Data.HyperLogLog

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

HyperLogLog

data HyperLogLog p

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

HasHyperLogLog (HyperLogLog p) (p :: k)

Defined in Data.HyperLogLog.Type

Methods

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

Eq (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

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

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

Show (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

showsPrec :: Int -> HyperLogLog p -> ShowS

show :: HyperLogLog p -> String

showList :: [HyperLogLog p] -> ShowS

Generic (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Associated Types

type Rep (HyperLogLog p) :: Type -> Type

Methods

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

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

Semigroup (HyperLogLog p)

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

Reifies p Integer => Monoid (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

mempty :: HyperLogLog p

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

mconcat :: [HyperLogLog p] -> HyperLogLog p

Binary (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

put :: HyperLogLog p -> Put

get :: Get (HyperLogLog p)

putList :: [HyperLogLog p] -> Put

Serial (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

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

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

Serialize (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

put :: Putter (HyperLogLog p)

get :: Get (HyperLogLog p)

NFData (HyperLogLog p)

Defined in Data.HyperLogLog.Type

Methods

rnf :: HyperLogLog p -> ()

type Rep (HyperLogLog p)

Defined in Data.HyperLogLog.Type

type Rep (HyperLogLog p) = D1 ('MetaData "HyperLogLog" "Data.HyperLogLog.Type" "hyperloglog-0.4.6-9vzHRrRRBy4LO8h6dQD0lH" 'True) (C1 ('MetaCons "HyperLogLog" 'PrefixI 'True) (S1 ('MetaSel ('Just "runHyperLogLog") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Vector Rank))))

class HasHyperLogLog a p | a -> p where

Methods

hyperLogLog :: Lens' a (HyperLogLog p)

Instances

HasHyperLogLog (HyperLogLog p) (p :: k)

Defined in Data.HyperLogLog.Type

Methods

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

size :: Reifies p Integer => HyperLogLog p -> Approximate Int64

Approximate size of our set

intersectionSize :: Reifies p Integer => [HyperLogLog p] -> Approximate Int64

insert :: (Reifies s Integer, Serial a) => a -> HyperLogLog s -> HyperLogLog s

insertHash :: Reifies s Integer => Word32 -> HyperLogLog s -> HyperLogLog s

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

cast :: forall p q. (Reifies p Integer, Reifies q Integer) => HyperLogLog p -> Maybe (HyperLogLog q)

coerceConfig :: forall p q. (Reifies p Integer, Reifies q Integer) => Maybe (Coercion (HyperLogLog p) (HyperLogLog q))

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.