Safe Haskell	None
Language	Haskell2010

DataFrame.Operations.Transformations

Synopsis

apply :: (Columnable b, Columnable c) => (b -> c) -> Text -> DataFrame -> DataFrame
safeApply :: (Columnable b, Columnable c) => (b -> c) -> Text -> DataFrame -> Either DataFrameException DataFrame
derive :: Columnable a => Text -> Expr a -> DataFrame -> DataFrame
deriveWithExpr :: Columnable a => Text -> Expr a -> DataFrame -> (Expr a, DataFrame)
deriveMany :: [NamedExpr] -> DataFrame -> DataFrame
applyMany :: (Columnable b, Columnable c) => (b -> c) -> [Text] -> DataFrame -> DataFrame
applyInt :: Columnable b => (Int -> b) -> Text -> DataFrame -> DataFrame
applyDouble :: Columnable b => (Double -> b) -> Text -> DataFrame -> DataFrame
applyWhere :: (Columnable a, Columnable b) => (a -> Bool) -> Text -> (b -> b) -> Text -> DataFrame -> DataFrame
applyAtIndex :: Columnable a => Int -> (a -> a) -> Text -> DataFrame -> DataFrame
imputeCore :: Columnable b => Expr (Maybe b) -> b -> DataFrame -> DataFrame
class Columnable a => ImputeOp a where
- runImpute :: Expr a -> BaseType a -> DataFrame -> DataFrame
- runImputeWith :: (Expr (BaseType a) -> Expr (BaseType a)) -> Expr a -> DataFrame -> DataFrame
impute :: ImputeOp a => Expr a -> BaseType a -> DataFrame -> DataFrame

Documentation

apply Source #

Arguments

:: (Columnable b, Columnable c)
=> (b -> c)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> DataFrame

O(k) Apply a function to a given column in a dataframe.

safeApply Source #

Arguments

:: (Columnable b, Columnable c)
=> (b -> c)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> Either DataFrameException DataFrame

O(k) Safe version of the apply function. Returns (instead of throwing) the error.

derive :: Columnable a => Text -> Expr a -> DataFrame -> DataFrame Source #

O(k) Apply a function to an expression in a dataframe and add the result into alias column.

deriveWithExpr :: Columnable a => Text -> Expr a -> DataFrame -> (Expr a, DataFrame) Source #

O(k) Apply a function to an expression in a dataframe and add the result into alias column but

Examples

Expand

>>> (z, df') = deriveWithExpr "z" (F.col @Int "x" + F.col "y") df
>>> filterWhere (z .>= 50)

deriveMany :: [NamedExpr] -> DataFrame -> DataFrame Source #

applyMany :: (Columnable b, Columnable c) => (b -> c) -> [Text] -> DataFrame -> DataFrame Source #

O(k * n) Apply a function to given column names in a dataframe.

applyInt Source #

Arguments

:: Columnable b
=> (Int -> b)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> DataFrame

O(k) Convenience function that applies to an int column.

applyDouble Source #

Arguments

:: Columnable b
=> (Double -> b)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> DataFrame

O(k) Convenience function that applies to an double column.

applyWhere Source #

Arguments

:: (Columnable a, Columnable b)
=> (a -> Bool)	Filter condition
-> Text	Criterion Column
-> (b -> b)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> DataFrame

O(k * n) Apply a function to a column only if there is another column value that matches the given criterion.

applyWhere (<20) "Age" (const "Gen-Z") "Generation" df

applyAtIndex Source #

Arguments

:: Columnable a
=> Int	Index
-> (a -> a)	function to apply
-> Text	Column name
-> DataFrame	DataFrame to apply operation to
-> DataFrame

O(k) Apply a function to the column at a given index.

imputeCore :: Columnable b => Expr (Maybe b) -> b -> DataFrame -> DataFrame Source #

Core impute implementation for nullable columns. Silently no-ops on non-nullable columns.

class Columnable a => ImputeOp a where Source #

Methods

runImpute :: Expr a -> BaseType a -> DataFrame -> DataFrame Source #

runImputeWith :: (Expr (BaseType a) -> Expr (BaseType a)) -> Expr a -> DataFrame -> DataFrame Source #

Instances

Instances details

Columnable a => ImputeOp a Source #
Instance details Defined in DataFrame.Operations.Transformations Methods runImpute :: Expr a -> BaseType a -> DataFrame -> DataFrame Source # runImputeWith :: (Expr (BaseType a) -> Expr (BaseType a)) -> Expr a -> DataFrame -> DataFrame Source #
Columnable b => ImputeOp (Maybe b) Source #	O(n) Impute missing values in a column using a derived scalar. Given an expression `f :: Expr b -> Expr b` that, when interpreted over a non-nullable column, produces the same value in every row (for example a mean, median, or other aggregate), and a nullable column `Expr (Maybe b)` this function: Drops all `Nothing` values from the target column. Interprets `f` on the remaining non-null values. Checks that the resulting column contains a single repeated value. Uses that value to impute all `Nothing`s in the original column. Throws Expand `DataFrameException` - if the column does not exist, is empty, Example Expand >>> :set -XOverloadedStrings >>> import qualified DataFrame as D >>> let df = ... D.fromNamedColumns ... [ ("age", D.fromList [Just 10, Nothing, Just 20 :: Maybe Int]) ] >>> >>> -- Impute missing ages with the mean of the observed ages >>> D.imputeWith F.mean "age" df -- age -- ---- -- 10 -- 15 -- 20
Instance details Defined in DataFrame.Operations.Statistics Methods runImpute :: Expr (Maybe b) -> BaseType (Maybe b) -> DataFrame -> DataFrame Source # runImputeWith :: (Expr (BaseType (Maybe b)) -> Expr (BaseType (Maybe b))) -> Expr (Maybe b) -> DataFrame -> DataFrame Source #

impute :: ImputeOp a => Expr a -> BaseType a -> DataFrame -> DataFrame Source #

Replace all instances of Nothing in a column with the given value. When the column is already non-nullable, this is a silent no-op.

Documentation

Examples

Instances

Throws

Example