月亮数据集

1. 使用线性核

导入包：

# 导入月亮数据集和svm方法
#这是线性svm
from sklearn import datasets #导入数据集
from sklearn.svm import LinearSVC #导入线性svm
from matplotlib.colors import ListedColormap
from sklearn.preprocessing import StandardScaler
data_x,data_y=datasets.make_moons(noise=0.15,random_state=777)#生成月亮数据集
# random_state是随机种子，nosie是方
plt.scatter(data_x[data_y==0,0],data_x[data_y==0,1])
plt.scatter(data_x[data_y==1,0],data_x[data_y==1,1])
data_x=data_x[data_y<2,:2]#只取data_y小于2的类别，并且只取前两个特征
plt.show()

进行标准化训练：

scaler=StandardScaler()# 标准化
scaler.fit(data_x)#计算训练数据的均值和方差
data_x=scaler.transform(data_x) #再用scaler中的均值和方差来转换X，使X标准化
liner_svc=LinearSVC(C=1e9,max_iter=100000)#线性svm分类器,iter是迭达次数，c值决定的是容错，c越大，容错越小
liner_svc.fit(data_x,data_y)
# 边界绘制函数
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))
    # meshgrid函数是从坐标向量中返回坐标矩阵
    x_new=np.c_[x0.ravel(),x1.ravel()]
    y_predict=model.predict(x_new)#获取预测值
    zz=y_predict.reshape(x0.shape)
    custom_cmap=ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    plt.contourf(x0,x1,zz,cmap=custom_cmap)
#画图并显示参数和截距
plot_decision_boundary(liner_svc,axis=[-3,3,-3,3])
plt.scatter(data_x[data_y==0,0],data_x[data_y==0,1],color='red')
plt.scatter(data_x[data_y==1,0],data_x[data_y==1,1],color='blue')
plt.show()
print('参数权重')
print(liner_svc.coef_)
print('模型截距')
print(liner_svc.intercept_)

多项式核

导入数据集：

# 导入月亮数据集和svm方法
#这是多项式核svm
from sklearn import datasets #导入数据集
from sklearn.svm import LinearSVC #导入线性svm
from sklearn.pipeline import Pipeline #导入python里的管道
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler,PolynomialFeatures #导入多项式回归和标准化
data_x,data_y=datasets.make_moons(noise=0.15,random_state=777)#生成月亮数据集
# random_state是随机种子，nosie是方
plt.scatter(data_x[data_y==0,0],data_x[data_y==0,1])
plt.scatter(data_x[data_y==1,0],data_x[data_y==1,1])
data_x=data_x[data_y<2,:2]#只取data_y小于2的类别，并且只取前两个特征
plt.show()
def PolynomialSVC(degree,c=10):#多项式svm
    return Pipeline([
            # 将源数据 映射到 3阶多项式
            ("poly_features", PolynomialFeatures(degree=degree)),
            # 标准化
            ("scaler", StandardScaler()),
            # SVC线性分类器
            ("svm_clf", LinearSVC(C=10, loss="hinge", random_state=42,max_iter=10000))
        ])
# 进行模型训练并画图
poly_svc=PolynomialSVC(degree=3)
poly_svc.fit(data_x,data_y)
plot_decision_boundary(poly_svc,axis=[-1.5,2.5,-1.0,1.5])#绘制边界
plt.scatter(data_x[data_y==0,0],data_x[data_y==0,1],color='red')#画点
plt.scatter(data_x[data_y==1,0],data_x[data_y==1,1],color='blue')
plt.show()
print('参数权重')
print(poly_svc.named_steps['svm_clf'].coef_)
print('模型截距')
print(poly_svc.named_steps['svm_clf'].intercept_)

高斯核

导入包：

## 导入包
from sklearn import datasets #导入数据集
from sklearn.svm import SVC #导入svm
from sklearn.pipeline import Pipeline #导入python里的管道
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler#导入标准化
def RBFKernelSVC(gamma=1.0):
    return Pipeline([
        ('std_scaler',StandardScaler()),
        ('svc',SVC(kernel='rbf',gamma=gamma))
    ])
svc=RBFKernelSVC(gamma=100)#gamma参数很重要，gamma参数越大，支持向量越小
svc.fit(data_x,data_y)
plot_decision_boundary(svc,axis=[-1.5,2.5,-1.0,1.5])
plt.scatter(data_x[data_y==0,0],data_x[data_y==0,1],color='red')#画点
plt.scatter(data_x[data_y==1,0],data_x[data_y==1,1],color='blue')
plt.show()

SVM代码实现（鸢尾花数据集）

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets

# 定义网格函数
def make_meshgrid(x, y, h=.02):
    """Create a mesh of points to plot in
    Parameters
    ----------
    x: data to base x-axis meshgrid on
    y: data to base y-axis meshgrid on
    h: stepsize for meshgrid, optional
    Returns
    -------
    xx, yy : ndarray
    """
    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
    
# 绘制填充颜色的二维等高线图_
def plot_contours(ax, clf, xx, yy, **params):
    """Plot the decision boundaries for a classifier.
    Parameters
    ----------
    ax: matplotlib axes object
    clf: a classifier
    xx: meshgrid ndarray
    yy: meshgrid ndarray
    params: dictionary of params to pass to contourf, optional
    """
    # np.c_中的c是column的缩写，是按列叠加两个矩阵的意思，就是把两矩阵左右相加
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    out = ax.contourf(xx, yy, Z, **params)
    return out

# import some data to play with
iris = datasets.load_iris()
# Take the first two features. We could avoid this by using a two-dim dataset
X = iris.data[:, :2]
y = iris.target

# we create an instance of SVM and fit out data. We do not scale our data since we want to plot the support vectors
C = 1.0  # SVM regularization parameter
models = (svm.SVC(kernel='linear', C=C),
          svm.LinearSVC(C=C, max_iter=10000),
          svm.SVC(kernel='rbf', gamma=0.7, C=C),
          svm.SVC(kernel='poly', degree=3, gamma='auto', C=C))
models = (clf.fit(X, y) for clf in models)
# title for the plots
titles = ('SVC with linear kernel',
          'LinearSVC (linear kernel)',
          'SVC with RBF kernel',
          'SVC with polynomial (degree 3) kernel')
# Set-up 2x2 grid for plotting.
fig, sub = plt.subplots(2, 2)
plt.subplots_adjust(wspace=0.4, hspace=0.4)
plt.rcParams['savefig.dpi'] = 600 #图片像素
plt.rcParams['figure.dpi'] = 600 #分辨率

X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)
for clf, title, ax in zip(models, titles, sub.flatten()):
    plot_contours(ax, clf, xx, yy,cmap=plt.cm.coolwarm, alpha=0.8)
    ax.scatter(X0, X1, c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xlabel('Sepal length')
    ax.set_ylabel('Sepal width')
    ax.set_xticks(())
    ax.set_yticks(())
    ax.set_title(title)
plt.show()