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 k (HyperLogLog k p) p

Methods

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

Eq (HyperLogLog k p)

Methods

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

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

Show (HyperLogLog k p)

Methods

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

show :: HyperLogLog k p -> String

showList :: [HyperLogLog k p] -> ShowS

Generic (HyperLogLog k p)

Associated Types

type Rep (HyperLogLog k p) :: * -> *

Methods

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

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

Semigroup (HyperLogLog k p)

Methods

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

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

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

Reifies k p Integer => Monoid (HyperLogLog k p)

Methods

mempty :: HyperLogLog k p

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

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

Binary (HyperLogLog k p)

Methods

put :: HyperLogLog k p -> Put

get :: Get (HyperLogLog k p)

putList :: [HyperLogLog k p] -> Put

Serial (HyperLogLog k p)

Methods

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

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

Serialize (HyperLogLog k p)

Methods

put :: Putter (HyperLogLog k p)

get :: Get (HyperLogLog k p)

NFData (HyperLogLog k p)

Methods

rnf :: HyperLogLog k p -> ()

type Rep (HyperLogLog k p)

type Rep (HyperLogLog k p) = D1 (MetaData "HyperLogLog" "Data.HyperLogLog.Type" "hyperloglog-0.4.2-AnOGzsypx2a5UPbh6Lv2OD" True) (C1 (MetaCons "HyperLogLog" PrefixI True) (S1 (MetaSel (Just Symbol "runHyperLogLog") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 (Vector Rank))))

class HasHyperLogLog a p | a -> p where

Minimal complete definition

hyperLogLog

Methods

hyperLogLog :: Lens' a (HyperLogLog p)

Instances

HasHyperLogLog k (HyperLogLog k p) p

Methods

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