Safe Haskell	None
Language	Haskell2010

DataFrame

Synopsis

range :: (Int, Int) -> DataFrame -> DataFrame
eq :: (Columnable a, Eq a) => Expr a -> Expr a -> Expr Bool
type family If (cond :: Bool) (yes :: k) (no :: k) :: k where ...
fromList :: [(Text, Column)] -> DataFrame
apply :: (Columnable b, Columnable c) => (b -> c) -> Text -> DataFrame -> DataFrame
data Rep
- = RBoxed
- | RUnboxed
- | ROptional
- | RGBoxed
- | RGUnboxed
- | RGOptional
data RowValue where
- Value :: forall a. Columnable' a => a -> RowValue
empty :: DataFrame
data Expr a where
- Col :: forall a. Columnable a => Text -> Expr a
- Lit :: forall a. Columnable a => a -> Expr a
- Apply :: forall a b. (Columnable a, Columnable b) => Text -> (b -> a) -> Expr b -> Expr a
- BinOp :: forall c b a. (Columnable c, Columnable b, Columnable a) => Text -> (c -> b -> a) -> Expr c -> Expr b -> Expr a
null :: DataFrame -> Bool
filter :: Columnable a => Text -> (a -> Bool) -> DataFrame -> DataFrame
defaultOptions :: ReadOptions
lift :: (Columnable a, Columnable b) => (a -> b) -> Expr a -> Expr b
take :: Int -> DataFrame -> DataFrame
sortBy :: SortOrder -> [Text] -> DataFrame -> DataFrame
sum :: Text -> DataFrame -> Maybe Double
drop :: Int -> DataFrame -> DataFrame
rotate :: [String] -> [String]
readInt :: HasCallStack => Text -> Maybe Int
data Aggregation
- = Count
- | Mean
- | Minimum
- | Median
- | Maximum
- | Sum
fold :: (a -> DataFrame -> DataFrame) -> [a] -> DataFrame -> DataFrame
groupBy :: [Text] -> DataFrame -> DataFrame
readInteger :: HasCallStack => Text -> Maybe Integer
toVector :: Columnable a => Column -> Vector a
select :: [Text] -> DataFrame -> DataFrame
data Column where
- BoxedColumn :: forall a. Columnable a => Vector a -> Column
- UnboxedColumn :: forall a. (Columnable a, Unbox a) => Vector a -> Column
- OptionalColumn :: forall a. Columnable a => Vector (Maybe a) -> Column
- GroupedBoxedColumn :: forall a. Columnable a => Vector (Vector a) -> Column
- GroupedUnboxedColumn :: forall a. (Columnable a, Unbox a) => Vector (Vector a) -> Column
- GroupedOptionalColumn :: forall a. Columnable a => Vector (Vector (Maybe a)) -> Column
- MutableBoxedColumn :: forall a. Columnable a => IOVector a -> Column
- MutableUnboxedColumn :: forall a. (Columnable a, Unbox a) => IOVector a -> Column
correlation :: Text -> Text -> DataFrame -> Maybe Double
median :: Text -> DataFrame -> Maybe Double
variance :: Text -> DataFrame -> Maybe Double
mean :: Text -> DataFrame -> Maybe Double
skewness :: Text -> DataFrame -> Maybe Double
formatNumber :: Double -> String
clip :: Int -> Int -> Int -> Int
geq :: (Columnable a, Ord a, Eq a) => Expr a -> Expr a -> Expr Bool
rename :: Text -> Text -> DataFrame -> DataFrame
selectBy :: (Text -> Bool) -> DataFrame -> DataFrame
data DataFrame = DataFrame (Vector (Maybe Column)) (Map Text Int) [Int] (Int, Int)
type Row = Vector RowValue
mkRowRep :: DataFrame -> Set Text -> Int -> Int
data DataFrameException where
- TypeMismatchException :: forall a b. (Typeable a, Typeable b) => TypeRep a -> TypeRep b -> Text -> Text -> DataFrameException
- TypeMismatchException' :: forall a. Typeable a => TypeRep a -> String -> Text -> Text -> DataFrameException
- ColumnNotFoundException :: Text -> Text -> [Text] -> DataFrameException
isNullish :: Text -> Bool
toColumn' :: (Columnable a, ColumnifyRep (KindOf a) a) => Vector a -> Column
toColumn :: (Columnable a, ColumnifyRep (KindOf a) a) => [a] -> Column
columnLength :: Column -> Int
columnTypeString :: Column -> String
expandColumn :: Int -> Column -> Column
type Columnable a = (Columnable' a, ColumnifyRep (KindOf a) a, UnboxIf a, SBoolI (Unboxable a))
getColumn :: Text -> DataFrame -> Maybe Column
dimensions :: DataFrame -> (Int, Int)
mkRowFromArgs :: [Text] -> DataFrame -> Int -> Row
toRowValue :: Columnable' a => a -> RowValue
frequencies :: Text -> DataFrame -> DataFrame
itransform :: (Typeable b, Typeable c, Columnable b, Columnable c) => (Int -> b -> c) -> Column -> Maybe Column
ifoldrColumn :: (Columnable a, Columnable b) => (Int -> a -> b -> b) -> b -> Column -> Maybe b
data TypedColumn a where
