本文详细介绍了支持向量机（SVM）的原理，包括线性SVM和非线性SVM的决策边界绘制，以及通过核函数解决非线性问题。此外，还探讨了SVM的参数调整，如C和gamma的影响，展示它们如何影响分类效果。最后，通过人脸识别任务展示了SVM在实际问题中的应用，并使用网格搜索调参。
原理
1.线性
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import make_blobs
from sklearn.svm import SVC
sns.set()
# 绘图函数
def plot_svc_decision_function(model, ax=None, plot_support=True):
"""Plot the decision function for a 2D SVC"""
if ax is None:
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
# create grid to evaluate model
x = np.linspace(xlim[0], xlim[1], 30)
y = np.linspace(ylim[0], ylim[1], 30)
Y, X = np.meshgrid(y, x)
xy = np.vstack([X.ravel(), Y.ravel()]).T
P = model.decision_function(xy).reshape(X.shape)
# plot decision boundary and margins
ax.contour(X, Y, P, colors='k',
levels=[-1, 0, 1], alpha=0.5,
linestyles=['--', '-', '--'])
# plot support vectors
if plot_support:
ax.scatter(model.support_vectors_[:, 0],
model.support_vectors_[:, 1],
s=300, linewidth=1, facecolors='none')
ax.set_xlim(xlim)
ax.set_ylim(ylim)
X, y = make_blobs(n_samples=50, centers=2,
random_state=0, cluster_std=0.60)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
model = SVC(kernel='linear')
model.fit(X, y)
plot_svc_decision_function(model)
2.非线性
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import make_blobs
from sklearn.svm import SVC
from mpl_toolkits import mplot3d
from sklearn.datasets import make_circles
sns.set()
def plot_svc_decision_function(model, ax=None, plot_support=True):
"""Plot the decision function for a 2D SVC"""
if ax is None:
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
# create grid to evaluate model
x = np.linspace(xlim[0], xlim[1], 30)
y = np.linspace(ylim[0], ylim[1], 30)
Y, X = np.meshgrid(y, x)
xy = np.vstack([X.ravel(), Y.ravel()]).T
P = model.decision_function(xy).reshape(X.shape)
# plot decision boundary and margins
ax.contour(X, Y, P, colors='k',
levels=[-1, 0, 1], alpha=0.5,
linestyles=['--', '-', '--'])
# plot support vectors
if plot_support:
ax.scatter(model.support_vectors_[:, 0],
model.support_vectors_[:, 1],
s=300, linewidth=1, facecolors='none')
ax.set_xlim(xlim)
ax.set_ylim(ylim)
def plot_3D(elev=30, azim=30, X=X, y=y):
ax = plt.subplot(projection='3d')
ax.scatter3D(X[:, 0], X[:, 1], r, c=y, s=50, cmap='autumn')
ax.view_init(elev=elev, azim=azim)
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('r')
# 线性核函数无法划分非线性分布的点
X, y = make_circles(100, factor=.1, noise=.1)
clf = SVC(kernel='linear').fit(X, y)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plot_svc_decision_function(clf, plot_support=False)
# 将数据维度上升一维观察数据
r = np.exp(-(X ** 2).sum(1))
plot_3D(elev=45, azim=45, X=X, y=y)
# 选择径向基函数作为核函数
clf = SVC(kernel='rbf', C=1E6)
clf.fit(X, y)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plot_svc_decision_function(clf)
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
s=300, lw=1, facecolors='none')
3.SVM调参
参数c正是影响了支持向量与决策平面之间的距离，具体效果为：c越大，分类越严格，不能有错误；c越小，意味着有更大的错误容忍度
gamma主要是对低维的样本进行高度度映射，gamma值越大映射的维度越高，训练的结果越好，但是越容易引起过拟合，即泛化能力低。
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import make_blobs
from sklearn.svm import SVC
sns.set()
def plot_svc_decision_function(model, ax=None, plot_support=True):
"""Plot the decision function for a 2D SVC"""
if ax is None:
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
# create grid to evaluate model
x = np.linspace(xlim[0], xlim[1], 30)
y = np.linspace(ylim[0], ylim[1], 30)
Y, X = np.meshgrid(y, x)
xy = np.vstack([X.ravel(), Y.ravel()]).T
