RandomForestClassifier() 和GridSearchCV使用

from sklearn.ensembleimport RandomForestClassifier

from sklearn.model_selectionimport GridSearchCV

from sklearn.model_selectionimport train_test_split

train_X,test_X,train_Y,test_Y= train_test_split(X,Y,test_size=0.2,random_state=1) #训练集，测试集

estimator= RandomForestClassifier(bootstrap=True,class_weight=None,criterion='gini',

                                  max_depth=None,max_features='auto',max_leaf_nodes=None,

                                  min_samples_leaf=1,min_samples_split=2,min_weight_fraction_leaf=0.0,

                                  oob_score=True,random_state=None) #gridsearchcv()中的分类器

param= {'n_estimator':range(10,100,10),'criterion':['gini','entropy']} #分类器需要调整的参数

gsearsh= GridSearchCV(estimator=estimator,param_grid=param,cv=5)#网格搜索来调参

gsearch.fit(train_X,train_Y)

best_param= gsearsh.best_params_ #最优的参数，类型为字典dict

clf= RandomForestClassifier(n_estimators = best_param["n_estimator"],

                            criterion=best_param["criterion"],oob_score=True) #使用经过网格搜索得到的 最优参数

clf.fit(train_X,train_Y) #生成训练模型

clf.predict(test_X) #对训练集进行预测

clf.score(test_X,test_Y) #查看效果