- TColumn :: forall a. Columnable a => Column -> TypedColumn a
transform :: (Columnable b, Columnable c, UnboxIf c, Typeable b, Typeable c) => (b -> c) -> Column -> Maybe Column
unwrapTypedColumn :: TypedColumn a -> Column
parseDefaults :: Bool -> DataFrame -> DataFrame
getIndicesUnboxed :: Unbox a => Vector Int -> Vector a -> Vector a
getIndices :: Vector Int -> Vector a -> Vector a
freezeColumn' :: [(Int, Text)] -> Column -> IO Column
writeColumn :: Int -> Text -> Column -> IO (Either Text Bool)
col :: Columnable a => Text -> Expr a
data HistogramConfig = HistogramConfig {
- width :: Int
- height :: Int
- barChar :: Char
- title :: Maybe String
}
addCallPointInfo :: Text -> Maybe Text -> String -> String
typeMismatchError :: TypeRep a -> TypeRep b -> String
typeMismatchError' :: String -> String -> String
columnNotFound :: Text -> Text -> [Text] -> String
guessColumnName :: Text -> [Text] -> Text
typeAnnotationSuggestion :: String -> String
editDistance :: Text -> Text -> Int
readValue :: (HasCallStack, Read a) => Text -> a
readByteStringInt :: HasCallStack => ByteString -> Maybe Int
readDouble :: HasCallStack => Text -> Maybe Double
readIntegerEither :: HasCallStack => Text -> Either Text Integer
readIntEither :: HasCallStack => Text -> Either Text Int
readDoubleEither :: HasCallStack => Text -> Either Text Double
safeReadValue :: Read a => Text -> Maybe a
readWithDefault :: (HasCallStack, Read a) => a -> Text -> a
lt :: (Columnable a, Ord a) => Expr a -> Expr a -> Expr Bool
gt :: (Columnable a, Ord a) => Expr a -> Expr a -> Expr Bool
type Columnable' a = (Typeable a, Show a, Ord a, Eq a)
isGrouped :: Column -> Bool
columnVersionString :: Column -> String
type family Unboxable a :: Bool where ...
type family KindOf a :: Rep where ...
class ColumnifyRep (r :: Rep) a where
- toColumnRep :: Vector a -> Column
type UnboxIf a = When (Unboxable a) (Unbox a)
class SBoolI (b :: Bool) where
- sbool :: SBool b
data SBool (b :: Bool) where
- STrue :: SBool 'True
- SFalse :: SBool 'False
sUnbox :: SBoolI (Unboxable a) => SBool (Unboxable a)
type family When (flag :: Bool) c where ...
toColumnUnboxed :: (Columnable a, Unbox a) => Vector a -> Column
takeColumn :: Int -> Column -> Column
takeLastColumn :: Int -> Column -> Column
sliceColumn :: Int -> Int -> Column -> Column
atIndices :: Set Int -> Column -> Column
atIndicesStable :: Vector Int -> Column -> Column
sortedIndexes :: Bool -> Column -> Vector Int
ifilterColumn :: Columnable a => (Int -> a -> Bool) -> Column -> Maybe Column
ifoldlColumn :: (Columnable a, Columnable b) => (b -> Int -> a -> b) -> b -> Column -> Maybe b
reduceColumn :: Columnable a => (a -> b) -> Column -> b
safeReduceColumn :: Typeable a => (a -> b) -> Column -> Maybe b
zipColumns :: Column -> Column -> Column
zipWithColumns :: (Columnable a, Columnable b, Columnable c) => (a -> b -> c) -> Column -> Column -> Column
nulls :: Column -> Int
leq :: (Columnable a, Ord a, Eq a) => Expr a -> Expr a -> Expr Bool
asText :: DataFrame -> Bool -> Text
initialColumnSize :: Int
metadata :: DataFrame -> String
toRowList :: [Text] -> DataFrame -> [Row]
toRowVector :: [Text] -> DataFrame -> Vector Row
sortedIndexes' :: Bool -> Vector Row -> Vector Int
interpret :: forall a b. Columnable a => DataFrame -> Expr a -> TypedColumn a
lit :: Columnable a => a -> Expr a
lift2 :: (Columnable c, Columnable b, Columnable a) => (c -> b -> a) -> Expr c -> Expr b -> Expr a
columnNames :: DataFrame -> [Text]
insertColumn :: Columnable a => Text -> Vector a -> DataFrame -> DataFrame
insertColumn' :: Text -> Maybe Column -> DataFrame -> DataFrame
cloneColumn :: Text -> Text -> DataFrame -> DataFrame
insertUnboxedColumn :: (Columnable a, Unbox a) => Text -> Vector a -> DataFrame -> DataFrame
insertColumnWithDefault :: Columnable a => a -> Text -> Vector a -> DataFrame -> DataFrame
columnSize :: Text -> DataFrame -> Maybe Int
data ColumnInfo = ColumnInfo {
- nameOfColumn :: !Text
- nonNullValues :: !Int
- nullValues :: !Int
- partiallyParsedValues :: !Int
- uniqueValues :: !Int
- typeOfColumn :: !Text
}
columnInfo :: DataFrame -> DataFrame
partiallyParsed :: Column -> Int
