mltool 0.1.0.2 → 0.2.0.0

raw patch · 17 files changed

+57/−33 lines, 17 filesdep +hmatrix-morpheusdep −hmatrix-gsl-statsdep ~hmatrixPVP ok

version bump matches the API change (PVP)

Dependencies added: hmatrix-morpheus

Dependencies removed: hmatrix-gsl-stats

Dependency ranges changed: hmatrix

API changes (from Hackage documentation)

Files

• LICENSE +1/−1
• README.md +16/−0
• mltool.cabal +6/−6
• src/MachineLearning.hs +5/−7
• src/MachineLearning/MultiSvmClassifier.hs +3/−1
• src/MachineLearning/NeuralNetwork/Layer.hs +2/−1
• src/MachineLearning/Optimization.hs +6/−3
• src/MachineLearning/PCA.hs +2/−1
• src/MachineLearning/Regression.hs +2/−1
• src/MachineLearning/SoftmaxClassifier.hs +2/−1
• test/MachineLearning/LeastSquaresModelTest.hs +5/−5
• test/MachineLearning/LogisticModelTest.hs +1/−1
• test/MachineLearning/MultiSvmClassifierTest.hs +1/−1
• test/MachineLearning/NeuralNetwork/WeightInitializationTest.hs +1/−1
• test/MachineLearning/Optimization/GradientDescentTest.hs +2/−1
• test/MachineLearning/Optimization/MinibatchGradientDescentTest.hs +1/−1
• test/MachineLearning/SoftmaxClassifierTest.hs +1/−1

@@ -1,4 +1,4 @@-Copyright Alexander Ignatyev (c) 2016+Copyright Alexander Ignatyev (c) 2016-2018  All rights reserved. 

@@ -39,6 +39,22 @@  ### Usage +#### OS X/macOS prerequisites setup++* Using [Homebrew](https://brew.sh/):++```+brew install pkg-config gsl+```++or ++* Using [MacPorts](https://www.macports.org/):++```+sudo port install pkgconfig gsl+```+ #### Build the project      stack build

@@ -1,5 +1,5 @@ name:                mltool-version:             0.1.0.2+version:             0.2.0.0 synopsis:            Machine Learning Toolbox description:     Haskell Machine Learning Toolkit@@ -12,7 +12,7 @@ license-file:        LICENSE author:              Alexander Ignatyev maintainer:          ignatyev.alexander@gmail.com-copyright:           (c) 2016-2017 Alexander Ignatyev+copyright:           (c) 2016-2018 Alexander Ignatyev category:            math build-type:          Simple extra-source-files:  README.md@@ -55,9 +55,9 @@   other-modules:       MachineLearning.Classification.Internal   build-depends:       base >= 4.7 && < 5                      , vector >= 0.11-                     , hmatrix >= 0.17.0.1+                     , hmatrix >= 0.18.0.0                      , hmatrix-gsl >= 0.17-                     , hmatrix-gsl-stats >= 0.4.1.3+                     , hmatrix-morpheus >= 0.1.1.0                      , ascii-progress >= 0.3.3.0                      , deepseq                      , random >= 1.1@@ -92,8 +92,8 @@   build-depends:       base                      , mltool                      , vector >= 0.11-                     , hmatrix >= 0.17.0.1-                     , hmatrix-gsl-stats >= 0.4.1.3+                     , hmatrix >= 0.18.0.0+                     , hmatrix-morpheus >= 0.1.1.0                      , random >= 1.1                      , MonadRandom >= 0.4.2.3                      , test-framework >= 0.8.1.1

@@ -24,7 +24,7 @@ import MachineLearning.Types (Vector, Matrix) import qualified Numeric.LinearAlgebra as LA import Numeric.LinearAlgebra((|||), (??))-import qualified Numeric.GSL.Statistics as Stat+import qualified Numeric.Morpheus.Statistics as Stat  import Control.Monad (replicateM, mfilter, MonadPlus) import Data.List (sort, group, foldl')@@ -44,11 +44,9 @@ -- | Caclulates mean and stddev values of every feature. -- Takes feature matrix X, returns pair of vectors of means and stddevs. meanStddev x =-  let cols = LA.toColumns x-      means = map Stat.mean cols-      stddevs = zipWith (\m col -> Stat.stddev_m m col) means cols-      stddevs' = map (\s -> if s < 2 then 1 else s) stddevs-  in (LA.row means, LA.row stddevs')+  let means = Stat.columnMean x+      stddevs = Stat.columnStddev_m means x+  in (LA.asRow means, LA.asRow stddevs)   featureNormalization (means, stddevs) x = (x - means) / stddevs@@ -64,7 +62,7 @@         makeTerm = foldl' (\c (index, power) -> c * (vv V.! index) ^ power) 1         terms :: Int -> [Vector]         terms d = foldl' (\l x -> (makeTerm x) : l) [] $ polynomialTerms d [ncols-1, ncols-2 .. 0]-        +  polynomialTerms :: Ord a => Int -> [a] -> [[(a, Int)]] polynomialTerms degree terms =

