机器学习测试笔记（13）——支持向量机（上）

# 导入NumPy库
import numpy as np
# 导入画图工具
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs
def SVM_linear():
#创建50个数据点，分成2类
        X , y =  make_blobs(n_samples=50,random_state=6,centers=2)
#创建一个线性内核的支持向量
        clf =  svm.SVC(kernel='linear',C=1000)# C-SVC的惩罚参数C，默认值是1.0
        clf.fit(X,y)
# 画出数据点
         plt.scatter(X[:,0],X[:,1],c=y,cmap=plt.cm.Paired,s=30)
# 建立图像坐标
        ax = plt.gca() #当前的图表和子图可以使用plt.gcf()和plt.gca()获得
xlim = ax.get_xlim() #返回当前Axes视图的x的上下限
        ylim = ax.get_ylim()  #返回当前Axes视图的y的上下限
# 生成等差数列
        xx =  np.linspace(xlim[0],xlim[1],30)
        yy =  np.linspace(ylim[0],ylim[1],30)
        YY , XX =  np.meshgrid(yy,xx) # meshgrid函数用两个坐标轴上的点在平面上画网格。
        xy =  np.vstack([XX.ravel(),YY.ravel()]).T# np.hstack():横向拼接，增加特征量；np.vstack():纵向拼接，增加样本个数
        Z =  clf.decision_function(xy). reshape(XX.shape)
#decision_function：计算样本点到分割超平面的函数距离
#shape是查看数据有多少行多少列
#reshape()是数组array中的方法，作用是将数据重新组织
# 把分类决定边界画出来
         ax.contour(XX,YY,Z,colors='k',levels=[-1,0,1],alpha=0.5,linestyles=['--','-','--'])  
#绘制等高线
         ax.scatter(clf.support_vectors_[:,0],clf.support_vectors_[:,1],s=100,linewidth=1,facecolors='none')
        plt.show()

import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs
def SVM_base(mykernel,title):
#创建50个数据点，分成2类
       X , y =  make_blobs(n_samples=50,random_state=6,centers=2)
#创建一个线性内核的支持向量
if mykernel ==  'LinearSVC':
              clf =  svm.LinearSVC()
else:
              clf =  svm.SVC(kernel=mykernel,C=1000)# C-SVC的惩罚参数C，默认值是1.0
       clf.fit(X,y)
# 画出数据点
       plt.scatter(X[:,0],X[:,1],c=y,cmap=plt.cm.Paired,s=30)
# 建立图像坐标
       ax = plt.gca() #当前的图表和子图可以使用plt.gcf()和plt.gca()获得
       xlim = ax.get_xlim() #返回当前Axes视图的x的上下限
       ylim = ax.get_ylim() #返回当前Axes视图的y的上下限
# 生成等差数列
       xx =  np.linspace(xlim[0],xlim[1],30)
       yy =  np.linspace(ylim[0],ylim[1],30)
       YY , XX =  np.meshgrid(yy,xx) # meshgrid函数用两个坐标轴上的点在平面上画网格。
       xy = np.vstack([XX.ravel(),YY.ravel()]).T#  np.hstack():横向拼接，增加特征量；np.vstack():纵向拼接，增加样本个数
       Z =  clf.decision_function(xy). reshape(XX.shape)
#decision_function：计算样本点到分割超平面的函数距离
#shape是查看数据有多少行多少列
#reshape()是数组array中的方法，作用是将数据重新组织
# 把分类决定边界画出来
       ax.set_title(title)
       ax.contour(XX,YY,Z,colors='k',levels=[-1,0,1],alpha=0.5,linestyles=['--','-','--'])#绘制等高线
if mykernel !=  'LinearSVC':
              ax.scatter(clf.support_vectors_[:,0],clf.support_vectors_[:,1],s=100,linewidth=1,facecolors='none')
def SVM_for_all_model():
       models =  ['linear','rbf','sigmoid','poly','LinearSVC']
       titles = ['SVC with  Linear Kernel','SVC with RBF Kernel','SVC with sigmoid Kernel','SVC with poly  Kernel','LinearSVC']
       figure, axs =  plt.subplots(2,3,figsize =(10,3))
       figure.suptitle('All  Model of SVM')
       i = 0
for model in models:
              plt.subplot(2,3,i+1)
              SVM_base(model,titles[i])
              i = i+1
       plt.show()

from sklearn import datasets
#定义一个函数来画图
def make_meshgrid(x, y, h=.02):
        x_min,x_max =  x.min()-1,x.max()+1
        y_min,y_max =  y.min()-1,y.max()+1
        xx, yy =  np.meshgrid(np.arange(x_min, x_max, h),np.arange(y_min, y_max, h))
return xx,yy
#定义一个绘制等高线的函数
def plot_contour(ax, clf, xx,yy,**params) :
        Z =  clf.predict(np.c_[xx.ravel(),yy.ravel()])
        Z =  Z.reshape(xx.shape)
        out =  ax.contourf(xx,yy,Z,**params)
return out
#不同核函数的SVM对比
def compare_with_different_SVM():
       wine =  datasets.load_wine()
#选取数据集前两个特征
       X = wine.data[:,:2]
       y = wine.target
       C = 2.5 #SVM参数正则化
       models =  (svm.SVC(kernel='linear',C=C),
                svm.LinearSVC(C=C),
                svm.SVC(kernel='rbf',gamma=0.7,C=C),
                svm.SVC(kernel='sigmoid',C=C),
                svm.SVC(kernel='poly',degree=3,C=C))
       models = (clf.fit(X,y)  for clf in models)
#设定图标
       titles = ('SVC with  Linear Kernel',
'LinearSVC(Linear Kernel)',
'SVC with RBF Kernel',
'SVC with sigmoid Kernel',
'SVC with polynomial(degree 3) Kernel'#设置子图形的个数和排列方式
fig, sub = plt.subplots(2,3,figsize =(10,3))
plt.subplots_adjust(wspace=0.4,hspace=0.4)
#使用前面定义的函数画图
X0, X1 = X[:,0],X[:,1]
        xx, yy =  make_meshgrid(X0, X1)
for clf, title, ax in zip(models, titles,sub.flatten()):
                 plot_contour(ax,clf,xx,yy,cmap=plt.cm.plasma,alpha=0.8)
                 ax.scatter(X0,X1,c=y,cmap=plt.cm.plasma,s=20,edgecolors='k')
                 ax.set_xlim(xx.min(),xx.max())
                 ax.set_ylim(yy.min(),yy.max())
                 ax.set_xlabel('Feature 0')
                 ax.set_ylabel('Feature 1')
                 ax.set_xticks(())
                 ax.set_yticks(())
                 ax.set_title(title)
        plt.show()