import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import seaborn as sns;sns.set()
%%html
<img src='./images/3.png', width='900'>
<img src=’./images/3.png’, width=‘900’>
支持向量基本原理
如何解决这个线性不可分问题呢?咱们给它映射到高维来试试
z
=
x
2
+
y
2
z=x^2+y^2
z=x2+y2.
例子
# 使用sklearn函数来创造数据集
from sklearn.datasets.samples_generator import make_blobs
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')
<matplotlib.collections.PathCollection at 0xb29a978>
xfit = np.linspace(-1, 3.5)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plt.plot([0.6], [2.1], 'x', color='red', markeredgewidth=2, markersize=10)
for m, b in [(1, 0.65), (0.5, 1.6), (-0.2, 2.9)]:
plt.plot(xfit, m * xfit + b, '-k')
plt.xlim(-1, 3.5)
(-1, 3.5)
Support Vector Machines: 最小化 雷区
xfit = np.linspace(-1, 3.5)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
for m, b, d in [(1, 0.65, 0.33), (0.5, 1.6, 0.55), (-0.2, 2.9, 0.2)]:
yfit = m * xfit + b
plt.plot(xfit, yfit, '-k')
plt.fill_between(xfit, yfit - d, yfit + d, edgecolor='none',
color='#AAAAAA', alpha=0.4)
plt.xlim(-1, 3.5);
训练一个基本的SVM
from sklearn.svm import SVC
model = SVC(kernel='linear')
model.fit(X, y)
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='auto_deprecated',
kernel='linear', max_iter=-1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False)
#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)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
plot_svc_decision_function(model)
-
这条线就是我们希望得到的决策边界啦
-
观察发现有3个点做了特殊的标记,它们恰好都是边界上的点
-
它们就是我们的support vectors(支持向量)
-
在Scikit-Learn中, 它们存储在这个位置
support_vectors_
(一个属性)
model.support_vectors_
array([[0.44359863, 3.11530945],
[2.33812285, 3.43116792],
[2.06156753, 1.96918596]])
观察可以发现,只需要支持向量我们就可以把模型构建出来
接下来我们尝试一下,用不同多的数据点,看看效果会不会发生变化
分别使用60个和120个数据点
def plot_svm(N=10, ax=None):
X, y = make_blobs(n_samples=200, centers=2,
random_state=0, cluster_std=0.60)
X = X[:N]
y = y[:N]
model = SVC(kernel='linear', C=1E10)
model.fit(X, y)
ax = ax or plt.gca()
ax.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
ax.set_xlim(-1, 4)
ax.set_ylim(-1, 6)
plot_svc_decision_function(model, ax)
fig, ax = plt.subplots(1, 2, figsize=(16, 6))
fig.subplots_adjust(left=0.0625, right=0.95, wspace=0.1)
for axi, N in zip(ax, [60, 120]):
plot_svm(N, axi)
axi.set_title('N = {0}'.format(N))
左边是60个点的结果,右边的是120个点的结果
观察发现,只要支持向量没变,其他的数据怎么加无所谓!
引入核函数的SVM
- 首先我们先用线性的核来看一下在下面这样比较难的数据集上还能分了吗?
from sklearn.datasets.samples_generator import make_circles
X, y = make_circles(100, factor=0.1, noise=0.1)
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)
- 试试高维核变换
- We can visualize this extra data dimension using a three-dimensional plot:
#加入了新的维度r
from mpl_toolkits import mplot3d
r = np.exp(-(X ** 2).sum(1))
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')
plot_3D(elev=45, azim=45, X=X, y=y)
# 试试径向基函数
clf = SVC(kernel='rbf', C=1E6)
clf.fit(X, y)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\svm\base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.
"avoid this warning.", FutureWarning)
SVC(C=1000000.0, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='auto_deprecated',
kernel='rbf', max_iter=-1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False)
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')
<matplotlib.collections.PathCollection at 0xc233e10>
使用这种核支持向量机,我们学习一个合适的非线性决策边界。这种核变换策略在机器学习中经常被使用
调节SVM参数: Soft Margin问题
调节C参数
- 当C趋近于无穷大时:意味着分类严格不能有错误
- 当C趋近于很小的时:意味着可以有更大的错误容忍
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');
X, y = make_blobs(n_samples=100, centers=2,
random_state=0, cluster_std=0.8)
fig, ax = plt.subplots(1, 2, figsize=(16, 6))
fig.subplots_adjust(left=0.0625, right=0.95, wspace=0.1)
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)
X, y = make_blobs(n_samples=100, centers=2,
random_state=0, cluster_std=1.1)
fig, ax = plt.subplots(1, 2, figsize=(16, 6))
fig.subplots_adjust(left=0.0625, right=0.95, wspace=0.1)
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)