dataframe-learn 2.4.1.0 → 2.4.2.0

raw patch · 21 files changed

+51/−40 lines, 21 filesdep ~dataframe-coredep ~dataframe-expr-serializerdep ~dataframe-operationsPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

Dependency ranges changed: dataframe-core, dataframe-expr-serializer, dataframe-operations

API changes (from Hackage documentation)

Files

• dataframe-learn.cabal +12/−12
• src-internal/DataFrame/DecisionTree/Cart.hs +1/−2
• src-internal/DataFrame/DecisionTree/Categorical.hs +2/−2
• src-internal/DataFrame/DecisionTree/Numeric.hs +1/−2
• src-internal/DataFrame/DecisionTree/Prune.hs +6/−1
• src-internal/DataFrame/Featurize/Internal.hs +7/−1
• src-internal/DataFrame/LinearSolver.hs +1/−1
• src-internal/DataFrame/SymbolicRegression/Expr.hs +1/−1
• src/DataFrame/Boosting/AdaBoost.hs +1/−1
• src/DataFrame/Boosting/GBM.hs +1/−1
• src/DataFrame/GMM.hs +1/−1
• src/DataFrame/KMeans.hs +1/−1
• src/DataFrame/PCA.hs +1/−1
• src/DataFrame/PCA/Kernel.hs +1/−1
• src/DataFrame/SVM/RFF.hs +1/−1
• src/DataFrame/Segmented.hs +5/−4
• src/DataFrame/Transform.hs +1/−1
• tests-internal/DecisionTree.hs +3/−2
• tests-internal/Properties/Simplify.hs +2/−2
• tests-internal/TreePruning.hs +1/−1
• tests-internal/Worklist.hs +1/−1

@@ -1,6 +1,6 @@ cabal-version:      3.4 name:               dataframe-learn-version:            2.4.1.0+version:            2.4.2.0 synopsis:           Interpretable, expression-returning machine learning for the dataframe ecosystem. description:     A small scikit-learn-style ML library where every model returns both an@@ -61,8 +61,8 @@                         containers >= 0.6.7 && < 0.10,                         parallel >= 3.3 && < 4,                         random >= 1.2 && < 2,-                        dataframe-core >= 2.4 && < 2.5,-                        dataframe-operations >= 2.4 && < 2.5,+                        dataframe-core >= 2.5 && < 2.6,+                        dataframe-operations >= 2.5 && < 2.6,                         text >= 2.1 && < 3,                         vector >= 0.13 && < 0.15,                         vector-algorithms >= 0.9 && < 0.11@@ -105,11 +105,11 @@                         containers >= 0.6.7 && < 0.10,                         parallel >= 3.3 && < 4,                         random >= 1.2 && < 2,-                        dataframe-core >= 2.4 && < 2.5,-                        dataframe-core >= 2.4 && < 2.5,-                        dataframe-operations >= 2.4 && < 2.5,-                        dataframe-operations >= 2.4 && < 2.5,-                        dataframe-expr-serializer >= 1.2.0.1 && < 1.3,+                        dataframe-core >= 2.5 && < 2.6,+                        dataframe-core >= 2.5 && < 2.6,+                        dataframe-operations >= 2.5 && < 2.6,+                        dataframe-operations >= 2.5 && < 2.6,+                        dataframe-expr-serializer >= 1.2.1 && < 1.3,                         dataframe-learn:internal,                         text >= 2.1 && < 3,                         vector >= 0.13 && < 0.15@@ -140,13 +140,13 @@                         aeson >= 0.11.0.0 && < 3,                         bytestring >= 0.11 && < 0.14,                         containers >= 0.6.7 && < 0.10,-                        dataframe-core >= 2.4 && < 2.5,-                        dataframe-core >= 2.4 && < 2.5,+                        dataframe-core >= 2.5 && < 2.6,+                        dataframe-core >= 2.5 && < 2.6,                         dataframe-csv >= 2.3 && < 2.4,                         dataframe-learn,                         dataframe-learn:internal,-                        dataframe-operations >= 2.4 && < 2.5,-                        dataframe-operations >= 2.4 && < 2.5,+                        dataframe-operations >= 2.5 && < 2.6,+                        dataframe-operations >= 2.5 && < 2.6,                         HUnit >= 1.6 && < 1.8,                         QuickCheck >= 2 && < 3,                         random >= 1 && < 2,

