/* Copyright 2010 Aaron J. Radke Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. */ package cc.drx object Bloom{ def apply(n:Int, confidence:Double = 3.sigma.toDouble.not) = { val p = confidence.not //probability of false positive val m = (-n*p.ln/2.ln.sq).ceil.toInt //number of bits to support confidence val k = (2.log*m/n).ceil.toInt //optimal hashCount new Bloom(n,m,k) } } class Bloom(val n:Int, val m:Int, val k:Int){ //TODO implement bloom filter feature test with murm3 hash from scala //TODO add byte/long data pseudo immutable lazy val p = (1 - (1 - m.inv)**(k*n))**k // val probFalsePositiveApprox = (1 - math.exp(-1d*k*n/m))**k val toKson = s"Bloom bits:$m elements:$n hashPoints:$k falseRate:$p confidence:${p.not} bits/elem:${m/n}" }