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

change model

Browse Source
This commit is contained in:
tqchen 2014-12-04 09:05:48 -08:00
parent 3033177e9e
commit 67229fd7a9
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
toolkit/kmeans.cpp
View File

@ -73,13 +73,13 @@ inline size_t GetCluster(const Matrix &centroids,
double dmin = Cos(centroids[0], v); double dmin = Cos(centroids[0], v);
for (size_t k = 1; k < centroids.nrow; ++k) { for (size_t k = 1; k < centroids.nrow; ++k) {
double dist = Cos(centroids[k], v); double dist = Cos(centroids[k], v);
if (dist < dmin) { if (dist > dmin) {
dmin = dist; imin = k; dmin = dist; imin = k;
} }
} }
return imin; return imin;
} }
int main(int argc, char *argv[]) { int main(int argc, char *argv[]) {
if (argc < 5) { if (argc < 5) {
printf("Usage: <data_dir> num_cluster max_iter <out_model>\n"); printf("Usage: <data_dir> num_cluster max_iter <out_model>\n");
@ -116,9 +116,11 @@ int main(int argc, char *argv[]) {
for (size_t i = 0; i < ndata; ++i) { for (size_t i = 0; i < ndata; ++i) {
SparseMat::Vector v = data[i]; SparseMat::Vector v = data[i];
size_t k = GetCluster(model.centroids, v); size_t k = GetCluster(model.centroids, v);
// temp[k] += v
for (size_t j = 0; j < v.length; ++j) { for (size_t j = 0; j < v.length; ++j) {
temp[k][v[j].findex] += v[j].fvalue; temp[k][v[j].findex] += v[j].fvalue;
} }
// use last column to record counts
temp[k][num_feat] += 1.0f; temp[k][num_feat] += 1.0f;
} }
// call allreduce // call allreduce
@ -126,6 +128,7 @@ int main(int argc, char *argv[]) {
// set number // set number
for (int k = 0; k < num_cluster; ++k) { for (int k = 0; k < num_cluster; ++k) {
float cnt = temp[k][num_feat]; float cnt = temp[k][num_feat];
utils::Check(cnt != 0.0f, "get zero sized cluster");
for (unsigned i = 0; i < num_feat; ++i) { for (unsigned i = 0; i < num_feat; ++i) {
model.centroids[k][i] = temp[k][i] / cnt; model.centroids[k][i] = temp[k][i] / cnt;
} }