机器学习——支持向量机

参数调整：https://www.cnblogs.com/pinard/p/6117515.html
https://www.cnblogs.com/pinard/p/6126077.html
原理：《统计学习方法》李航

练习：

import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
X,y=make_blobs(n_samples=50,centers=2,random_state=0,cluster_std=0.6)
plt.scatter(X[:,0],X[:,1],c=y,s=50,cmap='autumn')
plt.show()
from sklearn.svm import SVC
model=SVC(kernel='linear')
model.fit(X,y)
print(model.support_vectors_)      #支持向量
print(model.support_)

#rbf核函数
from sklearn.datasets.samples_generator import make_circles
X,y=make_circles(100,factor=.1,noise=.1)
plt.scatter(X[:,0],X[:,1],c=y,s=50,cmap='autumn')
plt.show()
clf=SVC(kernel='rbf',C=1E6,gamma=1)         #C越大分类要求越严格, gamma越大模型越复杂
clf.fit(X,y)
print(model.support_vectors_)

from sklearn.datasets import fetch_lfw_people
faces=fetch_lfw_people(min_faces_per_person=60)
print(faces.target_names)
print(faces.images.shape)

#降维
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
pca=PCA(n_components=150,whiten=True,random_state=42)
svc=SVC(kernel='rbf',class_weight='balanced')
model=make_pipeline(pca,svc)

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(faces.data,faces.target,random_state=40)

from sklearn.model_selection import GridSearchCV
param={'svc_C':[1,5,10],'svc_gamma':[0.0001,0.0005,0.001]}
grid=GridSearchCV(model,param_grid=param)
grid.fit(x_train,y_train)
print(grid.best_params_)
model=grid.best_estimator_
y_predict=model.predict(x_test)