feat: add Aenebris.ML.Inference and Aenebris.ML.Calibration
- New Aenebris.ML.Inference module: pure tree-walk over the unified Tree SoA produced by Aenebris.ML.Loader. Mirrors LightGBM C++ NumericalDecision exactly: NaN remapped to 0 unless MissingType=NaN; MissingType=Zero/NaN routes via default-left flag; '<=' predicate (not '<'); categorical bitmap test using cat_boundaries slice; average_output divisor for RF mode; sigmoid link for binary logistic objective. kZeroThreshold = 1e-35 matches LightGBM's IsZero exactly. Defensive against NaN/Inf/negative on categorical paths. 35 tests covering leaf-only, numerical splits, missing-value semantics, categorical routing, multi-tree sums, sigmoid saturation, average_output, regression vs binary objectives, and end-to-end against the disk fixture. - New Aenebris.ML.Calibration module: pure calibration of binary classifier outputs. Calibrator ADT (NoCalibrator | PlattCalibrator a b | IsotonicCalibrator bp). Platt scaling uses Newton's method with damped line search on Platt-1999 smoothed targets (N+ + 1)/(N+ + 2) and 1/(N- + 2); numerically stable softplus-based log-loss. Isotonic regression uses Pool Adjacent Violators on a stack with tie pre- grouping, sorted (raw, calibrated) breakpoints, linear interpolation, out-of-range clamping. Sub-2-sample input returns NoCalibrator. 28 tests covering all three calibrator constructors, fit edge cases, Platt convergence on logistic data, isotonic correction of non- monotone data, tie handling, all-same-label degenerate cases, and lookup behavior including clamping and interpolation. - aenebris.cabal: expose both new modules in the library stanza. - 301 total examples passing, 0 GHC warnings on either new module.
This commit is contained in:
CarterPerez-dev
parent
b70da08b70
commit
e5c2f59675
|
|
@ -41,6 +41,8 @@ library
|
|||
, Aenebris.ML.Features
|
||||
, Aenebris.ML.Model
|
||||
, Aenebris.ML.Loader
|
||||
, Aenebris.ML.Inference
|
||||
, Aenebris.ML.Calibration
|
||||
default-language: Haskell2010
|
||||
build-depends: base >= 4.7 && < 5
|
||||
, warp >= 3.3
|
||||
|
|
|
|||
|
|
@ -0,0 +1,245 @@
|
|||
{-
|
||||
©AngelaMos | 2026
|
||||
Calibration.hs
|
||||
-}
|
||||
{-# LANGUAGE BangPatterns #-}
|
||||
{-# LANGUAGE DeriveGeneric #-}
|
||||
|
||||
module Aenebris.ML.Calibration
|
||||
( Calibrator(..)
|
||||
, calibrate
|
||||
, fitPlatt
|
||||
, fitIsotonic
|
||||
) where
|
||||
|
||||
import Data.List (sortBy)
|
||||
import Data.Ord (comparing)
|
||||
import qualified Data.Vector.Unboxed as VU
|
||||
import GHC.Generics (Generic)
|
||||
|
||||
maxNewtonIterations :: Int
|
||||
maxNewtonIterations = 100
|
||||
|
||||
newtonConvergenceTol :: Double
|
||||
newtonConvergenceTol = 1.0e-7
|
||||
|
||||
initialPlattA :: Double
|
||||
initialPlattA = 0.0
|
||||
|
||||
initialPlattB :: Double
|
||||
initialPlattB = 0.0
|
||||
|
||||
minLineSearchStep :: Double
|
||||
minLineSearchStep = 1.0e-10
|
||||
|
||||
initialLineSearchStep :: Double
|
||||
initialLineSearchStep = 1.0
|
||||
|
||||
lineSearchShrinkFactor :: Double
|
||||
lineSearchShrinkFactor = 0.5
|
||||
|
||||
degenerateHessianThreshold :: Double
|
||||
degenerateHessianThreshold = 1.0e-12
|
||||
|
||||
degenerateFallbackStep :: Double
|
||||
degenerateFallbackStep = 0.01
|
||||
|
||||
minSamplesForFitting :: Int
|
||||
minSamplesForFitting = 2
|
||||
|
||||
singletonBlockWeight :: Double
|
||||
singletonBlockWeight = 1.0
|
||||
|
||||
labelTrueValue :: Double
|
||||
labelTrueValue = 1.0
|
||||
|
||||
labelFalseValue :: Double
|
||||
labelFalseValue = 0.0
|
||||
|
||||
plattLabelSmoothingNumeratorOffset :: Double
|
||||
plattLabelSmoothingNumeratorOffset = 1.0
|
||||
|
||||
plattLabelSmoothingDenominatorOffset :: Double
|
||||
