Mirror/zeek
1
0
Fork 0
mirror of https://github.com/zeek/zeek.git synced 2025-10-04 23:58:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Making the confidence configurable.

Browse source
This commit is contained in:
Robin Sommer 2013-08-31 10:23:00 -07:00
parent fb3ceae6d5
commit 295987c8d0
8 changed files with 49 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/probabilistic/CardinalityCounter.cc
View file

@ -10,7 +10,7 @@
using namespace probabilistic;
int CardinalityCounter::OptimalB(double error)
int CardinalityCounter::OptimalB(double error, double confidence)
{
double initial_estimate = 2 * (log(1.04) - log(error)) / log(2);
int answer = (int) floor(initial_estimate);
@ -20,7 +20,7 @@ int CardinalityCounter::OptimalB(double error)
do {
answer++;
k = pow(2, (answer - initial_estimate) / 2);
} while ( erf(k / sqrt(2)) < HLL_CONF );
} while ( erf(k / sqrt(2)) < confidence );
return answer;
}
@ -30,6 +30,9 @@ void CardinalityCounter::Init(uint64 size)
m = size;
buckets = new uint8_t[m];
// The following magic values are taken directly out of the
// description of the HyperLogLog algorithn.
if ( m == 16 )
alpha_m = 0.673;
@ -51,9 +54,9 @@ void CardinalityCounter::Init(uint64 size)
V = m;
}
CardinalityCounter::CardinalityCounter(double error_margin)
CardinalityCounter::CardinalityCounter(double error_margin, double confidence)
{
int b = OptimalB(error_margin);
int b = OptimalB(error_margin, confidence);
Init((uint64) pow(2, b));
}