mvpa2.kernels.base.CustomKernel

class mvpa2.kernels.base.CustomKernel(kernelfunc=None, *args, **kwargs)

Custom Kernel defined by an arbitrary function

Examples

Basic linear kernel >>> k = CustomKernel(kernelfunc=lambda a,b: numpy.dot(a,b.T))

Methods

add_conversion(typename, methodfull, methodraw)	Adds methods to the Kernel class for new conversions
as_np()	Converts this kernel to a Numpy-based representation
as_raw_np()	Directly return this kernel as a numpy array.
cleanup()	Wipe out internal representation
compute(ds1[, ds2])	Generic computation of any kernel
computed(*args, **kwargs)	Compute kernel and return self

Initialize CustomKernel with an arbitrary function.

Parameters:

kernelfunc : function

Any callable function which takes two numpy arrays and calculates a kernel function, treating the rows as samples and the columns as features. It is called from compute(d1, d2) -> func(d1,d2) and should return a numpy matrix K(i,j) which holds the kernel evaluated from d1 sample i and d2 sample j

enable_ca : None or list of str

Names of the conditional attributes which should be enabled in addition to the default ones

disable_ca : None or list of str

Names of the conditional attributes which should be disabled

Methods

add_conversion(typename, methodfull, methodraw)	Adds methods to the Kernel class for new conversions
as_np()	Converts this kernel to a Numpy-based representation
as_raw_np()	Directly return this kernel as a numpy array.
cleanup()	Wipe out internal representation
compute(ds1[, ds2])	Generic computation of any kernel
computed(*args, **kwargs)	Compute kernel and return self