HLearn-distributions 0.1.0.1 → 0.2.1

raw patch · 4 files changed

+103/−51 lines, 4 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• HLearn-distributions.cabal +1/−1
• src/HLearn/Gnuplot/Distributions.hs +97/−45
• src/HLearn/Models/Distributions/Categorical.hs +4/−4
• src/HLearn/Models/Distributions/Common.hs +1/−1

@@ -1,5 +1,5 @@ Name:                HLearn-distributions-Version:             0.1.0.1+Version:             0.2.1 Synopsis:            Distributions for use with the HLearn library Description:         This module is used to estimate statistical distributions from data.  The focus is a clean interface inspired by algebra. Category:            Data Mining, Machine Learning, Statistics

@@ -10,6 +10,7 @@ import HLearn.Algebra import HLearn.Models.Distributions +import qualified Data.Map as Map import qualified Data.Vector.Unboxed as VU  import Control.Monad@@ -20,62 +21,113 @@     { dataFile :: FilePath     , gnuFile :: FilePath     , picFile :: FilePath-    , plotPoints :: [Double]     } -class PlottableDistribution dist where-    genPlotPoints :: dist -> [Double]--instance PlottableDistribution (KDE Double) where-    genPlotPoints (SGJust kde) = VU.toList $ samplePoints $ params kde--genPlotParams :: (PlottableDistribution dist) => String -> dist -> PlotParams-genPlotParams str dist = PlotParams+plotFile :: String -> PlotParams+plotFile str = PlotParams     { dataFile = str++".dat"     , gnuFile  = str++".gnu"     , picFile  = str++".ps"-    , plotPoints = genPlotPoints dist     } +-- | provided due to backwards compatibility with the nuclear weapons blog post.+genPlotParams :: String -> a -> PlotParams+genPlotParams str a = plotFile str+ defPlotParams = PlotParams     { dataFile = "hlearn-distributions.dat"     , gnuFile = "hlearn-distributions.gnu"     , picFile = "hlearn-distributions.ps"-    , plotPoints = [-5..5]     }-    -plotDistribution :: (Distribution dist Double Double) => PlotParams -> dist -> IO ()-plotDistribution params dist = do-    -    -- Create data file-    putStrLn "Creating data file..."-    datah <- openFile (dataFile params) WriteMode-    forM_ (plotPoints params) $ \x -> do---     forM_ (map (/10) [-50..50]) $ \x -> do-        hPutStrLn datah $ show (x::Double) ++ " " ++ show (pdf dist x::Double)-    hClose datah-    -    -- Create gnuplot file-    putStrLn "Plotting data"-    gnuh <- openFile (gnuFile params) WriteMode-    hPutStrLn gnuh $ "set terminal postscript \"Times-Roman\" 25"-    hPutStrLn gnuh $ "set output \"" ++ (picFile params) ++ "\""-    hPutStrLn gnuh $ "unset xtics; unset ytics; unset key"-    hPutStrLn gnuh $ "set border 0; set xzeroaxis lt 1; set yzeroaxis lt 1"-    hPutStrLn gnuh $ "plot '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#ccccff' with filledcurves, \\"-    hPutStrLn gnuh $ "     '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#0000ff' with lines"-    hClose gnuh++class PlottableDistribution dist where+    plotDistribution :: PlotParams -> dist -> IO ()+    plotDistribution params dist = do+        -- Create data file+        putStrLn "Creating data file..."+        datah <- openFile (dataFile params) WriteMode+        hPutStrLn datah $ plotdata dist+        hClose datah+        +        -- Create gnuplot file+        putStrLn "Plotting data"+        gnuh <- openFile (gnuFile params) WriteMode+        hPutStrLn gnuh $ gnuplot params dist+        hClose gnuh+        +        -- Run gnuplot, creating picture+        system $ "gnuplot "++(gnuFile params)+        putStrLn "done."+        return ()++    plotdata :: dist -> String+    gnuplot  :: PlotParams -> dist -> String     -    -- Run gnuplot, creating picture-    system $ "gnuplot "++(gnuFile params)-    putStrLn "done."-    return ()+instance PlottableDistribution (KDE Double) where+    plotdata dist@(SGJust kde) = mconcat [show (x::Double) ++ " " ++ show (pdf dist x::Double) | x <- plotPoints]+        where+            plotPoints = VU.toList $ samplePoints $ params kde++    gnuplot params dist+        =  "set terminal postscript \"Times-Roman\" 25"+        ++ "set output \"" ++ (picFile params) ++ "\""+        ++ "unset xtics; unset ytics; unset key"+        ++ "set border 0; set xzeroaxis lt 1; set yzeroaxis lt 1"+        ++ "plot '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#ccccff' with filledcurves, \\"+        ++ "     '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#0000ff' with lines"+        +instance (Show label, Show prob, Num prob, Ord prob) => PlottableDistribution (Categorical label prob) where+    plotdata dist@(Categorical pdf) = concat $ do+        (label,prob) <- Map.toList pdf+        return $ show label++" "++show prob++"\n"+        +    gnuplot params (Categorical pdf)+        = "set terminal postscript \"Times-Roman\" 25; set output \""++ (picFile params) ++ "\"\n"+        ++"set tics scale 0; set xtics nomirror; unset ytics; unset key\n"+        ++"set border 2; set xzeroaxis lt 1\n"+        ++"set ylabel \"Probability\"\n"+        ++yrange+        ++"set style fill border -1\n"+        ++"set style data histogram; set style histogram cluster gap 1\n"+        ++"plot '"++(dataFile params)++"' using 2:xticlabels(1)\n"+        where+            positiveSamples = or $ map (\(k,v) -> v>0) $ Map.toList pdf+            negativeSamples = or $ map (\(k,v) -> v<0) $ Map.toList pdf+            yrange = if positiveSamples && negativeSamples+                then ""+                else if positiveSamples+                    then "set yrange [0:]\n"+                    else "set yrange [:0]\n"+{-        =  "set terminal postscript \"Times-Roman\" 25 \n"+        ++ "set output \"" ++ (picFile params) ++ "\" \n"+        ++ "unset xtics; unset ytics; unset key\n"+        ++ "set border 0; set xzeroaxis lt 1; set yzeroaxis lt 1\n"+        ++ "set style data histogram \n"+        ++ "plot '"++(dataFile params)++"' using 1:2 \n"-}     --- testL = [1,1.1,1.2,0,5,-3,2,1,2.5,2.9::Double]--- kde = train' (KDEParams 1 (VU.fromList $ map (/10) [-50..50::Double]) (KernelBox Gaussian)) testL :: KDE Double--- --- pdfL = sequence_ $ do---     x <- map (/10) [-50..50]---     let y = pdf kde x :: Double---     seq y (return ())---     return $ putStrLn $ (show (x::Double)) ++ " " ++ show y+-- plotDistribution :: (Distribution dist Double Double) => PlotParams -> dist -> IO ()+-- plotDistribution params dist = do+--     +--     -- Create data file+--     putStrLn "Creating data file..."+--     datah <- openFile (dataFile params) WriteMode+--     forM_ (plotPoints params) $ \x -> do+-- --     forM_ (map (/10) [-50..50]) $ \x -> do+--         hPutStrLn datah $ show (x::Double) ++ " " ++ show (pdf dist x::Double)+--     hClose datah+--     +--     -- Create gnuplot file+--     putStrLn "Plotting data"+--     gnuh <- openFile (gnuFile params) WriteMode+--     hPutStrLn gnuh $ "set terminal postscript \"Times-Roman\" 25"+--     hPutStrLn gnuh $ "set output \"" ++ (picFile params) ++ "\""+--     hPutStrLn gnuh $ "unset xtics; unset ytics; unset key"+--     hPutStrLn gnuh $ "set border 0; set xzeroaxis lt 1; set yzeroaxis lt 1"+--     hPutStrLn gnuh $ "plot '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#ccccff' with filledcurves, \\"+--     hPutStrLn gnuh $ "     '"++(dataFile params)++"' using 1:2 lt 1 lw 4 lc rgb '#0000ff' with lines"+--     hClose gnuh+--     +--     -- Run gnuplot, creating picture+--     system $ "gnuplot "++(gnuFile params)+--     putStrLn "done."+--     return ()

