1. 线性可分SVM

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

%matplotlib inline

1.1 生成模拟数据

# 导入sklearn模拟二分类数据生成模块
from sklearn.datasets import make_blobs
# 生成模拟二分类数据集
X, y =  make_blobs(n_samples=150, n_features=2, centers=2, cluster_std=1.2, random_state=40)
# 设置颜色参数
colors = {0:'r', 1:'g'}
# 绘制二分类数据集的散点图
plt.scatter(X[:,0], X[:,1], marker='o', c=pd.Series(y).map(colors))
plt.show();

​

​

# 将标签转换为1/-1
y_ = y.copy()
y_[y_==0] = -1
y_ = y_.astype(float)

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y_, test_size=0.3, random_state=43)
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)

(105, 2) (105,) (45, 2) (45,)

1.2 线性可分支持向量机

# 导入sklearn线性SVM分类模块
from sklearn.svm import LinearSVC
# 创建模型实例
clf = LinearSVC(random_state=0, tol=1e-5)
# 训练
clf.fit(X_train, y_train)
# 预测
y_pred = clf.predict(X_test)

from sklearn.metrics import accuracy_score
# 计算测试集准确率
print(accuracy_score(y_test, y_pred))

1.0

from matplotlib.colors import ListedColormap### 绘制线性可分支持向量机决策边界图
def plot_classifer(model, X, y):# 超参数边界x_min = -7x_max = 12y_min = -12y_max = -1step = 0.05# meshgridxx, yy = np.meshgrid(np.arange(x_min, x_max, step),np.arange(y_min, y_max, step))# 模型预测z = model.predict(np.c_[xx.ravel(), yy.ravel()])# 定义color mapcmap_light = ListedColormap(['#FFAAAA', '#AAFFAA'])cmap_bold = ListedColormap(['#FF0000', '#003300'])z = z.reshape(xx.shape)plt.figure(figsize=(8, 5), dpi=96)plt.pcolormesh(xx, yy, z, cmap=cmap_light)plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)plt.show()

plot_classifer(clf, X_train, y_train)

plot_classifer(clf, X_test, y_test)

​

2. 广义线性可分SVM

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

%matplotlib inline

2.1 生成模拟数据

mean1, mean2 = np.array([0, 2]), np.array([2, 0])
covar = np.array([[1.5, 1.0], [1.0, 1.5]])
X1 = np.random.multivariate_normal(mean1, covar, 100)
y1 = np.ones(X1.shape[0])
X2 = np.random.multivariate_normal(mean2, covar, 100)
y2 = -1 * np.ones(X2.shape[0])
X_train = np.vstack((X1[:80], X2[:80]))
y_train = np.hstack((y1[:80], y2[:80]))
X_test = np.vstack((X1[80:], X2[80:]))
y_test = np.hstack((y1[80:], y2[80:]))
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
print(X_train.shape)

(160, 2) (160,) (40, 2) (40,)
(160, 2)

# 设置颜色参数
colors = {1:'r', -1:'g'}
# 绘制二分类数据集的散点图
plt.scatter(X_train[:,0], X_train[:,1], marker='o', c=pd.Series(y_train).map(colors))
plt.show();

​

​

2.2 广义线性可分支持向量机

from sklearn import svm
# 创建svm模型实例
clf = svm.SVC(kernel='linear')
# 模型拟合
clf.fit(X_train, y_train)
# 模型预测
y_pred = clf.predict(X_test)

from sklearn.metrics import accuracy_score
# 计算测试集准确率
print(accuracy_score(y_test, y_pred))
# 计算测试集准确率
print('Accuracy of soft margin svm based on sklearn: ', accuracy_score(y_test, y_pred))

1.0
Accuracy of soft margin svm based on sklearn:  1.0

2.3 结果可视化

def plot_classifier(X1_train, X2_train, clf):plt.plot(X1_train[:,0], X1_train[:,1], "ro")plt.plot(X2_train[:,0], X2_train[:,1], "go")plt.scatter(clf.support_vectors_[:,0], clf.support_vectors_[:,1], s=100, c="r", edgecolors="b", label="support vector")X1, X2 = np.meshgrid(np.linspace(-4,4,50), np.linspace(-4,4,50))X = np.array([[x1, x2] for x1, x2 in zip(np.ravel(X1), np.ravel(X2))])Z = clf.decision_function(X).reshape(X1.shape)plt.contour(X1, X2, Z, [0.0], colors='k', linewidths=1, origin='lower')plt.contour(X1, X2, Z + 1, [0.0], colors='grey', linewidths=1, origin='lower')plt.contour(X1, X2, Z - 1, [0.0], colors='grey', linewidths=1, origin='lower')plt.legend()plt.show()plot_classifier(X_train[y_train==1], X_train[y_train==-1], clf)

