we have in the training set only the numeric identifier for the feature.
Indeed the model is going to be built using that integer identifier for each feature.
There is no example of the feature file, but I assume it is simply one line per id.
Is there any mechanism to manage a mapping betweeen the featureId and the feature name ?
Curious if it is possible to build a more human readable model.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi gents,
according to the file format for Ranklib :
<line> .=. <target> qid:<qid> <feature>:<value> <feature>:<value> ... <feature>:<value> # <info>
<target> .=. <positive integer="">
<qid> .=. <positive integer="">
<feature> .=. <positive integer="">
<value> .=. <float>
<info> .=. <string></string></info></float></value></positive></feature></positive></qid></positive></target></info></value></feature></value></feature></value></feature></qid></target></line>
we have in the training set only the numeric identifier for the feature.
Indeed the model is going to be built using that integer identifier for each feature.
There is no example of the feature file, but I assume it is simply one line per id.
Is there any mechanism to manage a mapping betweeen the featureId and the feature name ?
Curious if it is possible to build a more human readable model.