@@ -19,6 +19,7 @@  import DataFrame.DecisionTree.Types (Tree (..), TreeConfig (..)) import DataFrame.Errors (DataFrameException (..), TypeErrorContext (..))+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import DataFrame.Internal.Column import DataFrame.Internal.DataFrame (@@ -29,9 +30,7 @@  ) import DataFrame.Internal.Expression (Expr (..)) import DataFrame.Internal.Interpreter (interpret)-import DataFrame.Internal.Types import DataFrame.Operations.Core (nRows)-import DataFrame.Operators  import Control.Exception (throw) import Data.Either (fromRight)

@@ -35,12 +35,12 @@     TreeConfig (..),     withOrdFrom,  )+import DataFrame.Expression.Operators import DataFrame.Internal.Column+import DataFrame.Internal.Column.Bitmap import DataFrame.Internal.DataFrame (DataFrame, columnNames, unsafeGetColumn) import DataFrame.Internal.Expression (Expr (..)) import DataFrame.Internal.Interpreter (interpret)-import DataFrame.Internal.Types-import DataFrame.Operators  import Data.Either (fromRight) import Data.Function (on)

@@ -27,13 +27,12 @@  import DataFrame.DecisionTree.CondVec (CondVec (..), materializeCondVec) import DataFrame.DecisionTree.Types (SynthConfig (..), TreeConfig (..))+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import DataFrame.Internal.Column import DataFrame.Internal.DataFrame (DataFrame, columnNames, unsafeGetColumn) import DataFrame.Internal.Expression (Expr (..), eqExpr, getColumns, normalize) import DataFrame.Internal.Interpreter (interpret)-import DataFrame.Internal.Types-import DataFrame.Operators  import Data.List (sort) import Data.Maybe (catMaybes, mapMaybe)

@@ -15,7 +15,12 @@ import DataFrame.DecisionTree.Types (Tree (..)) import DataFrame.Internal.Column (Columnable) import DataFrame.Internal.Expression (Expr (..), eqExpr)-import DataFrame.Internal.Simplify (PredFact, entails, factFalse, factTrue)+import DataFrame.Internal.Expression.Simplify (+    PredFact,+    entails,+    factFalse,+    factTrue,+ )  {- | Drop branches whose test is forced by the path conditions reaching them, and collapse @Branch c t t@ to @t@. Sound for the decidable threshold subset;

@@ -35,6 +35,13 @@  import Data.Either (fromRight) import DataFrame.Errors (DataFrameException (..), TypeErrorContext (..))+import DataFrame.Expression.Operators (+    (.&&.),+    (.*.),+    (.+.),+    (.<=.),+    (.>=.),+ ) import qualified DataFrame.Functions as F import DataFrame.Internal.Column (Columnable, columnBitmap, columnTypeString) import qualified DataFrame.Internal.Column as D@@ -46,7 +53,6 @@     columnAsUnboxedVector,     columnAsVector,  )-import DataFrame.Operators ((.&&.), (.*.), (.+.), (.<=.), (.>=.))  -- | Every column name except the supervised target's. featureNames :: Expr a -> DataFrame -> [T.Text]

@@ -28,6 +28,7 @@     dotProduct, ) where +import DataFrame.Expression.Operators ((.*.), (.+.), (.>.)) import qualified DataFrame.Functions as F import DataFrame.Internal.Expression (Expr (..)) import DataFrame.LinearAlgebra (Matrix, gram, scaleV)@@ -37,7 +38,6 @@     logisticLoss,     sigmoid,  )-import DataFrame.Operators ((.*.), (.+.), (.>.))  import Control.Monad.ST (ST, runST) import qualified Data.Text as T

@@ -21,9 +21,9 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.*.), (.+.), (.-.), (./.)) import qualified DataFrame.Functions as F import DataFrame.Internal.Expression (Expr (..))-import DataFrame.Operators ((.*.), (.+.), (.-.), (./.))  data BinOp = SAdd | SSub | SMul | SDiv     deriving (Eq, Ord, Show, Enum, Bounded)

