colada 0.7.0.0 → 0.8.0.0

raw patch · 2 files changed

+18/−10 lines, 2 filesdep ~swift-lda

Dependency ranges changed: swift-lda

Files

• Colada/WordClass.hs +15/−7
• colada.cabal +3/−3

@@ -180,14 +180,20 @@                          (get topicNum opts)                          (get alphasum opts)                          (get beta opts)-                         (get exponent opts)-        Fold.forM_ bs $ \b -> do+        Fold.forM_ bs $ \b -> do +          _ <- ST.stToIO . LDA.run m (get passes opts) . Fold.msum $ b +          when (get progressive opts) $ do+            Fold.forM_ b $ \sent -> do+              ls <- ST.stToIO $ V.mapM (interpWordClasses m (get lambda opts)) sent+              f ls+ {-                    Fold.forM_ [1..get passes opts] $ \i -> do             Fold.forM_ b $ \sent -> do               _ <- ST.stToIO $ LDA.pass 1 m sent               when (get progressive opts && i == get passes opts) $ do                 ls <- ST.stToIO $ V.mapM (interpWordClasses m (get lambda opts)) sent                 f ls+-}         ST.stToIO $ LDA.finalize m       lda <- sampler   return (WordClass lda atomTabD atomTabW opts)@@ -219,7 +225,8 @@   where doc (d, ws) = do           da  <- Symbols.toAtomA . compress $ d           was <- mapM (Symbols.toAtomB . compress) ws-          return (da, U.fromList $ zip was (repeat Nothing))+          --return (da, U.fromList $ zip was (repeat Nothing))+          return (da, U.fromList was)  -- | @summary m@ returns a textual summary of word classes found in -- model @m@@@ -259,8 +266,9 @@ -- | @interpWordClasses m lambda doc@ gives the class probabilities for -- word type in context @doc@ according to evolving model @m@. It -- interpolates the prior word type probability with the--- context-conditioned probabilities using alpha: --- P(d,w) = lambda * P(z|d) + (1-lambda) * P(z|d,w)+-- context-conditioned probabilities using lambda: +-- P(d,w) = lambda * P(z|d) + (1-lambda) * P(z|d,w).+-- This function does not mutate any weights of the model. interpWordClasses ::    LDA.LDA s                      -> Double                       -> LDA.Doc @@ -296,7 +304,7 @@                                       (L.get wordTypeTable m)                                        (L.get featureTable m)    where dectx doc@(d, _) = if noctx -                           then (d, U.singleton (-1,Nothing)) --FIXME: ugly hack+                           then (d, U.singleton (-1)) --FIXME: ugly hack                            else doc         label' = do           let fm = L.get ldaModel m@@ -319,7 +327,7 @@                     . V.toList                      $ s'           mapM (V.mapM fromAtom) ws-        docToWs = U.map fst . snd+        docToWs = snd         fromAtom (n,w) = do w' <- Symbols.fromAtomA w                             return (n, decompress w') 

@@ -1,5 +1,5 @@ Name:                colada-Version:             0.7.0.0+Version:             0.8.0.0 Synopsis:            Colada implements incremental word class class induction                       using online LDA Description:  Colada implements incremental word class class induction using @@ -27,7 +27,7 @@                , cmdargs >= 0.9                , bytestring >= 0.9                , mtl >= 2.0-               , swift-lda >= 0.4 && <= 0.5+               , swift-lda >= 0.7 && < 0.8   Exposed-modules:  Colada.WordClass                   , NLP.CoNLL   Other-modules: Colada.Features@@ -50,7 +50,7 @@                , cmdargs >= 0.9                , bytestring >= 0.9                , mtl >= 2.0-               , swift-lda >= 0.4 && <= 0.5+               , swift-lda >= 0.7 && < 0.8   Other-modules: Colada.WordClass                , Colada.Features                , NLP.CoNLL