Age | Commit message (Collapse) | Author | Lines |
|
Iteration over states/transitions and model attributes is no longer hardcoded
into most model generation code. This should make support for decision trees
and sub-states much easier.
|
|
|
|
Note that outliers are removed from both training and evaluation data
|
|
|
|
TODO: Fix send duration model generation for cc1200, should improve eval
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
It doesn't work and is not methodically sound. Decision/Regression Trees
seem to be the way to go
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|