Model.Defaults, Model.Transform
Value.Atomic, Value.Bool, Value.Char, Value.Chars, Value.Cts, Value.Defer, Value.Discrete, Value.Enum, Value.Inc_Or, Value.Int, Value.Lambda, Value.List, Value.Maybe, Value.Option, Value.Real, Value.Scannable, Value.Structured, Value.Triv, Value.Tuple
Modifier and Type | Field and Description |
---|---|
int |
choice
The index of the best of the
upms[] (parameterised). |
Model |
mdl
|
Constructor and Description |
---|
M(double msg1,
double msg2,
Value sp)
Two part message lengths, msg1 and msg2,
and statistical parameter(s) sp=〈i,spi〉.
|
Modifier and Type | Method and Description |
---|---|
double |
nlLH(Value ss)
Given sufficient statistics, ss=stats(ds), of a data-set ds,
return
mdl 's negative log LikeliHood of ds. |
double |
nlPr(Value d)
Return
mdl 's negative log probability of data 'd'. |
Value |
random()
Return a Value from
mdl . |
Value |
stats(boolean add,
Value ss0,
Value ss1)
Return
mdl 's stats ss0±ss1,
"+" if add is true otherwise "-". |
Value |
stats(Vector ds,
int lo,
int hi)
Return
mdl 's stats for ds[lo,hi). |
asEstimator, asUPModel, m1m2sp, msg, msg1, msg1bits, msg2, msg2bits, msgBits, nl2LH, nl2Pr, pr, random, randomSeries, statParams, stats, stats, sumNlPr, transform, type, zeroTriv
public int choice
upms[]
(parameterised).public Model mdl
public Value stats(Vector ds, int lo, int hi)
mdl
's stats for ds[lo,hi).
Also see BestOf.stats(...))
which is more extensive.public Value stats(boolean add, Value ss0, Value ss1)
mdl
's stats ss0±ss1,
"+" if add is true otherwise "-".
Also see BestOf.stats(...))
.public double nlLH(Value ss)
mdl
's negative log LikeliHood of ds.