LightGBM模型Python代码调用(含GridSearch）

1.调用原生包

# 取出特征和标签
import lightgbm as lgb
import pandas as pd

try:
    import matplotlib.pyplot as plt
except ImportError:
    raise ImportError('You need to install matplotlib for plotting.')
y_train = train_y.values
y_test = test_y.values
X_train = train_X.values
X_test = test_X.values
y_val = val_y.values
X_val = val_X.values
# 构建lgb中的Dataset数据格式
lgb_train = lgb.Dataset(X_train, y_train)
lgb_test = lgb.Dataset(X_test, y_test, reference=lgb_train)
lgb_val = lgb.Dataset(X_val, y_val, reference=lgb_train)
# 设定参数
params = {
    'num_leaves': 5,
    'metric': ('auc'),
    'verbose': 0
}

evals_result = {}  # to record eval results for plotting

print('开始训练...')
# 训练
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=500,
                valid_sets=[lgb_train, lgb_val,lgb_test],
                feature_name=['f' + str(i + 1) for i in range(train_X.shape[1])],
                categorical_feature=[0,2,3,4,6,7,12,25,26,27,28,29,31,32,33,34,35,36,37,38,39,40,41,42,43],
                evals_result=evals_result,
                verbose_eval=10)

print('在训练过程中绘图...')
ax = lgb.plot_metric(evals_result, metric='auc')
plt.show()

print('画出特征重要度...')
ax = lgb.plot_importance(gbm, max_num_features=10)
plt.show()

# print('画出第84颗树...')
# ax = lgb.plot_tree(gbm, tree_index=83, figsize=(20, 8), show_info=['split_gain'])
# plt.show()

2.LightGBM + GridSearch

import lightgbm as lgb
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
# 加载数据
iris = load_iris()
data = iris.data
target = iris.target
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2)
# 创建模型，训练模型
gbm = lgb.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)
# 测试机预测
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)
# feature importances
print('Feature importances:', list(gbm.feature_importances_))
# 网格搜索，参数优化
estimator = lgb.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_)