Lazy dataframe for computations larger than memory (#35)

Implement and expose functionality for doing basic operations on a lazy dataframes.

Author: mchav

dataframe.cabal

@@ -22,7 +22,8 @@ source-repository head
   location: https://github.com/mchav/dataframe
 
 library
-    exposed-modules: DataFrame
+    exposed-modules: DataFrame,
+                     DataFrame.Lazy
     other-modules: DataFrame.Internal.Types,
                    DataFrame.Internal.Expression,
                    DataFrame.Internal.Parsing,
@@ -33,20 +34,24 @@ library
                    DataFrame.Internal.Row,
                    DataFrame.Errors,
                    DataFrame.Operations.Core,
+                   DataFrame.Operations.Merge,
                    DataFrame.Operations.Subset,
                    DataFrame.Operations.Sorting,
                    DataFrame.Operations.Statistics,
                    DataFrame.Operations.Transformations,
                    DataFrame.Operations.Typing,
                    DataFrame.Operations.Aggregation,
                    DataFrame.Display.Terminal.Plot,
-                   DataFrame.IO.CSV
+                   DataFrame.IO.CSV,
+                   DataFrame.Lazy.IO.CSV,
+                   DataFrame.Lazy.Internal.DataFrame
     build-depends:    base >= 4.17.2.0 && < 4.22,
                       array ^>= 0.5,
                       attoparsec >= 0.12 && <= 0.14.4,
                       bytestring >= 0.11 && <= 0.12.2.0,
                       containers >= 0.6.7 && < 0.8,
                       directory >= 1.3.0.0 && <= 1.3.9.0,
+                      filepath >= 1.0.0.0 && <= 1.5.4.0,
                       hashable >= 1.2 && <= 1.5.0.0,
                       statistics >= 0.16.2.1 && <= 0.16.3.0,
                       text >= 2.0 && <= 2.1.2,
@@ -76,7 +81,8 @@ executable dataframe
                    DataFrame.Operations.Typing,
                    DataFrame.Operations.Aggregation,
                    DataFrame.Display.Terminal.Plot,
-                   DataFrame.IO.CSV
+                   DataFrame.IO.CSV,
+                   DataFrame.Lazy.IO.CSV
     build-depends:    base >= 4.17.2.0 && < 4.22,
                       array ^>= 0.5,
                       attoparsec >= 0.12 && <= 0.14.4,

src/DataFrame/IO.hs

@@ -0,0 +1,3 @@
+module DataFrame.IO where
+
+data InputTypes = CSV deriving Show

src/DataFrame/Internal/Column.hs

@@ -4,7 +4,7 @@
 {-# LANGUAGE OverloadedStrings #-}
 {-# LANGUAGE RankNTypes #-}
 {-# LANGUAGE ScopedTypeVariables #-}
-{-# LANGUAGE StrictData #-}
+{-# LANGUAGE Strict #-}
 {-# LANGUAGE TypeApplications #-}
 {-# LANGUAGE FlexibleContexts #-}
 {-# LANGUAGE FlexibleInstances #-}
@@ -521,6 +521,31 @@ expandColumn n (UnboxedColumn col) = OptionalColumn $ VB.map Just (VU.convert co
 expandColumn n (GroupedBoxedColumn col) = GroupedBoxedColumn $ col <> VB.replicate n VB.empty
 expandColumn n (GroupedUnboxedColumn col) = GroupedUnboxedColumn $ col <> VB.replicate n VU.empty
 
+leftExpandColumn :: Int -> Column -> Column
+leftExpandColumn n (OptionalColumn col) = OptionalColumn $ VB.replicate n Nothing <> col
+leftExpandColumn n (BoxedColumn col) = OptionalColumn $ VB.replicate n Nothing <> VB.map Just col
+leftExpandColumn n (UnboxedColumn col) = OptionalColumn $ VB.replicate n Nothing <> VB.map Just (VU.convert col)
+leftExpandColumn n (GroupedBoxedColumn col) = GroupedBoxedColumn $ VB.replicate n VB.empty <> col
+leftExpandColumn n (GroupedUnboxedColumn col) = GroupedUnboxedColumn $ VB.replicate n VU.empty <> col
+
+concatColumns :: Column -> Column -> Maybe Column
+concatColumns (OptionalColumn left) (OptionalColumn right) = case testEquality (typeOf left) (typeOf right) of
+  Nothing   -> Nothing
+  Just Refl -> Just (OptionalColumn $ left <> right)
+concatColumns (BoxedColumn left) (BoxedColumn right) = case testEquality (typeOf left) (typeOf right) of
+  Nothing   -> Nothing
+  Just Refl -> Just (BoxedColumn $ left <> right)
+concatColumns (UnboxedColumn left) (UnboxedColumn right) = case testEquality (typeOf left) (typeOf right) of
+  Nothing   -> Nothing
+  Just Refl -> Just (UnboxedColumn $ left <> right)
+concatColumns (GroupedBoxedColumn left) (GroupedBoxedColumn right) = case testEquality (typeOf left) (typeOf right) of
+  Nothing   -> Nothing
+  Just Refl -> Just (GroupedBoxedColumn $ left <> right)
+concatColumns (GroupedUnboxedColumn left) (GroupedUnboxedColumn right) = case testEquality (typeOf left) (typeOf right) of
+  Nothing   -> Nothing
+  Just Refl -> Just (GroupedUnboxedColumn $ left <> right)
+concatColumns _ _ = Nothing
+
 toVector :: forall a . Columnable a => Column -> VB.Vector a
 toVector column@(OptionalColumn (col :: VB.Vector b)) =
   case testEquality (typeRep @a) (typeRep @b) of

src/DataFrame/Internal/DataFrame.hs

@@ -4,7 +4,7 @@
 {-# LANGUAGE ScopedTypeVariables #-}
 {-# LANGUAGE TypeApplications #-}
 {-# LANGUAGE GADTs #-}
-{-# LANGUAGE StrictData #-}
+{-# LANGUAGE Strict #-}
 {-# LANGUAGE FlexibleContexts #-}
 module DataFrame.Internal.DataFrame where
 

src/DataFrame/Internal/Expression.hs

@@ -32,7 +32,7 @@ data Expr a where
     Apply :: (Columnable a, Columnable b) => T.Text -> (b -> a) -> Expr b -> Expr a
     BinOp :: (Columnable c, Columnable b, Columnable a) => T.Text -> (c -> b -> a) -> Expr c -> Expr b -> Expr a
 
-interpret :: forall a b . (Columnable a) => DataFrame -> Expr a -> TypedColumn a
+interpret :: forall a . (Columnable a) => DataFrame -> Expr a -> TypedColumn a
 interpret df (Lit value) = TColumn $ toColumn' $ V.replicate (fst $ dataframeDimensions df) value
 interpret df (Col name) = case getColumn name df of
     Nothing -> throw $ ColumnNotFoundException name "" (map fst $ M.toList $ columnIndices df)

src/DataFrame/Internal/Types.hs

@@ -19,4 +19,4 @@ import Data.Word ( Word8, Word16, Word32, Word64 )
 import Type.Reflection (TypeRep, typeOf, typeRep)
 import Data.Type.Equality (TestEquality(..))
 
-type Columnable' a = (Typeable a, Show a, Ord a, Eq a)
+type Columnable' a = (Typeable a, Show a, Ord a, Eq a, Read a)

src/DataFrame/Lazy.hs

@@ -0,0 +1,3 @@
+module DataFrame.Lazy (module DataFrame.Lazy.Internal.DataFrame) where
+
+import DataFrame.Lazy.Internal.DataFrame