hinduce-examples 0.0.0.1 → 0.0.0.2

raw patch · 5 files changed

+135/−82 lines, 5 filesdep +containersdep +hinduce-associations-aprioridep +vectorPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

Dependencies added: containers, hinduce-associations-apriori, vector

API changes (from Hackage documentation)

Files

• data/T10I4D100K.dat too large to diff
• hinduce-examples.cabal +9/−1
• src/Data/HInduce/Examples.hs +19/−81
• src/Data/HInduce/Examples/Associations.hs +27/−0
• src/Data/HInduce/Examples/DecisionTree.hs +80/−0

file too large to diff

@@ -1,5 +1,5 @@ Name:           hinduce-examples-Version:        0.0.0.1+Version:        0.0.0.2 License:        BSD3 Author:         Robert Hensing Synopsis:       Example data for hInduce@@ -13,6 +13,7 @@     data/iris/iris.data     data/iris/bezdekIris.data     data/iris/iris.names+    data/T10I4D100K.dat  Library     Build-Depends:      base >= 4 && < 5@@ -21,7 +22,14 @@                         , csv >= 0.1.2                         , hinduce-classifier >= 0.0.0.0                         , hinduce-classifier-decisiontree >= 0.0.0.0+                        , hinduce-associations-apriori >= 0.0.0.0                         , convertible+                        , containers >= 0.4.2.0+                        , vector >= 0.9.1     Exposed-Modules:    Data.HInduce.Examples+                        -- These need not be exposed, but we do to make+                        -- the haddock documentation more readable.+                        , Data.HInduce.Examples.DecisionTree+                        , Data.HInduce.Examples.Associations     Other-Modules:	Paths_hinduce_examples     Hs-Source-Dirs:     src

@@ -1,89 +1,27 @@-{-# LANGUAGE MultiParamTypeClasses #-}-module Data.HInduce.Examples (-  -- * Re-exports-  module Data.HInduce.Classifier+-- | This package / module provides example data and example code to help you+-- get started with HInduce. You are advised to import this module (ghci: +-- @:m + Data.HInduce.Examples@), not the individual ones below, because+-- @Data.HInduce.Examples@ re-exports modules that are required to run the+-- examples yourself.+--+-- Click on a module below to view the examples you're interested in. Also note+-- the grey "Source" links at the right hand site of the webpage.+module Data.HInduce.Examples ( -- * The Examples+                             module Data.HInduce.Examples.DecisionTree+                             , module Data.HInduce.Examples.Associations+  -- * Re-exports for convenience+  , module Data.HInduce.Classifier   , module Data.HInduce.Classifier.DecisionTree+  , module Data.HInduce.Associations.Apriori   , module Data.List.HIUtils   , module Text.Layout-  , module Data.Convertible-  -- * Helpers (TODO move to module)-  , readCSV-  -- * Iris data set-  -- | Taken from the UCI Machine Learning Repository: <http://archive.ics.uci.edu/ml/datasets/Iris>-  -- -  -- Let's build a decision tree and try it:-  ---  -- >>> let model = buildDTree (genMany autoDeciders) irisAttrs irisClass iris-  ---  -- >>> classify model [5,4,2,1]-  -- Setosa-  -- >>> iris !! 10-  -- Iris {sepalLength = 5.4, sepalWidth = 3.7, petalLength = 1.5, petalWidth = 0.2, irisClass = Setosa}-  ---  -- Seems good! But can we really know that?-  -- Let's train and test on separate data-  ---  -- >>> let model' = buildDTree (genMany autoDeciders) irisAttrs irisClass (oddIx iris)-  ---  -- >>> dt $ confusion' model' (map (irisAttrs &&& irisClass) $ evenIx iris)-  -- Table: Confusion Matrix-  --          ||-->Actual-  -- Predicted\/             Setosa           Versicolor           Virginica-  --     Setosa 0.3333333333333333                                         -  -- Versicolor                     0.30666666666666664              4.0e-2-  --  Virginica                    2.666666666666667e-2 0.29333333333333333-  ---  -- Now we see that even though not the whole data set was available-  -- when the model was induced, only few misclassifications occur.--  , Iris(..), IrisClass(..), irisAttrs, irisAttrs', readIris, iris-  ) where-import Paths_hinduce_examples+                             ) where +import Data.HInduce.Examples.DecisionTree+import Data.HInduce.Examples.Associations import Data.HInduce.Classifier import Data.HInduce.Classifier.DecisionTree-import Text.Layout-import Data.Convertible+import Data.HInduce.Associations.Apriori import Data.List.HIUtils-import System.IO-import Text.CSV-import System.IO.Unsafe--test :: FilePath -> IO FilePath-test = getDataFileName--readCSV x = do-  f <- getDataFileName $ "data/" ++ x-  parseCSVFromFile f--openDataR x = do-  f <- getDataFileName $ "data/" ++ x-  openFile f ReadMode--data IrisClass = Setosa | Versicolor | Virginica-                                       deriving (Eq, Ord, Show, Read)-instance Layout IrisClass DisplayText where format = fromShow--data Iris = Iris { sepalLength :: Double -                 , sepalWidth :: Double -                 , petalLength :: Double -                 , petalWidth :: Double -                 , irisClass :: IrisClass-                 }-          deriving (Eq, Ord, Show, Read)-  -irisAttrs (Iris p q r s _) = [p, q, r, s]-irisAttrs' (Iris p q r s _) = ((p, q), (r, s))--readIris = do-  (Right csv) <- readCSV "iris/iris.data"-  return $ map readIrisEntry $ filter (/=[""]) csv--readIrisEntry [p,q,r,s,"Iris-setosa"] = -  Iris (read p) (read q) (read r) (read s) Setosa-readIrisEntry [p,q,r,s,"Iris-versicolor"] = -  Iris (read p) (read q) (read r) (read s) Versicolor-readIrisEntry [p,q,r,s,"Iris-virginica"] =-  Iris (read p) (read q) (read r) (read s) Virginica+import Text.Layout -iris = unsafePerformIO readIris

