scikit-learn 支持向量机实现乳腺癌检测

随书代码，阅读笔记。

• 载入数据并准备测试机和训练集

# 载入数据
from sklearn.datasets import load_breast_cancer

cancer = load_breast_cancer()
X = cancer.data
y = cancer.target
print('data shape: {0}; no. positive: {1}; no. negative: {2}'.format(
    X.shape, y[y==1].shape[0], y[y==0].shape[0]))

# 准备训练集和测试集
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

• 使用高斯核函数

from sklearn.svm import SVC

clf = SVC(C=1.0, kernel='rbf', gamma=0.1)
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
test_score = clf.score(X_test, y_test)
print('train score: {0}; test score: {1}'.format(train_score, test_score))

#output:train score: 1.0; test score: 0.526315789474

从代码中可以看出，在训练集上得分很高，但是在测试集上表现很差。

很明显，过拟合了。因为我们的数据集很小，高斯核函数太复杂，容易造成过拟合。

我们尝试着修改高斯核函数的参数，看看效果如何：

from common.utils import plot_param_curve
from sklearn.model_selection import GridSearchCV

gammas = np.linspace(0, 0.0003, 30)
param_grid = {'gamma': gammas}
clf = GridSearchCV(SVC(), param_grid, cv=5) # cv:交叉验证参数，默认是None， 使用三折交叉验证，指定 fold数量， default = 3
clf.fit(X, y)
print("best param: {0}\nbest score: {1}".format(clf.best_params_,
                                                clf.best_score_))

plt.figure(figsize=(10, 4), dpi=144)
plot_param_curve(plt, gammas, clf.cv_results_, xlabel='gamma');

#output:
#
# best param: {'gamma': 0.00011379310344827585}
# best score: 0.936731107206

使用自动搜索出来的参数gamma = 0.0001重新训练并验证，得到如下数据：

train score: 0.9516483516483516; test score: 0.9385964912280702

可以看到，参数设置的不同，对整个结果影响很大

• 图形化learning curve

import time
from common.utils import plot_learning_curve
from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
title = 'Learning Curves for Gaussian Kernel'

start = time.clock()
plt.figure(figsize=(10, 4), dpi=144)
plot_learning_curve(plt, SVC(C=1.0, kernel='rbf', gamma=0.01),
                    title, X, y, ylim=(0.5, 1.01), cv=cv)

print('elaspe: {0:.6f}'.format(time.clock()-start))

• 多项式核函数

from sklearn.svm import SVC

clf = SVC(C=1.0, kernel='poly', degree=2)
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
test_score = clf.score(X_test, y_test)
print('train score: {0}; test score: {1}'.format(train_score, test_score))

#output:train score: 0.978021978021978; test score: 0.9473684210526315

多项式不同的阶数对分类结果的影响

import time
from common.utils import plot_learning_curve
from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)
title = 'Learning Curves with degree={0}'
degrees = [1, 2]

start = time.clock()
plt.figure(figsize=(12, 4), dpi=144)
for i in range(len(degrees)):
    plt.subplot(1, len(degrees), i + 1)
    plot_learning_curve(plt, SVC(C=1.0, kernel='poly', degree=degrees[i]),
                        title.format(degrees[i]), X, y, ylim=(0.8, 1.01), cv=cv, n_jobs=4)

print('elaspe: {0:.6f}'.format(time.clock()-start))

 

• 多项式 LinearSVC

from sklearn.svm import LinearSVC
from sklearn.preprocessing import PolynomialFeatures
from sklearn.preprocessing import MinMaxScaler
from sklearn.pipeline import Pipeline

def create_model(degree=2, **kwarg):
    polynomial_features = PolynomialFeatures(degree=degree,
                                             include_bias=False)
    scaler = MinMaxScaler()
    linear_svc = LinearSVC(**kwarg)
    pipeline = Pipeline([("polynomial_features", polynomial_features),
                         ("scaler", scaler),
                         ("linear_svc", linear_svc)])
    return pipeline


clf = create_model(penalty='l1', dual=False)
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
test_score = clf.score(X_test, y_test)
print('train score: {0}; test score: {1}'.format(train_score, test_score))

#output:train score: 0.984615384615; test score: 0.991228070175

show出来learning curve

import time
from common.utils import plot_learning_curve
from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)
title = 'Learning Curves for LinearSVC with Degree={0}'
degrees = [1, 2]

start = time.clock()
plt.figure(figsize=(12, 4), dpi=144)
for i in range(len(degrees)):
    plt.subplot(1, len(degrees), i + 1)
    plot_learning_curve(plt, create_model(penalty='l1', dual=False, degree=degrees[i]),
                        title.format(degrees[i]), X, y, ylim=(0.8, 1.01), cv=cv)

print('elaspe: {0:.6f}'.format(time.clock()-start))

 

扩展阅读：

如何选择核函数？

如何调整参数？

SVC, linearSVC, NuSVC 都有什么区别？