LightGBM原生包

LightGBM原生包，可以可视化出训练过程，还可以可视化出tree。

先根据数据量、特征量确定大概的参数。主要是max_depth、num_leaves、max_bin、min_data_in_leaf。网上可以找到很多参数确定的技巧。
#Gridsearch调参
import lightgbm as lgb
from sklearn import metrics
from sklearn import joblib
from sklearn.datasets import load_svmlight_file
from sklearn.model_selection import GridSearchCV
from matplotlib import pyplot as plt

def get_data(path):
	data = load_svmlight_file(path,dtype=np.float32)
	return(data[0],data[1])

def gsearch_train(path):
	 evals_result = {}  #存放训练过程中的评估数据，用于plot过程
	 x,y = get_data(path)
	 x_train,y_train,x_test,y_test = train_test_split(0.2)
	 #划定网格搜索的调参范围
	 param_test = {
	 	'boosting':['gbdt'],
	 	'objective':['binary'],
	 	'num_boost_round':[1000],
	 	'verbose_eval':[5],
	 	'learning_rate':[0.1],
	 	'max_depth':range(10,15,1),
	 	'max_bin':[255],
	 	'min_data_in_leaf':[50],
	 	'feature_fraction':[0.5],
	 		 }
	 gsearch = GridSearchCV(estimator=lgb.LGBMClassifier(boosting_type='gbdt',n_jobs=-1,verbose=1),param_grid=param_test,scoring='roc_auc')
	 gsearch.fit(x_train,y_train)
	 return(gsearch.best_params_,gsearch.best_score_,gsearch.cv_results_,gsearch.best_estimator_)

def train(path,param):
	evals_result = {}  #存放训练过程中的评估数据，用于plot过程
	x,y = get_data(path)
	x_train,y_train,x_test,y_test = train_test_split(0.2)
	params = {
	#根据gridsearch确定
	}
	train_set = lgb.Dataset(x_train,y_train)
	test_set = lgb.Dataset(x_test,y_test)
	model = lgb.train(params,train_set,valid_sets=[test_set],evals_result=evals_result,early_stopping=10)
	return(model,evals_result)

if __name == '__main__':
	path = ''
	params,_,_,best_estimator = gsearch_train(path)
	model,evals_result = train(path,params)
	#画出tree
	ax = lgb.plot_tree(best_estimator,tree_index=3,figsize=(20,8),show_info=['split_gain'])
	plt.show()
	#画出训练过程
	ax = lgb.plot_metric(evals_result,metirc='auc',title='AUC')
	plt.show()
	#画出训练过程
	ax = lgb.plot_metric(evals_result,metirc='bianry_logloss',title='Logloss')
	plt.show()