fromColumnList :: [Column] -> DataFrame
valueCounts :: Columnable a => Text -> DataFrame -> [(a, Int)]
data HistogramOrientation
- = VerticalHistogram
- | HorizontalHistogram
data PlotColumns
- = PlotAll
- | PlotSubset [Text]
plotHistograms :: HasCallStack => PlotColumns -> HistogramOrientation -> DataFrame -> IO ()
plotForColumn :: HasCallStack => Text -> Maybe Column -> HistogramOrientation -> DataFrame -> IO ()
plotHistogramsBy :: HasCallStack => Text -> PlotColumns -> HistogramOrientation -> DataFrame -> IO ()
plotForColumnBy :: HasCallStack => Text -> Text -> Maybe Column -> Maybe Column -> HistogramOrientation -> DataFrame -> IO ()
countOccurrences :: Ord a => Vector a -> [(a, Int)]
plotGivenCounts' :: HasCallStack => Text -> [((String, String), Int)] -> IO ()
numericHistogram :: (HasCallStack, Columnable a) => Text -> Vector a -> String
plotVerticalGivenCounts :: HasCallStack => Text -> [(String, Int)] -> IO ()
plotGivenCounts :: HasCallStack => Text -> [(String, Int)] -> IO ()
leftJustify :: String -> Int -> String
smallestPartition :: Ord a => a -> [a] -> a
intPlotRanges :: [Int]
defaultConfig :: HistogramConfig
createHistogram :: HistogramConfig -> [Double] -> String
largestPartition :: Ord a => a -> [a] -> a
calculateBins :: [Double] -> Int -> [(Double, Int)]
data SortOrder
- = Ascending
- | Descending
applyStatistic :: (Vector Double -> Double) -> Text -> DataFrame -> Maybe Double
standardDeviation :: Text -> DataFrame -> Maybe Double
interQuartileRange :: Text -> DataFrame -> Maybe Double
_getColumnAsDouble :: Text -> DataFrame -> Maybe (Vector Double)
applyStatistics :: (Vector Double -> Vector Double) -> Text -> DataFrame -> Maybe (Vector Double)
summarize :: DataFrame -> DataFrame
field :: Char -> Parser Text
derive :: Columnable a => Text -> Expr a -> 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
impute :: Columnable b => Text -> b -> DataFrame -> DataFrame
takeLast :: Int -> DataFrame -> DataFrame
dropLast :: Int -> DataFrame -> DataFrame
filterBy :: Columnable a => (a -> Bool) -> Text -> DataFrame -> DataFrame
filterWhere :: Expr Bool -> DataFrame -> DataFrame
filterJust :: Text -> DataFrame -> DataFrame
filterAllJust :: DataFrame -> DataFrame
cube :: (Int, Int) -> DataFrame -> DataFrame
selectIntRange :: (Int, Int) -> DataFrame -> DataFrame
selectRange :: (Text, Text) -> DataFrame -> DataFrame
exclude :: [Text] -> DataFrame -> DataFrame
appendWithFrontMin :: Ord a => a -> [a] -> [a]
groupColumns :: Vector (Vector Int) -> DataFrame -> DataFrame -> Text -> DataFrame
mkGroupedColumns :: Vector Int -> DataFrame -> DataFrame -> Text -> DataFrame
hash' :: Columnable a => a -> Double
groupByAgg :: Aggregation -> [Text] -> DataFrame -> DataFrame
reduceBy :: (Columnable a, Columnable b) => (forall (v :: Type -> Type). Vector v a => v a -> b) -> Text -> DataFrame -> DataFrame
reduceByAgg :: Aggregation -> Text -> DataFrame -> DataFrame
aggregate :: [(Text, Aggregation)] -> DataFrame -> DataFrame
distinct :: DataFrame -> DataFrame
data ReadOptions = ReadOptions {
- hasHeader :: Bool
- inferTypes :: Bool
- safeRead :: Bool
}
parseDefault :: Bool -> Maybe Column -> Maybe Column
readCsv :: String -> IO DataFrame
readSeparated :: Char -> ReadOptions -> String -> IO DataFrame
readTsv :: String -> IO DataFrame
countRows :: Char -> FilePath -> IO Int
parseSep :: Char -> Text -> [Text]
getInitialDataVectors :: Int -> IOVector Column -> [Text] -> IO ()
fillColumns :: Int -> Char -> IOVector Column -> IOVector [(Int, Text)] -> Handle -> IO ()
freezeColumn :: IOVector Column -> Vector [(Int, Text)] -> ReadOptions -> Int -> IO (Maybe Column)
inferValueType :: Text -> Text
parseRow :: Char -> Parser [Text]
writeValue :: IOVector Column -> IOVector [(Int, Text)] -> Int -> Int -> Text -> IO ()
record :: Char -> Parser [Text]
lineEnd :: Parser ()
quotedField :: Parser Text
unquotedField :: Char -> Parser Text
unquotedTerminators :: Char -> Set Char
writeCsv :: String -> DataFrame -> IO ()
writeSeparated :: Char -> String -> DataFrame -> IO ()
getRowAsText :: DataFrame -> Int -> [Text]
(|>) :: a -> (a -> b) -> b

