crf-chain1-constrained 0.1.0 → 0.1.1

raw patch · 6 files changed

+51/−32 lines, 6 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• Data/CRF/Chain1/Constrained/Dataset/Codec.hs +15/−1
• Data/CRF/Chain1/Constrained/Dataset/Internal.hs +2/−0
• Data/CRF/Chain1/Constrained/Inference.hs +1/−1
• Data/CRF/Chain1/Constrained/Model.hs +30/−27
• Data/CRF/Chain1/Constrained/Train.hs +2/−2
• crf-chain1-constrained.cabal +1/−1

@@ -1,6 +1,8 @@ module Data.CRF.Chain1.Constrained.Dataset.Codec ( Codec , CodecM+, obMax+, lbMax  , encodeWord'Cu , encodeWord'Cn@@ -40,6 +42,18 @@ -- of type a, the second one is used to encode labels of type b. type Codec a b = (C.AtomCodec a, C.AtomCodec (Maybe b)) +-- | The maximum internal observation included in the codec.+obMax :: Codec a b -> Ob+obMax =+    let idMax m = M.size m - 1+    in  Ob . idMax . C.to . fst++-- | The maximum internal label included in the codec.+lbMax :: Codec a b -> Lb+lbMax =+    let idMax m = M.size m - 1+    in  Lb . idMax . C.to . snd+ -- | The empty codec.  The label part is initialized with Nothing -- member, which represents unknown labels.  It is taken on account -- in the model implementation because it is assigned to the@@ -106,7 +120,7 @@     return $ mkX x' r'  -- | Encode the word and do *not* update the codec.-encodeWord'Cn :: (Ord a, Ord b) =>Word a b -> CodecM a b X+encodeWord'Cn :: (Ord a, Ord b) => Word a b -> CodecM a b X encodeWord'Cn word = do     x' <- catMaybes <$> mapM encodeObN (S.toList (obs word))     r' <- mapM encodeLbN (S.toList (lbs word))

@@ -92,6 +92,8 @@ -- potential labels for corresponding 'X' word. -- TODO: Perhaps we should substitute 'Lb's with label indices -- corresponding to labels from the vector of potential labels?+-- FIXME: The type definition is incorrect (see 'fromList' definition),+-- it should be something like AVec2. newtype Y = Y { _unY :: AVec (Lb, Double) }     deriving (Show, Read, Eq, Ord) 

@@ -106,7 +106,7 @@         | i == 0    = (0, 0)         | otherwise = (0, lbNum crf xs (i-1) - 1)     withMem psi beta i-        | i == V.length xs = const 0+        | i == V.length xs = const 1         | i == 0 = const $ sum             [ beta (i+1) k * psi k             * sgValue crf (lbOn crf (xs V.! i) k)