plattLabelSmoothingDenominatorOffset = 2.0
|
||||
|
||||
data Calibrator
|
||||
= NoCalibrator
|
||||
| PlattCalibrator !Double !Double
|
||||
| IsotonicCalibrator !(VU.Vector (Double, Double))
|
||||
deriving (Eq, Show, Generic)
|
||||
|
||||
calibrate :: Calibrator -> Double -> Double
|
||||
calibrate NoCalibrator p = p
|
||||
calibrate (PlattCalibrator a b) p = sigmoidPositiveExponent (a * p + b)
|
||||
calibrate (IsotonicCalibrator bp) p = isotonicLookup bp p
|
||||
|
||||
sigmoidPositiveExponent :: Double -> Double
|
||||
sigmoidPositiveExponent z = 1.0 / (1.0 + exp z)
|
||||
|
||||
softplus :: Double -> Double
|
||||
softplus z = max 0.0 z + log (1.0 + exp (negate (abs z)))
|
||||
|
||||
boolToTarget :: Bool -> Double
|
||||
boolToTarget True = labelTrueValue
|
||||
boolToTarget False = labelFalseValue
|
||||
|
||||
fitPlatt :: VU.Vector (Double, Bool) -> Calibrator
|
||||
fitPlatt samples
|
||||
| VU.length samples < minSamplesForFitting = NoCalibrator
|
||||
| otherwise =
|
||||
let !nPos = VU.length (VU.filter snd samples)
|
||||
!nNeg = VU.length samples - nPos
|
||||
!targetPos = (fromIntegral nPos + plattLabelSmoothingNumeratorOffset)
|
||||
/ (fromIntegral nPos + plattLabelSmoothingDenominatorOffset)
|
||||
!targetNeg = plattLabelSmoothingNumeratorOffset
|
||||
/ (fromIntegral nNeg + plattLabelSmoothingDenominatorOffset)
|
||||
smoothed = VU.map
|
||||
(\(p, lbl) -> (p, if lbl then targetPos else targetNeg))
|
||||
samples
|
||||
(!a, !b) = plattNewton smoothed
|
||||
in PlattCalibrator a b
|
||||
|
||||
plattNewton :: VU.Vector (Double, Double) -> (Double, Double)
|
||||
plattNewton !smoothed = go 0 initialPlattA initialPlattB initialLoss
|
||||
where
|
||||
!initialLoss = computeNll smoothed initialPlattA initialPlattB
|
||||
|
||||
go :: Int -> Double -> Double -> Double -> (Double, Double)
|
||||
go !iter !a !b !prevLoss
|
||||
| iter >= maxNewtonIterations = (a, b)
|
||||
| otherwise =
|
||||
let (!gA, !gB, !hAA, !hAB, !hBB) = gradHessian smoothed a b
|
||||
!det = hAA * hBB - hAB * hAB
|
||||
(!stepA, !stepB)
|
||||
| abs det < degenerateHessianThreshold =
|
||||
( negate gA * degenerateFallbackStep
|
||||
, negate gB * degenerateFallbackStep
|
||||
)
|
||||
| otherwise =
|
||||
( negate (hBB * gA - hAB * gB) / det
|
||||
, negate (negate hAB * gA + hAA * gB) / det
|
||||
)
|
||||
(!newA, !newB, !newLoss) =
|
||||
lineSearch smoothed a b stepA stepB prevLoss initialLineSearchStep
|
||||
in if abs (prevLoss - newLoss) < newtonConvergenceTol
|
||||
then (newA, newB)
|
||||
else go (iter + 1) newA newB newLoss
|
||||
|
||||
lineSearch
|
||||
:: VU.Vector (Double, Double)
|
||||
-> Double -> Double -> Double -> Double -> Double -> Double
|
||||
-> (Double, Double, Double)
|
||||
lineSearch !smoothed !a !b !stepA !stepB !prevLoss !step
|
||||
| step < minLineSearchStep = (a, b, prevLoss)
|
||||
| otherwise =
|
||||
let !trialA = a + step * stepA
|
||||
!trialB = b + step * stepB
|
||||
!trialLoss = computeNll smoothed trialA trialB
|
||||
in if trialLoss < prevLoss
|
||||
then (trialA, trialB, trialLoss)
|
||||
else lineSearch smoothed a b stepA stepB prevLoss
|
||||
(step * lineSearchShrinkFactor)
|
||||
|
||||
computeNll :: VU.Vector (Double, Double) -> Double -> Double -> Double
|
||||
computeNll !smoothed !a !b = VU.foldl' addSample 0.0 smoothed
|
||||
where
|
||||
addSample !acc (!p, !t) =
|
||||
let !z = a * p + b
|
||||
in acc + softplus z - (1.0 - t) * z
|
||||
|
||||
gradHessian
|
||||
:: VU.Vector (Double, Double)
|
||||
-> Double
|
||||
-> Double
|
||||
-> (Double, Double, Double, Double, Double)
|
||||
gradHessian !smoothed !a !b =
|
||||
VU.foldl' step (0.0, 0.0, 0.0, 0.0, 0.0) smoothed
|
||||
where
|
||||
step (!gA, !gB, !hAA, !hAB, !hBB) (!p, !t) =