Documentation

range :: (Int, Int) -> DataFrame -> DataFrame Source #

O(k * n) Take a range of rows of a DataFrame.

eq :: (Columnable a, Eq a) => Expr a -> Expr a -> Expr Bool Source #

type family If (cond :: Bool) (yes :: k) (no :: k) :: k where ... Source #

Equations

If 'True (yes :: k) (_1 :: k) = yes
If 'False (_1 :: k) (no :: k) = no

fromList :: [(Text, Column)] -> DataFrame Source #

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.

data Rep Source #

Constructors

RBoxed
RUnboxed
ROptional
RGBoxed
RGUnboxed
RGOptional

data RowValue where Source #

Constructors

Value :: forall a. Columnable' a => a -> RowValue

Instances

Instances details

Show RowValue Source #
Instance details Defined in DataFrame.Internal.Row Methods showsPrec :: Int -> RowValue -> ShowS # show :: RowValue -> String # showList :: [RowValue] -> ShowS #
Eq RowValue Source #
Instance details Defined in DataFrame.Internal.Row Methods (==) :: RowValue -> RowValue -> Bool # (/=) :: RowValue -> RowValue -> Bool #
Ord RowValue Source #
Instance details Defined in DataFrame.Internal.Row Methods compare :: RowValue -> RowValue -> Ordering # (<) :: RowValue -> RowValue -> Bool # (<=) :: RowValue -> RowValue -> Bool # (>) :: RowValue -> RowValue -> Bool # (>=) :: RowValue -> RowValue -> Bool # max :: RowValue -> RowValue -> RowValue # min :: RowValue -> RowValue -> RowValue #

empty :: DataFrame Source #

O(1) Creates an empty dataframe

data Expr a where Source #

Constructors

Col :: forall a. Columnable a => Text -> Expr a
Lit :: forall a. Columnable a => a -> Expr a
Apply :: forall a b. (Columnable a, Columnable b) => Text -> (b -> a) -> Expr b -> Expr a
BinOp :: forall c b a. (Columnable c, Columnable b, Columnable a) => Text -> (c -> b -> a) -> Expr c -> Expr b -> Expr a

Instances

Instances details

(Floating a, Columnable a) => Floating (Expr a) Source #
Instance details Defined in DataFrame.Internal.Expression Methods pi :: Expr a # exp :: Expr a -> Expr a # log :: Expr a -> Expr a # sqrt :: Expr a -> Expr a # (**) :: Expr a -> Expr a -> Expr a # logBase :: Expr a -> Expr a -> Expr a # sin :: Expr a -> Expr a # cos :: Expr a -> Expr a # tan :: Expr a -> Expr a # asin :: Expr a -> Expr a # acos :: Expr a -> Expr a # atan :: Expr a -> Expr a # sinh :: Expr a -> Expr a # cosh :: Expr a -> Expr a # tanh :: Expr a -> Expr a # asinh :: Expr a -> Expr a # acosh :: Expr a -> Expr a # atanh :: Expr a -> Expr a # log1p :: Expr a -> Expr a # expm1 :: Expr a -> Expr a # log1pexp :: Expr a -> Expr a # log1mexp :: Expr a -> Expr a #
(Num a, Columnable a) => Num (Expr a) Source #
Instance details Defined in DataFrame.Internal.Expression Methods (+) :: Expr a -> Expr a -> Expr a # (-) :: Expr a -> Expr a -> Expr a # (*) :: Expr a -> Expr a -> Expr a # negate :: Expr a -> Expr a # abs :: Expr a -> Expr a # signum :: Expr a -> Expr a # fromInteger :: Integer -> Expr a #
(Fractional a, Columnable a) => Fractional (Expr a) Source #
Instance details Defined in DataFrame.Internal.Expression Methods (/) :: Expr a -> Expr a -> Expr a # recip :: Expr a -> Expr a # fromRational :: Rational -> Expr a #
Show a => Show (Expr a) Source #
Instance details Defined in DataFrame.Internal.Expression Methods showsPrec :: Int -> Expr a -> ShowS # show :: Expr a -> String # showList :: [Expr a] -> ShowS #

null :: DataFrame -> Bool Source #

filter Source #

Arguments

:: Columnable a
=> Text	Column to filter by
-> (a -> Bool)	Filter condition
-> DataFrame	Dataframe to filter
-> DataFrame

O(n * k) Filter rows by a given condition.

filter "x" even df

defaultOptions :: ReadOptions Source #

By default we assume the file has a header, we infer the types on read and we convert any rows with nullish objects into Maybe (safeRead).

lift :: (Columnable a, Columnable b) => (a -> b) -> Expr a -> Expr b Source #

take :: Int -> DataFrame -> DataFrame Source #

O(k * n) Take the first n rows of a DataFrame.

sortBy :: SortOrder -> [Text] -> DataFrame -> DataFrame Source #

O(k log n) Sorts the dataframe by a given row.

sortBy "Age" df

sum :: Text -> DataFrame -> Maybe Double Source #

drop :: Int -> DataFrame -> DataFrame Source #

rotate :: [String] -> [String] Source #

readInt :: HasCallStack => Text -> Maybe Int Source #

data Aggregation Source #

Constructors

Count
Mean
Minimum
Median
Maximum
Sum

Instances

Instances details

Show Aggregation Source #
Instance details Defined in DataFrame.Operations.Aggregation Methods showsPrec :: Int -> Aggregation -> ShowS # show :: Aggregation -> String # showList :: [Aggregation] -> ShowS #
Eq Aggregation Source #
Instance details Defined in DataFrame.Operations.Aggregation Methods (==) :: Aggregation -> Aggregation -> Bool # (/=) :: Aggregation -> Aggregation -> Bool #

fold :: (a -> DataFrame -> DataFrame) -> [a] -> DataFrame -> DataFrame Source #

groupBy :: [Text] -> DataFrame -> DataFrame Source #

O(k * n) groups the dataframe by the given rows aggregating the remaining rows into vector that should be reduced later.

readInteger :: HasCallStack => Text -> Maybe Integer Source #

toVector :: Columnable a => Column -> Vector a Source #

select :: [Text] -> DataFrame -> DataFrame Source #

O(n) Selects a number of columns in a given dataframe.