@@ -44,8 +44,8 @@ instance Model CategoricalParams (Categorical label probtype) where     getparams model = CategoricalParams --- instance DefaultModel CategoricalParams (Categorical label probtype) where-instance DefaultModel CategoricalParams (Categorical Int Double) where+instance DefaultModel CategoricalParams (Categorical label probtype) where+-- instance DefaultModel CategoricalParams (Categorical Int Double) where     defparams = CategoricalParams  -------------------------------------------------------------------------------@@ -69,10 +69,10 @@ ------------------------------------------------------------------------------- -- Distribution -instance (Ord label, Ord prob, Floating prob, Random prob) => Distribution (Categorical label prob) label prob where+instance (Ord label, Ord prob, Fractional prob, Random prob) => Distribution (Categorical label prob) label prob where      {-# INLINE pdf #-}-    pdf dist label = 0.0001+(val/tot)+    pdf dist label = {-0.0001+-}(val/tot)         where             val = case Map.lookup label (pdfmap dist) of                 Nothing -> 0

@@ -12,7 +12,7 @@ -- Distribution      -- | We use the same class for both discrete and continuous distributions.  Unfortunately, we cannot use the type classes from the 'statistics' package because we require more generalilty.-class Distribution dist dp prob | dist -> dp where+class Distribution dist dp prob | dist -> dp, dist -> prob where     pdf :: dist -> dp -> prob  --     cdf :: dist -> dp -> prob  --     cdfInverse :: dist -> prob -> dp