colada 0.4.2 → 0.4.3

raw patch · 3 files changed

+34/−4 lines, 3 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• Colada/WordClass.hs +14/−1
• colada.cabal +1/−1
• colada.hs +19/−2

@@ -31,6 +31,7 @@        , defaultOptions          -- * Extracting information        , summary+       , summarize        , wordTypeClasses          -- * Class and word prediction        , label@@ -98,6 +99,7 @@ import qualified Data.Traversable           as Trav import qualified Control.Monad.ST           as ST import qualified Control.Monad.ST.Lazy      as LST+import Data.Function (on) import Control.Monad.Writer        import Data.Word           (Word32) import Data.Typeable       (Typeable)@@ -261,7 +263,10 @@ -- | @summary m@ returns a textual summary of word classes found in -- model @m@ summary :: WordClass -> Text.Text-summary m = +summary = summarize False++summarize :: Bool -> WordClass -> Text.Text+summarize harden m =    let format (z,cs) =  do          cs' <-  mapM (Atom.fromAtom . fst)                 . takeWhile ((>0) . snd)@@ -276,6 +281,14 @@     . IntMap.toList     . IntMap.fromListWith (IntMap.unionWith (+))     . concatMap (\(d,zs) -> [ (z, IntMap.singleton d c) | (z,c) <- zs ])+    -- Maybe harden    +    . (if harden +       then +        map (\(d,zs) -> let s = sum . map snd $ zs +                            (z',_) = List.maximumBy (Ord.compare `on` snd) zs+                        in (d, [ (z, if z == z' then s else 0) | (z,_) <- zs ]))+      else id)+    --                 . IntMap.toList     . IntMap.map  IntMap.toList     . LDA.docTopics

@@ -1,5 +1,5 @@ Name:                colada-Version:             0.4.2+Version:             0.4.3 Synopsis:            Colada implements incremental word class class induction                       using online LDA Description:  Colada implements incremental word class class induction using 

@@ -32,6 +32,9 @@                        , _modelPath :: FilePath }              | Label { _modelPath :: FilePath                       , _noContext :: Bool }+             | Summary { _modelPath :: FilePath +                       ,_harden :: Bool }+              deriving (Show) $(L.mkLabels [''Program])                                        @@ -55,7 +58,16 @@          "NAT" "Number of most probable words to show"   ]-  ++summary :: Mode Program  +summary =+  mode "summary" Summary { _modelPath = "model" , _harden = False } +        "Display summary of word classes"+  (flagArg (\x p -> Right $ maybe p id (M.set modelPath x p)) "FILE")  +  [ flagNone ["harden"] (\p -> p { _harden = True })+    "Harden class assignments for summary"+  ]  + label :: Mode Program label =   mode "label" Label { _modelPath = "model" , _noContext = False } @@ -128,7 +140,7 @@    program :: Mode Program                      program = modes "colada" Help "Word class learning" -          [learn, predict, label, help] +          [learn, predict, label, summary, help]    -- Run the program@@ -163,6 +175,11 @@         then do Text.putStr . Text.unlines . map formatLabeling $ ls         else do Text.putStr . C.summary $ m           BS.writeFile p . Serialize.encode $ m      +    Summary { _modelPath = p , _harden = h } -> do  +      m <- parseModel p+      if h+        then do Text.putStr . C.summarize True  $ m   +        else do Text.putStr . C.summarize False $ m        formatLabeling :: (V.Vector v Int, V.Vector v Text.Text) =>      v Int -> Text.Text