test, y_test)
|
|||
|
|
|
|||
|
|
model = CatBoostClassifier(
|
|||
|
|
iterations=1000,
|
|||
|
|
learning_rate=0.05,
|
|||
|
|
depth=5,
|
|||
|
|
l2_leaf_reg=3,
|
|||
|
|
min_data_in_leaf=10,
|
|||
|
|
bootstrap_type="Bayesian",
|
|||
|
|
bagging_temperature=0.5,
|
|||
|
|
loss_function="Logloss",
|
|||
|
|
eval_metric="AUC",
|
|||
|
|
random_seed=42,
|
|||
|
|
verbose=50,
|
|||
|
|
od_type="Iter",
|
|||
|
|
od_wait=100,
|
|||
|
|
use_best_model=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print("\nНачало обучения...")
|
|||
|
|
model.fit(train_pool, eval_set=test_pool)
|
|||
|
|
|
|||
|
|
# Оценка
|
|||
|
|
best_scores = model.get_best_score()
|
|||
|
|
train_auc_cb = best_scores.get("learn", {}).get("AUC", np.nan)
|
|||
|
|
test_auc_cb = best_scores.get("validation", {}).get("AUC", np.nan)
|
|||
|
|
|
|||
|
|
y_train_proba = model.predict_proba(train_pool)[:, 1]
|
|||
|
|
y_test_proba = model.predict_proba(test_pool)[:, 1]
|
|||
|
|
train_auc = roc_auc_score(y_train, y_train_proba)
|
|||
|
|
test_auc = roc_auc_score(y_test, y_test_proba)
|
|||
|
|
|
|||
|
|
print(f"\nCatBoost best AUC (learn/valid): {train_auc_cb:.4f} / {test_auc_cb:.4f}")
|
|||
|
|
print(f"Recomputed AUC (train/test): {train_auc:.4f} / {test_auc:.4f}")
|
|||
|
|
|
|||
|
|
# Сохранение
|
|||
|
|
os.makedirs("artifacts", exist_ok=True)
|
|||
|
|
model_path = "artifacts/model_from_db_pro_v3.cbm"
|
|||
|
|
model.save_model(model_path)
|
|||
|
|
print(f"\nМодель сохранена: {model_path}")
|
|||
|
|
|
|||
|
|
# Важность (топ-30)
|
|||
|
|
importance = model.get_feature_importance(train_pool)
|
|||
|
|
importance_df = (
|
|||
|
|
pd.DataFrame({"feature": X_train.columns, "importance": importance})
|
|||
|
|
.sort_values("importance", ascending=False)
|
|||
|
|
.reset_index(drop=True)
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print("\nВажность признаков (top 30):")
|
|||
|
|
print(importance_df.head(30).to_string(index=False))
|
|||
|
|
|
|||
|
|
importance_df.to_csv("artifacts/feature_importance_db.csv", index=False)
|
|||
|
|
|
|||
|
|
# Сохраняем список всех возможных признаков для инференса
|
|||
|
|
all_features = sorted(X.columns.tolist())
|
|||
|
|
pd.DataFrame(all_features, columns=["feature"]).to_csv(
|
|||
|
|
"artifacts/feature_order_db.csv", index=False
|
|||
|
|
)
|
|||
|
|
print(f"Порядок фичей сохранен в artifacts/feature_order_db.csv ({len(all_features)} признаков)")
|