|
||||
let !z = a * p + b
|
||||
!q = sigmoidPositiveExponent z
|
||||
!d = t - q
|
||||
!dh = q * (1.0 - q)
|
||||
in ( gA + d * p
|
||||
, gB + d
|
||||
, hAA + dh * p * p
|
||||
, hAB + dh * p
|
||||
, hBB + dh
|
||||
)
|
||||
|
||||
fitIsotonic :: VU.Vector (Double, Bool) -> Calibrator
|
||||
fitIsotonic samples
|
||||
| VU.length samples < minSamplesForFitting = NoCalibrator
|
||||
| otherwise =
|
||||
let sorted = sortBy (comparing fst) (VU.toList samples)
|
||||
grouped = groupTies sorted
|
||||
smoothed = pav grouped
|
||||
breakpoints = map blockToBreakpoint smoothed
|
||||
in IsotonicCalibrator (VU.fromList breakpoints)
|
||||
|
||||
groupTies :: [(Double, Bool)] -> [(Double, Double, Double)]
|
||||
groupTies [] = []
|
||||
groupTies ((r0, l0) : rest) = goGroup r0 singletonBlockWeight (boolToTarget l0) rest
|
||||
where
|
||||
goGroup !curR !w !sumL [] = [(curR * w, sumL, w)]
|
||||
goGroup !curR !w !sumL ((r, l) : rs)
|
||||
| r == curR = goGroup curR (w + singletonBlockWeight) (sumL + boolToTarget l) rs
|
||||
| otherwise = (curR * w, sumL, w)
|
||||
: goGroup r singletonBlockWeight (boolToTarget l) rs
|
||||
|
||||
pav :: [(Double, Double, Double)] -> [(Double, Double, Double)]
|
||||
pav xs = reverse (foldl' push [] xs)
|
||||
where
|
||||
push :: [(Double, Double, Double)]
|
||||
-> (Double, Double, Double)
|
||||
-> [(Double, Double, Double)]
|
||||
push [] b = [b]
|
||||
push (top : rest) b
|
||||
| blockMean top > blockMean b = push rest (mergeBlocks top b)
|
||||
| otherwise = b : top : rest
|
||||
|
||||
blockMean :: (Double, Double, Double) -> Double
|
||||
blockMean (_, sumL, w) = sumL / w
|
||||
|
||||
blockRawMean :: (Double, Double, Double) -> Double
|
||||
blockRawMean (sumR, _, w) = sumR / w
|
||||
|
||||
blockToBreakpoint :: (Double, Double, Double) -> (Double, Double)
|
||||
blockToBreakpoint b = (blockRawMean b, blockMean b)
|
||||
|
||||
mergeBlocks
|
||||
:: (Double, Double, Double)
|
||||
-> (Double, Double, Double)
|
||||
-> (Double, Double, Double)
|
||||
mergeBlocks (r1, l1, w1) (r2, l2, w2) = (r1 + r2, l1 + l2, w1 + w2)
|
||||
|
||||
isotonicLookup :: VU.Vector (Double, Double) -> Double -> Double
|
||||
isotonicLookup !bp !p
|
||||
| VU.null bp = p
|
||||
| p <= fst (VU.head bp) = snd (VU.head bp)
|
||||
| p >= fst (VU.last bp) = snd (VU.last bp)
|
||||
| otherwise = interpolateBp bp p
|
||||
|
||||
interpolateBp :: VU.Vector (Double, Double) -> Double -> Double
|
||||
interpolateBp !bp !p =
|
||||
let !i = bisectRight bp p
|
||||
(!loRaw, !loCal) = VU.unsafeIndex bp (i - 1)
|
||||
(!hiRaw, !hiCal) = VU.unsafeIndex bp i
|
||||
!range = hiRaw - loRaw
|
||||
in if range == 0.0
|
||||
then loCal
|
||||
else
|
||||
let !frac = (p - loRaw) / range
|
||||
in loCal + frac * (hiCal - loCal)
|
||||
|
||||
bisectRight :: VU.Vector (Double, Double) -> Double -> Int
|
||||
bisectRight !bp !p = go 0 (VU.length bp)
|
||||
where
|
||||
go !lo !hi
|
||||
| lo >= hi = lo
|
||||
| otherwise =
|
||||
let !mid = lo + (hi - lo) `div` 2
|
||||
(!midRaw, _) = VU.unsafeIndex bp mid
|
||||
in if midRaw > p
|
||||
then go lo mid
|
||||
else go (mid + 1) hi
|
||||
|
|
@ -0,0 +1,124 @@
|
|||
{-
|
||||
©AngelaMos | 2026
|
||||
Inference.hs
|
||||
-}
|
||||
{-# LANGUAGE BangPatterns #-}
|
||||
|
||||
module Aenebris.ML.Inference
|
||||
( walkTree
|
||||
, predictRaw
|
||||
, predictScore
|
||||
, predictProba
|
||||
, sigmoidLink
|
||||
, kZeroThreshold
|
||||
) where
|
||||
|
||||
import Data.Bits (shiftR, testBit, (.&.))
|
||||
import qualified Data.Vector as V
|
||||
import qualified Data.Vector.Unboxed as VU
|
||||
|
||||
import Aenebris.ML.Model
|
||||
( Ensemble(..)
|
||||
, MissingType(..)
|
||||
, Objective(..)
|
||||
, SplitKind(..)
|
||||
, Tree(..)
