Copyright | (c) Edward Kmett 2013-2015 |
---|---|
License | BSD3 |
Maintainer | Edward Kmett <ekmett@gmail.com> |
Stability | experimental |
Portability | non-portable |
Safe Haskell | None |
Language | Haskell98 |
See the original paper for details: http://algo.inria.fr/flajolet/Publications/FlFuGaMe07.pdf
- data HyperLogLog p
- class HasHyperLogLog a p | a -> p where
- hyperLogLog :: Lens' a (HyperLogLog p)
- size :: ReifiesConfig p => HyperLogLog p -> Approximate Int64
- intersectionSize :: ReifiesConfig p => [HyperLogLog p] -> Approximate Int64
- insert :: (ReifiesConfig s, Serial a) => a -> HyperLogLog s -> HyperLogLog s
- insertHash :: ReifiesConfig s => Word32 -> HyperLogLog s -> HyperLogLog s
- cast :: forall p q. (ReifiesConfig p, ReifiesConfig q) => HyperLogLog p -> Maybe (HyperLogLog q)
- data Config
- hll :: Int -> Config
- class ReifiesConfig o
- reifyConfig :: Int -> (forall o. ReifiesConfig o => Proxy o -> r) -> r
HyperLogLog
data HyperLogLog p Source
Initialize a new counter:
>>>
mempty :: HyperLogLog $(3)
HyperLogLog {runHyperLogLog = fromList [0,0,0,0,0,0,0,0]}
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.
HasHyperLogLog k (HyperLogLog k p) p | |
Eq (HyperLogLog k p) | |
Show (HyperLogLog k p) | |
Generic (HyperLogLog k p) | |
ReifiesConfig k p => Monoid (HyperLogLog k p) | |
Serialize (HyperLogLog k p) | |
Semigroup (HyperLogLog k p) | |
ReifiesConfig k p => HasConfig (HyperLogLog k p) | |
type Rep (HyperLogLog k p) |
class HasHyperLogLog a p | a -> p where Source
hyperLogLog :: Lens' a (HyperLogLog p) Source
HasHyperLogLog k (HyperLogLog k p) p |
size :: ReifiesConfig p => HyperLogLog p -> Approximate Int64 Source
Approximate size of our set
intersectionSize :: ReifiesConfig p => [HyperLogLog p] -> Approximate Int64 Source
insert :: (ReifiesConfig s, Serial a) => a -> HyperLogLog s -> HyperLogLog s Source
insertHash :: ReifiesConfig s => Word32 -> HyperLogLog s -> HyperLogLog s Source
Insert a value that has already been hashed by whatever user defined hash function you want.
cast :: forall p q. (ReifiesConfig p, ReifiesConfig q) => HyperLogLog p -> Maybe (HyperLogLog q) Source
Config
Constants required for a bucketing factor b
ReifiesConfig
class ReifiesConfig o Source
KnownNat n => ReifiesConfig Nat n | |
Reifies * n Int => ReifiesConfig * (D n) | |
Reifies * n Int => ReifiesConfig * (SD n) |
reifyConfig :: Int -> (forall o. ReifiesConfig o => Proxy o -> r) -> r Source