Merge remote-tracking branch 'origin/topic/bernhard/topk'

* origin/topic/bernhard/topk:
  adapt to new folder structure
  fix opaqueval-related memleak
  synchronize pruned attribute
  potentially found wrong Ref.
  add sum function that can be used to get the number of total observed elements.
  in cluster settings, the resultvals can apparently been uninitialized in some special cases
  fix memory leaks
  fix warnings
  add topk cluster test
  make size of topk-list configureable when using sumstats
  implement merging for top-k.
  add serialization for topk
  make the get function const
  topk for sumstats
  well, a test that works..
  implement topk.
This commit is contained in:
Robin Sommer 2013-08-01 10:27:18 -07:00
commit 81dcda3eb4
19 changed files with 1288 additions and 3 deletions

View file

@ -5,5 +5,6 @@
@load ./sample
@load ./std-dev
@load ./sum
@load ./topk
@load ./unique
@load ./variance

View file

@ -0,0 +1,50 @@
@load base/frameworks/sumstats
module SumStats;
export {
redef record Reducer += {
## number of elements to keep in the top-k list
topk_size: count &default=500;
};
redef enum Calculation += {
TOPK
};
redef record ResultVal += {
topk: opaque of topk &optional;
};
}
hook init_resultval_hook(r: Reducer, rv: ResultVal)
{
if ( TOPK in r$apply && ! rv?$topk )
rv$topk = topk_init(r$topk_size);
}
hook observe_hook(r: Reducer, val: double, obs: Observation, rv: ResultVal)
{
if ( TOPK in r$apply )
topk_add(rv$topk, obs);
}
hook compose_resultvals_hook(result: ResultVal, rv1: ResultVal, rv2: ResultVal)
{
if ( rv1?$topk )
{
result$topk = topk_init(topk_size(rv1$topk));
topk_merge(result$topk, rv1$topk);
if ( rv2?$topk )
topk_merge(result$topk, rv2$topk);
}
else if ( rv2?$topk )
{
result$topk = topk_init(topk_size(rv2$topk));
topk_merge(result$topk, rv2$topk);
}
}