|
||||
, decisionTypeBits
|
||||
, defaultRootIndex
|
||||
, ensembleTreeCount
|
||||
, nodeIsLeaf
|
||||
)
|
||||
|
||||
kZeroThreshold :: Double
|
||||
kZeroThreshold = 1.0e-35
|
||||
|
||||
bitsPerWordShift :: Int
|
||||
bitsPerWordShift = 5
|
||||
|
||||
bitsPerWordMask :: Int
|
||||
bitsPerWordMask = 31
|
||||
|
||||
zeroFeatureValue :: Double
|
||||
zeroFeatureValue = 0.0
|
||||
|
||||
sigmoidNumerator :: Double
|
||||
sigmoidNumerator = 1.0
|
||||
|
||||
sigmoidBias :: Double
|
||||
sigmoidBias = 1.0
|
||||
|
||||
walkTree :: Tree -> VU.Vector Double -> Int
|
||||
walkTree !tree !fv = go defaultRootIndex
|
||||
where
|
||||
go !i
|
||||
| nodeIsLeaf tree i = i
|
||||
| otherwise = go (chooseChild tree i fv)
|
||||
|
||||
chooseChild :: Tree -> Int -> VU.Vector Double -> Int
|
||||
chooseChild !tree !i !fv =
|
||||
let !dt = treeDecisionType tree VU.! i
|
||||
!featIdx = treeFeatureIdx tree VU.! i
|
||||
!rawFval = fv VU.! featIdx
|
||||
(!kind, !defaultLeft, !mtype) = decisionTypeBits dt
|
||||
!goLeft = treeLeftChild tree VU.! i
|
||||
!goRight = treeRightChild tree VU.! i
|
||||
!fval = if isNaN rawFval && mtype /= MissingTypeNaN
|
||||
then zeroFeatureValue
|
||||
else rawFval
|
||||
in if hitsMissingDefault mtype fval
|
||||
then if defaultLeft then goLeft else goRight
|
||||
else case kind of
|
||||
SplitNumerical
|
||||
| fval <= treeThreshold tree VU.! i -> goLeft
|
||||
| otherwise -> goRight
|
||||
SplitCategorical
|
||||
| categoricalGoesLeft tree i fval -> goLeft
|
||||
| otherwise -> goRight
|
||||
|
||||
hitsMissingDefault :: MissingType -> Double -> Bool
|
||||
hitsMissingDefault MissingTypeZero fval = isZeroLgbm fval
|
||||
hitsMissingDefault MissingTypeNaN fval = isNaN fval
|
||||
hitsMissingDefault MissingTypeNone _ = False
|
||||
|
||||
isZeroLgbm :: Double -> Bool
|
||||
isZeroLgbm fval =
|
||||
fval > negate kZeroThreshold && fval < kZeroThreshold
|
||||
|
||||
categoricalGoesLeft :: Tree -> Int -> Double -> Bool
|
||||
categoricalGoesLeft !tree !i !fval
|
||||
| isNaN fval || isInfinite fval || fval < 0 = False
|
||||
| otherwise =
|
||||
let !ifval = floor fval :: Int
|
||||
!catIdx = floor (treeThreshold tree VU.! i) :: Int
|
||||
!bStart = treeCatBoundaries tree VU.! catIdx
|
||||
!bEnd = treeCatBoundaries tree VU.! (catIdx + 1)
|
||||
!nWords = bEnd - bStart
|
||||
!off = ifval `shiftR` bitsPerWordShift
|
||||
in (off < nWords)
|
||||
&& testBit (treeCatThreshold tree VU.! (bStart + off))
|
||||
(ifval .&. bitsPerWordMask)
|
||||
|
||||
predictRaw :: Ensemble -> VU.Vector Double -> Double
|
||||
predictRaw !ens !fv = V.foldl' addLeafValue 0.0 (ensembleTrees ens)
|
||||
where
|
||||
addLeafValue !acc !tree =
|
||||
acc + treeLeafValue tree VU.! walkTree tree fv
|
||||
|
||||
predictScore :: Ensemble -> VU.Vector Double -> Double
|
||||
predictScore !ens !fv =
|
||||
let !raw = predictRaw ens fv
|
||||
!n = ensembleTreeCount ens
|
||||
in if ensembleAverageOutput ens && n > 0
|
||||
then raw / fromIntegral n
|
||||
else raw
|
||||
|
||||
predictProba :: Ensemble -> VU.Vector Double -> Double
|
||||
predictProba !ens !fv =
|
||||
let !s = predictScore ens fv
|
||||
in case ensembleObjective ens of
|
||||
ObjectiveBinaryLogistic -> sigmoidLink (ensembleSigmoidScale ens) s
|
||||
ObjectiveRegression -> s
|
||||
|
||||
sigmoidLink :: Double -> Double -> Double
|
||||
sigmoidLink !scale !x =
|
||||
sigmoidNumerator / (sigmoidBias + exp (negate (scale * x)))
|
||||
|
|
@ -180,6 +180,20 @@ import Aenebris.ML.Features
|
|||
, uaSecChConsistency
|
||||
, userAgentLengthCap
|
||||
)
|
||||
import Aenebris.ML.Calibration
|
||||
( Calibrator(..)
|
||||
, calibrate
|
||||
, fitIsotonic
|
||||
, fitPlatt
|
||||
)
|
||||
import Aenebris.ML.Inference
|
||||
( kZeroThreshold
|
||||
, predictProba
|
||||
, predictRaw
|
||||
, predictScore
|
||||
, sigmoidLink
|
||||
, walkTree
|
||||
)
|
||||
import Aenebris.ML.Loader
|
||||
( ParseError(..)
