mvpa2.datasets.formats.from_lightsvm_format¶

mvpa2.datasets.formats.from_lightsvm_format(in_, targets_attr='targets', am=None)¶

Loads dataset from a file in lightsvm format

Parameters:

in_

Anything we could iterate over and obtain strings, such as File

targets_attr : string, optional

Name of the samples attribute to be used to store targets/labels

am : AttributeMap or None, optional

Which mapping to use for mapping labels back into possibly a literal representation.

Returns:

dataset