@@ -1,7 +1,7 @@ {-| Module: MachineLearning.MultiSvmClassifier Description: Multiclass Support Vector Machines Classifier.-Copyright: (c) Alexander Ignatyev, 2017.+Copyright: (c) Alexander Ignatyev, 2017-2018. License: BSD-3 Stability: experimental Portability: POSIX@@ -18,6 +18,8 @@  where ++import Prelude hiding ((<>)) import qualified Numeric.LinearAlgebra as LA import Numeric.LinearAlgebra((<>), (<.>), (|||)) import qualified Data.Vector.Storable as V

@@ -2,7 +2,7 @@ {-| Module: MachineLearning.NeuralNetwork.Layer Description: Neural Network's Layer-Copyright: (c) Alexander Ignatyev, 2017+Copyright: (c) Alexander Ignatyev, 2017-2018. License: BSD-3 Stability: experimental Portability: POSIX@@ -22,6 +22,7 @@ where  +import Prelude hiding ((<>)) import MachineLearning.Types (R, Matrix) import MachineLearning.Utils (sumByColumns) import qualified Numeric.LinearAlgebra as LA

@@ -75,10 +75,13 @@   where theta_m = LA.asColumn theta         eps_v = V.replicate (V.length theta) eps         eps_m = LA.diag eps_v-        theta_m1 = theta_m + eps_m-        theta_m2 = theta_m - eps_m+        -- +/- eps_m in case of zero theta+        theta_m1 = theta_m * (1 + eps_m) + eps_m+        theta_m2 = theta_m * (1 - eps_m) - eps_m         cost1 = LA.vector $ map (cost model reg x y) $ LA.toColumns theta_m1         cost2 = LA.vector $ map (cost model reg x y) $ LA.toColumns theta_m2-        grad1 = (cost1 - cost2) / (LA.scalar $ 2*eps)+        eps_v1 = LA.takeDiag $ theta_m1 - theta_m+        eps_v2 = LA.takeDiag $ theta_m - theta_m2+        grad1 = (cost1 - cost2) / (eps_v1 + eps_v2)         grad2 = gradient model reg x y theta 

@@ -1,7 +1,7 @@ {-| Module: MachineLearning.PCA Description: Principal Component Analysis.-Copyright: (c) Alexander Ignatyev, 2017+Copyright: (c) Alexander Ignatyev, 2017-2018. License: BSD-3 Stability: experimental Portability: POSIX@@ -18,6 +18,7 @@  where +import Prelude hiding ((<>)) import Data.Maybe (fromMaybe) import qualified Data.Vector.Storable as V import qualified Numeric.LinearAlgebra as LA

@@ -1,7 +1,7 @@ {-| Module: MachineLearning.Regression Description: Regression-Copyright: (c) Alexander Ignatyev, 2016-2017+Copyright: (c) Alexander Ignatyev, 2016-2018. License: BSD-3 Stability: experimental Portability: POSIX@@ -20,6 +20,7 @@  where +import Prelude hiding ((<>)) import MachineLearning.Types (Vector, Matrix) import MachineLearning.Optimization as Optimization import MachineLearning.Model as Model

@@ -1,7 +1,7 @@ {-| Module: MachineLearning.SoftmaxClassifier Description: Softmax Classifier.-Copyright: (c) Alexander Ignatyev, 2017.+Copyright: (c) Alexander Ignatyev, 2017-2018. License: BSD-3 Stability: experimental Portability: POSIX@@ -18,6 +18,7 @@  where +import Prelude hiding ((<>)) import qualified Numeric.LinearAlgebra as LA import Numeric.LinearAlgebra((<>), (<.>), (|||)) import qualified Data.Vector.Storable as V

