0

我正在尝试使用 optuna 来调整 LGBM 的超参数，但它会报告标题提到的错误。奇怪的是我y的是熊猫系列。

错误如下所示：

[1158]  valid_0's auc: 0.812934 valid_0's binary_logloss: 0.509509
[W 2021-10-01 22:14:20,509] Trial 0 failed because of the following error: ValueError('y should be a 1d array, got an array of shape (191584, 2) instead.',)
Traceback (most recent call last):

我的代码在下面列出。

y = train['claim']
X = train.drop(['id', 'claim'], axis=1)

# tuning with optuna
def objective(trial, X, y):
    param_grid = {
        "device_type": trial.suggest_categorical("device_type", ['gpu']),
        "n_estimators": trial.suggest_categorical("n_estimators", [10000]),
        "learning_rate": trial.suggest_float("learning_rate", 0.01, 0.3),
        "num_leaves": trial.suggest_int("num_leaves", 20, 3000, step=20),
        "max_depth": trial.suggest_int("max_depth", 3, 12),
        "min_data_in_leaf": trial.suggest_int("min_data_in_leaf", 200, 10000, step=100),
        "lambda_l1": trial.suggest_int("lambda_l1", 0, 100, step=5),
        "lambda_l2": trial.suggest_int("lambda_l2", 0, 100, step=5),
        "min_gain_to_split": trial.suggest_float("min_gain_to_split", 0, 15),
        "bagging_fraction": trial.suggest_float(
            "bagging_fraction", 0.2, 0.95, step=0.1
        ),
        "bagging_freq": trial.suggest_categorical("bagging_freq", [1]),
        "feature_fraction": trial.suggest_float(
            "feature_fraction", 0.2, 0.95, step=0.1
        ),
    }

    cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=1121218)

    cv_scores = np.empty(5)
    for idx, (train_idx, test_idx) in enumerate(cv.split(X, y)):
        X_train, X_test = X.iloc[train_idx], X.iloc[test_idx]
        y_train, y_test = y[train_idx], y[test_idx]

        model = lgbm.LGBMClassifier(objective="binary", **param_grid)
        model.fit(
            X_train,
            y_train,
            eval_set=[(X_test, y_test)],
            eval_metric="auc",
            early_stopping_rounds=100,
            callbacks=[
                LightGBMPruningCallback(trial, "auc")
            ],  # Add a pruning callback
        )
        preds = model.predict_proba(X_test)
        cv_scores[idx] = roc_auc_score(y_test, preds)

    return np.mean(cv_scores)


study = optuna.create_study(direction="maximize", study_name="LGBM Classifier")
func = lambda trial: objective(trial, X, y)
study.optimize(func, n_trials=20)

print(f"\tBest value (rmse): {study.best_value:.5f}")
print(f"\tBest params:")

for key, value in study.best_params.items():
    print(f"\t\t{key}: {value}")
4

1 回答 1

1

我发现问题出在哪里。

在下面的代码中：

preds = model.predict_proba(X_test)

我忘了添加[:, 1]，它返回一个列表而不是一个值。

于 2021-10-01T15:57:57.507 回答