SVM分类与回归

NSummer

已于 2023-09-18 15:18:24 修改

阅读量239

点赞数 1

文章标签：支持向量机分类回归

于 2023-06-13 16:51:10 首次发布

本文链接：https://blog.csdn.net/weixin_38692258/article/details/131190484

版权

SVM分类

#SVM分类
from sklearn.svm import SVC
from sklearn.preprocessing import StandardScaler 
from sklearn import datasets
from sklearn.model_selection import train_test_split

#读数据
iris = datasets.load_iris()
X = iris.data
y = iris.target

#标准化
std = StandardScaler()
X_std = std.fit_transform(X)

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_std, y, test_size=0.3)

# 创建SVM回归模型
svm_classfication = SVC(kernel='linear', C=1.0)  #C:错误样本的惩罚参数，kernel：核函数

# 拟合训练数据
svm_classfication.fit(X_train, y_train)

#模型效果
svm_classfication.score(X_test,y_test)

SVM回归

#SVM回归
from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler 
from sklearn import datasets
from sklearn.model_selection import train_test_split

#读数据
boston = datasets.load_boston()
X = boston.data
y = boston.target

#标准化
std = StandardScaler()
X_std = std.fit_transform(X)

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_std, y, test_size=0.3)

# 创建SVM回归模型
svm_regression = SVR(kernel='linear', C=1.0)  #C:错误样本的惩罚参数，kernel：核函数

# 拟合训练数据
svm_regression.fit(X_train, y_train)

#模型效果
svm_regression.score(X_test,y_test)