@@ -39,11 +39,11 @@             , testCase "gradient, lambda = 1000" $ assertVector "" 1e-5 gradient_l1000 (gradient LeastSquares (L2 1000) x1 y initialTheta)             ]           , testGroup "gradient checking" [-              testCase "non-zero theta, no reg" $ assertBool "" $ (checkGradient LeastSquares RegNone x1 y initialTheta 1e-4) < 10-              , testCase "non-zero theta, non-zero lambda" $ assertBool "" $ (checkGradient LeastSquares (L2 2) x1 y initialTheta 1e-4) < 10-              , testCase "zero theta, non-zero lambda" $ assertBool "" $ (checkGradient LeastSquares (L2 2) x1 y zeroTheta 1e-4) < 1-              , testCase "non-zero theta, zero lambda" $ assertBool "" $ (checkGradient LeastSquares (L2 0) x1 y initialTheta 1e-4) < 5-              , testCase "zero theta, zero lambda" $ assertBool "" $ (checkGradient LeastSquares (L2 0) x1 y zeroTheta 1e-4) < 1+              testCase "non-zero theta, no reg" $ assertApproxEqual "" 1 0 (checkGradient LeastSquares RegNone x1 y initialTheta 1e-4)+              , testCase "non-zero theta, non-zero lambda" $ assertApproxEqual "" 1 0 (checkGradient LeastSquares (L2 2) x1 y initialTheta 1e-4)+              , testCase "zero theta, non-zero lambda" $ assertApproxEqual "" 1 0 (checkGradient LeastSquares (L2 2) x1 y zeroTheta 1e-4) +              , testCase "non-zero theta, zero lambda" $ assertApproxEqual "" 1 0 (checkGradient LeastSquares (L2 0) x1 y initialTheta 1e-4)+              , testCase "zero theta, zero lambda" $ assertApproxEqual "" 1 0(checkGradient LeastSquares (L2 0) x1 y zeroTheta 1e-4)               ]         ] 

@@ -32,7 +32,7 @@  checkGradientTest lambda theta = do   let diffs = take 5 $ map (\e -> checkGradient Logistic lambda x1 y theta e) [1e-3, 1.1e-3 ..]-      diff = minimum $ filter (not . isNaN) diffs+      diff = minimum diffs   assertApproxEqual (show theta) gradientCheckingEps 0 diff  

@@ -59,7 +59,7 @@  checkGradientTest lambda theta eps = do   let diffs = take 5 $ map (\e -> checkGradient model lambda x1 y theta e) [1e-3, 1.1e-3 ..]-      diff = minimum $ filter (not . isNaN) diffs+      diff = minimum diffs   assertApproxEqual "" eps 0 diff  

@@ -13,7 +13,7 @@ import Control.Monad (replicateM) import qualified Data.Vector.Storable as V import qualified Numeric.LinearAlgebra as LA-import qualified Numeric.GSL.Statistics as Stat+import qualified Numeric.Morpheus.Statistics as Stat import qualified Control.Monad.Random as RndM import MachineLearning.NeuralNetwork.WeightInitialization 

@@ -27,7 +27,8 @@ xNorm = ML.featureNormalization muSigma x x1 = ML.addBiasDimension xNorm initialTheta = LA.konst 0 (LA.cols x1)-lsExpectedTheta = LA.vector [340412.660, 110630.879, -8737.743]+-- Normal Equation's Result: 340412.660,110631.050,-6649.474+lsExpectedTheta = LA.vector [340412.660, 110630.886, -6649.310] eps = 1e-3  

@@ -29,7 +29,7 @@ x1 = ML.addBiasDimension xNorm initialTheta :: Vector initialTheta = LA.konst 0 (LA.cols x1)-lsExpectedTheta = LA.vector [325009.354,113890.981,6876.935]+lsExpectedTheta = LA.vector [325010.120,113889.649,5234.404] eps = 1e-3  

@@ -44,7 +44,7 @@ yExpected = LA.vector [1, 1, 0, 0, 1, 0]  -checkSoftmaxGradient theta eps lambda = minimum . take 5 . filter (not . isNaN) $ map check [eps, eps+0.001 ..]+checkSoftmaxGradient theta eps lambda = minimum . take 5 $ map check [eps, eps+0.001 ..]   where check e = checkGradient model lambda x1 y theta e