SVM算法编程练习

未经标准化的原始数据点分布

import numpy as np 
import matplotlib.pyplot as plt 
from sklearn import datasets 
from sklearn.preprocessing import StandardScaler 
from sklearn.svm import LinearSVC 

iris = datasets.load_iris() 
X = iris.data 
y = iris.target 
X = X [y<2,:2] #只取y<2的类别，也就是0 1 并且只取前两个特征
y = y[y<2] # 只取y<2的类别 
# 分别画出类别0和1的点 
plt.scatter(X[y==0,0],X[y==0,1],color='red') 
plt.scatter(X[y==1,0],X[y==1,1],color='blue') 
plt.show() 

绘制决策边界

from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC

# 标准化 
standardScaler = StandardScaler() 
standardScaler.fit(X) #计算训练数据的均值和方差 
X_standard = standardScaler.transform(X) #再用scaler中的均值和方差来转换X，使X标准化 
svc = LinearSVC(C=1e9) #线性SVM分类器 
svc.fit(X_standard,y) # 训练svm

def plot_decision_boundary(model, axis):
    x0, x1 = np.meshgrid( np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1,1), np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1,1) )
    X_new = np.c_[x0.ravel(), x1.ravel()] 
    y_predict = model.predict(X_new) 
    zz = y_predict.reshape(x0.shape)
    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap) # 绘制决策边界 
plot_decision_boundary(svc,axis=[-3,3,-3,3]) # x,y轴都在-3到3之间 
# 绘制原始数据 
plt.scatter(X_standard[y==0,0],X_standard[y==0,1],color='red') 
plt.scatter(X_standard[y==1,0],X_standard[y==1,1],color='blue') 
plt.show()   

D:\apps\anaconda\lib\site-packages\ipykernel_launcher.py:18: UserWarning: The following kwargs were not used by contour: 'linewidth'

再次实例化svc

svc2 = LinearSVC(C=0.01)
svc2.fit(X_standard, y)
plot_decision_boundary(svc2, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y==0, 0], X_standard[y==0, 1], color='red')
plt.scatter(X_standard[y==1, 0], X_standard[y==1, 1], color='blue')
plt.show()

D:\apps\anaconda\lib\site-packages\ipykernel_launcher.py:18: UserWarning: The following kwargs were not used by contour: 'linewidth'

获得权重系数

 svc.coef_  #获取学习到的权重