|
||||
, parseEnsemble
|
||||
|
|
@ -333,6 +347,8 @@ main = hspec $ do
|
|||
mlFeaturesSpec
|
||||
mlModelSpec
|
||||
mlLoaderSpec
|
||||
mlInferenceSpec
|
||||
mlCalibrationSpec
|
||||
|
||||
configSpec :: Spec
|
||||
configSpec = describe "Config" $ do
|
||||
|
|
@ -2042,6 +2058,353 @@ mlLoaderSpec = describe "ML.Loader" $ do
|
|||
Left err -> peKey err `shouldBe` "version"
|
||||
Right _ -> expectationFailure "expected Left"
|
||||
|
||||
mkCatStump :: Bool -> MissingType -> [Word32] -> Double -> Double -> Tree
|
||||
mkCatStump defaultLeft mtype bitmap leftV rightV =
|
||||
let bitmapVec = VU.fromList bitmap
|
||||
boundaries = VU.fromList [0, VU.length bitmapVec]
|
||||
dt = makeDecisionType SplitCategorical defaultLeft mtype
|
||||
in Tree
|
||||
{ treeFeatureIdx = VU.fromList [0, leafSentinel, leafSentinel]
|
||||
, treeThreshold = VU.fromList [0.0, 0.0, 0.0]
|
||||
, treeLeftChild = VU.fromList [1, noChildIndex, noChildIndex]
|
||||
, treeRightChild = VU.fromList [2, noChildIndex, noChildIndex]
|
||||
, treeLeafValue = VU.fromList [0.0, leftV, rightV]
|
||||
, treeDecisionType = VU.fromList [dt, 0, 0]
|
||||
, treeCatBoundaries = boundaries
|
||||
, treeCatThreshold = bitmapVec
|
||||
}
|
||||
|
||||
mkSingleFeatureEnsemble :: Objective -> Double -> Bool -> [Tree] -> Ensemble
|
||||
mkSingleFeatureEnsemble obj sig avg trees = Ensemble
|
||||
{ ensembleVersion = currentEnsembleVersion
|
||||
, ensembleFeatureCount = 1
|
||||
, ensembleObjective = obj
|
||||
, ensembleBaseScore = 0.0
|
||||
, ensembleSigmoidScale = sig
|
||||
, ensembleAverageOutput = avg
|
||||
, ensembleTrees = V.fromList trees
|
||||
}
|
||||
|
||||
binaryEnsemble :: [Tree] -> Ensemble
|
||||
binaryEnsemble = mkSingleFeatureEnsemble ObjectiveBinaryLogistic defaultSigmoidScale False
|
||||
|
||||
singletonFv :: Double -> VU.Vector Double
|
||||
singletonFv = VU.singleton
|
||||
|
||||
mlInferenceSpec :: Spec
|
||||
mlInferenceSpec = describe "ML.Inference" $ do
|
||||
tinyBytes <- runIO (BS.readFile "test/fixtures/ml/tiny_lgbm_v4.txt")
|
||||
|
||||
describe "walkTree on a leaf-only tree" $ do
|
||||
it "returns the root index for a stump tree" $
|
||||
walkTree (makeLeafTree 0.42) (singletonFv 0.0) `shouldBe` 0
|
||||
|
||||
it "predictRaw returns the leaf value for a single-leaf single-tree ensemble" $
|
||||
predictRaw (binaryEnsemble [makeLeafTree 0.42]) (singletonFv 0.0)
|
||||
`shouldBe` 0.42
|
||||
|
||||
describe "walkTree on a numerical stump (defaultLeft=True, MissingTypeNone)" $ do
|
||||
let tree = makeStumpTreeWithMissing 0 0.5 (-1.0) 1.0 True MissingTypeNone
|
||||
ens = binaryEnsemble [tree]
|
||||
|
||||
it "fval below threshold goes left (leaf value -1.0)" $
|
||||
predictRaw ens (singletonFv 0.0) `shouldBe` (-1.0)
|
||||
|
||||
it "fval above threshold goes right (leaf value 1.0)" $
|
||||
predictRaw ens (singletonFv 0.9) `shouldBe` 1.0
|
||||
|
||||
it "fval exactly at threshold goes left (predicate is <=, not <)" $
|
||||
predictRaw ens (singletonFv 0.5) `shouldBe` (-1.0)
|
||||
|
||||
it "NaN with MissingTypeNone is remapped to 0 then compared (0 <= 0.5 -> left)" $
|
||||
predictRaw ens (singletonFv (0.0 / 0.0)) `shouldBe` (-1.0)
|
||||
|
||||
describe "MissingType=Zero routes via default-left flag" $ do
|
||||
let leftTree = makeStumpTreeWithMissing 0 (-10.0) 7.0 (-7.0) True MissingTypeZero
|
||||
rightTree = makeStumpTreeWithMissing 0 (-10.0) 7.0 (-7.0) False MissingTypeZero
|
||||
|
||||
it "0.0 with defaultLeft=True hits left branch (ignoring threshold)" $
|
||||
predictRaw (binaryEnsemble [leftTree]) (singletonFv 0.0) `shouldBe` 7.0
|
||||
|
||||
it "0.0 with defaultLeft=False hits right branch (ignoring threshold)" $
|
||||
predictRaw (binaryEnsemble [rightTree]) (singletonFv 0.0) `shouldBe` (-7.0)
|
||||
|
||||
it "tiny non-zero (2e-36) is treated as zero by IsZero(kZeroThreshold=1e-35)" $
|
||||
predictRaw (binaryEnsemble [leftTree]) (singletonFv 2.0e-36)