@@ -92,8 +92,8 @@ -- the set of observations is of the {0, 1, .. 'obMax'} form. -- There should be no repetition of features in the input list. -- TODO: We can change this function to take M.Map Feature Double.-fromList :: [(Feature, Double)] -> Model-fromList fs =+fromList :: Ob -> Lb -> [(Feature, Double)] -> Model+fromList obMax' lbMax' fs =     let _ixMap = M.fromList $ zip             (map fst fs)             (map FeatIx [0..])@@ -102,10 +102,13 @@         tFeats = [feat | (feat, _val) <- fs, isTFeat feat]         oFeats = [feat | (feat, _val) <- fs, isOFeat feat] -        obMax = (unOb . maximum . Set.toList . obSet) (map fst fs)-        lbs   = (Set.toList . lbSet) (map fst fs)-        lbMax = (unLb . maximum) lbs-        _r0   = A.fromList lbs+        obMax = unOb obMax'+        lbMax = unLb lbMax'+        _r0   = A.fromList (map Lb [0 .. lbMax])+        -- obMax = (unOb . maximum . Set.toList . obSet) (map fst fs)+        -- lbs   = (Set.toList . lbSet) (map fst fs)+        -- lbMax = (unLb . maximum) lbs+        -- _r0   = A.fromList lbs                  _sgIxsV = sgVects lbMax             [ (unLb x, featToJustIx crf feat)@@ -125,13 +128,13 @@          -- | Adjacency vectors.         adjVects n xs =-            V.replicate n (A.fromList []) V.// update+            V.replicate (n + 1) (A.fromList []) V.// update           where             update = map mkVect $ groupBy ((==) `on` fst) $ sort xs             mkVect (y:ys) = (fst y, A.fromList $ map snd (y:ys))             mkVect [] = error "mkVect: null list" -        sgVects n xs = U.replicate n dummyFeatIx U.// xs+        sgVects n xs = U.replicate (n + 1) dummyFeatIx U.// xs          _values = U.replicate (length fs) 0.0             U.// [ (featToJustInt crf feat, val)@@ -139,33 +142,33 @@         crf = Model _values _ixMap _r0 _sgIxsV _obIxsV _prevIxsV _nextIxsV     in  crf --- | Compute the set of observations.-obSet :: [Feature] -> Set.Set Ob-obSet =-    Set.fromList . concatMap toObs-  where-    toObs (OFeature o _) = [o]-    toObs _              = []---- | Compute the set of labels.-lbSet :: [Feature] -> Set.Set Lb-lbSet =-    Set.fromList . concatMap toLbs-  where-    toLbs (SFeature x)   = [x]-    toLbs (OFeature _ x) = [x]-    toLbs (TFeature x y) = [x, y]+-- -- | Compute the set of observations.+-- obSet :: [Feature] -> Set.Set Ob+-- obSet =+--     Set.fromList . concatMap toObs+--   where+--     toObs (OFeature o _) = [o]+--     toObs _              = []+-- +-- -- | Compute the set of labels.+-- lbSet :: [Feature] -> Set.Set Lb+-- lbSet =+--     Set.fromList . concatMap toLbs+--   where+--     toLbs (SFeature x)   = [x]+--     toLbs (OFeature _ x) = [x]+--     toLbs (TFeature x y) = [x, y]  -- | Construct the model from the list of features.  All parameters will be -- set to 0.  There can be repetitions in the input list. -- We assume that the set of labels is of the {0, 1, .. 'lbMax'} form and, -- similarly, the set of observations is of the {0, 1, .. 'obMax'} form.-mkModel :: [Feature] -> Model-mkModel fs =+mkModel :: Ob -> Lb -> [Feature] -> Model+mkModel obMax lbMax fs =     let fSet = Set.fromList fs         fs'  = Set.toList fSet         vs   = replicate (Set.size fSet) 0.0-    in  fromList (zip fs' vs)+    in  fromList obMax lbMax (zip fs' vs)  -- | Model potential defined for the given feature interpreted as a -- number in logarithmic domain.

@@ -18,7 +18,7 @@ import Data.CRF.Chain1.Constrained.Dataset.Internal import Data.CRF.Chain1.Constrained.Dataset.External (SentL, unknown, unDist) import Data.CRF.Chain1.Constrained.Dataset.Codec-    (mkCodec, Codec, encodeDataL, encodeLabels)+    (mkCodec, Codec, obMax, lbMax, encodeDataL, encodeLabels) import Data.CRF.Chain1.Constrained.Feature (Feature, featuresIn) import Data.CRF.Chain1.Constrained.Model     (Model (..), mkModel, FeatIx (..), featToJustInt)@@ -62,7 +62,7 @@         Just evalIO -> Just . encodeDataL _codec <$> evalIO         Nothing     -> return Nothing     let feats = extractFeats _r0 trainData-        crf = (mkModel feats) { r0 = _r0 }+        crf = (mkModel (obMax _codec) (lbMax _codec) feats) { r0 = _r0 }     para <- SGD.sgdM sgdArgs         (notify sgdArgs crf trainData evalDataM)         (gradOn crf) (V.fromList trainData) (values crf)

@@ -1,5 +1,5 @@ name:               crf-chain1-constrained-version:            0.1.0+version:            0.1.1 synopsis:           First-order, constrained, linear-chain conditional random fields description:     The library provides efficient implementation of the first-order,