LightGBM调参与模型权重可视化

构建模型与调参

import lightgbm as lgb
import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split

# 构建LightGBM模型
print('Training/Fitting ...')
params = {
    'task': 'train',
    'boosting_type': 'gbdt',
    'objective': 'regression',
    'metric': {'mse'},
    'num_leaves': 50,
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
}
lgb_train = lgb.Dataset(train_data_x, train_data_y)
lgb_eval = lgb.Dataset(test_data_x, test_data_y, reference=lgb_train)
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=1000,
                valid_sets=lgb_eval,
                early_stopping_rounds=50)

# 预测测试集并输出RMSE
print('Predicting ...')
y_pred = gbm.predict(test_data_x.values, num_iteration=gbm.best_iteration)
LGBM_mse = mean_squared_error(test_data_y, y_pred)
LGBM_mae = np.mean(abs(test_data_y - y_pred))
print("MSE: %.4f" % LGBM_mse)
print("MSE: %.4f" % LGBM_mae)

模型权重可视化

from lightgbm import plot_importance
fig,ax = plt.subplots(figsize=(10,8))
plot_importance(gbm,max_num_features=50,ax=ax)
plt.show()