lightgbm案例

import lightgbm as lgb
import pandas as pd
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.datasets import  make_classification
# 加載數據
print('Load data...')

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)

# df_train = pd.read_csv('../regression/regression.train', header=None, sep='\t')
# df_test = pd.read_csv('../regression/regression.test', header=None, sep='\t')
# y_train = df_train[0].values
# y_test = df_test[0].values
# X_train = df_train.drop(0, axis=1).values
# X_test = df_test.drop(0, axis=1).values

print('Start training...')
# 創建模型，訓練模型
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)

print('Start predicting...')
# 測試機預測
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)
# 模型評估
print('The rmse of prediction is:', mean_squared_error(y_test, y_pred) ** 0.5)

# feature importances
print('Feature importances:', list(gbm.feature_importances_))

# 網格搜索，參數優化
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_)