機器學習系列（十） 支持向量機SVM 2020.6.11

前言

本節學習支持向量機SVM

• 決策邊界離兩邊的點都儘可能遠
• 模型泛化能力強

1、原理

如圖所示
SVM就是希望決策邊界離兩邊的點都儘量遠
求最大化的margin=2d

公式推導如下

得到的公式是

正則

2、實現

通過scikit庫來實現SVM如下

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

"""使用scikit庫實現SVM"""
# 數據
iris = datasets.load_iris()
X = iris.data
y = iris.target
X = X[y<2,:2]
y = y[y<2]
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()
# 數據標準化
standardScaler = StandardScaler()
standardScaler.fit(X)
X_standard = standardScaler.transform(X)
# 線性SVM
svc = LinearSVC(C=1e9) #正則裏的C
svc.fit(X_standard, y)
# 決策邊界可視化
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)
plot_decision_boundary(svc, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y == 0, 0], X_standard[y == 0, 1])
plt.scatter(X_standard[y == 1, 0], X_standard[y == 1, 1])
plt.show()
# 繪製margin
def plot_svc_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)
    w = model.coef_[0]
    b = model.intercept_[0]
    # w0*x0 + w1*x1 + b = 0
    # => x1 = -w0/w1 * x0 - b/w1
    plot_x = np.linspace(axis[0], axis[1], 200)
    up_y = -w[0] / w[1] * plot_x - b / w[1] + 1 / w[1]
    down_y = -w[0] / w[1] * plot_x - b / w[1] - 1 / w[1]
    up_index = (up_y >= axis[2]) & (up_y <= axis[3])
    down_index = (down_y >= axis[2]) & (down_y <= axis[3])
    plt.plot(plot_x[up_index], up_y[up_index], color='black')
    plt.plot(plot_x[down_index], down_y[down_index], color='black')
plot_svc_decision_boundary(svc, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y == 0, 0], X_standard[y == 0, 1])
plt.scatter(X_standard[y == 1, 0], X_standard[y == 1, 1])
plt.show()
svc2 = LinearSVC(C=0.01)
svc2.fit(X_standard, y)
plot_svc_decision_boundary(svc2, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y==0,0], X_standard[y==0,1])
plt.scatter(X_standard[y==1,0], X_standard[y==1,1])
plt.show()

得到的兩個margin圖
C=e9

C=0.01

3、添加多項式特徵

普通的添加多項式特徵如之前的文章所述

這裏還有個添加方法是通過核函數


有個特殊的核函數是高斯核函數

實現如下

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline

"""在SVM中添加多項式特徵"""
# 數據
X, y = datasets.make_moons()
X, y = datasets.make_moons(noise=0.15, random_state=666)
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
# 添加多項式特徵的SVM
def PolynomialSVC(degree, C=1.0):
    return Pipeline([
        ("poly", PolynomialFeatures(degree=degree)),
        ("std_scaler", StandardScaler()),
        ("linearSVC", LinearSVC(C=C))
    ])
poly_svc = PolynomialSVC(degree=3)
poly_svc.fit(X, y)
# 決策邊界可視化
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)
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()

# 使用多項式核函數的SVM
from sklearn.svm import SVC
def PolynomialKernelSVC(degree, C=1.0):
    return Pipeline([
        ("std_scaler", StandardScaler()),
        ("kernelSVC", SVC(kernel="poly", degree=degree, C=C))
    ])
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()

# 高斯核函數的SVM
def RBFKernelSVC(gamma):
    return Pipeline([
        ("std_scaler", StandardScaler()),
        ("svc", SVC(kernel="rbf", gamma=gamma))
    ])
svc = RBFKernelSVC(gamma=1)
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()

添加多項式

多項式核函數

高斯核函數

結語

本節學習SVM
可以用來做分類問題
也可以用來做迴歸問題