Useing SVM By Python

 

code:

from sklearn import svm
X = [[0,0],[1,1]]
Y = [0,1]
clf = svm.SVC()
clf.fit(X,Y)
print("clf.predict([[2.0,2.0]])" % clf.predict([[2.0,2.0]]))

#get support vectors
print("support vectors, clf.support_vectors_ : " , clf.support_vectors_ )

#get indices of support vectors
print("indices of supprt vectors, clf.support_ :" , clf.support_)

#get number of support vectors for each class
print("get number of support vectors for eache class " , clf.n_support_)

 

执行结果，如下图：

 

转载于:https://www.cnblogs.com/ordili/p/8390869.html