前言
本次内容是对SVM算法的补充
重做例子代码
import matplotlib.pyplot as plt
import numpy as np
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()
# 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()
处理非线性
# 接下来我们看下如何处理非线性的数据。
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
X, y = datasets.make_moons() #使用生成的数据
print(X.shape) # (100,2)
print(y.shape) # (100,)
# 接下来绘制下生成的数据
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
X, y = datasets.make_moons(noise=0.15,random_state=777)
#随机生成噪声点,random_state是随机种子,noise是方差
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.preprocessing import PolynomialFeatures,StandardScaler
from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline
def PolynomialSVC(degree,C=1.0):
return Pipeline([ ("poly",PolynomialFeatures(degree=degree)),#生成多项式
("std_scaler",StandardScaler()),#标准化
("linearSVC",LinearSVC(C=C))#最后生成svm
])
poly_svc = PolynomialSVC(degree=3)
poly_svc.fit(X,y)
plot_decision_boundary(poly_svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.svm import SVC
def PolynomialKernelSVC(degree,C=1.0):
return Pipeline([ ("std_scaler",StandardScaler()),
("kernelSVC",SVC(kernel="poly"))# poly代表多项式特征
])
poly_kernel_svc = PolynomialKernelSVC(degree=3)
poly_kernel_svc.fit(X,y)
plot_decision_boundary(poly_kernel_svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(-4,5,1)
#生成测试数据
y = np.array((x >= -2 ) & (x <= 2),dtype='int')
plt.scatter(x[y==0],[0]*len(x[y==0]))
# x取y=0的点, y取0,有多少个x,就有多少个y
plt.scatter(x[y==1],[0]*len(x[y==1]))
plt.show()
高斯核函数
# 高斯核函数
def gaussian(x,l):
gamma = 1.0
return np.exp(-gamma * (x -l)**2)
l1,l2 = -1,1
X_new = np.empty((len(x),2))#len(x) ,2
for i,data in enumerate(x):
X_new[i,0] = gaussian(data,l1)
X_new[i,1] = gaussian(data,l2)
plt.scatter(X_new[y==0,0],X_new[y==0,1])
plt.scatter(X_new[y==1,0],X_new[y==1,1])
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
X,y = datasets.make_moons(noise=0.15,random_state=777)
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
def RBFKernelSVC(gamma=1.0):
return Pipeline([ ('std_scaler',StandardScaler()), ('svc',SVC(kernel='rbf',gamma=gamma)) ])
svc = RBFKernelSVC()
svc.fit(X,y)
plot_decision_boundary(svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
def RBFKernelSVC(gamma=100):
return Pipeline([ ('std_scaler',StandardScaler()), ('svc',SVC(kernel='rbf',gamma=gamma)) ])
svc = RBFKernelSVC()
svc.fit(X,y)
plot_decision_boundary(svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
def RBFKernelSVC(gamma=10):
return Pipeline([ ('std_scaler',StandardScaler()), ('svc',SVC(kernel='rbf',gamma=gamma)) ])
svc = RBFKernelSVC()
svc.fit(X,y)
plot_decision_boundary(svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
def RBFKernelSVC(gamma=0.1):
return Pipeline([ ('std_scaler',StandardScaler()), ('svc',SVC(kernel='rbf',gamma=gamma)) ])
svc = RBFKernelSVC()
svc.fit(X,y)
plot_decision_boundary(svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
boston = datasets.load_boston()
X = boston.data
y = boston.target
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=777)
# 把数据集拆分成训练数据和测试数据
from sklearn.svm import LinearSVR
from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler
def StandardLinearSVR(epsilon=0.1):
return Pipeline([ ('std_scaler',StandardScaler()), ('linearSVR',LinearSVR(epsilon=epsilon)) ])
svr = StandardLinearSVR()
svr.fit(X_train,y_train)
svr.score(X_test,y_test)
参考文章
https://blog.csdn.net/weixin_56102526/article/details/121110135?spm=1001.2014.3001.5501