From 67229fd7a9e97a4c032921592f91bfc0d8730cd0 Mon Sep 17 00:00:00 2001
From: tqchen <tianqi.tchen@gmail.com>
Date: Thu, 4 Dec 2014 09:05:48 -0800
Subject: [PATCH] change model

---
 toolkit/kmeans.cpp | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/toolkit/kmeans.cpp b/toolkit/kmeans.cpp
index 24f784923..109b49826 100644
--- a/toolkit/kmeans.cpp
+++ b/toolkit/kmeans.cpp
@@ -73,13 +73,13 @@ inline size_t GetCluster(const Matrix &centroids,
   double dmin = Cos(centroids[0], v);
   for (size_t k = 1; k < centroids.nrow; ++k) {
     double dist = Cos(centroids[k], v);
-    if (dist < dmin) {
+    if (dist > dmin) {
       dmin = dist; imin = k;
-    }    
+    }
   }
   return imin;
 }
-                  
+             
 int main(int argc, char *argv[]) {
   if (argc < 5) {
     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) {
       SparseMat::Vector v = data[i];
       size_t k = GetCluster(model.centroids, v);
+      // temp[k] += v
       for (size_t j = 0; j < v.length; ++j) {
         temp[k][v[j].findex] += v[j].fvalue;
       }
+      // use last column to record counts
       temp[k][num_feat] += 1.0f;
     }
     // call allreduce
@@ -126,6 +128,7 @@ int main(int argc, char *argv[]) {
     // set number
     for (int k = 0; k < num_cluster; ++k) {
       float cnt = temp[k][num_feat];
+      utils::Check(cnt != 0.0f, "get zero sized cluster");
       for (unsigned i = 0; i < num_feat; ++i) {
         model.centroids[k][i] = temp[k][i] / cnt;
       }