|
||||
`shouldBe` 7.0
|
||||
|
||||
it "value just above kZeroThreshold is NOT treated as zero" $
|
||||
predictRaw (binaryEnsemble [leftTree]) (singletonFv 1.0e-30)
|
||||
`shouldBe` (-7.0)
|
||||
|
||||
describe "MissingType=NaN routes only when feature is NaN" $ do
|
||||
let nanTree = makeStumpTreeWithMissing 0 0.5 (-1.0) 1.0 True MissingTypeNaN
|
||||
|
||||
it "NaN feature uses default-left (left leaf -1.0)" $
|
||||
predictRaw (binaryEnsemble [nanTree]) (singletonFv (0.0 / 0.0))
|
||||
`shouldBe` (-1.0)
|
||||
|
||||
it "non-NaN feature still uses normal threshold comparison" $
|
||||
predictRaw (binaryEnsemble [nanTree]) (singletonFv 0.9)
|
||||
`shouldBe` 1.0
|
||||
|
||||
describe "categorical bitmap routing" $ do
|
||||
let bitmap5 = [5 :: Word32]
|
||||
|
||||
it "category 0 in bitmap 0b101 routes left" $
|
||||
predictRaw (binaryEnsemble [mkCatStump False MissingTypeNone bitmap5 (-2.0) 2.0])
|
||||
(singletonFv 0.0)
|
||||
`shouldBe` (-2.0)
|
||||
|
||||
it "category 1 NOT in bitmap 0b101 routes right" $
|
||||
predictRaw (binaryEnsemble [mkCatStump False MissingTypeNone bitmap5 (-2.0) 2.0])
|
||||
(singletonFv 1.0)
|
||||
`shouldBe` 2.0
|
||||
|
||||
it "category 2 in bitmap 0b101 routes left" $
|
||||
predictRaw (binaryEnsemble [mkCatStump False MissingTypeNone bitmap5 (-2.0) 2.0])
|
||||
(singletonFv 2.0)
|
||||
`shouldBe` (-2.0)
|
||||
|
||||
it "category beyond bitmap range routes right" $
|
||||
predictRaw (binaryEnsemble [mkCatStump False MissingTypeNone bitmap5 (-2.0) 2.0])
|
||||
(singletonFv 99.0)
|
||||
`shouldBe` 2.0
|
||||
|
||||
it "negative categorical feature routes right" $
|
||||
predictRaw (binaryEnsemble [mkCatStump False MissingTypeNone bitmap5 (-2.0) 2.0])
|
||||
(singletonFv (-1.0))
|
||||
`shouldBe` 2.0
|
||||
|
||||
it "categorical NaN with MissingTypeZero routes via default-left" $
|
||||
predictRaw (binaryEnsemble [mkCatStump True MissingTypeZero bitmap5 (-2.0) 2.0])
|
||||
(singletonFv (0.0 / 0.0))
|
||||
`shouldBe` (-2.0)
|
||||
|
||||
describe "multi-tree ensemble sums leaf contributions" $ do
|
||||
let t1 = makeStumpTreeWithMissing 0 0.0 (-0.3) 0.3 False MissingTypeNone
|
||||
t2 = makeStumpTreeWithMissing 0 0.5 (-0.2) 0.2 False MissingTypeNone
|
||||
|
||||
it "sums each tree's chosen leaf value" $
|
||||
predictRaw (binaryEnsemble [t1, t2]) (singletonFv 0.7)
|
||||
`shouldBe` 0.5
|
||||
|
||||
it "different feature value picks different leaves and changes the sum" $
|
||||
predictRaw (binaryEnsemble [t1, t2]) (singletonFv (-0.1))
|
||||
`shouldBe` (-0.5)
|
||||
|
||||
describe "predictScore: average_output divisor" $ do
|
||||
let t1 = makeLeafTree 1.0
|
||||
t2 = makeLeafTree 3.0
|
||||
|
||||
it "no average_output: predictScore equals predictRaw" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveBinaryLogistic defaultSigmoidScale False [t1, t2]
|
||||
predictScore ens (singletonFv 0.0) `shouldBe` 4.0
|
||||
|
||||
it "average_output=True divides raw by num_trees" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveBinaryLogistic defaultSigmoidScale True [t1, t2]
|
||||
predictScore ens (singletonFv 0.0) `shouldBe` 2.0
|
||||
|
||||
it "average_output=True with empty tree vector falls back to raw (n=0 guard)" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveBinaryLogistic defaultSigmoidScale True []
|
||||
predictScore ens (singletonFv 0.0) `shouldBe` 0.0
|
||||
|
||||
describe "sigmoidLink" $ do
|
||||
it "scale*x = 0 yields 0.5" $
|
||||
sigmoidLink 1.0 0.0 `shouldBe` 0.5
|
||||
|
||||
it "very large positive x saturates near 1.0" $
|
||||
sigmoidLink 1.0 1000.0 `shouldBe` 1.0
|
||||
|
||||
it "very large negative x saturates near 0.0" $
|
||||
sigmoidLink 1.0 (-1000.0) `shouldBe` 0.0
|
||||
|
||||
it "scale=0.5 halves the steepness" $
|
||||
sigmoidLink 0.5 2.0 `shouldBe` (1.0 / (1.0 + exp (-1.0)))
|
||||
|
||||
describe "predictProba: objective-specific link function" $ do
|
||||
