lightgbm分类 python代码

LightGBM是一个高效的梯度提升库，特别适合大规模数据集。以下是使用Python进行分类任务的一个简单示例：

# 首先，安装必要的库
!pip install lightgbm pandas sklearn

import lightgbm as lgb
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data
y = iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 定义特征列和标签列
features = ['feature_column_1', 'feature_column_2', ...]  # 替换为实际的特征列名
dtrain = lgb.Dataset(X_train[features], label=y_train)
dtest = lgb.Dataset(X_test[features], label=y_test)

# 设置模型参数
params = {
    'boosting_type': 'gbdt',  # 使用梯度提升算法
    'objective': 'multiclass',  # 多类别分类任务
    'num_class': len(set(y)),  # 根据实际类别数设置
    'metric': 'multi_logloss',  # 用于评估的指标
}

# 训练模型
model = lgb.train(params, dtrain, num_boost_round=100, valid_sets=[dtest])

# 预测
y_pred = model.predict(X_test[features])

# 评估准确率
accuracy = accuracy_score(y_test, y_pred.argmax(axis=1))
print("Accuracy:", accuracy)

#