LightGBM两种使用方式

原生形式使用lightgbm(import lightgbm as lgb)

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

# 加载数据
iris = load_iris()
data = iris.data
target = iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2)
print("Train data length:", len(X_train))
print("Test data length:", len(X_test))

# 转换为Dataset数据格式
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

# 参数
params = {
    'task': 'train',
    'boosting_type': 'gbdt',  # 设置提升类型
    'objective': 'regression',  # 目标函数
    'metric': {'l2', 'auc'},  # 评估函数
    'num_leaves': 31,  # 叶子节点数
    'learning_rate': 0.05,  # 学习速率
    'feature_fraction': 0.9,  # 建树的特征选择比例
    'bagging_fraction': 0.8,  # 建树的样本采样比例
    'bagging_freq': 5,  # k 意味着每 k 次迭代执行bagging
    'verbose': 1  # <0 显示致命的, =0 显示错误 (警告), >0 显示信息
}

# 模型训练
gbm = lgb.train(params, lgb_train, num_boost_round=20, valid_sets=lgb_eval, early_stopping_rounds=5)

# 模型保存
gbm.save_model('model.txt')

# 模型加载
gbm = lgb.Booster(model_file='model.txt')

# 模型预测
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)

# 模型评估
print('The rmse of prediction is:', mean_squared_error(y_test, y_pred) ** 0.5)

Sklearn接口形式使用lightgbm(from lightgbm import LGBMRegressor)

from lightgbm import LGBMRegressor
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.externals import joblib

# 加载数据
iris = load_iris()
data = iris.data
target = iris.target

# 划分训练数据和测试数据
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2)

# 模型训练
gbm = LGBMRegressor(objective='regression', num_leaves=31, learning_rate=0.05, n_estimators=20)
gbm.fit(X_train, y_train, eval_set=[(X_test, y_test)], eval_metric='l1', early_stopping_rounds=5)

# 模型存储
joblib.dump(gbm, 'loan_model.pkl')
# 模型加载
gbm = joblib.load('loan_model.pkl')

# 模型预测
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)

# 模型评估
print('The rmse of prediction is:', mean_squared_error(y_test, y_pred) ** 0.5)

# 特征重要度
print('Feature importances:', list(gbm.feature_importances_))

# 网格搜索，参数优化
estimator = LGBMRegressor(num_leaves=31)
param_grid = {
    'learning_rate': [0.01, 0.1, 1],
    'n_estimators': [20, 40]
}
gbm = GridSearchCV(estimator, param_grid)
gbm.fit(X_train, y_train)
print('Best parameters found by grid search are:', gbm.best_params_)