支持向量机svm及python测试

最新推荐文章于 2024-06-11 16:41:26 发布

原创最新推荐文章于 2024-06-11 16:41:26 发布 · 581 阅读

1 ·

CC 4.0 BY-SA版权

算法学习专栏收录该内容

10 篇文章

订阅专栏

本文通过实战案例介绍支持向量机(SVM)在房价预测及酒类分类的应用。使用sklearn库实现线性核与径向基核函数(RBF)的SVR回归分析及SVC分类任务，并对数据进行标准化预处理提升模型效果。

from sklearn.svm import SVR,SVC
from sklearn.datasets import load_boston
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import numpy as np
#支持向量机

#波士顿房价回归分析
def svm_svr():
    boston=load_boston()

    # x代表数据集,y代表分类标签
    x_train, x_test, y_train, y_test = train_test_split(boston["data"], boston["target"], random_state=8)

    #对训练数据集核测试数据集进行标准化预处理
    scaler=StandardScaler()
    scaler.fit(x_train)
    x_train_scaler=scaler.transform(x_train)
    x_test_scaler=scaler.transform(x_test)

    #linear核函数
    svr=SVR(kernel='linear')
    svr.fit(x_train_scaler,y_train)

    print("linear核函数模型训练集得分:{}".format(svr.score(x_train_scaler,y_train)))
    print("linear核函数模型测试集得分:{}".format(svr.score(x_test_scaler, y_test)))

    #rbf核函数
    svr=SVR(kernel='rbf',C=100,gamma=0.1)
    svr.fit(x_train_scaler,y_train)

    print("linear核函数模型训练集得分:{}".format(svr.score(x_train_scaler,y_train)))
    print("linear核函数模型测试集得分:{}".format(svr.score(x_test_scaler, y_test)))

def svm_svc():
    # 酒的分类
    wine_dataset = load_wine()

    # x代表数据集,y代表分类标签
    x_train, x_test, y_train, y_test = train_test_split(wine_dataset["data"], wine_dataset["target"], random_state=0)
    #对训练数据集核测试数据集进行标准化预处理
    scaler=StandardScaler()
    scaler.fit(x_train)
    x_train_scaler=scaler.transform(x_train)
    x_test_scaler=scaler.transform(x_test)

    # linear核函数
    svc = SVC(kernel='linear')
    svc.fit(x_train_scaler, y_train)

    print("linear核函数模型训练集得分:{}".format(svc.score(x_train_scaler, y_train)))
    print("linear核函数模型测试集得分:{}".format(svc.score(x_test_scaler, y_test)))

    # rbf核函数
    svc = SVC(kernel='rbf', C=100, gamma=0.1)
    svc.fit(x_train_scaler, y_train)

    print("linear核函数模型训练集得分:{}".format(svc.score(x_train_scaler, y_train)))
    print("linear核函数模型测试集得分:{}".format(svc.score(x_test_scaler, y_test)))

    # 使用模型完成预测
    x_news = np.array([[13.2, 2.77, 2.51, 18.5, 96.6, 1.04, 2.55, 0.57, 1.47, 6.2, 1.05, 3.33, 820]])
    prediction = svc.predict(x_news)
    print(wine_dataset["target_names"][prediction])