随机森林学习笔记

集成学习方法

随机森林

实例

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split,GridSearchCV

from sklearn.ensemble import RandomForestClassifier

#导入数据集
data = load_breast_cancer()
#查看特征维度
print('特征维度是：',data.data.shape)

#特征值名字
print('特征值名字：',data.feature_names)

#目标值名字
print('目标值名字：',data.target_names)

#分为训练集及测试集
x_train,x_test,y_train,y_test = train_test_split(data.data,data.target,train_size=0.25)

#随机森林预测（超参数调优）
rf = RandomForestClassifier()

param = {'n_estimators':[120,200,300,500,800],'max_depth':[5,8,15,20]}

#交叉验证与网格搜索
gc = GridSearchCV(rf,param_grid=param,cv=3)

gc.fit(x_train,y_train)

print('准确率：',gc.score(x_test,y_test))

print('最优参数模型：',gc.best_params_)

找到参数

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split,GridSearchCV

from sklearn.ensemble import RandomForestClassifier

#导入数据集
data = load_breast_cancer()
#查看特征维度
print('特征维度是：',data.data.shape)

#特征值名字
print('特征值名字：',data.feature_names)

#目标值名字
print('目标值名字：',data.target_names)

#分为训练集及测试集
x_train,x_test,y_train,y_test = train_test_split(data.data,data.target,train_size=0.25)

#随机森林预测（超参数调优）
rf = RandomForestClassifier(n_estimators=800,max_depth=5)

# param = {'n_estimators':[120,200,300,500,800],'max_depth':[5,8,15,20]}
#
# #交叉验证与网格搜索
# gc = GridSearchCV(rf,param_grid=param,cv=3)
#
# gc.fit(x_train,y_train)
#
# print('准确率：',gc.score(x_test,y_test))
#
# print('最优参数模型：',gc.best_params_)

rf.fit(x_train,y_train)
#输出预测值
y_pre = rf.predict(x_test)
print('预测的值是：',y_pre)

#输出准确率
print('准确率是：',rf.score(x_test,y_test))