Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

optimize heavy hitter

Browse Source
This commit is contained in:
tqchen
2014-11-10 21:18:37 -08:00
parent b426eef527
commit 9d101b47f9
3 changed files with 101 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/mkquantest.py
View File

@@ -7,7 +7,11 @@ import subprocess
funcs = {
'seq': 'lambda n: sorted([(x,1) for x in range(1,n+1)], key = lambda x:random.random())',
'seqlogw': 'lambda n: sorted([(x, math.log(x)) for x in range(1,n+1)], key = lambda x:random.random())',
'lots0': 'lambda n: sorted([(max(x - n*3/4,0), 1) for x in range(1,n+1)], key = lambda x:random.random())'
'lots0': 'lambda n: sorted([(max(x - n*3/4,0), 1) for x in range(1,n+1)], key = lambda x:random.random())',
'lots9': 'lambda n: sorted([(9 if x > n / 4 else x, 1) for x in range(1,n+1)], key = lambda x:random.random())',
'lotsm': 'lambda n: sorted([(n/8 if x > n / 4 else x, 1) for x in range(1,n+1)], key = lambda x:random.random())',
'lotsmr': 'lambda n: sorted([( x * 4 / n + n / 20 if x > n / 10 else x, 1) for x in range(1,n+1)], key = lambda x:random.random())',
'lotsmr2': 'lambda n: sorted([( x * 10 / n + n / 20 if x > n / 10 else x, 1) for x in range(1,n+1)], key = lambda x:random.random())'
}
if len(sys.argv) < 3:

9
test/test_quantile.cpp
View File

@@ -2,7 +2,6 @@
#include <utils/quantile.h>
using namespace xgboost;
template<typename Sketch, typename RType>
inline void test(void) {
Sketch sketch;
@@ -11,7 +10,6 @@ inline void test(void) {
float eps, x, w;
utils::Check(scanf("%lu%f", &n, &eps) == 2, "needs to start with n eps");
sketch.Init(n, eps);
printf("nlevel = %lu, limit_size=%lu\n", sketch.nlevel, sketch.limit_size);
while (scanf("%f%f", &x, &w) == 2) {
sketch.Push(x, static_cast<RType>(w));
wsum += w;
@@ -20,8 +18,10 @@ inline void test(void) {
typename Sketch::SummaryContainer out;
sketch.GetSummary(&out);
double maxerr = static_cast<double>(out.MaxError());
printf("MaxError=%g/%g = %g\n", maxerr, wsum, maxerr / wsum);
out.Print();
printf("MaxError=%g/%g = %g\n", maxerr, wsum, maxerr / wsum);
printf("maxlevel = %lu, usedlevel=%lu, limit_size=%lu\n", sketch.nlevel, sketch.level.size(), sketch.limit_size);
}
int main(int argc, char *argv[]) {
@@ -30,6 +30,9 @@ int main(int argc, char *argv[]) {
if (!strcmp(method, "wq")) {
test<utils::WQuantileSketch<float, float>, float>();
}
if (!strcmp(method, "wx")) {
test<utils::WXQuantileSketch<float, float>, float>();
}
if (!strcmp(method, "gk")) {
test<utils::GKQuantileSketch<float, unsigned>, unsigned>();
}