it "binary logistic applies sigmoid with the ensemble's scale" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveBinaryLogistic 1.0 False [makeLeafTree 0.0]
|
||||
predictProba ens (singletonFv 0.0) `shouldBe` 0.5
|
||||
|
||||
it "binary logistic with sigmoidScale=0.5 applies the scale" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveBinaryLogistic 0.5 False [makeLeafTree 2.0]
|
||||
predictProba ens (singletonFv 0.0) `shouldBe` (1.0 / (1.0 + exp (-1.0)))
|
||||
|
||||
it "regression returns the score directly (no sigmoid)" $ do
|
||||
let ens = mkSingleFeatureEnsemble ObjectiveRegression 1.0 False [makeLeafTree 7.5]
|
||||
predictProba ens (singletonFv 0.0) `shouldBe` 7.5
|
||||
|
||||
describe "kZeroThreshold matches LightGBM" $
|
||||
it "is exactly 1e-35" $
|
||||
kZeroThreshold `shouldBe` 1.0e-35
|
||||
|
||||
describe "end-to-end against the tiny LightGBM v4 fixture" $ do
|
||||
case parseEnsemble tinyBytes of
|
||||
Left err -> it "parses tinyBytes" $ expectationFailure (show err)
|
||||
Right ens -> do
|
||||
it "feature vector [0, 0] (cat_feat=0 -> left, num_feat=0 -> left) hits leaf 0 (0.3)" $
|
||||
predictRaw ens (VU.fromList [0.0, 0.0]) `shouldBe` 0.3
|
||||
|
||||
it "feature vector [10, 1] (cat_feat=1 -> left, num_feat=10 -> right) hits leaf 1 (-0.2)" $
|
||||
predictRaw ens (VU.fromList [10.0, 1.0]) `shouldBe` (-0.2)
|
||||
|
||||
it "feature vector [0, 2] (cat_feat=2 -> right) hits leaf 2 (-0.4)" $
|
||||
predictRaw ens (VU.fromList [0.0, 2.0]) `shouldBe` (-0.4)
|
||||
|
||||
it "predictProba on tinyBytes feeds the sum through binary sigmoid scale=1" $
|
||||
predictProba ens (VU.fromList [0.0, 0.0])
|
||||
`shouldBe` (1.0 / (1.0 + exp (-0.3)))
|
||||
|
||||
isPlatt :: Calibrator -> Bool
|
||||
isPlatt (PlattCalibrator _ _) = True
|
||||
isPlatt _ = False
|
||||
|
||||
isIsotonic :: Calibrator -> Bool
|
||||
isIsotonic (IsotonicCalibrator _) = True
|
||||
isIsotonic _ = False
|
||||
|
||||
mlCalibrationSpec :: Spec
|
||||
mlCalibrationSpec = describe "ML.Calibration" $ do
|
||||
describe "NoCalibrator" $
|
||||
it "is identity for any input" $ do
|
||||
calibrate NoCalibrator 0.0 `shouldBe` 0.0
|
||||
calibrate NoCalibrator 0.5 `shouldBe` 0.5
|
||||
calibrate NoCalibrator 1.0 `shouldBe` 1.0
|
||||
calibrate NoCalibrator (-3.7) `shouldBe` (-3.7)
|
||||
|
||||
describe "PlattCalibrator basic shape" $ do
|
||||
it "(a=0, b=0) yields constant 0.5 regardless of p" $ do
|
||||
calibrate (PlattCalibrator 0.0 0.0) 0.3 `shouldBe` 0.5
|
||||
calibrate (PlattCalibrator 0.0 0.0) 1000.0 `shouldBe` 0.5
|
||||
|
||||
it "negative a produces output increasing in p" $ do
|
||||
let cal = PlattCalibrator (-2.0) 1.0
|
||||
calibrate cal 0.0 `shouldSatisfy` (< calibrate cal 1.0)
|
||||
|
||||
it "positive (a*p + b) saturates near 0 for large p" $
|
||||
calibrate (PlattCalibrator 1.0 0.0) 1000.0 `shouldBe` 0.0
|
||||
|
||||
it "negative (a*p + b) saturates near 1 for large p" $
|
||||
calibrate (PlattCalibrator (-1.0) 0.0) 1000.0 `shouldBe` 1.0
|
||||
|
||||
describe "fitPlatt edge cases" $ do
|
||||
it "returns NoCalibrator for empty input" $
|
||||
fitPlatt VU.empty `shouldBe` NoCalibrator
|
||||
|
||||
it "returns NoCalibrator for single sample" $
|
||||
fitPlatt (VU.singleton (0.5, True)) `shouldBe` NoCalibrator
|
||||
|
||||
it "returns PlattCalibrator for >=2 samples" $
|
||||
fitPlatt (VU.fromList [(0.1, False), (0.9, True)])
|
||||
`shouldSatisfy` isPlatt
|
||||
|
||||
describe "fitPlatt convergence on logistic-like data" $ do
|
||||
let negativeExamples = [(fromIntegral i / 100.0, False) | i <- [0 :: Int .. 49]]
|
||||
positiveExamples = [(fromIntegral i / 100.0, True) | i <- [50 :: Int .. 99]]
|
||||
samples = VU.fromList (negativeExamples ++ positiveExamples)
|
||||
cal = fitPlatt samples
|
||||
|
||||
it "fit recovers a < 0 (output increases with p)" $
|
||||
case cal of
|
||||
PlattCalibrator a _ -> a `shouldSatisfy` (< 0.0)
|
||||