select ["name", "age"] df

data Column where Source #

Our representation of a column is a GADT that can store data in either a vector with boxed elements or

Constructors

BoxedColumn :: forall a. Columnable a => Vector a -> Column
UnboxedColumn :: forall a. (Columnable a, Unbox a) => Vector a -> Column
OptionalColumn :: forall a. Columnable a => Vector (Maybe a) -> Column
GroupedBoxedColumn :: forall a. Columnable a => Vector (Vector a) -> Column
GroupedUnboxedColumn :: forall a. (Columnable a, Unbox a) => Vector (Vector a) -> Column
GroupedOptionalColumn :: forall a. Columnable a => Vector (Vector (Maybe a)) -> Column
MutableBoxedColumn :: forall a. Columnable a => IOVector a -> Column
MutableUnboxedColumn :: forall a. (Columnable a, Unbox a) => IOVector a -> Column

Instances

Instances details

Show Column Source #
Instance details Defined in DataFrame.Internal.Column Methods showsPrec :: Int -> Column -> ShowS # show :: Column -> String # showList :: [Column] -> ShowS #
Eq Column Source #
Instance details Defined in DataFrame.Internal.Column Methods (==) :: Column -> Column -> Bool # (/=) :: Column -> Column -> Bool #

correlation :: Text -> Text -> DataFrame -> Maybe Double Source #

median :: Text -> DataFrame -> Maybe Double Source #

variance :: Text -> DataFrame -> Maybe Double Source #

mean :: Text -> DataFrame -> Maybe Double Source #

skewness :: Text -> DataFrame -> Maybe Double Source #

formatNumber :: Double -> String Source #

clip :: Int -> Int -> Int -> Int Source #

geq :: (Columnable a, Ord a, Eq a) => Expr a -> Expr a -> Expr Bool Source #

rename :: Text -> Text -> DataFrame -> DataFrame Source #

selectBy :: (Text -> Bool) -> DataFrame -> DataFrame Source #

O(n) select columns by column predicate name.

data DataFrame Source #

Constructors

DataFrame (Vector (Maybe Column)) (Map Text Int) [Int] (Int, Int)

Instances

Instances details

Show DataFrame Source #
Instance details Defined in DataFrame.Internal.DataFrame Methods showsPrec :: Int -> DataFrame -> ShowS # show :: DataFrame -> String # showList :: [DataFrame] -> ShowS #
Eq DataFrame Source #
Instance details Defined in DataFrame.Internal.DataFrame Methods (==) :: DataFrame -> DataFrame -> Bool # (/=) :: DataFrame -> DataFrame -> Bool #

type Row = Vector RowValue Source #

mkRowRep :: DataFrame -> Set Text -> Int -> Int Source #

data DataFrameException where Source #

Constructors

TypeMismatchException
Fields :: forall a b. (Typeable a, Typeable b) => TypeRep a given type -> TypeRep b expected type -> Text column name -> Text call point -> DataFrameException
TypeMismatchException'
Fields :: forall a. Typeable a => TypeRep a given type -> String expected type -> Text column name -> Text call point -> DataFrameException
ColumnNotFoundException :: Text -> Text -> [Text] -> DataFrameException

Instances

Instances details

Exception DataFrameException Source #
Instance details Defined in DataFrame.Errors Methods toException :: DataFrameException -> SomeException # fromException :: SomeException -> Maybe DataFrameException # displayException :: DataFrameException -> String # backtraceDesired :: DataFrameException -> Bool #
Show DataFrameException Source #
Instance details Defined in DataFrame.Errors Methods showsPrec :: Int -> DataFrameException -> ShowS # show :: DataFrameException -> String # showList :: [DataFrameException] -> ShowS #

isNullish :: Text -> Bool Source #

toColumn' :: (Columnable a, ColumnifyRep (KindOf a) a) => Vector a -> Column Source #

toColumn :: (Columnable a, ColumnifyRep (KindOf a) a) => [a] -> Column Source #

columnLength :: Column -> Int Source #

O(1) Gets the number of elements in the column.

columnTypeString :: Column -> String Source #

expandColumn :: Int -> Column -> Column Source #

type Columnable a = (Columnable' a, ColumnifyRep (KindOf a) a, UnboxIf a, SBoolI (Unboxable a)) Source #

getColumn :: Text -> DataFrame -> Maybe Column Source #

dimensions :: DataFrame -> (Int, Int) Source #

O(1) Get DataFrame dimensions i.e. (rows, columns)

mkRowFromArgs :: [Text] -> DataFrame -> Int -> Row Source #

toRowValue :: Columnable' a => a -> RowValue Source #

frequencies :: Text -> DataFrame -> DataFrame Source #

itransform :: (Typeable b, Typeable c, Columnable b, Columnable c) => (Int -> b -> c) -> Column -> Maybe Column Source #

Applies a function that returns an unboxed result to an unboxed vector, storing the result in a column.

ifoldrColumn :: (Columnable a, Columnable b) => (Int -> a -> b -> b) -> b -> Column -> Maybe b Source #

data TypedColumn a where Source #

Constructors

TColumn :: forall a. Columnable a => Column -> TypedColumn a

Instances

Instances details

Show a => Show (TypedColumn a) Source #
Instance details Defined in DataFrame.Internal.Column Methods showsPrec :: Int -> TypedColumn a -> ShowS # show :: TypedColumn a -> String # showList :: [TypedColumn a] -> ShowS #

transform :: (Columnable b, Columnable c, UnboxIf c, Typeable b, Typeable c) => (b -> c) -> Column -> Maybe Column Source #

