Lightgbm模型两种保存方式

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

# 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)

二、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


# 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_)

Reference：

1、https://www.wandouip.com/t5i289440/ LightGBM两种使用方式