%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
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]))
data shape: (569, 30); no. positive: 357; no. negative: 212
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)
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))
train score: 1.0; test score: 0.6140350877192983
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)
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');
best param: {'gamma': 0.00011379310344827585}
best score: 0.9367311072056239

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))
D:\anaconda\lib\site-packages\sklearn\model_selection\_validation.py:811: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
if np.issubdtype(train_sizes_abs.dtype, np.float):
elaspe: 5.527530

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))
train score: 0.978021978021978; test score: 0.9824561403508771
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))
D:\anaconda\lib\site-packages\sklearn\model_selection\_validation.py:811: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
if np.issubdtype(train_sizes_abs.dtype, np.float):
D:\anaconda\lib\site-packages\sklearn\model_selection\_validation.py:811: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
if np.issubdtype(train_sizes_abs.dtype, np.float):
elaspe: 359.281419