@@ -0,0 +1,27 @@+-- | An example of association rule mining:+--+-- >>> rules transactions items (top ((take 40) . (filter (\(_,a)->a>= 60))))+-- > fromList [((fromList [32],fromList [947]),0.1694915254237288),((fromList [39],fromList [145]),0.17238139971817754),((fromList [39],fromList [145,419]),8.266791921089714e-2),((fromList [39],fromList [368]),0.1326914044152184),((fromList [39],fromList [419]),0.1200093940817285),+module Data.HInduce.Examples.Associations where+import Data.HInduce.Associations.Apriori+import Text.Layout+import System.IO.Unsafe+import qualified Data.Set as S+import qualified Data.Vector as V+import Control.Arrow+import Data.Set+import Data.Vector++import Paths_hinduce_examples++-- | The transactions in the T10I4D100K.dat data set.+transactions :: Data.Vector.Vector (Data.Set.Set Int)++-- | The items in the T10I4D100K.dat data set.+items :: Data.Set.Set Int++(transactions, items) = unsafePerformIO $ do+  name <- getDataFileName "data/T10I4D100K.dat"+  ds <- loadDataSet name+  return $ V.fromList &&& S.unions $ ds+

@@ -0,0 +1,80 @@+{-# LANGUAGE MultiParamTypeClasses #-}+module Data.HInduce.Examples.DecisionTree (+  -- * Helpers (TODO move to module)+  readCSV+  -- * Iris data set+  -- | Taken from the UCI Machine Learning Repository: <http://archive.ics.uci.edu/ml/datasets/Iris>+  -- +  -- Let's build a decision tree and try it:+  --+  -- >>> let model = buildDTree (genMany autoDeciders) irisAttrs irisClass iris+  --+  -- >>> classify model [5,4,2,1]+  -- Setosa+  -- >>> iris !! 10+  -- Iris {sepalLength = 5.4, sepalWidth = 3.7, petalLength = 1.5, petalWidth = 0.2, irisClass = Setosa}+  --+  -- Seems good! But can we really know that?+  -- Let's train and test on separate data+  --+  -- >>> let model' = buildDTree (genMany autoDeciders) irisAttrs irisClass (oddIx iris)+  --+  -- >>> dt $ confusion' model' (map (irisAttrs &&& irisClass) $ evenIx iris)+  -- Table: Confusion Matrix+  --          ||-->Actual+  -- Predicted\/             Setosa           Versicolor           Virginica+  --     Setosa 0.3333333333333333                                         +  -- Versicolor                     0.30666666666666664              4.0e-2+  --  Virginica                    2.666666666666667e-2 0.29333333333333333+  --+  -- Now we see that even though not the whole data set was available+  -- when the model was induced, only few misclassifications occur.++  , Iris(..), IrisClass(..), irisAttrs, irisAttrs', readIris, iris+  ) where+import Paths_hinduce_examples++import Data.HInduce.Classifier+import Data.HInduce.Classifier.DecisionTree+import Text.Layout+import Data.Convertible+import Data.List.HIUtils+import System.IO+import Text.CSV+import System.IO.Unsafe++readCSV x = do+  f <- getDataFileName $ "data/" ++ x+  parseCSVFromFile f++openDataR x = do+  f <- getDataFileName $ "data/" ++ x+  openFile f ReadMode++data IrisClass = Setosa | Versicolor | Virginica+                                       deriving (Eq, Ord, Show, Read)+instance Layout IrisClass DisplayText where format = fromShow++data Iris = Iris { sepalLength :: Double +                 , sepalWidth :: Double +                 , petalLength :: Double +                 , petalWidth :: Double +                 , irisClass :: IrisClass+                 }+          deriving (Eq, Ord, Show, Read)+  +irisAttrs (Iris p q r s _) = [p, q, r, s]+irisAttrs' (Iris p q r s _) = ((p, q), (r, s))++readIris = do+  (Right csv) <- readCSV "iris/iris.data"+  return $ map readIrisEntry $ filter (/=[""]) csv++readIrisEntry [p,q,r,s,"Iris-setosa"] = +  Iris (read p) (read q) (read r) (read s) Setosa+readIrisEntry [p,q,r,s,"Iris-versicolor"] = +  Iris (read p) (read q) (read r) (read s) Versicolor+readIrisEntry [p,q,r,s,"Iris-virginica"] =+  Iris (read p) (read q) (read r) (read s) Virginica++iris = unsafePerformIO readIris