为什么LinearSVC不能做这个简单的分类？

Question

我正在尝试使用该LinearSVC对象进行以下简单分类scikit-learn.我尝试过同时使用0.10和0.14版本.使用代码:

from sklearn.svm import LinearSVC, SVC
from numpy import *

data = array([[ 1007.,  1076.],
              [ 1017.,  1009.],
              [ 2021.,  2029.],
              [ 2060.,  2085.]])
groups = array([1, 1, 2, 2])

svc = LinearSVC()
svc.fit(data, groups)
svc.predict(data)

我得到输出:

array([2, 2, 2, 2])

但是,如果我用分隔符替换分类器

svc = SVC(kernel='linear')

然后我得到了结果

array([ 1.,  1.,  2.,  2.])

哪个是对的.有谁知道为什么使用LinearSVC会破坏这个简单的问题？

Answer 1

底层算法LinearSVC对其输入中的极值非常敏感:

>>> svc = LinearSVC(verbose=1)
>>> svc.fit(data, groups)
[LibLinear]....................................................................................................
optimization finished, #iter = 1000

WARNING: reaching max number of iterations
Using -s 2 may be faster (also see FAQ)

Objective value = -0.001256
nSV = 4
LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='l2', multi_class='ovr', penalty='l2',
     random_state=None, tol=0.0001, verbose=1)

(该警告涉及LibLinear常见问题解答,因为scikit-learn LinearSVC是基于该库的.)

您应该在拟合之前进行标准化:

>>> from sklearn.preprocessing import scale
>>> data = scale(data)
>>> svc.fit(data, groups)
[LibLinear]...
optimization finished, #iter = 39
Objective value = -0.240988
nSV = 4
LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='l2', multi_class='ovr', penalty='l2',
     random_state=None, tol=0.0001, verbose=1)
>>> svc.predict(data)
array([1, 1, 2, 2])