Generic column transformation (no index).

unwrapTypedColumn :: TypedColumn a -> Column Source #

parseDefaults :: Bool -> DataFrame -> DataFrame Source #

getIndicesUnboxed :: Unbox a => Vector Int -> Vector a -> Vector a Source #

getIndices :: Vector Int -> Vector a -> Vector a Source #

freezeColumn' :: [(Int, Text)] -> Column -> IO Column Source #

writeColumn :: Int -> Text -> Column -> IO (Either Text Bool) Source #

col :: Columnable a => Text -> Expr a Source #

data HistogramConfig Source #

Constructors

HistogramConfig
Fields width :: Int height :: Int barChar :: Char title :: Maybe String

addCallPointInfo :: Text -> Maybe Text -> String -> String Source #

typeMismatchError :: TypeRep a -> TypeRep b -> String Source #

typeMismatchError' :: String -> String -> String Source #

columnNotFound :: Text -> Text -> [Text] -> String Source #

guessColumnName :: Text -> [Text] -> Text Source #

typeAnnotationSuggestion :: String -> String Source #

editDistance :: Text -> Text -> Int Source #

readValue :: (HasCallStack, Read a) => Text -> a Source #

readByteStringInt :: HasCallStack => ByteString -> Maybe Int Source #

readDouble :: HasCallStack => Text -> Maybe Double Source #

readIntegerEither :: HasCallStack => Text -> Either Text Integer Source #

readIntEither :: HasCallStack => Text -> Either Text Int Source #

readDoubleEither :: HasCallStack => Text -> Either Text Double Source #

safeReadValue :: Read a => Text -> Maybe a Source #

readWithDefault :: (HasCallStack, Read a) => a -> Text -> a Source #

lt :: (Columnable a, Ord a) => Expr a -> Expr a -> Expr Bool Source #

gt :: (Columnable a, Ord a) => Expr a -> Expr a -> Expr Bool Source #

type Columnable' a = (Typeable a, Show a, Ord a, Eq a) Source #

isGrouped :: Column -> Bool Source #

columnVersionString :: Column -> String Source #

type family Unboxable a :: Bool where ... Source #

Equations

Unboxable Int = 'True
Unboxable Int8 = 'True
Unboxable Int16 = 'True
Unboxable Int32 = 'True
Unboxable Int64 = 'True
Unboxable Word = 'True
Unboxable Word8 = 'True
Unboxable Word16 = 'True
Unboxable Word32 = 'True
Unboxable Word64 = 'True
Unboxable Char = 'True
Unboxable Bool = 'True
Unboxable Double = 'True
Unboxable Float = 'True
Unboxable _1 = 'False

type family KindOf a :: Rep where ... Source #

Compute the column representation tag for any ‘a’.

Equations

KindOf (Maybe a) = 'ROptional
KindOf (Vector a) = 'RGBoxed
KindOf (Vector a) = 'RGUnboxed
KindOf a = If (Unboxable a) 'RUnboxed 'RBoxed

class ColumnifyRep (r :: Rep) a where Source #

Methods

toColumnRep :: Vector a -> Column Source #

Instances

Instances details

Columnable a => ColumnifyRep 'RBoxed a Source #
Instance details Defined in DataFrame.Internal.Column Methods toColumnRep :: Vector a -> Column Source #
(Columnable a, Unbox a) => ColumnifyRep 'RUnboxed a Source #
Instance details Defined in DataFrame.Internal.Column Methods toColumnRep :: Vector a -> Column Source #
Columnable a => ColumnifyRep 'RGBoxed (Vector a) Source #
Instance details Defined in DataFrame.Internal.Column Methods toColumnRep :: Vector (Vector a) -> Column Source #
(Columnable a, Unbox a) => ColumnifyRep 'RGUnboxed (Vector a) Source #
Instance details Defined in DataFrame.Internal.Column Methods toColumnRep :: Vector (Vector a) -> Column Source #
Columnable a => ColumnifyRep 'ROptional (Maybe a) Source #
Instance details Defined in DataFrame.Internal.Column Methods toColumnRep :: Vector (Maybe a) -> Column Source #

type UnboxIf a = When (Unboxable a) (Unbox a) Source #

class SBoolI (b :: Bool) where Source #

Methods

sbool :: SBool b Source #

Instances

Instances details

SBoolI 'False Source #
Instance details Defined in DataFrame.Internal.Column Methods sbool :: SBool 'False Source #
SBoolI 'True Source #
Instance details Defined in DataFrame.Internal.Column Methods sbool :: SBool 'True Source #

data SBool (b :: Bool) where Source #

Constructors

STrue :: SBool 'True
SFalse :: SBool 'False

sUnbox :: SBoolI (Unboxable a) => SBool (Unboxable a) Source #

type family When (flag :: Bool) c where ... Source #

Equations

When 'True c = c
When 'False c = ()

toColumnUnboxed :: (Columnable a, Unbox a) => Vector a -> Column Source #

Converts a an unboxed vector to a column making sure to put the vector into an appropriate column type by reflection on the vector's type parameter.

takeColumn :: Int -> Column -> Column Source #

takeLastColumn :: Int -> Column -> Column Source #

sliceColumn :: Int -> Int -> Column -> Column Source #

atIndices :: Set Int -> Column -> Column Source #

atIndicesStable :: Vector Int -> Column -> Column Source #

sortedIndexes :: Bool -> Column -> Vector Int Source #

ifilterColumn :: Columnable a => (Int -> a -> Bool) -> Column -> Maybe Column Source #

