Numeric.Datasets

Using datasets

getDataset :: Dataset a -> IO [a]

Load a dataset, using the system temporary directory as a cache

type Dataset a

Arguments

 = FilePath

Directory for caching downloaded datasets

-> IO [a]

A dataset is defined as a function from the caching directory to the IO action that loads the data

Defining datasets

data Source

Constructors

URL String

CabalDataFile FilePath

csvDatasetPreprocess :: FromRecord a => (ByteString -> ByteString) -> Source -> Dataset a

Define a dataset from a pre-processing function and a source for a CSV file

csvDataset :: FromRecord a => Source -> Dataset a

Define a dataset from a source for a CSV file

getFileFromSource :: FilePath -> Source -> IO ByteString

Helper functions for parsing

dashToCamelCase :: String -> String

Turn dashes to CamlCase

parseDashToCamelField :: Read a => Field -> Parser a

Parse a field, first turning dashes to CamlCase

parseReadField :: Read a => Field -> Parser a

parse somethign, based on its read instance

dropLines :: Int -> ByteString -> ByteString

Drop lines from a bytestring

fixAmericanDecimals :: ByteString -> ByteString

Turn US-style decimals starting with a period (e.g. .2) into something Haskell can parse (e.g. 0.2)