RandomForest

#-*- coding:utf-8 -*-
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, Y = make_classification(n_samples=1500, n_features=4, n_informative=2, n_redundant=0, random_state=0, shuffle=False)
X1,X2,Y1,Y2 = train_test_split( X, Y, test_size=0.2, random_state=0)

#随机森林的参数包含的是决策树和弱分类器的参数 

clf = RandomForestClassifier( n_estimators=50, max_depth=3, random_state=43)
clf.fit(X1,Y1) 

answer = clf.predict(X2) 
print(clf.score(X1,Y1)) 
print(clf.score(X2,Y2))
#使用交叉验证其标准差获得最优参数 
from sklearn.model_selection import cross_val_score 
scores = cross_val_score(clf, X, Y, cv=3) 
print(scores.std()) 
print(clf.feature_importances_)