Filter column with index.

ifoldlColumn :: (Columnable a, Columnable b) => (b -> Int -> a -> b) -> b -> Column -> Maybe b Source #

reduceColumn :: Columnable a => (a -> b) -> Column -> b Source #

safeReduceColumn :: Typeable a => (a -> b) -> Column -> Maybe b Source #

zipColumns :: Column -> Column -> Column Source #

zipWithColumns :: (Columnable a, Columnable b, Columnable c) => (a -> b -> c) -> Column -> Column -> Column Source #

nulls :: Column -> Int Source #

leq :: (Columnable a, Ord a, Eq a) => Expr a -> Expr a -> Expr Bool Source #

asText :: DataFrame -> Bool -> Text Source #

initialColumnSize :: Int Source #

metadata :: DataFrame -> String Source #

toRowList :: [Text] -> DataFrame -> [Row] Source #

toRowVector :: [Text] -> DataFrame -> Vector Row Source #

sortedIndexes' :: Bool -> Vector Row -> Vector Int Source #

interpret :: forall a b. Columnable a => DataFrame -> Expr a -> TypedColumn a Source #

lit :: Columnable a => a -> Expr a Source #

lift2 :: (Columnable c, Columnable b, Columnable a) => (c -> b -> a) -> Expr c -> Expr b -> Expr a Source #

columnNames :: DataFrame -> [Text] Source #

O(k) Get column names of the DataFrame in order of insertion.

insertColumn Source #

Arguments

:: Columnable a
=> Text	Column Name
-> Vector a	Vector to add to column
-> DataFrame	DataFrame to add column to
-> DataFrame

O(n) Adds a vector to the dataframe.

insertColumn' Source #

Arguments

:: Text	Column Name
-> Maybe Column	Column to add
-> DataFrame	DataFrame to add to column
-> DataFrame

cloneColumn :: Text -> Text -> DataFrame -> DataFrame Source #

insertUnboxedColumn Source #

Arguments

:: (Columnable a, Unbox a)
=> Text	Column Name
-> Vector a	Unboxed vector to add to column
-> DataFrame	DataFrame to add to column
-> DataFrame

O(n) Adds an unboxed vector to the dataframe.

insertColumnWithDefault Source #

Arguments

:: Columnable a
=> a	Default Value
-> Text	Column name
-> Vector a	Data to add to column
-> DataFrame	DataFrame to add to column
-> DataFrame

O(k) Add a column to the dataframe providing a default. This constructs a new vector and also may convert it to an unboxed vector if necessary. Since columns are usually large the runtime is dominated by the length of the list, k.

columnSize :: Text -> DataFrame -> Maybe Int Source #

O(1) Get the number of elements in a given column.

data ColumnInfo Source #

Constructors

ColumnInfo
Fields nameOfColumn :: !Text nonNullValues :: !Int nullValues :: !Int partiallyParsedValues :: !Int uniqueValues :: !Int typeOfColumn :: !Text

columnInfo :: DataFrame -> DataFrame Source #

O(n) Returns the number of non-null columns in the dataframe and the type associated with each column.

partiallyParsed :: Column -> Int Source #

fromColumnList :: [Column] -> DataFrame Source #

valueCounts :: Columnable a => Text -> DataFrame -> [(a, Int)] Source #

O (k * n) Counts the occurences of each value in a given column.

data HistogramOrientation Source #

Constructors

VerticalHistogram
HorizontalHistogram

data PlotColumns Source #

Constructors

PlotAll
PlotSubset [Text]

plotHistograms :: HasCallStack => PlotColumns -> HistogramOrientation -> DataFrame -> IO () Source #

plotForColumn :: HasCallStack => Text -> Maybe Column -> HistogramOrientation -> DataFrame -> IO () Source #

plotHistogramsBy :: HasCallStack => Text -> PlotColumns -> HistogramOrientation -> DataFrame -> IO () Source #

plotForColumnBy :: HasCallStack => Text -> Text -> Maybe Column -> Maybe Column -> HistogramOrientation -> DataFrame -> IO () Source #

countOccurrences :: Ord a => Vector a -> [(a, Int)] Source #

plotGivenCounts' :: HasCallStack => Text -> [((String, String), Int)] -> IO () Source #

numericHistogram :: (HasCallStack, Columnable a) => Text -> Vector a -> String Source #

plotVerticalGivenCounts :: HasCallStack => Text -> [(String, Int)] -> IO () Source #

plotGivenCounts :: HasCallStack => Text -> [(String, Int)] -> IO () Source #

leftJustify :: String -> Int -> String Source #

smallestPartition :: Ord a => a -> [a] -> a Source #

intPlotRanges :: [Int] Source #

defaultConfig :: HistogramConfig Source #

createHistogram :: HistogramConfig -> [Double] -> String Source #

largestPartition :: Ord a => a -> [a] -> a Source #

calculateBins :: [Double] -> Int -> [(Double, Int)] Source #

data SortOrder Source #

Sort order taken as a parameter by the sortby function.

