import numpy as np
import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
from sklearn.metrics import accuracy_score

# 生成模拟数据
X, y = make_classification(n_samples=1000, n_features=20, n_classes=2, random_state=42)

# 分割数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建LightGBM数据集
train_data = lgb.Dataset(X_train, label=y_train)
test_data = lgb.Dataset(X_test, label=y_test, reference=train_data)

print(X_train.shape)
for line in X_train:
    print(line)
# print(X_train)
print(y_test)
# 设置模型的参数
params = {
    'objective': 'binary',       # 指定二分类任务
    'metric': 'binary_logloss',  # 评估指标为二分类的log损失
    'num_leaves': 31,            # 叶子节点数
    'learning_rate': 0.05,       # 学习率
    'bagging_fraction': 0.9,     # 建树的样本采样比例
    'feature_fraction': 0.8,     # 建树的特征选择比例
    'bagging_freq': 5,           # k 意味着每 k 次迭代执行bagging
}

# 训练模型
num_round = 100
bst = lgb.train(params, train_data, num_round, valid_sets=[test_data])

# 预测
y_pred = bst.predict(X_test, num_iteration=bst.best_iteration)
# 转换为二进制输出
y_pred_binary = np.where(y_pred > 0.5, 1, 0)

# 评估模型
accuracy = accuracy_score(y_test, y_pred_binary)
print(f'Accuracy: {accuracy}')