feat: Add TH function for deriving schema from CSV file.

Author: mchav

src/DataFrame/Typed.hs

@@ -165,6 +165,7 @@ module DataFrame.Typed (
 
     -- * Template Haskell
     deriveSchema,
+    deriveSchemaFromCsvFile,
 
     -- * Schema type families (for advanced use)
     Lookup,
@@ -208,7 +209,7 @@ import DataFrame.Typed.Freeze (freeze, freezeWithError, thaw, unsafeFreeze)
 import DataFrame.Typed.Join (fullOuterJoin, innerJoin, leftJoin, rightJoin)
 import DataFrame.Typed.Operations
 import DataFrame.Typed.Schema
-import DataFrame.Typed.TH (deriveSchema)
+import DataFrame.Typed.TH (deriveSchema, deriveSchemaFromCsvFile)
 import DataFrame.Typed.Types (
     Column,
     TExpr (..),

src/DataFrame/Typed/Operations.hs

@@ -215,7 +215,9 @@ derive ::
     , Columnable a
     , AssertAbsent name cols
     ) =>
-    TExpr cols a -> TypedDataFrame cols -> TypedDataFrame (Snoc cols (T.Column name a))
+    TExpr cols a ->
+    TypedDataFrame cols ->
+    TypedDataFrame (Snoc cols (T.Column name a))
 derive (TExpr expr) (TDF df) = unsafeFreeze (D.derive colName expr df)
   where
     colName = T.pack (symbolVal (Proxy @name))

src/DataFrame/Typed/Schema.hs

@@ -79,7 +79,7 @@ type family Lookup (name :: Symbol) (cols :: [Type]) :: Type where
 
 -- | Add type to the end of a list.
 type family Snoc (xs :: [k]) (x :: k) :: [k] where
-    Snoc '[]       x = '[x]
+    Snoc '[] x = '[x]
     Snoc (y ': ys) x = y ': Snoc ys x
 
 -- | Check whether a column name exists in a schema (type-level Bool).

src/DataFrame/Typed/TH.hs

@@ -7,19 +7,22 @@
 module DataFrame.Typed.TH (
     -- * Schema inference
     deriveSchema,
+    deriveSchemaFromCsvFile,
 
     -- * Re-export for TH splices
     TypedDataFrame,
     Column,
 ) where
 
+import Control.Monad.IO.Class
 import qualified Data.List as L
 import qualified Data.Map as M
 import qualified Data.Text as T
 
 import Language.Haskell.TH
 import Language.Haskell.TH.Syntax (Lift (..))
 
+import qualified DataFrame.IO.CSV as D
 import qualified DataFrame.Internal.Column as C
 import qualified DataFrame.Internal.DataFrame as D
 import DataFrame.Typed.Types (Column, TypedDataFrame)
@@ -46,6 +49,11 @@ deriveSchema typeName df = do
     let synName = mkName typeName
     pure [TySynD synName [] schemaType]
 
+deriveSchemaFromCsvFile :: String -> String -> DecsQ
+deriveSchemaFromCsvFile typeName path = do
+    df <- liftIO (D.readCsv path)
+    deriveSchema typeName df
+
 -------------------------------------------------------------------------------
 -- Internal helpers
 -------------------------------------------------------------------------------