要做到这一点的方法之一是使用
Pipeline，SVC(kernel='precomputed')和包装定制的内核函数的
sklearn估计（的子类
baseEstimator和
TransformerMixin））。
例如，
sklearn包含一个自定义内核函数
chi2_kernel(X, Y=None, gamma=1.0)，该函数可计算特征向量
X和的内核矩阵
Y。该函数采用一个参数
gamma，最好使用交叉验证进行设置。我们可以按以下方式对该函数的参数进行网格搜索：
from __future__ import print_functionfrom __future__ import divisionimport sysimport numpy as npimport sklearnfrom sklearn.base import baseEstimator, TransformerMixinfrom sklearn.cross_validation import train_test_splitfrom sklearn.datasets import load_digitsfrom sklearn.grid_search import GridSearchCVfrom sklearn.metrics import accuracy_scorefrom sklearn.metrics.pairwise import chi2_kernelfrom sklearn.pipeline import Pipelinefrom sklearn.svm import SVC# Wrapper class for the custom kernel chi2_kernelclass Chi2Kernel(baseEstimator,TransformerMixin): def __init__(self, gamma=1.0): super(Chi2Kernel,self).__init__() self.gamma = gamma def transform(self, X): return chi2_kernel(X, self.X_train_, gamma=self.gamma) def fit(self, X, y=None, **fit_params): self.X_train_ = X return selfdef main(): print('python: {}'.format(sys.version)) print('numpy: {}'.format(np.__version__)) print('sklearn: {}'.format(sklearn.__version__)) np.random.seed(0) # Get some data to evaluate dataset = load_digits() X = dataset.data y = dataset.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33) # Create a pipeline where our custom predefined kernel Chi2Kernel # is run before SVC. pipe = Pipeline([ ('chi2', Chi2Kernel()), ('svm', SVC()), ]) # Set the parameter 'gamma' of our custom kernel by # using the 'estimator__param' syntax. cv_params = dict([ ('chi2__gamma', 10.0**np.arange(-9,4)), ('svm__kernel', ['precomputed']), ('svm__C', 10.0**np.arange(-2,9)), ]) # Do grid search to get the best parameter value of 'gamma'. model = GridSearchCV(pipe, cv_params, cv=5, verbose=1, n_jobs=-1) model.fit(X_train, y_train) y_pred = model.predict(X_test) acc_test = accuracy_score(y_test, y_pred) print("Test accuracy: {}".format(acc_test)) print("Best params:") print(model.best_params_)if __name__ == '__main__': main()输出：
python: 2.7.3 (default, Dec 18 2014, 19:10:20) [GCC 4.6.3] numpy: 1.8.0 sklearn: 0.16.1 Fitting 5 folds for each of 143 candidates, totalling 715 fits [Parallel(n_jobs=-1)]: Done 1 jobs | elapsed: 0.4s [Parallel(n_jobs=-1)]: Done 50 jobs | elapsed: 2.7s [Parallel(n_jobs=-1)]: Done 200 jobs | elapsed: 9.8s [Parallel(n_jobs=-1)]: Done 450 jobs | elapsed: 21.6s [Parallel(n_jobs=-1)]: Done 701 out of 715 | elapsed: 34.8s remaining: 0.7s [Parallel(n_jobs=-1)]: Done 715 out of 715 | elapsed: 35.4s finished Test accuracy: 0.989898989899 Best params: {'chi2__gamma': 0.01, 'svm__C': 10.0, 'svm__kernel': 'precomputed'}在您的情况下，只需将其替换chi2_kernel为计算内核矩阵的函数即可。