@@ -35,6 +35,7 @@  ) import DataFrame.DecisionTree.Fit (treeToExpr) import DataFrame.DecisionTree.Types (Tree (..))+import DataFrame.Expression.Operators ((.*.), (.+.), (.==.)) import DataFrame.Featurize.Internal (argMaxExpr, targetValues) import qualified DataFrame.Functions as F import DataFrame.Internal.Column (Columnable, TypedColumn (..), toVector)@@ -42,7 +43,6 @@ import DataFrame.Internal.Expression (Expr (..)) import DataFrame.Internal.Interpreter (interpret) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.==.))  data AdaBoostConfig = AdaBoostConfig     { abNEstimators :: !Int

@@ -35,6 +35,7 @@ import DataFrame.DecisionTree.Fit (treeToExpr) import DataFrame.DecisionTree.Regression (RegTreeConfig (..), fitRegTreeOn) import DataFrame.DecisionTree.Types (Tree)+import DataFrame.Expression.Operators ((.*.), (.+.), (.>.)) import DataFrame.Featurize.Internal (targetDoubles) import qualified DataFrame.Functions as F import DataFrame.Internal.Column (TypedColumn (..), toVector)@@ -42,7 +43,6 @@ import DataFrame.Internal.Expression (Expr (..), getColumns) import DataFrame.Internal.Interpreter (interpret) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.>.))  -- | The boosting loss. data GBLoss = SquaredError | LogisticDeviance

@@ -29,6 +29,7 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.*.), (.+.), (.-.)) import DataFrame.Featurize.Internal (Features (..), argMaxExpr, extractFeatures) import qualified DataFrame.Functions as F import DataFrame.Internal.DataFrame (DataFrame)@@ -36,7 +37,6 @@ import DataFrame.LinearAlgebra (Matrix, logSumExp) import DataFrame.LinearAlgebra.Solve (backSubst, cholesky, forwardSubst) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.-.)) import DataFrame.Random (mkGen, sampleIndices)  data CovType = FullCov | DiagCov

@@ -25,13 +25,13 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.*.), (.+.), (.-.)) import DataFrame.Featurize.Internal (Features (..), argMinExpr, extractFeatures) import qualified DataFrame.Functions as F import DataFrame.Internal.DataFrame (DataFrame) import DataFrame.Internal.Expression (Expr (..), UExpr (..)) import DataFrame.LinearAlgebra (Matrix, nearestCenter, sqDist) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.-.)) import DataFrame.Random (Gen, mkGen, nextDouble, nextIntR, splitGen) import DataFrame.Transform (Transform (..)) 

@@ -23,6 +23,7 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.*.), (.+.), (.-.)) import DataFrame.Featurize.Internal (Features (..), extractFeatures) import qualified DataFrame.Functions as F import DataFrame.Internal.DataFrame (DataFrame)@@ -30,7 +31,6 @@ import DataFrame.LinearAlgebra (gram) import DataFrame.LinearAlgebra.Eigen (jacobiEigenSym) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.-.)) import DataFrame.Transform (Transform (..))  -- | How many components to keep.

@@ -21,6 +21,7 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.*.), (.+.), (.-.)) import DataFrame.Featurize.Internal (Features (..), extractFeatures) import qualified DataFrame.Functions as F import DataFrame.Internal.DataFrame (DataFrame)@@ -28,7 +29,6 @@ import DataFrame.LinearAlgebra (sqDist) import DataFrame.LinearAlgebra.Eigen (jacobiEigenSym) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.-.)) import DataFrame.Random (mkGen, sampleIndices) import DataFrame.Transform (Transform (..)) 

@@ -25,6 +25,7 @@ import qualified Data.Vector.Unboxed as VU import DataFrame.Errors (DataFrameException (..)) +import DataFrame.Expression.Operators ((.*.), (.+.), (.>.)) import DataFrame.Featurize.Internal (featureNames, numericMatrix, targetValues) import qualified DataFrame.Functions as F import DataFrame.Internal.Column (Columnable)@@ -34,7 +35,6 @@ import DataFrame.LinearSolver (LinearModel (..), SolverConfig (..), fitProx) import DataFrame.LinearSolver.Loss (sqHingeLoss) import DataFrame.Model-import DataFrame.Operators ((.*.), (.+.), (.>.)) import DataFrame.Random (Gen, gaussianVector, mkGen, nextDouble)  data RFFConfig = RFFConfig