Constructors

Ascending
Descending

Instances

Instances details

Eq SortOrder Source #
Instance details Defined in DataFrame.Operations.Sorting Methods (==) :: SortOrder -> SortOrder -> Bool # (/=) :: SortOrder -> SortOrder -> Bool #

applyStatistic :: (Vector Double -> Double) -> Text -> DataFrame -> Maybe Double Source #

standardDeviation :: Text -> DataFrame -> Maybe Double Source #

interQuartileRange :: Text -> DataFrame -> Maybe Double Source #

_getColumnAsDouble :: Text -> DataFrame -> Maybe (Vector Double) Source #

applyStatistics :: (Vector Double -> Vector Double) -> Text -> DataFrame -> Maybe (Vector Double) Source #

summarize :: DataFrame -> DataFrame Source #

field :: Char -> Parser Text Source #

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

O(k) Apply a function to a combination of columns in a dataframe and add the result into alias column.

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)	Column name \| function to apply
-> Text
-> DataFrame	DataFrame to apply operation to
-> DataFrame

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

applyDouble Source #

Arguments

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

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

applyWhere :: (Columnable a, Columnable b) => (a -> Bool) -> Text -> (b -> b) -> Text -> DataFrame -> DataFrame Source #

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

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

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.

impute :: Columnable b => Text -> b -> DataFrame -> DataFrame Source #

takeLast :: Int -> DataFrame -> DataFrame Source #

dropLast :: Int -> DataFrame -> DataFrame Source #

filterBy :: Columnable a => (a -> Bool) -> Text -> DataFrame -> DataFrame Source #

O(k) a version of filter where the predicate comes first.

filterBy even "x" df

filterWhere :: Expr Bool -> DataFrame -> DataFrame Source #

O(k) filters the dataframe with a row predicate. The arguments in the function must appear in the same order as they do in the list.

filterWhere (["x", "y"], func (\x y -> x + y > 5)) df

filterJust :: Text -> DataFrame -> DataFrame Source #

O(k) removes all rows with Nothing in a given column from the dataframe.

filterJust df

filterAllJust :: DataFrame -> DataFrame Source #

O(n * k) removes all rows with Nothing from the dataframe.

filterJust df

cube :: (Int, Int) -> DataFrame -> DataFrame Source #

O(k) cuts the dataframe in a cube of size (a, b) where a is the length and b is the width.

cube (10, 5) df

selectIntRange :: (Int, Int) -> DataFrame -> DataFrame Source #

O(n) select columns by index range of column names.

selectRange :: (Text, Text) -> DataFrame -> DataFrame Source #

O(n) select columns by index range of column names.

exclude :: [Text] -> DataFrame -> DataFrame Source #

O(n) inverse of select

exclude ["Name"] df

appendWithFrontMin :: Ord a => a -> [a] -> [a] Source #

groupColumns :: Vector (Vector Int) -> DataFrame -> DataFrame -> Text -> DataFrame Source #

mkGroupedColumns :: Vector Int -> DataFrame -> DataFrame -> Text -> DataFrame Source #

hash' :: Columnable a => a -> Double Source #

This hash function returns the hash when given a non numeric type but the value when given a numeric.

groupByAgg :: Aggregation -> [Text] -> DataFrame -> DataFrame Source #

reduceBy :: (Columnable a, Columnable b) => (forall (v :: Type -> Type). Vector v a => v a -> b) -> Text -> DataFrame -> DataFrame Source #

reduceByAgg :: Aggregation -> Text -> DataFrame -> DataFrame Source #

aggregate :: [(Text, Aggregation)] -> DataFrame -> DataFrame Source #

distinct :: DataFrame -> DataFrame Source #

data ReadOptions Source #

Record for CSV read options.

Constructors

ReadOptions
Fields hasHeader :: Bool inferTypes :: Bool safeRead :: Bool

parseDefault :: Bool -> Maybe Column -> Maybe Column Source #

readCsv :: String -> IO DataFrame Source #

Reads a CSV file from the given path. Note this file stores intermediate temporary files while converting the CSV from a row to a columnar format.

readSeparated :: Char -> ReadOptions -> String -> IO DataFrame Source #

Reads a character separated file into a dataframe using mutable vectors.

readTsv :: String -> IO DataFrame Source #

Reads a tab separated file from the given path. Note this file stores intermediate temporary files while converting the CSV from a row to a columnar format.

countRows :: Char -> FilePath -> IO Int Source #

First pass to count rows for exact allocation

parseSep :: Char -> Text -> [Text] Source #

getInitialDataVectors :: Int -> IOVector Column -> [Text] -> IO () Source #

fillColumns :: Int -> Char -> IOVector Column -> IOVector [(Int, Text)] -> Handle -> IO () Source #

Reads rows from the handle and stores values in mutable vectors.

freezeColumn :: IOVector Column -> Vector [(Int, Text)] -> ReadOptions -> Int -> IO (Maybe Column) Source #

Freezes a mutable vector into an immutable one, trimming it to the actual row count.

inferValueType :: Text -> Text Source #

parseRow :: Char -> Parser [Text] Source #

writeValue :: IOVector Column -> IOVector [(Int, Text)] -> Int -> Int -> Text -> IO () Source #

Writes a value into the appropriate column, resizing the vector if necessary.

record :: Char -> Parser [Text] Source #

lineEnd :: Parser () Source #

quotedField :: Parser Text Source #

unquotedField :: Char -> Parser Text Source #

unquotedTerminators :: Char -> Set Char Source #

writeCsv :: String -> DataFrame -> IO () Source #

writeSeparated Source #

Arguments

:: Char	Separator
-> String	Path to write to
-> DataFrame
-> IO ()

getRowAsText :: DataFrame -> Int -> [Text] Source #

(|>) :: a -> (a -> b) -> b Source #