Specifically, the integration returned an NaN if the integration was
*up to* an NaN (real inegrals are robust); and the results were negative
if integrating from a to b where a > b.
This project is now purely a library only; the code for running directly from the command line will be
put into a new project. This was important because we were including large dependencies into the R code
that weren't needed and created some minor licensing inconveniences.
Apparently older versions of Jackson contain a security vulnerability
(not really important for this project, given that users are only ever
using Jackson on their own settings files)
Benefits are for when we restart a previously parallel task
in which, say, trees 1, 2, and 4 were completed but tree 3
never did complete. Under the previous implementation we'd start
at tree 4 (we'd just count how many trees were done). To fix this
would require some additional effort. Since the order of trees
is irrelevant, it made sense to just stop ordering them.
This was done so that when we serialize trees (and thus SplitRules) we don't awkwardly also serialize ntree versions of the Covariates,
which is really awkward when deserializing them.
Changed the covariates to be more clever with how they produce the different splits. In the future (not yet implemented) a clever GroupDifferentiator
could update the current score calculation based just on how many rows moved from one hand to the other. There were a few other changes as well;
TreeTrainer#growTree now accepts a Random as a parameter which is used throughout the entire growing process. This means it's now theoretically
possible to grow trees using a seed, so that results can be fully reproducible.
Naive mortality error was an ad-hoc method I implemented earlier on. It
didn't provide any useful performance, nor was it theoretically
grounded. It's better to remove it before someone accidently uses it.