3. 非线性SVM

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

%matplotlib inline

3.1 生成模拟数据

mean1, mean2 = np.array([-1, 2]), np.array([1, -1])
mean3, mean4 = np.array([4, -4]), np.array([-4, 4])
covar = np.array([[1.0, 0.8], [0.8, 1.0]])
X1 = np.random.multivariate_normal(mean1, covar, 50)
X1 = np.vstack((X1, np.random.multivariate_normal(mean3, covar, 50)))
y1 = np.ones(X1.shape[0])
X2 = np.random.multivariate_normal(mean2, covar, 50)
X2 = np.vstack((X2, np.random.multivariate_normal(mean4, covar, 50)))
y2 = -1 * np.ones(X2.shape[0])
X_train = np.vstack((X1[:80], X2[:80]))
y_train = np.hstack((y1[:80], y2[:80]))
X_test = np.vstack((X1[80:], X2[80:]))
y_test = np.hstack((y1[80:], y2[80:]))
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)

(160, 2) (160,) (40, 2) (40,)

# 设置颜色参数
colors = {1:'r', -1:'g'}
# 绘制二分类数据集的散点图
plt.scatter(X_train[:,0], X_train[:,1], marker='o', c=pd.Series(y_train).map(colors))
plt.show();

​

3.2 非线性SVM

from sklearn import svm
# 创建svm模型实例
clf = svm.SVC(kernel='rbf')
# 模型拟合
clf.fit(X_train, y_train)

SVC()

SVC()

# 导入sklearn准确率评估函数
from sklearn.metrics import accuracy_score
# 模型预测
y_pred = clf.predict(X_test)
# 计算测试集准确率
print('Accuracy of soft margin svm based on cvxopt: ', accuracy_score(y_test, y_pred))

Accuracy of soft margin svm based on cvxopt:  1.0

3.3 结果可视化

### 绘制非线性可分支持向量机
def plot_classifier(X1_train, X2_train, clf):plt.plot(X1_train[:,0], X1_train[:,1], "ro")plt.plot(X2_train[:,0], X2_train[:,1], "go")plt.scatter(clf.support_vectors_[:,0], clf.support_vectors_[:,1], s=100, c="r", edgecolors="b", label="support vector")X1, X2 = np.meshgrid(np.linspace(-4,4,50), np.linspace(-4,4,50))X = np.array([[x1, x2] for x1, x2 in zip(np.ravel(X1), np.ravel(X2))])Z = clf.decision_function(X).reshape(X1.shape)plt.contour(X1, X2, Z, [0.0], colors='k', linewidths=1, origin='lower')plt.contour(X1, X2, Z + 1, [0.0], colors='grey', linewidths=1, origin='lower')plt.contour(X1, X2, Z - 1, [0.0], colors='grey', linewidths=1, origin='lower')plt.legend()plt.show()plot_classifier(X_train[y_train==1], X_train[y_train==-1], clf)

​

​

4. SVR

import numpy as np
import matplotlib.pyplot as plt

%matplotlib inline

4.1 生成模拟数据

np.random.seed(0)
X = np.sort(np.random.uniform(0,6,50),axis=0)
y = 2*np.sin(X)+0.1*np.random.randn(50)
X = X.reshape(-1,1)

4.2 SVR建模

from sklearn import svm

svr_rbf = svm.SVR(kernel='rbf',gamma=0.4,C=100)
svr_rbf.fit(X,y)

SVR(C=100, gamma=0.4)

SVR(C=100, gamma=0.4)

svr_linear = svm.SVR(kernel='linear',C=100)
svr_linear.fit(X,y)

SVR(C=100, kernel='linear')

SVR(C=100, kernel='linear')

svr_poly = svm.SVR(kernel='poly',degree=3,C=100)
svr_poly.fit(X,y)

SVR(C=100, kernel='poly')

SVR(C=100, kernel='poly')

4.3 生成测试数据集

X_test = np.linspace(X.min(), 1.5*X.max(), 50)
np.random.seed(0)
y_test = 2*np.sin(X_test) + 0.1*np.random.randn(50)
X_test=X_test.reshape(-1,1)

4.4 预测并可视化

y_rbf = svr_rbf.predict(X_test)
y_linear = svr_linear.predict(X_test)
y_poly = svr_poly.predict(X_test)
sp = svr_rbf.support_
plt.figure(figsize=(9, 8),facecolor='w')
plt.scatter(X[sp], y[sp], s=200, c='r', marker='*', label='RBF Support Vectors')
plt.plot(X_test, y_rbf, 'r-', linewidth=2, label='RBF Kernel')
plt.plot(X_test, y_linear, 'g-', linewidth=2, label='Linear Kernel')
plt.plot(X_test, y_poly, 'b-', linewidth=2, label='Polynomial Kernel')
plt.plot(X, y, 'ks', markersize=5, label='train data')
plt.plot(X_test, y_test, 'mo', markersize=5, label='test data')
plt.legend(loc='lower left')
plt.title('SVR', fontsize=16)
plt.xlabel('X')
plt.ylabel('Y')
plt.grid(True)
plt.show()

​

​