@@ -34,17 +34,19 @@ import qualified Data.Vector.Unboxed as VU import DataFrame.Errors (DataFrameException (..)) +import DataFrame.Expression.Operators ((.&&.), (.==.)) import DataFrame.Featurize.Internal (featureNames, numericMatrix, targetDoubles) import DataFrame.Internal.Column (     Column (..),     Columnable,-    bitmapTestBit,     columnBitmap,+    columnToTextVec,     hasElemType,  )+import DataFrame.Internal.Column.Bitmap (bitmapTestBit)+import DataFrame.Internal.Column.Types (SBool (..), sIntegral) import DataFrame.Internal.DataFrame (DataFrame, unsafeGetColumn) import DataFrame.Internal.Expression (Expr (..))-import DataFrame.Internal.Types (SBool (..), sIntegral) import DataFrame.LinearAlgebra (Matrix, gram, matVec, tMatVec) import DataFrame.LinearAlgebra.Solve (choleskySolve, qrLeastSquares) import DataFrame.LinearModel.Logistic (LogisticConfig)@@ -54,8 +56,7 @@  ) import DataFrame.Model import DataFrame.Operations.Core (nRows)-import DataFrame.Operations.Subset (columnToTextVec, exclude, rowsAtIndices)-import DataFrame.Operators ((.&&.), (.==.))+import DataFrame.Operations.Subset (exclude, rowsAtIndices) import DataFrame.SymbolicRegression (SRConfig)  {- | A base estimator @cfg@ wrapped to fit one model per categorical

@@ -26,6 +26,7 @@ import qualified Data.Vector as V import qualified Data.Vector.Unboxed as VU +import DataFrame.Expression.Operators ((.-.), (./.)) import qualified DataFrame.Functions as F import DataFrame.Internal.Column (Columnable) import DataFrame.Internal.DataFrame (DataFrame)@@ -37,7 +38,6 @@  ) import DataFrame.Operations.Core (columnAsDoubleVector) import DataFrame.Operations.Transformations (deriveMany)-import DataFrame.Operators ((.-.), (./.))  -- | A fitted transform: named output columns derived from the input frame. newtype Transform = Transform {transformOutputs :: [NamedExpr]}

@@ -43,13 +43,14 @@  ) import DataFrame.DecisionTree.Tao (taoIteration, taoOptimize) import DataFrame.DecisionTree.Types (CarePoint (..), Direction (..))+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import qualified DataFrame.Internal.Column as DI+import qualified DataFrame.Internal.Column.Bitmap as DI+import DataFrame.Internal.Data.PackedText (mkPackedContiguous) import DataFrame.Internal.Expression (Expr (..), eqExpr, getColumns) import DataFrame.Internal.Interpreter (interpret)-import DataFrame.Internal.PackedText (mkPackedContiguous) import qualified DataFrame.LinearSolver-import DataFrame.Operators import qualified DataFrameApi as D  import Control.Monad (zipWithM_)

@@ -11,13 +11,13 @@ import DataFrame.DecisionTree.Predict (predictWithTree) import DataFrame.DecisionTree.Prune (pruneDead) import DataFrame.DecisionTree.Types (Tree (..))+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import DataFrame.Internal.Column (TypedColumn (TColumn), toVector) import qualified DataFrame.Internal.Column as DI import DataFrame.Internal.Expression (Expr, eqExpr)+import DataFrame.Internal.Expression.Simplify (simplify) import DataFrame.Internal.Interpreter (interpret)-import DataFrame.Internal.Simplify (simplify)-import DataFrame.Operators import qualified DataFrameApi as D  import qualified Data.Text as T

@@ -8,9 +8,9 @@  import DataFrame.DecisionTree.Prune (pruneDead) import DataFrame.DecisionTree.Types (Tree (..))+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import DataFrame.Internal.Expression (eqExpr)-import DataFrame.Operators  import qualified Data.Text as T import Test.HUnit

@@ -18,6 +18,7 @@     boolExprsVec,     saturateCandidates,  )+import DataFrame.Expression.Operators import qualified DataFrame.Functions as F import qualified DataFrame.Internal.Column as DI import DataFrame.Internal.Expression (@@ -27,7 +28,6 @@     eqExpr,     normalize,  )-import DataFrame.Operators import qualified DataFrameApi as D  import Data.Function (on)