_ -> expectationFailure "expected PlattCalibrator"
|
||||
|
||||
it "calibrated output at low p is less than at high p" $
|
||||
calibrate cal 0.1 `shouldSatisfy` (< calibrate cal 0.9)
|
||||
|
||||
it "calibrated output stays in (0, 1)" $ do
|
||||
let mid = calibrate cal 0.5
|
||||
mid `shouldSatisfy` (> 0.0)
|
||||
mid `shouldSatisfy` (< 1.0)
|
||||
|
||||
describe "fitIsotonic edge cases" $ do
|
||||
it "returns NoCalibrator for empty input" $
|
||||
fitIsotonic VU.empty `shouldBe` NoCalibrator
|
||||
|
||||
it "returns NoCalibrator for single sample" $
|
||||
fitIsotonic (VU.singleton (0.5, True)) `shouldBe` NoCalibrator
|
||||
|
||||
it "returns IsotonicCalibrator for >=2 samples" $
|
||||
fitIsotonic (VU.fromList [(0.1, False), (0.9, True)])
|
||||
`shouldSatisfy` isIsotonic
|
||||
|
||||
describe "fitIsotonic on already-monotone data" $ do
|
||||
let samples = VU.fromList
|
||||
[(0.1, False), (0.3, False), (0.6, True), (0.9, True)]
|
||||
cal = fitIsotonic samples
|
||||
|
||||
it "low raw clamps to 0.0" $
|
||||
calibrate cal 0.0 `shouldBe` 0.0
|
||||
|
||||
it "high raw clamps to 1.0" $
|
||||
calibrate cal 1.0 `shouldBe` 1.0
|
||||
|
||||
it "calibrated values are monotone non-decreasing" $
|
||||
case cal of
|
||||
IsotonicCalibrator bp ->
|
||||
let cals = VU.toList (VU.map snd bp)
|
||||
in all (uncurry (<=)) (zip cals (drop 1 cals)) `shouldBe` True
|
||||
_ -> expectationFailure "expected IsotonicCalibrator"
|
||||
|
||||
describe "fitIsotonic corrects non-monotone data" $ do
|
||||
let samples = VU.fromList
|
||||
[(0.1, False), (0.4, True), (0.5, False), (0.9, True)]
|
||||
cal = fitIsotonic samples
|
||||
|
||||
it "produces 3 breakpoints (one PAV merge)" $
|
||||
case cal of
|
||||
IsotonicCalibrator bp -> VU.length bp `shouldBe` 3
|
||||
_ -> expectationFailure "expected IsotonicCalibrator"
|
||||
|
||||
it "calibrated values are monotone non-decreasing" $
|
||||
case cal of
|
||||
IsotonicCalibrator bp ->
|
||||
let cals = VU.toList (VU.map snd bp)
|
||||
in all (uncurry (<=)) (zip cals (drop 1 cals)) `shouldBe` True
|
||||
_ -> expectationFailure "expected IsotonicCalibrator"
|
||||
|
||||
describe "fitIsotonic ties" $ do
|
||||
let samples = VU.fromList [(0.5, True), (0.5, False)]
|
||||
cal = fitIsotonic samples
|
||||
|
||||
it "merges identical raw values into one breakpoint" $
|
||||
case cal of
|
||||
IsotonicCalibrator bp -> VU.length bp `shouldBe` 1
|
||||
_ -> expectationFailure "expected IsotonicCalibrator"
|
||||
|
||||
it "merged breakpoint has averaged label" $
|
||||
calibrate cal 0.5 `shouldBe` 0.5
|
||||
|
||||
describe "fitIsotonic with all-same labels" $ do
|
||||
it "all True calibrates to 1.0 across the range" $ do
|
||||
let cal = fitIsotonic (VU.fromList [(0.1, True), (0.5, True), (0.9, True)])
|
||||
calibrate cal 0.5 `shouldBe` 1.0
|
||||
|
||||
it "all False calibrates to 0.0 across the range" $ do
|
||||
let cal = fitIsotonic (VU.fromList [(0.1, False), (0.5, False), (0.9, False)])
|
||||
calibrate cal 0.5 `shouldBe` 0.0
|
||||
|
||||
describe "isotonic lookup behavior" $ do
|
||||
let cal = IsotonicCalibrator
|
||||
(VU.fromList [(0.25, 0.0), (0.5, 0.5), (0.75, 1.0)])
|
||||
|
||||
it "clamps below first breakpoint" $
|
||||
calibrate cal 0.0 `shouldBe` 0.0
|
||||
|
||||
it "clamps above last breakpoint" $
|
||||
calibrate cal 1.5 `shouldBe` 1.0
|
||||
|
||||
it "returns exact value at a breakpoint" $
|
||||
calibrate cal 0.5 `shouldBe` 0.5
|
||||
|
||||
it "linearly interpolates between breakpoints" $ do
|
||||
let bp = VU.fromList [(0.0, 0.25), (1.0, 0.75)]
|
||||
calibrate (IsotonicCalibrator bp) 0.5 `shouldBe` 0.5
|
||||
|
||||
it "empty breakpoints pass through" $
|
||||
calibrate (IsotonicCalibrator VU.empty) 0.42 `shouldBe` 0.42
|
||||
|
||||
headersOnlyRequest :: [(BS.ByteString, BS.ByteString)] -> Request
|
||||
headersOnlyRequest hs =
|
||||
Network.Wai.Test.defaultRequest
|
||||
|
|
|
|||
Loading…
Reference in New Issue