Safe Haskell	None
Language	Haskell2010

DataFrame.IO.CSV

Synopsis

data GrowingVector a = GrowingVector {
- gvData :: !(IORef (IOVector a))
- gvSize :: !(IORef Int)
- gvCapacity :: !(IORef Int)
}
data GrowingUnboxedVector a = GrowingUnboxedVector {
- guvData :: !(IORef (IOVector a))
- guvSize :: !(IORef Int)
- guvCapacity :: !(IORef Int)
}
data GrowingColumn
- = GrowingInt !(GrowingUnboxedVector Int) !(IORef [Int])
- | GrowingDouble !(GrowingUnboxedVector Double) !(IORef [Int])
- | GrowingText !(GrowingVector Text) !(IORef [Int])
data HeaderSpec
- = NoHeader
- | UseFirstRow
- | ProvideNames [Text]
data TypeSpec
- = InferFromSample Int
- | SpecifyTypes [SchemaType]
- | NoInference
shouldInferFromSample :: TypeSpec -> Bool
typeInferenceSampleSize :: TypeSpec -> Int
data ReadOptions = ReadOptions {
- headerSpec :: HeaderSpec
- typeSpec :: TypeSpec
- safeRead :: Bool
- chunkSize :: Int
- dateFormat :: String
}
defaultReadOptions :: ReadOptions
newGrowingVector :: Int -> IO (GrowingVector a)
newGrowingUnboxedVector :: Unbox a => Int -> IO (GrowingUnboxedVector a)
appendGrowingVector :: GrowingVector a -> a -> IO ()
appendGrowingUnboxedVector :: Unbox a => GrowingUnboxedVector a -> a -> IO ()
freezeGrowingVector :: GrowingVector a -> IO (Vector a)
freezeGrowingUnboxedVector :: Unbox a => GrowingUnboxedVector a -> IO (Vector a)
readCsv :: FilePath -> IO DataFrame
readCsvWithOpts :: ReadOptions -> FilePath -> IO DataFrame
readTsv :: FilePath -> IO DataFrame
readSeparated :: Char -> ReadOptions -> FilePath -> IO DataFrame
initializeColumns :: [ByteString] -> ReadOptions -> IO [GrowingColumn]
data InferredType
- = IntType
- | DoubleType
- | TextType
inferType :: Text -> InferredType
processRow :: Int -> [ByteString] -> [GrowingColumn] -> IO ()
isNull :: Text -> Bool
processFile :: Handle -> Char -> [GrowingColumn] -> Int -> Int -> IO ()
parseLine :: Char -> ByteString -> [ByteString]
parseRow :: Char -> Parser [ByteString]
record :: Char -> Parser [ByteString]
field :: Char -> Parser ByteString
unquotedField :: Char -> Parser ByteString
quotedField :: Parser ByteString
endOfLine :: Parser ()
freezeGrowingColumn :: GrowingColumn -> IO Column
writeCsv :: FilePath -> DataFrame -> IO ()
writeSeparated :: Char -> FilePath -> DataFrame -> IO ()
getRowAsText :: DataFrame -> Int -> [Text]

Documentation

data GrowingVector a Source #

Constructors

GrowingVector
Fields gvData :: !(IORef (IOVector a)) gvSize :: !(IORef Int) gvCapacity :: !(IORef Int)

data GrowingUnboxedVector a Source #

Constructors

GrowingUnboxedVector
Fields guvData :: !(IORef (IOVector a)) guvSize :: !(IORef Int) guvCapacity :: !(IORef Int)

data GrowingColumn Source #

Constructors

GrowingInt !(GrowingUnboxedVector Int) !(IORef [Int])
GrowingDouble !(GrowingUnboxedVector Double) !(IORef [Int])
GrowingText !(GrowingVector Text) !(IORef [Int])

data HeaderSpec Source #

Constructors

NoHeader	File has no header row
UseFirstRow	Use first row as column names
ProvideNames [Text]	Supply names for a no-header file

Instances

Instances details

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

data TypeSpec Source #

Constructors

InferFromSample Int
SpecifyTypes [SchemaType]
NoInference

shouldInferFromSample :: TypeSpec -> Bool Source #

typeInferenceSampleSize :: TypeSpec -> Int Source #

data ReadOptions Source #

CSV read parameters.

Constructors

ReadOptions

Fields

headerSpec :: HeaderSpec
Where to get the headers from. (default: UseFirstRow)
typeSpec :: TypeSpec
Whether/how to infer types. (default: InferFromSample 100)
safeRead :: Bool
Whether to partially parse values into Maybe/Either. (default: True)
chunkSize :: Int
Default chunk size (in bytes) for csv reader. (default: 512'000)

dateFormat :: String

Format of date fields as recognized by the Data.Time.Format module.

Examples:

   > parseTimeM True defaultTimeLocale "%Y%-m%-d" "2010304" :: Maybe Day
   Just 2010-03-04
   > parseTimeM True defaultTimeLocale "%d%-m%-Y" "0432010" :: Maybe Day
   Just 2010-03-04

defaultReadOptions :: ReadOptions Source #

newGrowingVector :: Int -> IO (GrowingVector a) Source #

newGrowingUnboxedVector :: Unbox a => Int -> IO (GrowingUnboxedVector a) Source #

appendGrowingVector :: GrowingVector a -> a -> IO () Source #

appendGrowingUnboxedVector :: Unbox a => GrowingUnboxedVector a -> a -> IO () Source #

freezeGrowingVector :: GrowingVector a -> IO (Vector a) Source #

freezeGrowingUnboxedVector :: Unbox a => GrowingUnboxedVector a -> IO (Vector a) Source #

readCsv :: FilePath -> IO DataFrame Source #

Read CSV file from path and load it into a dataframe.

Example

Expand

ghci> D.readCsv "./data/taxi.csv"

readCsvWithOpts :: ReadOptions -> FilePath -> IO DataFrame Source #

Read CSV file from path and load it into a dataframe.

Example

Expand

ghci> D.readCsvWithOpts "./data/taxi.csv" (D.defaultReadOptions { dateFormat = "%d%-m%-Y" })

readTsv :: FilePath -> IO DataFrame Source #

Read TSV (tab separated) file from path and load it into a dataframe.

Example

Expand

ghci> D.readTsv "./data/taxi.tsv"

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

Read text file with specified delimiter into a dataframe.

Example

Expand

ghci> D.readSeparated ';' D.defaultReadOptions "./data/taxi.txt"

initializeColumns :: [ByteString] -> ReadOptions -> IO [GrowingColumn] Source #

data InferredType Source #

Constructors

IntType
DoubleType
TextType

inferType :: Text -> InferredType Source #

processRow :: Int -> [ByteString] -> [GrowingColumn] -> IO () Source #

isNull :: Text -> Bool Source #

processFile :: Handle -> Char -> [GrowingColumn] -> Int -> Int -> IO () Source #

parseLine :: Char -> ByteString -> [ByteString] Source #

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

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

field :: Char -> Parser ByteString Source #

unquotedField :: Char -> Parser ByteString Source #

quotedField :: Parser ByteString Source #

endOfLine :: Parser () Source #

freezeGrowingColumn :: GrowingColumn -> IO Column Source #

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

writeSeparated Source #

Arguments

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

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