随机森林

代码

from sklearn.datasets import load_boston
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
data = load_boston()
X = data['data']
Y = data['target']
train_X,test_X,train_y,test_y = train_test_split(X,y,test_size = 0.3) # 如果想固定划分结果，用种子

rfr = RandomForestRegressor()
rfr.fit(train_X,train_y)
train_predicts = rfr.predict(train_X)
test_predicts = rfr.predict(test_X)

mean_squared_error(train_predicts,train_y)
mean_squared_error(test_predicts,test_y)

# 调节参数，决策树棵数
error_trains = []
error_tests = []
for i in range(10,200,10):
    # 修改n_estimators，也就是决策树棵数，并确定随机种子
    rfr = RandomForestRegressor(n_estimators = i,random_state = 90) # 控制种子，保证变量唯一
    rfr.fit(train_X,train_y)
    train_predicts = rfr.predict(train_X)
    test_predicts = rfr.predict(test_X)
    error_trains.append(mean_squared_error(train_predicts,train_y))
    mean_squared_error.append((test_predicts,test_y))

# 绘制调参图
x = list(range(10,200,10))
plt.plot(x,error_trains,'--',label = 'train')
plt.plot(x,error_tests,'o',label = 'test')
plt.xlabel('n_estimators')
plt.ylabel('MSE')
plt.legend()
plt.show()