Cross validation for custom kernel SVM in scikit-learn -

i grid-search through cross-validation custom kernel svm using scikit-learn. more precisely following this example want define kernel function like

def my_kernel(x, y): """ create custom kernel: k(x, y) = x * m *y.t           """ return np.dot(np.dot(x, m), y.t) 

where m parameter of kernel (like gamma in gaussian kernel).

i want feed parameter m through gridsearchcv,

parameters = {'kernel':('my_kernel'), 'c':[1, 10], 'm':[m1,m2]} svr = svm.svc() clf = grid_search.gridsearchcv(svr, parameters) 

so question : how define my_kernel m variable given gridsearchcv ?

you may have make wrapper class. like:

class mysvc(baseestimator,classifiermixin):     def __init__( self,                # svc attributes               m ):          self.m = m          # etc...      def fit( self, x, y ):          kernel = lambda x,y : np.dot(np.dot(x,m),y.t)          self.svc_ = svc( kernel=kernel, # other parameters )          return self.svc_.fit( x, y )     def predict( self, x ):          return self.svc_.predict( x )     # et cetera