Copyright	(c) Edward Kmett 2013-2015
License	BSD3
Maintainer	Edward Kmett <[email protected]>
Stability	experimental
Portability	non-portable
Safe Haskell	None
Language	Haskell2010

Data.HyperLogLog

Contents

HyperLogLog

Description

See the original paper for details: http://algo.inria.fr/flajolet/Publications/FlFuGaMe07.pdf

Synopsis

data HyperLogLog (p :: k)
class HasHyperLogLog a (p :: k) | a -> p where
- hyperLogLog :: Lens' a (HyperLogLog p)
size :: forall {k} (p :: k). Reifies p Integer => HyperLogLog p -> Approximate Int64
intersectionSize :: forall {k} (p :: k). Reifies p Integer => [HyperLogLog p] -> Approximate Int64
insert :: forall {k} (s :: k) a. (Reifies s Integer, Serial a) => a -> HyperLogLog s -> HyperLogLog s
insertHash :: forall {k} (s :: k). Reifies s Integer => Word32 -> HyperLogLog s -> HyperLogLog s
cast :: forall {k1} {k2} (p :: k1) (q :: k2). (Reifies p Integer, Reifies q Integer) => HyperLogLog p -> Maybe (HyperLogLog q)
coerceConfig :: forall {k1} {k2} (p :: k1) (q :: k2). (Reifies p Integer, Reifies q Integer) => Maybe (Coercion (HyperLogLog p) (HyperLogLog q))

HyperLogLog

data HyperLogLog (p :: k) Source #

Initialize a new counter:

>>> runHyperLogLog (mempty :: HyperLogLog 3) == V.fromList [0,0,0,0,0,0,0,0]
True

Please note how you specify a counter size with the n invocation. Sizes of up to 16 are valid, with 7 being a likely good minimum for decent accuracy.

Let's count a list of unique items and get the latest estimate:

>>> size (foldr insert mempty [1..10] :: HyperLogLog 4)
Approximate {_confidence = 0.9972, _lo = 2, _estimate = 9, _hi = 17}

Note how insert can be used to add new observations to the approximate counter.

Instances

Instances details

HasHyperLogLog (HyperLogLog p) (p :: k) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

hyperLogLog :: Lens' (HyperLogLog p) (HyperLogLog p) Source #

Reifies p Integer => Monoid (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

mempty :: HyperLogLog p #

mappend :: HyperLogLog p -> HyperLogLog p -> HyperLogLog p #

mconcat :: [HyperLogLog p] -> HyperLogLog p #

Semigroup (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

(<>) :: HyperLogLog p -> HyperLogLog p -> HyperLogLog p #

sconcat :: NonEmpty (HyperLogLog p) -> HyperLogLog p #

stimes :: Integral b => b -> HyperLogLog p -> HyperLogLog p #

Generic (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Associated Types

type Rep (HyperLogLog p)
Instance details Defined in Data.HyperLogLog.Type type Rep (HyperLogLog p) = D1 ('MetaData "HyperLogLog" "Data.HyperLogLog.Type" "hyperloglog-0.4.6-sufGSCvuzT1xTRKvdpLBq" 'True) (C1 ('MetaCons "HyperLogLog" 'PrefixI 'True) (S1 ('MetaSel ('Just "runHyperLogLog") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Vector Rank))))

Methods

from :: HyperLogLog p -> Rep (HyperLogLog p) x #

to :: Rep (HyperLogLog p) x -> HyperLogLog p #

Show (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

showsPrec :: Int -> HyperLogLog p -> ShowS #

show :: HyperLogLog p -> String #

showList :: [HyperLogLog p] -> ShowS #

Binary (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

put :: HyperLogLog p -> Put #

get :: Get (HyperLogLog p) #

putList :: [HyperLogLog p] -> Put #

Serial (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

serialize :: MonadPut m => HyperLogLog p -> m () #

deserialize :: MonadGet m => m (HyperLogLog p) #

Serialize (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

put :: Putter (HyperLogLog p) #

get :: Get (HyperLogLog p) #

NFData (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

rnf :: HyperLogLog p -> () #

Eq (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

Methods

(==) :: HyperLogLog p -> HyperLogLog p -> Bool #

(/=) :: HyperLogLog p -> HyperLogLog p -> Bool #

type Rep (HyperLogLog p) Source #

Instance details

Defined in Data.HyperLogLog.Type

type Rep (HyperLogLog p) = D1 ('MetaData "HyperLogLog" "Data.HyperLogLog.Type" "hyperloglog-0.4.6-sufGSCvuzT1xTRKvdpLBq" 'True) (C1 ('MetaCons "HyperLogLog" 'PrefixI 'True) (S1 ('MetaSel ('Just "runHyperLogLog") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Vector Rank))))

class HasHyperLogLog a (p :: k) | a -> p where Source #

Methods

hyperLogLog :: Lens' a (HyperLogLog p) Source #

Instances

Instances details

HasHyperLogLog (HyperLogLog p) (p :: k) Source #
Instance details Defined in Data.HyperLogLog.Type Methods hyperLogLog :: Lens' (HyperLogLog p) (HyperLogLog p) Source #

size :: forall {k} (p :: k). Reifies p Integer => HyperLogLog p -> Approximate Int64 Source #

Approximate size of our set

intersectionSize :: forall {k} (p :: k). Reifies p Integer => [HyperLogLog p] -> Approximate Int64 Source #

insert :: forall {k} (s :: k) a. (Reifies s Integer, Serial a) => a -> HyperLogLog s -> HyperLogLog s Source #

insertHash :: forall {k} (s :: k). Reifies s Integer => Word32 -> HyperLogLog s -> HyperLogLog s Source #

Insert a value that has already been hashed by whatever user defined hash function you want.

cast :: forall {k1} {k2} (p :: k1) (q :: k2). (Reifies p Integer, Reifies q Integer) => HyperLogLog p -> Maybe (HyperLogLog q) Source #

coerceConfig :: forall {k1} {k2} (p :: k1) (q :: k2). (Reifies p Integer, Reifies q Integer) => Maybe (Coercion (HyperLogLog p) (HyperLogLog q)) Source #

If two types p and q reify the same configuration, then we can coerce between HyperLogLog p and HyperLogLog q. We do this by building a hole in the nominal role for the configuration parameter.