支持向量机SVM
SVM最基本的应用就是分类。对于SVM,有一个分类平面,两个点集到此平面的最小距离最大,两个点集中的边缘点到此平面的距离最大。
代码实现:
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
data = pd.read_csv(r'G:\学习文件\机器学习\data_mining_data\breast_cancer.csv')
# 切分特征和标签
features = data.iloc[:, :-1]
labels = data.iloc[:, -1]
# 归一化
ss = StandardScaler()
# ss.fit(features)
features_std = ss.fit_transform(features)
# 切分训练集和测试集
features_train, features_test, labels_train, labels_test = train_test_split(features_std, labels)
# 创建模型
svm_module = SVC()
svm_module.fit(features_test, labels_test)
score = svm_module.score(features_test, labels_test)
print(score)