人工智能学习---SVM算法编程练习

一.什么是SVM？

Svm（support Vector Mac）又称为支持向量机，是一种二分类的模型。当然如果进行修改之后也是可以用于多类别问题的分类。支持向量机可以分为线性核非线性两大类。其主要思想为找到空间中的一个更够将所有数据样本划开的超平面，并且使得本本集中所有数据到这个超平面的距离最短。

二.Soft Margin SVM

鸢尾花数据集散点图分布：

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

LinearSVC(C=1000000000.0, class_weight=None, dual=True, fit_intercept=True,
          intercept_scaling=1, loss='squared_hinge', max_iter=1000,
          multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
          verbose=0)

绘制决策边界:

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
# 绘制原始数据即散点图
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()

三.多项式与核函数

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
#月亮数据集
X, y = datasets.make_moons() #使用生成的数据
print(X.shape) # (100,2)
print(y.shape) # (100,)
plt.scatter(X[y==0,0],X[y==0,1]) 
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()

(100, 2)
(100,)

加入噪声点:

X, y = datasets.make_moons(noise=0.05,random_state=777) #随机生成噪声点，random_state是随机种子，noise是方差
#分类
plt.scatter(X[y==0,0],X[y==0,1]) 
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()

多项式特征的SVM进行分类:

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()

D:\Program Files (x86)\anaconda\lib\site-packages\ipykernel_launcher.py:11: UserWarning: The following kwargs were not used by contour: 'linewidth'
  # This is added back by InteractiveShellApp.init_path()

核技巧来对数据进行处理:

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()

四.超参数γ

y为100:

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(100)
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()