117 lines
4.0 KiB
Python
117 lines
4.0 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: {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}%)")
|
|||
|
|
|
|||
|
|
# --- Фичи под новый формат датасета ---
|
|||
|
|
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, 5+1)]
|
|||
|
|
# player_cols_r = [f"r_p{i}" for i in range(1, 6)]
|
|||
|
|
# player_cols_d = [f"d_p{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)]
|
|||
|
|
|
|||
|
|
feature_cols = (
|
|||
|
|
["is_first_pick_radiant"]
|
|||
|
|
+ hero_cols_r + hero_cols_d
|
|||
|
|
# + player_cols_r + player_cols_d # Убрали игроков - мало данных
|
|||
|
|
+ pos_cols_r + pos_cols_d
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
# Целевая
|
|||
|
|
target_col = "y"
|
|||
|
|
|
|||
|
|
# Отделяем признаки/таргет
|
|||
|
|
X = df[feature_cols].copy()
|
|||
|
|
y = df[target_col].astype(int).copy()
|
|||
|
|
|
|||
|
|
# На всякий случай убедимся, что бинарный признак int
|
|||
|
|
X["is_first_pick_radiant"] = X["is_first_pick_radiant"].astype(int)
|
|||
|
|
|
|||
|
|
# Разбиение
|
|||
|
|
X_train, X_test, y_train, y_test = train_test_split(
|
|||
|
|
X, y,
|
|||
|
|
test_size=0.1,
|
|||
|
|
random_state=42,
|
|||
|
|
stratify=y
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print(f"\nTrain: {len(X_train)} записей")
|
|||
|
|
print(f"Test: {len(X_test)} записей")
|
|||
|
|
|
|||
|
|
# Категориальные признаки: герои и позиции (их ID — это категории)
|
|||
|
|
cat_features = hero_cols_r + hero_cols_d + pos_cols_r + pos_cols_d
|
|||
|
|
# CatBoost принимает либо индексы, либо имена колонок. Передаем имена.
|
|||
|
|
train_pool = Pool(X_train, y_train, cat_features=cat_features)
|
|||
|
|
test_pool = Pool(X_test, y_test, cat_features=cat_features)
|
|||
|
|
|
|||
|
|
# Модель
|
|||
|
|
model = CatBoostClassifier(
|
|||
|
|
iterations=2500,
|
|||
|
|
learning_rate=0.03,
|
|||
|
|
depth=7,
|
|||
|
|
l2_leaf_reg=2,
|
|||
|
|
bootstrap_type="Bayesian",
|
|||
|
|
bagging_temperature=1.0, # <- вместо subsample
|
|||
|
|
loss_function="Logloss",
|
|||
|
|
eval_metric="AUC",
|
|||
|
|
random_seed=42,
|
|||
|
|
verbose=100,
|
|||
|
|
od_type="Iter",
|
|||
|
|
od_wait=200
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print("\nНачало обучения...")
|
|||
|
|
model.fit(train_pool, eval_set=test_pool, use_best_model=True)
|
|||
|
|
|
|||
|
|
# --- Оценка качества ---
|
|||
|
|
# Лучшие метрики по мнению CatBoost
|
|||
|
|
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)
|
|||
|
|
|
|||
|
|
# Перепроверим AUC напрямую
|
|||
|
|
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}")
|
|||
|
|
|
|||
|
|
# Порядок фичей
|
|||
|
|
pd.DataFrame(feature_cols, columns=["feature"]).to_csv(
|
|||
|
|
"artifacts/feature_order_db.csv", index=False
|
|||
|
|
)
|
|||
|
|
print("Порядок фичей сохранен в artifacts/feature_order_db.csv")
|
|||
|
|
|
|||
|
|
# Важность признаков
|
|||
|
|
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 25):")
|
|||
|
|
print(importance_df.head(25).to_string(index=False))
|
|||
|
|
|
|||
|
|
# При желании — сохранить важности целиком
|
|||
|
|
importance_df.to_csv("artifacts/feature_importance_db.csv", index=False)
|