P = model.decision_function(xy).reshape(X.shape)
# plot decision boundary and margins
ax.contour(X, Y, P, colors='k',
levels=[-1, 0, 1], alpha=0.5,
linestyles=['--', '-', '--'])
# plot support vectors
if plot_support:
ax.scatter(model.support_vectors_[:, 0],
model.support_vectors_[:, 1],
s=300, linewidth=1, facecolors='none')
ax.set_xlim(xlim)
ax.set_ylim(ylim)
# 调节SVM参数
X, y = make_blobs(n_samples=100, centers=2,
random_state=0, cluster_std=0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
fig, ax = plt.subplots(1, 2, figsize=(16, 6))
fig.subplots_adjust(left=0.0625, right=0.95, wspace=0.1)
# 参数C
for axi, C in zip(ax, [10.0, 0.1]):
model = SVC(kernel='linear', C=C).fit(X, y)
axi.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plot_svc_decision_function(model, axi)
axi.scatter(model.support_vectors_[:, 0],
model.support_vectors_[:, 1],
s=300, lw=1, facecolors='none')
axi.set_title('C = {0:.1f}'.format(C), size=14)
fig, ax = plt.subplots(1, 2, figsize=(16, 6))
fig.subplots_adjust(left=0.0625, right=0.95, wspace=0.1)
# 参数gamma
for axi, gamma in zip(ax, [10.0, 0.1]):
model = SVC(kernel='rbf', gamma=gamma).fit(X, y)
axi.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plot_svc_decision_function(model, axi)
axi.scatter(model.support_vectors_[:, 0],
model.support_vectors_[:, 1],
s=300, lw=1, facecolors='none')
axi.set_title('gamma = {0:.1f}'.format(gamma), size=14)
人脸识别
from sklearn.datasets import fetch_lfw_people
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns
# 下载人脸数据库
faces = fetch_lfw_people(min_faces_per_person=60)
# 查看数据集
fig, ax = plt.subplots(3, 5)
for i, axi in enumerate(ax.flat):
axi.imshow(faces.images[i], cmap='bone')
axi.set(xticks=[], yticks=[],
xlabel=faces.target_names[faces.target[i]])
# PCA降维
pca = PCA(n_components=150, whiten=True, random_state=42)
svc = SVC(kernel='rbf', class_weight='balanced')
model = make_pipeline(pca, svc)
# 划分数据集
Xtrain, Xtest, ytrain, ytest = train_test_split(faces.data, faces.target,
random_state=40)
# 网格搜索
param_grid = {'svc__C': [1, 5, 10],
'svc__gamma': [0.0001, 0.0005, 0.001]}
grid = GridSearchCV(model, param_grid)
grid.fit(Xtrain, ytrain)
model = grid.best_estimator_
yfit = model.predict(Xtest)
# 查看分类结果
fig, ax = plt.subplots(4, 6)
for i, axi in enumerate(ax.flat):
axi.imshow(Xtest[i].reshape(62, 47), cmap='bone')
axi.set(xticks=[], yticks=[])
axi.set_ylabel(faces.target_names[yfit[i]].split()[-1],
color='black' if yfit[i] == ytest[i] else 'red')
fig.suptitle('Predicted Names; Incorrect Labels in Red', size=14)
# 打印分类报告
print(classification_report(ytest, yfit,
target_names=faces.target_names))
# 打印混淆矩阵
mat = confusion_matrix(ytest, yfit)
sns.heatmap(mat.T, square=True, annot=True, fmt='d', cbar=False,
xticklabels=faces.target_names,
yticklabels=faces.target_names)
plt.xlabel('true label')
plt.ylabel('predicted label')
1.比较逻辑回归和支持向量机
- LR和SVM都可以处理分类问题，且一般都用于处理线性二分类问题（在改进的情况下可以处理多分类问题）
- 两个方法都可以增加不同的正则化项，如L1、L2等等。所以在很多实验中，两种算法的结果是很接近的。
区别：
- LR是参数模型，SVM是非参数模型。
- 从目标函数来看，区别在于逻辑回归采用的是Logistical Loss，SVM采用的是hinge loss.这两个损失函数的目的都是增加对分类影响较大的数据点的权重，减少与分类关系较小的数据点的权重。
- SVM的处理方法是只考虑Support Vectors，也就是和分类最相关的少数点，去学习分类器。而逻辑回归通过非线性映射，大大减小了离分类平面较远的点的权重，相对提升了与分类最相关的数据点的权重。
- 逻辑回归相对来说模型更简单，好理解，特别是大规模线性分类时比较方便。而SVM的理解和优化相对来说复杂一些，SVM转化为对偶问题后,分类只需要计算与少数几个支持向量的距离,这个在进行复杂核函数计算时优势很明显,能够大大简化模型和计算。
- Logic 能做的 SVM能做，但可能在准确率上有问题，SVM能做的Logic有的做不了。
扫一扫
1911
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
