Closed tixxit closed 9 years ago
The goal of this PR is really to allow new ways to deal with missing features when evaluating a tree. Some changes to support this:
true
IsPresent
FirstMatch
MaxWeightedMatch
ProbabilisticWeightedMatch
LGTM modulo comments.
The goal of this PR is really to allow new ways to deal with missing features when evaluating a tree. Some changes to support this:
true
if a feature value is missing,IsPresent
) was added which returns false if a feature is missing,FirstMatch
- returns first node whose predicate istrue
,MaxWeightedMatch
- returns node whose predicate istrue
with the most weight (annotation),ProbabilisticWeightedMatch
- returns random node whose predicate istrue
, but the probability of being chosen is weighted (annotation).